No full-text available
To read the full-text of this research,
you can request a copy directly from the authors.
Development and validation of a risk scoring tool for predicting incident reversible cognitive frailty among community‐dwelling older adults: A prospective cohort study
Abstract
Aim
Reversible cognitive frailty (RCF) is an ideal target to prevent asymptomatic cognitive impairment and dependency. This study aimed to develop and validate prediction models for incident RCF.
Methods
A total of 1230 older adults aged ≥60 years from China Health and Retirement Longitudinal Study 2011–2013 survey were included as the training set. The modified Poisson regression and three machine learning algorithms including eXtreme Gradient Boosting, support vector machine and random forest were used to develop prediction models. All models were evaluated internally with fivefold cross‐validation, and evaluated externally using a temporal validation method through the China Health and Retirement Longitudinal Study 2013–2015 survey.
Results
The incidence of RCF was 27.4% in the training set and 27.5% in the external validation set. A total of 13 important predictors were selected to develop the model, including age, education, contact with their children, medical insurance, vision impairment, heart diseases, medication types, self‐rated health, pain locations, loneliness, self‐medication, night‐time sleep and having running water. All models showed acceptable or approximately acceptable discrimination (AUC 0.683–0.809) for the training set, but fair discrimination (AUC 0.568–0.666) for the internal and external validation. For calibration, only modified Poisson regression and eXtreme Gradient Boosting were acceptable in the training set. All models had acceptable overall prediction performance and clinical usefulness. Older adults were divided into three groups by the risk scoring tool constructed based on modified Poisson regression: low risk (≤24), median risk (24–29) and high risk (>29).
Conclusions
This risk tool could assist healthcare providers to predict incident RCF among older adults in the next 2 years, facilitating early identification of a high‐risk population of RCF. Geriatr Gerontol Int 2024; 24: 874–882 .
ResearchGate has not been able to resolve any citations for this publication.
Background
Few studies emphasize on predictors of incident cognitive frailty (CF) and examine relationships between various gait characteristics and CF. Therefore, we conducted a 2-year prospective study to investigate potential predictors, including gait characteristics, of incident reversible CF (RCF) and potentially RCF (PRCF) among Taiwanese older adults.
Methods
Eligible participants were individuals aged ≥ 65 years, who could ambulate independently, and did not have RCF/PRCF at the baseline. The baseline assessment collected information on physical frailty and cognitive measures, in addition to sociodemographic and lifestyle characteristics, preexisting comorbidities and medications, gait characteristics, Tinetti’s balance, balance confidence as assessed by Activities-specific Balance Confidence (ABC) scale, and the depressive status as assessed by the Geriatric Depression Scale. The Mini-Mental State Examination (MMSE), Mattis Dementia Rating Scale, and Digit Symbol Substitution Test were used to evaluate cognitive functions. Incident RCF and PRCF were ascertained at a 2-year follow-up assessment.
Results
Results of the multinomial logistic regression analysis showed that incident RCF was significantly associated with older age (odds ratio [OR] = 1.05) and lower ABC scores (OR = 0.97). Furthermore, incident PRCF was significantly associated with older age (OR = 1.07), lower ABC scores (OR = 0.96), the presence of depression (OR = 3.61), lower MMSE scores (OR = 0.83), slower gait velocity (OR = 0.97), and greater double-support time variability (OR = 1.09).
Conclusions
Incident RCF was independently associated with older age and lower balance confidence while incident PRCF independently associated with older age, reduced global cognition, the presence of depression, slower gait velocity, and greater double-support time variability. Balance confidence was the only modifiable factor associated with both incident RCF and PRCF.
Background: This study aims to explore the mediating role of loneliness between depressive symptoms and cognitive frailty among older adults in the community. Methods: A total of 527 community-dwelling older adults aged ≥ 60 years were included in this cross-sectional study. A five-item geriatric depression scale was used to assess depression symptoms. Then, an eight-item University of California at Los Angeles Loneliness Scale was used to assess loneliness. Moreover, the FRAIL scale and Mini-Mental State Examination were used to assess cognitive frailty. Furthermore, regression and bootstrap analyses were used to explore the mediating role of loneliness in depression symptoms and cognitive frailty. Results: Loneliness mediates the association between depression symptoms and cognitive frailty (95% CI = 0.164~0.615), and after adjusting for loneliness, the direct effect is no longer significant (95% CI = −0.113~1.318, p = 0.099). Conclusions: Results show that the effect of cognitive frailty is not depression symptoms but loneliness. All levels of society (the government, medical institutions, and communities) need to pay more attention to the mental health of the older adults, screen for loneliness, and take timely intervention and treatment measures. They should also build an age-friendly society and promote active aging.
Background:
This study aims to identify the status of successful aging and the factors influencing empty-nest elderly in China based on the social-ecological system theory.
Methods:
The data came from the follow-up survey (2018) of the China Health and Retirement Longitudinal Study and 3074 empty-nesters aged 60 and over are included. Chi-squared tests and logistic regressions were used to identify factors associated with successful aging.
Results:
The successful aging rate of empty-nesters in China was 5.9%. The results of the multifactor analysis showed that younger age, higher education level, good self-rated health, good hearing, high life satisfaction, availability of financial resources at the microsystem level, higher frequency of contact with children at the mesosystem level, and medical insurance at the macrosystem level were the contributing influencing factors for successful aging of empty-nesters in China.
Conclusion:
This study is an important attempt to explore the successful aging of empty-nesters in China. Because this study is based on social-ecological system theory, it confirms the important role of individual characteristics of older adults and their surrounding environment in achieving successful aging. Therefore, we should pay attention not only to the individual characteristics of the elderly, but also to the role of the surrounding environment on the health of the elderly, so that we can develop intervention measures to promote their successful aging.
Background
Cognitive frailty (CF) is characterized by the simultaneous presence of physical frailty and cognitive impairment. Previous studies have investigated its prevalence and impact on different adverse health-related outcomes. Few studies have focused on the progression and reversibility of CF and their potential predictors.
Methods
Data were derived from the China Health and Retirement Longitudinal Study (CHARLS). A total of 4051 older adults with complete data on three waves of the survey (2011, 2013, and 2015) were included and categorized into four groups: normal state (NS), cognitive impairment (CI) only, physical frailty (PF) only and CF (with both PF and CI). A multi-state Markov model was constructed to explore the transitions and predicting factors of CF.
Results
The incidence and improvement rates of CF were 1.70 and 11.90 per 100 person-years, respectively. The 1-year transition probability of progression to CF in those with CI was higher than that in the PF population (0.340 vs. 0.054), and those with CF were more likely to move to PF (0.208). Being female [hazard ratio (HR) = 1.46, 95%CI = 1.06, 2.02)], dissatisfied with life (HR = 4.94, 95%CI = 1.04, 23.61), had a history of falls (HR = 2.36, 95%CI = 1.02, 5.51), rural household registration (HR = 2.98, 95%CI = 1.61, 5.48), multimorbidity (HR = 2.17, 95%CI = 1.03, 4.59), and depression (HR = 1.75, 95%CI = 1.26, 2.45) increased the risk of progression to CF, whereas literacy (HR = 0.46, 95%CI = 0.33, 0.64) decreased such risk. Depression (HR = 0.43, 95%CI = 0.22, 0.84) reduced the likelihood of CF improvement, whereas literacy (HR = 2.23, 95%CI = 1.63, 3.07) increased such likelihood.
Conclusions
Cognitive frailty is a dynamically changing condition in older adults. Possible interventions aimed at preventing the onset and facilitating the recovery of cognitive frailty should focus on improving cognitive function in older adults.
Aims:
Although evidence suggests that cognitive decline and physical frailty in elderly patients with heart failure (HF) are associated with prognosis, the impact of concurrent physical frailty and cognitive impairment, that is, cognitive frailty, on prognosis has yet to be fully investigated. The current study sought to investigate the prevalence and prognostic impact of cognitive frailty in elderly patients with HF.
Methods and results:
This study is a sub-analysis of FRAGILE-HF, a prospective multicentre observational study involving patients aged ≥65 years hospitalized for HF. The Fried criteria and Mini-Cog were used to diagnose physical frailty and cognitive impairment, respectively. The association between cognitive frailty and the combined endpoint of mortality and HF rehospitalization within 1 year was then evaluated. Among the 1332 patients identified, 1215 who could be assessed using Mini-Cog and the Fried criteria were included in this study. Among those included, 279 patients (23.0%) had cognitive frailty. During the follow-up 1 year after discharge, 398 combined events were observed. Moreover, cognitive frailty was determined to be associated with a higher incidence of combined events (log-rank: P = 0.0146). This association was retained even after adjusting for other prognostic factors (hazard ratio: 1.55, 95% confidence interval: 1.13-2.13). Furthermore, a sensitivity analysis using grip strength, short physical performance battery, and gait speed to determine physical frailty instead of the Fried criteria showed similar results.
Conclusions:
This cohort study found that 23% of elderly patients with HF had cognitive frailty, which was associated with a 1.55-fold greater risk for combined events within 1 year compared with patients without cognitive frailty.
Objective
Currently, the prevalence of CF (Cognitive Frailty) is not very clear, and the relationship between CF and its associated risk factors has not been accurately evaluated. Therefore, it is necessary to conduct a systematic review and meta-analysis further to understand CF's prevalence and associated factors.
Methods
Embase, PubMed, Web of Science, Ovid, and Cochrane were systematically searched for articles exploring the prevalence of CF, the deadline of searching date was up to March 2021. For the prevalence of CF, the events of CF and the total number of patients in every included study were extracted to estimate the prevalence of CF. For associated factors of CF, Odds Ratios (ORs) with (corresponding) 95% confidence intervals (CIs) were used for estimations.
Results
Firstly, the estimated prevalence of CF I (Cognitive Frailty in the model I) was 16%, 95% CI (0.13–0.19), and the estimated prevalence of CF II (Cognitive Frailty in model II) was 6%, 95% CI (0.05–0.07). Secondly, both lower engagement in activities and age were calculated to be independent risk factors of CF, and the OR (95% CI) was 3.31 (2.28–4.81) and 1.10 (1.04–1.16), respectively. Finally, depression was also a prominent risk factor of CF, with the overall OR (95% CI) as 1.57 (1.32–1.87).
Conclusion
CF was a high prevalence in community older. The various assessment scales and the different cutoff values of diagnostic criteria would affect the prevalence of CF. Lower engagement in activities, age, and depression was the risky factor of CF.
Systematic Review Registration
http://www.crd.york.ac.uk/PROSPERO/ , identifier: CRD42019121369.
Purpose
A prediction model for 4-year risk of metabolic syndrome in adults was previously developed and internally validated. However, external validity or generalizability for this model was not assessed so it is not appropriate for clinical application. We aimed to externally validate this model based on a retrospective cohort.
Patients and Methods
A retrospective cohort design and a temporal validation strategy were used in this study based on a dataset from 1 January 2015 to 31 December 2018. Multiple imputation was used for missing values. Model performance was evaluated by using discrimination, calibration (calibration plot, calibration slope, and calibration intercept), overall performance (Brier score), and decision curve analysis.
Results
In external validation, the C-statistic was 0.782 (95% CI, 0.771–0.793). The calibration plot shows good calibration, calibration slope was 1.006 (95% CI, −0.011–1.063), and calibration intercept was −0.045 (95% CI, −0.113–0.022). Brier score was 0.164.The discrimination and calibration of the prediction model were good in temporal external validation.
Conclusion
The discrimination and calibration of the prediction model were satisfactory in the temporal external validation. However, clinicians should be aware that this prediction model was developed and validated in a tertiary setting. It is strongly recommended that further studies validate this model in international cohorts and large, prospective cohorts in different institutions.
Frailty is one of the most important geriatric syndromes, which can be associated with increased risk for incident disability and hospitalization. Developing a real-time classification model of elderly frailty level could be beneficial for designing a clinical predictive assessment tool. Hence, the objective of this study was to predict the elderly frailty level utilizing the machine learning approach on skeleton data acquired from a Kinect sensor. Seven hundred and eighty-seven community elderly were recruited in this study. The Kinect data were acquired from the elderly performing different functional assessment exercises including: (1) 30-s arm curl; (2) 30-s chair sit-to-stand; (3) 2-min step; and (4) gait analysis tests. The proposed methodology was successfully validated by gender classification with accuracies up to 84 percent. Regarding frailty level evaluation and prediction, the results indicated that support vector classifier (SVC) and multi-layer perceptron (MLP) are the most successful estimators in prediction of the Fried’s frailty level with median accuracies up to 97.5 percent. The high level of accuracy achieved with the proposed methodology indicates that ML modeling can identify the risk of frailty in elderly individuals based on evaluating the real-time skeletal movements using the Kinect sensor.
Reliable prediction of outcomes of aneurysmal subarachnoid hemorrhage (aSAH) based on factors available at patient admission may support responsible allocation of resources as well as treatment decisions. Radiographic and clinical scoring systems may help clinicians estimate disease severity, but their predictive value is limited, especially in devising treatment strategies. In this study, we aimed to examine whether a machine learning (ML) approach using variables available on admission may improve outcome prediction in aSAH compared to established scoring systems. Combined clinical and radiographic features as well as standard scores (Hunt & Hess, WFNS, BNI, Fisher, and VASOGRADE) available on patient admission were analyzed using a consecutive single-center database of patients that presented with aSAH ( n = 388). Different ML models (seven algorithms including three types of traditional generalized linear models, as well as a tree bosting algorithm, a support vector machine classifier (SVMC), a Naive Bayes (NB) classifier, and a multilayer perceptron (MLP) artificial neural net) were trained for single features, scores, and combined features with a random split into training and test sets (4:1 ratio), ten-fold cross-validation, and 50 shuffles. For combined features, feature importance was calculated. There was no difference in performance between traditional and other ML applications using traditional clinico-radiographic features. Also, no relevant difference was identified between a combined set of clinico-radiological features available on admission (highest AUC 0.78, tree boosting) and the best performing clinical score GCS (highest AUC 0.76, tree boosting). GCS and age were the most important variables for the feature combination. In this cohort of patients with aSAH, the performance of functional outcome prediction by machine learning techniques was comparable to traditional methods and established clinical scores. Future work is necessary to examine input variables other than traditional clinico-radiographic features and to evaluate whether a higher performance for outcome prediction in aSAH can be achieved.
Background: Early detection of potential depression among elderly people is conducive for timely preventive intervention and clinical care to improve quality of life. Therefore, depression prediction considering sequential progression patterns in elderly needs to be further explored.
Methods: We selected 1,538 elderly people from Chinese Longitudinal Healthy Longevity Study (CLHLS) wave 3–7 survey. Long short-term memory (LSTM) and six machine learning (ML) models were used to predict different depression risk factors and the depression risks in the elderly population in the next two years. Receiver operating curve (ROC) and decision curve analysis (DCA) were used to evaluate the prediction accuracy of the reference model and ML models.
Results: The area under the ROC curve (AUC) values of logistic regression with lasso regularisation (AUC=0.629, p-value=0.020) was the highest among ML models. DCA results showed that the net benefit of six ML models was similar (threshold: 0.00-0.10), the net benefit of lasso regression was the largest (threshold: 0.10-0.17 and 0.22-0.25), and the net benefit of DNN was the largest (threshold: 0.17–0.22 and 0.25–0.40). In two ML models, activities of daily living (ADL)/ instrumental ADL (IADL), self-rated health, marital status, arthritis, and number of cohabiting were the most important predictors for elderly with depression.
Limitations: The retrospective waves used in the LSTM model need to be further increased.
Conclusion: The decision support system based on the proposed LSTM+ML model may be very valuable for doctors, nurses and community medical providers for early diagnosis and intervention.
Our objectives were to evaluate: 1) the associations of cognitive frailty with various health outcomes including disability, hospitalization, and death; 2) whether the associations differed by multimorbidity. We included data of 5113 Chinese older adults (aged 60+ years) who had baseline cognition and physical frailty assessments (2011 wave) and follow-up for 4 years. About 16.0% (n=820) had cognitive impairment; 6.7% (n=342) had physical frailty; and 1.6% (n=82) met criteria for cognitive frailty. Both cognitive impairment (odds ratios (ORs) range: 1.41 to 2.11) and physical frailty (ORs range: 1.51 to 2.43) were independently associated with basic activities of daily living (BADL), instrumental ADL (IADL), mobility disability, hospitalization, and death among participants without that corresponding outcome at baseline, even after accounting for covariates. Relative to participants who had normal cognition and were nonfrail, those with cognitive frailty had the highest risk for IADL disability (OR=3.40, 95% CI, 1.23-9.40) and death (OR=3.89, 95% CI, 2.25-6.47). We did not find significant interaction effects between cognitive frailty and multimorbidity (Pinteractions>0.05). Overall, cognitive frailty was associated with disability and death, independent of multimorbidity. This highlights the importance of assessing cognitive frailty in the community to promote primary and secondary preventions for healthy aging.
Smoking-induced noncommunicable diseases (SiNCDs) have become a significant threat to public health and cause of death globally. In the last decade, numerous studies have been proposed using artificial intelligence techniques to predict the risk of developing SiNCDs. However, determining the most significant features and developing interpretable models are rather challenging in such systems. In this study, we propose an efficient extreme gradient boosting (XGBoost) based framework incorporated with the hybrid feature selection (HFS) method for SiNCDs prediction among the general population in South Korea and the United States. Initially, HFS is performed in three stages: (I) significant features are selected by t-test and chi-square test; (II) multicollinearity analysis serves to obtain dissimilar features; (III) final selection of best representative features is done based on least absolute shrinkage and selection operator (LASSO). Then, selected features are fed into the XGBoost predictive model. The experimental results show that our proposed model outperforms several existing baseline models. In addition, the proposed model also provides important features in order to enhance the interpretability of the SiNCDs prediction model. Consequently, the XGBoost based framework is expected to contribute for early diagnosis and prevention of the SiNCDs in public health concerns.
Objectives
This study aimed to identify the influencing factors associated with long onset‐to‐door time and establish predictive models that could help to assess the probability of prehospital delay in populations with a high risk for stroke.
Materials and Methods
Patients who were diagnosed with acute ischemic stroke (AIS) and hospitalized between 1 November 2018 and 31 July 2019 were interviewed, and their medical records were extracted for data analysis. Two machine learning algorithms (support vector machine and Bayesian network) were applied in this study, and their predictive performance was compared with that of the classical logistic regression models after using several variable selection methods. Timely admission (onset‐to‐door time < 3 hr) and prehospital delay (onset‐to‐door time ≥ 3 hr) were the outcome variables. We computed the area under curve (AUC) and the difference in the mean AUC values between the models.
Results
A total of 450 patients with AIS were enrolled; 57 (12.7%) with timely admission and 393 (87.3%) patients with prehospital delay. All models, both those constructed by logistic regression and those by machine learning, performed well in predicting prehospital delay (range mean AUC: 0.800–0.846). The difference in the mean AUC values between the best performing machine learning model and the best performing logistic regression model was negligible (0.014; 95% CI: 0.013–0.015).
Conclusions
Machine learning algorithms were not inferior to logistic regression models for prediction of prehospital delay after stroke. All models provided good discrimination, thereby creating valuable diagnostic programs for prehospital delay prediction.
Objective: Decision-tree methods are machine-learning methods which provide results that are relatively easy to interpret and apply by human decision makers. The resulting decision trees show how baseline patient characteristics can be combined to predict treatment outcomes for individual patients, for example. This paper introduces GLMM trees, a decision-tree method for multilevel and longitudinal data.
Method: To illustrate, we apply GLMM trees to a dataset of 3,256 young people (mean age 11.33, 48% girls) receiving treatment at one of several mental-health service providers in the UK. Two treatment outcomes (mental-health difficulties scores corrected for baseline) were regressed on 18 demographic, case and severity characteristics at baseline. We compared the performance of GLMM trees with that of traditional GLMMs and random forests.
Results: GLMM trees yielded modest predictive accuracy, with cross-validated multiple R values of .18 and .25. Predictive accuracy did not differ significantly from that of traditional GLMMs and random forests, while GLMM trees required evaluation of a lower number of variables.
Conclusion: GLMM trees provide a useful data-analytic tool for clinical prediction problems. The supplemental material provides a tutorial for replicating the GLMM tree analyses in R.
Background
Using big data and the theory of cumulative deficits to develop the multimorbidity frailty index (mFI) has become a widely accepted approach in public health and health care services. However, constructing the mFI using the most critical determinants and stratifying different risk groups with dose-response relationships remain major challenges in clinical practice.
Objective
This study aimed to develop the mFI by using machine learning methods that select variables based on the optimal fitness of the model. In addition, we aimed to further establish 4 entities of risk using a machine learning approach that would achieve the best distinction between groups and demonstrate the dose-response relationship.
Methods
In this study, we used Taiwan’s National Health Insurance Research Database to develop a machine learning multimorbidity frailty index (ML-mFI) using the theory of cumulative diseases/deficits of an individual older person. Compared to the conventional mFI, in which the selection of diseases/deficits is based on expert opinion, we adopted the random forest method to select the most influential diseases/deficits that predict adverse outcomes for older people. To ensure that the survival curves showed a dose-response relationship with overlap during the follow-up, we developed the distance index and coverage index, which can be used at any time point to classify the ML-mFI of all subjects into the categories of fit, mild frailty, moderate frailty, and severe frailty. Survival analysis was conducted to evaluate the ability of the ML-mFI to predict adverse outcomes, such as unplanned hospitalizations, intensive care unit (ICU) admissions, and mortality.
Results
The final ML-mFI model contained 38 diseases/deficits. Compared with conventional mFI, both indices had similar distribution patterns by age and sex; however, among people aged 65 to 69 years, the mean mFI and ML-mFI were 0.037 (SD 0.048) and 0.0070 (SD 0.0254), respectively. The difference may result from discrepancies in the diseases/deficits selected in the mFI and the ML-mFI. A total of 86,133 subjects aged 65 to 100 years were included in this study and were categorized into 4 groups according to the ML-mFI. Both the Kaplan-Meier survival curves and Cox models showed that the ML-mFI significantly predicted all outcomes of interest, including all-cause mortality, unplanned hospitalizations, and all-cause ICU admissions at 1, 5, and 8 years of follow-up (P<.01). In particular, a dose-response relationship was revealed between the 4 ML-mFI groups and adverse outcomes.
Conclusions
The ML-mFI consists of 38 diseases/deficits that can successfully stratify risk groups associated with all-cause mortality, unplanned hospitalizations, and all-cause ICU admissions in older people, which indicates that precise, patient-centered medical care can be a reality in an aging society.
Background:
Frailty is one of the most critical age-related conditions in older adults. It is often recognized as a syndrome of physiological decline in late life, characterized by a marked vulnerability to adverse health outcomes. A clear operational definition of frailty, however, has not been agreed so far. There is a wide range of studies on the detection of frailty and their association with mortality. Several of these studies have focused on the possible risk factors associated with frailty in the elderly population while predicting who will be at increased risk of frailty is still overlooked in clinical settings.
Objective:
The objective of our study was to develop predictive models for frailty conditions in older people using different machine learning methods based on a database of clinical characteristics and socioeconomic factors.
Methods:
An administrative health database containing 1,095,612 elderly people aged 65 or older with 58 input variables and 6 output variables was used. We first identify and define six problems/outputs as surrogates of frailty. We then resolve the imbalanced nature of the data through resampling process and a comparative study between the different machine learning (ML) algorithms - Artificial neural network(ANN), Genetic programming (GP), Support vector machines (SVM), Random Forest (RF), Logistic regression (LR) and Decision tree (DT) - was carried out. The performance of each model was evaluated using a separate unseen dataset.
Results:
Predicting mortality outcome has shown higher performance with ANN (TPR 0.81, TNR 0.76, accuracy 0.78, F1-score 0.79) and SVM (TPR 0.77, TNR 0.80, accuracy 0.79, F1-score 0.78) than predicting the other outcomes. On average, over the six problems, the DT classifier has shown the lowest accuracy, while other models (GP, LR, RF, ANN, and SVM) performed better. All models have shown lower accuracy in predicting an event of an emergency admission with red code than predicting fracture and disability. In predicting urgent hospitalization, only SVM achieved better performance (TPR 0.75, TNR 0.77, accuracy 0.73, F1-score 0.76) with the 10-fold cross validation compared with other models in all evaluation metrics.
Conclusions:
We developed machine learning models for predicting frailty conditions (mortality, urgent hospitalization, disability, fracture, and emergency admission). The results show that the prediction performance of machine learning models significantly varies from problem to problem in terms of different evaluation metrics. Through further improvement, the model that performs better can be used as a base for developing decision-support tools to improve early identification and prediction of frail older adults.
Objectives
Cognitive frailty was notable target for the prevention of adverse health outcomes in future. The goal of this study was to use a population-based survey to investigate cognitive frailty phenotypes and potentially sociodemographic factors in elderly Chinese individuals.
Design
Cross-sectional study.
Setting
General community.
Participants
A total of 5328 elderly adults (aged 60 years or older, mean age 71.36 years) enrolled in the Shanghai study of health promotion for elderly individuals with frailty.
Measurements
The 5-item FRAIL scale and the 3-item Rapid Cognitive Screen tools were used to assess physical frailty and cognitive impairment, including dementia or mild cognitive impairment (MCI). Physical frailty was diagnosed by limitations in 3 or more of the FRAIL scale domains and pre-physical frailty by 1–2 limitations. Subjective cognitive decline (SCD) and pre-MCI SCD, was diagnosed with two self-report measures based on memory and other cognitive domains in elderly adults.
Results
Of the participating individuals, 97.17% (n= 5177, female 53.4%) were eligible. Notably, 9.67%, 41.61% and 35.20% of participants were MCI, SCD and pre-MCI SCD; 35.86% and 4.41% exhibited physical pre-frailty and frailty; and 19.86% and 6.30% exhibited reversible and potential reversible cognitive frailty. Logistic regression analyses indicated that physical frailty phenotypes were significantly associated with MCI with SCD, and pre-MCI with SCD. Older single females with a high education level were more likely to exhibit the reversible cognitive frailty; and younger elderly individuals with a middle education level were at lower risk for potentially reversible cognitive frailty.
Conclusions
The prevalence of pre-physical and reversible cognitive frailty was high in elderly individuals and age was the most significant risk factor for all types of frailty phenotypes. To promote the rapid screening protocol of cognitive frailty in community-dwelling elderly is important to find high-risk population, implement effective intervention, and decrease adverse prognosis.
Background
Increasing life expectancy results in more elderly people struggling with age related diseases and functional conditions. This poses huge challenges towards establishing new approaches for maintaining health at a higher age. An important aspect for age related deterioration of the general patient condition is frailty. The frailty syndrome is associated with a high risk for falls, hospitalization, disability, and finally increased mortality. Using predictive data mining enables the discovery of potential risk factors and can be used as clinical decision support system, which provides the medical doctor with information on the probable clinical patient outcome. This enables the professional to react promptly and to avert likely adverse events in advance.
Methods
Medical data of 474 study participants containing 284 health related parameters, including questionnaire answers, blood parameters and vital parameters from the Toledo Study for Healthy Aging (TSHA) was used. Binary classification models were built in order to distinguish between frail and non-frail study subjects.
Results
Using the available TSHA data and the discovered potential predictors, it was possible to design, develop and evaluate a variety of different predictive models for the frailty syndrome. The best performing model was the support vector machine (SVM, 78.31%). Moreover, a methodology was developed, making it possible to explore and to use incomplete medical data and further identify potential predictors and enable interpretability.
Conclusions
This work demonstrates that it is feasible to use incomplete, imbalanced medical data for the development of a predictive model for the frailty syndrome. Moreover, potential predictive factors have been discovered, which were clinically approved by the clinicians. Future work will improve prediction accuracy, especially with regard to separating the group of frail patients into frail and pre-frail ones and analyze the differences among them.
Objective: To compare performance of logistic regression (LR) with machine learning (ML) for clinical prediction modeling.
Study design and setting: We conducted a Medline literature search (1/2016 to 8/2017), and extracted comparisons between LR and ML models for binary outcomes.
Results: We included 71 out of 927 studies. The median sample size was 1250 (range 72-3,994,872), with 19 predictors considered (range 5-563) and 8 events per predictor (range 0.3-6,697). The most common ML methods were classification trees (30 studies), random forests (28), artificial neural networks (26), and support vector machines (24). Sixty-four (90%) studies used the area under the receiver operating characteristic curve (AUC) to assess discrimination. Calibration was not addressed in 56 (79%) studies. We identified 282 comparisons between a LR and ML model (AUC range, 0.52-0.99).
For 145 comparisons at low risk of bias, the difference in logit(AUC) between LR and ML was 0.00 (95% confidence interval, -0.18 to 0.18). For 137 comparisons at high risk of bias, logit(AUC) was 0.34 (0.20 to 0.47) higher for ML.
Conclusions: We found no evidence of superior performance of ML over LR for clinical prediction modeling, but improvements in methodology and reporting are needed for studies that compare modeling algorithms.
Bayesian network is an increasingly popular method in modeling uncertain and complex problems, because its interpretability is often more useful than plain prediction. To satisfy the core requirement in medical research to obtain interpretable prediction with high accuracy, we constructed an inference engine for post-stroke outcomes based on Bayesian network classifiers. The prediction system that was trained on data of 3,605 patients with acute stroke forecasts the functional independence at 3 months and the mortality 1 year after stroke. Feature selection methods were applied to eliminate less relevant and redundant features from 76 risk variables. The Bayesian network classifiers were trained with a hill-climbing searching for the qualified network structure and parameters measured by maximum description length. We evaluated and optimized the proposed system to increase the area under the receiver operating characteristic curve (AUC) while ensuring acceptable sensitivity for the class-imbalanced data. The performance evaluation demonstrated that the Bayesian network with selected features by wrapper-type feature selection can predict 3-month functional independence with an AUC of 0.889 using only 19 risk variables and 1-year mortality with an AUC of 0.893 using 24 variables. The Bayesian network with 50 features filtered by information gain can predict 3-month functional independence with an AUC of 0.875 and 1-year mortality with an AUC of 0.895. We also built an online prediction service, Yonsei Stroke Outcome Inference System, to substantialize the proposed solution for patients with stroke.
Background.:
Frailty is an age-related clinical syndrome of decreased resilience to stressors and is associated with numerous adverse outcomes. Although there is preponderance of literature on frailty in developed countries, limited investigations have been conducted in less developed regions including China-a country that has the world's largest aging population. We examined frailty prevalence in China by socio-demographics and geographic region, and investigated correlates of frailty.
Methods.:
Participants were 5301 adults aged ≥60 years from the China Health and Retirement Longitudinal Study. Frailty was identified by the validated physical frailty phenotype (PFP) scale. We estimated frailty prevalence in the overall sample and by socio-demographics. We identified age-adjusted frailty prevalence by geographical region. Bivariate associations of frailty with health and function measures were evaluated by chi-squared test and analysis of variance.
Results.:
We found 7.0% of adults aged ≥60 years were frail. Frailty is more prevalent at advanced ages, among women, and persons with low education. Age-adjusted frailty prevalence ranged from 3.3% in the Southeast and the Northeast to 9.1% in the Northwest, and was >1.5 times higher in rural vs. urban areas. Frail vs. nonfrail persons had higher prevalence of comorbidities, falls, disability, and functional limitation.
Conclusions.:
We demonstrated the utility of the PFP scale in identifying frail Chinese elders, and found substantial socio-demographic and regional disparities in frailty prevalence. The PFP scale may be incorporated into clinical practice in China to identify the most vulnerable elders to reduce morbidity, prevent disability, and enable more efficient use of healthcare resources.
Introduction:
Subjective cognitive decline (SCD) manifesting before clinical impairment could serve as a target population for early intervention trials in Alzheimer's disease (AD). A working group, the Subjective Cognitive Decline Initiative (SCD-I), published SCD research criteria in the context of preclinical AD. To successfully apply them, a number of issues regarding assessment and implementation of SCD needed to be addressed.
Methods:
Members of the SCD-I met to identify and agree on topics relevant to SCD criteria operationalization in research settings. Initial ideas and recommendations were discussed with other SCD-I working group members and modified accordingly.
Results:
Topics included SCD inclusion and exclusion criteria, together with the informant's role in defining SCD presence and the impact of demographic factors.
Discussion:
Recommendations for the operationalization of SCD in differing research settings, with the aim of harmonization of SCD measurement across studies are proposed, to enhance comparability and generalizability across studies.
Background:
Depressive symptoms and memory impairment are prevalent in patients with chronic heart failure (CHF). Although the mechanisms remain to be elucidated, the hippocampus (an important brain area for emotion and memory) may be a possible neural substrate for these symptoms.Methods and Results:We prospectively enrolled 40 Stage C patients, who had past or current CHF symptoms, and as controls 40 Stage B patients, who had structural heart disease but had never had symptoms of HF, in the Brain Assessment and Investigation in Heart Failure Trial (B-HeFT) (UMIN000008584). As the primary index, we measured cerebral blood flow (CBF) in the 4 anterior-posterior segments of the hippocampus, using brain MRI analysis. Depressive symptoms, immediate memory (IM) and delayed memory (DM) were assessed using the Geriatric Depression Scale (GDS), and Wechsler Memory Scale-revised (WMS-R), respectively. Hippocampus CBF in the most posterior segment was significantly lower in the Stage C than in the Stage B group (P=0.029 adjusted for Holm's method). Multiple regression analysis identified a significant association between hippocampus CBF and GDS or DM score in the Stage C group (all P<0.05). Scores of GDS, IM and DM were significantly lower in Stage C patients with hippocampus CBF above the median than in those with hippocampus CBF below the median (all P<0.05).
Conclusions:
Hippocampus abnormalities were associated with depressive symptoms and cognitive impairment in CHF patients.
Frailty is a complex and heterogeneous clinical syndrome. Cognitive frailty has been considered a subtype of frailty. In this study, we refine the definition of cognitive frailty based on existing reports about frailty and the latest progress in cognition research. We obtain evidence from the literature regarding the role of pre-physical frailty in pathological aging. We propose that cognitive impairment of cognitive frailty results from physical or pre-physical frailty and comprises two subtypes: the reversible and the potentially reversible. Reversible cognitive impairment is indicated by SCD and/or positive fluid and imaging biomarkers of amyloid-β accumulation and neurodegeneration. Potentially reversible cognitive impairment is MCI (CDR=0.5). Based on the severity of cognitive impairment, it is possible to determine the primary and secondary preventative measures for cognitive frailty. We further determine whether SCD is a component of pre-clinical AD or the early stage of other neurodegenerative diseases, which is required for guiding personal clinical intervention.
Copyright © 2014. Published by Elsevier B.V.
There is increasing evidence that subjective cognitive decline (SCD) in individuals with unimpaired performance on cognitive tests may represent the first symptomatic manifestation of Alzheimer's disease (AD). The research on SCD in early AD, however, is limited by the absence of common standards. The working group of the Subjective Cognitive Decline Initiative (SCD-I) addressed this deficiency by reaching consensus on terminology and on a conceptual framework for research on SCD in AD. In this publication, research criteria for SCD in pre-mild cognitive impairment (MCI) are presented. In addition, a list of core features proposed for reporting in SCD studies is provided, which will enable comparability of research across different settings. Finally, a set of features is presented, which in accordance with current knowledge, increases the likelihood of the presence of preclinical AD in individuals with SCD. This list is referred to as SCD plus.
The China Health and Retirement Longitudinal Study (CHARLS) is a nationally representative longitudinal survey of persons in China 45 years of age or older and their spouses, including assessments of social, economic, and health circumstances of community-residents. CHARLS examines health and economic adjustments to rapid ageing of the population in China. The national baseline survey for the study was conducted between June 2011 and March 2012 and involved 17 708 respondents. CHARLS respondents are followed every 2 years, using a face-to-face computer-assisted personal interview (CAPI). Physical measurements are made at every 2-year follow-up, and blood sample collection is done once in every two follow-up periods. A pilot survey for CHARLS was conducted in two provinces of China in 2008, on 2685 individuals, who were resurveyed in 2012. To ensure the adoption of best practices and international comparability of results, CHARLS was harmonized with leading international research studies in the Health and Retirement Study (HRS) model. Requests for collaborations should be directed to Dr Yaohui Zhao ([email protected]
/* */). All data in CHARLS are maintained at the National School of Development of Peking University and will be accessible to researchers around the world at the study website. The 2008 pilot data for CHARLS are available at: http://charls.ccer.edu.cn/charls/. National baseline data for the study are expected to be released in January 2013.
The performance of prediction models can be assessed using a variety of methods and metrics. Traditional measures for binary and survival outcomes include the Brier score to indicate overall model performance, the concordance (or c) statistic for discriminative ability (or area under the receiver operating characteristic [ROC] curve), and goodness-of-fit statistics for calibration.Several new measures have recently been proposed that can be seen as refinements of discrimination measures, including variants of the c statistic for survival, reclassification tables, net reclassification improvement (NRI), and integrated discrimination improvement (IDI). Moreover, decision-analytic measures have been proposed, including decision curves to plot the net benefit achieved by making decisions based on model predictions.We aimed to define the role of these relatively novel approaches in the evaluation of the performance of prediction models. For illustration, we present a case study of predicting the presence of residual tumor versus benign tissue in patients with testicular cancer (n = 544 for model development, n = 273 for external validation).We suggest that reporting discrimination and calibration will always be important for a prediction model. Decision-analytic measures should be reported if the predictive model is to be used for clinical decisions. Other measures of performance may be warranted in specific applications, such as reclassification metrics to gain insight into the value of adding a novel predictor to an established model.
Objective:
To develop the wed-based system for predicting risk of (pre)frailty among community-dwelling older adults.
Materials and methods:
(Pre)frailty was determined by physical frailty phenotype scale. A total of 2802 robust older adults aged ≥60 years from the China Health and Retirement Longitudinal Study (CHARLS) 2013-2015 survey were randomly assigned to derivation or internal validation cohort at a ratio of 8:2. Logistic regression, Random Forest, Support Vector Machine and eXtreme Gradient Boosting (XGBoost) were used to construct (pre)frailty prediction models. The Grid search and 5-fold cross validation were combined to find the optimal parameters. All models were evaluated externally using the temporal validation method via the CHARLS 2011-2013 survey. The (pre)frailty predictive system was web-based and built upon representational state transfer application program interfaces.
Results:
The incidence of (pre)frailty was 34.2 % in derivation cohort, 34.8 % in internal validation cohort, and 32.4 % in external validation cohort. The XGBoost model achieved better prediction performance in derivation and internal validation cohorts, and all models had similar performance in external validation cohort. For internal validation cohort, XGBoost model showed acceptable discrimination (AUC: 0.701, 95 % CI: [0.655-0.746]), calibration (p-value of Hosmer-Lemeshow test > 0.05; good agreement on calibration plot), overall performance (Brier score: 0.200), and clinical usefulness (decision curve analysis: more net benefit than default strategies within the threshold of 0.15-0.80). The top 3 of 14 important predictors generally available in community were age, waist circumference and cognitive function. We embedded XGBoost model into the server and this (pre)frailty predictive system is accessible at http://www.frailtyprediction.com.cn. A nomogram was also conducted to enhance the practical use.
Conclusions:
A user-friendly web-based system was developed with good performance to assist healthcare providers to measure the probability of being (pre)frail among community-dwelling older adults in the next two years, facilitating the early identification of high-risk population of (pre)frailty. Further research is needed to validate this preliminary system across more controlled cohorts.
Aims:
Cognitive frailty can increase the risk of adverse health outcomes in older adults. Estimates of the prevalence of cognitive frailty among older adults with diabetes varied widely in literature. This study aimed to conduct a systematic review and meta-analysis to assess the pooled prevalence of cognitive frailty and risk factors in community-dwelling older adults with diabetes, providing evidence for healthcare professionals to better understand the status of cognitive frailty and help develop effective interventions.
Methods:
Databases of PubMed, Web of Science, Cochrane Library, Embase, Cumulative Index of Nursing and Allied Health, Proquest, China National Knowledge Infrastructure and China Biology Medicine were searched from inception to February 10th, 2022. The reviewers independently selected studies, extracted data and assessed the quality of studies. Pooled prevalence of cognitive frailty and risk factors were estimated. Subgroup analysis, meta-regression analysis, sensitivity analysis and publication bias were also conducted.
Results:
A total of 15 studies with 6377 participants were included in this review. The pooled prevalence of cognitive frailty was 11% (95%CI=7.9-14%) in community-dwelling older adults with diabetes. Pooled estimates showed that increasing age, higher level of HbAc1, shorter night sleep duration and depression were risk factors, and regular exercise was the protective factor of cognitive frailty in community-dwelling older adults with diabetes.
Conclusion:
Cognitive frailty was common in community-dwelling older adults with diabetes. Routine screening of cognitive frailty and effective interventions should be implemented for this population in community settings.
Objectives
Cognitive frailty, a potentially reversible condition describing the concurrence of physical frailty and mild cognitive impairment (MCI), has been recently proposed to incorporate subjective cognitive decline (SCD), a reversible pre-MCI state with more readily available cognitive reserve, as well as pre-physical frailty. Reversible cognitive frailty has been associated with dementia and mortality. We aimed to examine the association of reversible cognitive frailty with other adverse outcomes including disability, poor quality of life (QOL), depression, and hospitalization.
Methods
This was a cohort study with 1-year follow-up among 735 Chinese community-dwelling older adults with intact cognition. Reversible cognitive frailty was operationalized with the presence of pre-physical or physical frailty identified by the Frailty Phenotype and SCD identified by the simplified SCD questionnaire including four self-report cognitive domains of memory, naming, orientation, and mathematical reasoning. Adverse outcomes included incident Activities of Daily Living (ADL)-Instrumental ADL (IADL) disability, poor physical, mental and overall QOL, depression, and hospitalization over 1-year follow-up.
Results
The prevalence of reversible cognitive frailty was 27.8%. Participants with reversible cognitive frailty had higher risk of the incidence of ADL-IADL disability, poor physical QOL, poor mental QOL, poor overall QOL, and depression (Odds Ratios: 1.67–4.38, P < 0.05), but not higher risk of hospitalization over 1-year follow-up.
Conclusion
Reversible cognitive frailty was not uncommon and associated with incident disability, poor QOL, and depression among community-dwelling older adults. Early identification of reversible cognitive frailty can facilitate targeted interventions and may promote independence in older adults.
Supplemental data for this article is available online at http://dx.doi.org/10.1080/13607863.2021.2011835
Since the concept and operational definition of “cognitive frailty” (simultaneous presence of physical frailty and cognitive impairment without concurrent dementia) were proposed by the International Academy of Nutrition and Aging and the International Association of Gerontology and Geriatrics, cognitive frailty has been widely investigated. This review is intended to address the operational definition of cognitive frailty, its consequences, contributing factors and underlying mechanisms, as well as interventions for cognitive frailty. Although the definitions and assessments of cognitive frailty vary among researchers, older adults with both physical frailty and cognitive impairment are shown to be at higher risk of adverse health outcomes, including death, disability, hospitalization and incident dementia, than those with either condition alone. While the underlying mechanisms of cognitive frailty are still unclear, factors shown to be associated with cognitive frailty include sociodemographic factors, social status, nutritional status, geriatric syndrome, physical and cognitive activities, functional status, comorbidities, medication use, gut‐derived metabolites and structural changes in the brain. Accumulating evidence indicates the need for comprehensive geriatric assessment that helps identify the possible causes of cognitive frailty and develop a multimodal individualized intervention to prevent adverse health outcomes for older adults with cognitive frailty. Further studies are required to clarify the mechanisms through which physical frailty and cognitive impairment interact to accelerate adverse health outcomes, particularly cognitive outcomes. In addition, for older adults with cognitive frailty, an effective flow diagram from primary screening through comprehensive assessment to multidimensional intervention needs to be developed for future implementation in both clinical and community settings. Geriatr Gerontol Int 2021; ••: ••–••.
There is currently no tool to predict incident frailty despite various frailty assessment tools. This study aimed to develop risk prediction models for incident frailty and evaluated their performance on discrimination, calibration, and internal validity. This 2-year follow-up study used data from 5076 non-frail older adults (51% women) living in Tokyo at baseline. We used the Kaigo-Yobo checklist, a standardised assessment instrument, to determine frailty. Twenty questionnaire-based variables that include sociodemographic, medical, behavioural, and subjective factors were entered into binary logistic regression analysis with stepwise backward elimination (p < 0.1 for retention in the model). Discrimination and calibration were assessed by area under the receiver operating characteristic curve (AUC) and the Hosmer-Lemeshow test, respectively. For the assessment of internal validity, we used a 5-fold cross-validation method and calculated the mean AUC. At the follow-up survey, 15.0% of men and 10.2% of women were frail. The frailty risk prediction model was composed of 10 variables for men and 11 for women. AUC of the model was 0.71 in men and 0.72 in women. The P-value for the Hosmer-Lemeshow test in both models was more than 0.05. For internal validity, the mean AUC was 0.71 in men and 0.72 in women. Probability of incident frailty rose with an increasing risk score that was calculated from the developed models. These results demonstrated that the developed models enable the identification of non-frail older adults at high risk of incident frailty, which could help to implement preventive approaches in community settings.
Background and Objective Medical machine learning (ML) models tend to perform better on data from the same cohort than on new data, often due to overfitting, or co-variate shifts. For these reasons, external validation (EV) is a necessary practice in the evaluation of medical ML. However, there is still a gap in the literature on how to interpret EV results and hence assess the robustness of ML models.
Methods:
We fill this gap by proposing a meta-validation method, to assess the soundness of EV procedures. In doing so, we complement the usual way to assess EV by considering both dataset cardinality, and the similarity of the EV dataset with respect to the training set. We then investigate how the notions of cardinality and similarity can be used to inform on the reliability of a validation procedure, by integrating them into two summative data visualizations.
Results:
We illustrate our methodology by applying it to the validation of a state-of-the-art COVID-19 diagnostic model on 8 EV sets, collected across 3 different continents. The model performance was moderately impacted by data similarity (Pearson ρ = 0.38, p< 0.001). In the EV, the validated model reported good AUC (average: 0.84), acceptable calibration (average: 0.17) and utility (average: 0.50). The validation datasets were adequate in terms of dataset cardinality and similarity, thus suggesting the soundness of the results. We also provide a qualitative guideline to evaluate the reliability of validation procedures, and we discuss the importance of proper external validation in light of the obtained results.
Conclusions:
In this paper, we propose a novel, lean methodology to: 1) study how the similarity between training and validation sets impacts the generalizability of a ML model; 2) assess the soundness of EV evaluations along three complementary performance dimensions: discrimination, utility and calibration; 3) draw conclusions on the robustness of the model under validation. We applied this methodology to a state-of-the-art model for the diagnosis of COVID-19 from routine blood tests, and showed how to interpret the results in light of the presented framework.
Objective
Frailty state progression is common among older adults, so it is necessary to identify predictors to implement individualized interventions. We aimed to develop and validate a nomogram to predict frailty progression in community-living older adults.
Design
Prospective cohort study.
Setting and Participants
A total of 3170 Chinese community-living people aged ≥60 years were randomly assigned to a training set or validation set at a ratio of 6:4.
Methods
Candidate predictors (demographic, lifestyle, and medical characteristics) were used to predict frailty state progression as measured with the Fried frailty phenotype at a 4-year follow-up, and multivariate logistic regression analysis was conducted to develop a nomogram, which was validated internally with 1000 bootstrap resamples and externally with the use of a validation set. The C index and calibration plot were used to assess discrimination and calibration of the nomogram, respectively.
Results
After a follow-up period of 4 years, 64.1% (917/1430) of the participants in the robust group and 26.0% (453/1740) in the prefrail group experienced frailty progression, which included 9.1% and 21.0%, respectively, who progressed to frailty. Predictors in the final nomogram were age, marital status, physical exercise, baseline frailty state, and diabetes. Based on this nomogram, an online calculator was also developed for easy use. The discriminative ability was good in the training set (C index = 0.861) and was validated using both the internal bootstrap method (C index = 0.861) and an external validation set (C index = 0.853). The calibration plots showed good agreement in both the training and validation sets.
Conclusions and Implications
An easy-to-use nomogram was developed with good apparent performance using 5 readily available variables to help physicians and public health practitioners to identify older adults at high risk for frailty progression and implement medical interventions.
Machine learning, a branch of artificial intelligence, is increasingly used in health research, including nursing and maternal outcomes research. Machine learning algorithms are complex and involve statistics and terminology that are not common in health research. The purpose of this methods paper is to describe three machine learning algorithms in detail and provide an example of their use in maternal outcomes research. The three algorithms, classification and regression trees, least absolute shrinkage and selection operator, and random forest, may be used to understand risk groups, select variables for a model, and rank variables' contribution to an outcome, respectively. While machine learning has plenty to contribute to health research, it also has some drawbacks, and these are discussed as well. To provide an example of the different algorithms' function, they were used on a completed cross-sectional study examining the association of oxytocin total dose exposure with primary cesarean section. The results of the algorithms are compared to what was done or found using more traditional methods.
The net reclassification improvement (NRI) and the integrated discrimination improvement (IDI) were originally proposed to characterize accuracy improvement in predicting a binary outcome, when new biomarkers are added to regression models. These two indices have been extended from binary outcomes to multi-categorical and survival outcomes. Working on an AIDS study where the onset of cognitive impairment is competing risk censored by death, we extend the NRI and the IDI to competing risk outcomes, by using cumulative incidence functions to quantify cumulative risks of competing events, and adopting the definitions of the two indices for multi-category outcomes. The “missing” category due to independent censoring is handled through inverse probability weighting. Various competing risk models are considered, such as the Fine and Gray, multistate, and multinomial logistic models. Estimation methods for the NRI and the IDI from competing risk data are presented. The inference for the NRI is constructed based on asymptotic normality of its estimator, and the bias-corrected and accelerated bootstrap procedure is used for the IDI. Simulations demonstrate that the proposed inferential procedures perform very well. The Multicenter AIDS Cohort Study is used to illustrate the practical utility of the extended NRI and IDI for competing risk outcomes.
Importance
Patients with chronic illness frequently use Physician Orders for Life-Sustaining Treatment (POLST) to document treatment limitations.
Objectives
To evaluate the association between POLST order for medical interventions and intensive care unit (ICU) admission for patients hospitalized near the end of life.
Design, Setting, and Participants
Retrospective cohort study of patients with POLSTs and with chronic illness who died between January 1, 2010, and December 31, 2017, and were hospitalized 6 months or less before death in a 2-hospital academic health care system.
Exposures
POLST order for medical interventions (“comfort measures only” vs “limited additional interventions” vs “full treatment”), age, race/ethnicity, education, days from POLST completion to admission, histories of cancer or dementia, and admission for traumatic injury.
Main Outcomes and Measures
The primary outcome was the association between POLST order and ICU admission during the last hospitalization of life; the secondary outcome was receipt of a composite of 4 life-sustaining treatments: mechanical ventilation, vasopressors, dialysis, and cardiopulmonary resuscitation. For evaluating factors associated with POLST-discordant care, the outcome was ICU admission contrary to POLST order for medical interventions during the last hospitalization of life.
Results
Among 1818 decedents (mean age, 70.8 [SD, 14.7] years; 41% women), 401 (22%) had POLST orders for comfort measures only, 761 (42%) had orders for limited additional interventions, and 656 (36%) had orders for full treatment. ICU admissions occurred in 31% (95% CI, 26%-35%) of patients with comfort-only orders, 46% (95% CI, 42%-49%) with limited-interventions orders, and 62% (95% CI, 58%-66%) with full-treatment orders. One or more life-sustaining treatments were delivered to 14% (95% CI, 11%-17%) of patients with comfort-only orders and to 20% (95% CI, 17%-23%) of patients with limited-interventions orders. Compared with patients with full-treatment POLSTs, those with comfort-only and limited-interventions orders were significantly less likely to receive ICU admission (comfort only: 123/401 [31%] vs 406/656 [62%], aRR, 0.53 [95% CI, 0.45-0.62]; limited interventions: 349/761 [46%] vs 406/656 [62%], aRR, 0.79 [95% CI, 0.71-0.87]). Across patients with comfort-only and limited-interventions POLSTs, 38% (95% CI, 35%-40%) received POLST-discordant care. Patients with cancer were significantly less likely to receive POLST-discordant care than those without cancer (comfort only: 41/181 [23%] vs 80/220 [36%], aRR, 0.60 [95% CI, 0.43-0.85]; limited interventions: 100/321 [31%] vs 215/440 [49%], aRR, 0.63 [95% CI, 0.51-0.78]). Patients with dementia and comfort-only orders were significantly less likely to receive POLST-discordant care than those without dementia (23/111 [21%] vs 98/290 [34%], aRR, 0.44 [95% CI, 0.29-0.67]). Patients admitted for traumatic injury were significantly more likely to receive POLST-discordant care (comfort only: 29/64 [45%] vs 92/337 [27%], aRR, 1.52 [95% CI, 1.08-2.14]; limited interventions: 51/91 [56%] vs 264/670 [39%], aRR, 1.36 [95% CI, 1.09-1.68]). In patients with limited-interventions orders, older age was significantly associated with less POLST-discordant care (aRR, 0.93 per 10 years [95% CI, 0.88-1.00]).
Conclusions and Relevance
Among patients with POLSTs and with chronic life-limiting illness who were hospitalized within 6 months of death, treatment-limiting POLSTs were significantly associated with lower rates of ICU admission compared with full-treatment POLSTs. However, 38% of patients with treatment-limiting POLSTs received intensive care that was potentially discordant with their POLST.
Introduction:
Research has shown that frailty, a geriatric syndrome associated with an increased risk of negative outcomes for older people, is highly prevalent among residents of residential aged care facilities (also called long term care facilities or nursing homes). However, progress on effective identification of frailty within residential care remains at an early stage, necessitating the development of new methods for accurate and efficient screening.
Objectives:
We aimed to determine the effectiveness of artificial intelligence (AI) algorithms in accurately identifying frailty among residents aged 75 years and over in comparison with a calculated electronic Frailty Index (eFI) based on a routinely-collected residential aged care administrative data set drawn from 10 residential care facilities located in Queensland, Australia. A secondary objective included the identification of best-performing candidate algorithms.
Methods:
We designed a frailty prediction system based on the eFI identification of frailty, allocating 84.5 % and 15.5 % of the data to training and test data sets respectively. We compared the performance of 18 specific scenarios to predict frailty against eFI based on unique combinations of three ML algorithms (support vector machines [SVM], decision trees [DT] and K-nearest neighbours [KNN]) and six cases (6, 10, 11, 14, 39 and 70 input variables). We calculated accuracy, percentage positive and negative agreement, sensitivity, specificity, Cohen's kappa and Prevalence- and Bias- Adjusted Kappa (PABAK), table frequencies and positive and negative predictive values.
Results:
Of 592 eligible resident records, 500 were allocated to the training set and 92 to the test set. Three scenarios (10, 11 and 70 input variables), all based on SVM algorithm, returned overall accuracy above 75 %.
Conclusions:
There is some potential for AI techniques to contribute towards better frailty identification within residential care. However, potential benefits will need to be weighed against administrative burden, data quality concerns and presence of potential bias.
This study aims to examine the extent to which people are socially integrated and the association between social support and depressive symptoms among Chinese adults, with regard to the moderating effect of the rural or urban residence. The author used data from the China health and longitudinal study (CHARLS), a nationally representative longitudinal survey of the population of adults aged over 45 in China. A total of 16,372 participants were included in this study, and the mean age of the sample was 59.7. Three variables were used to measure participants' social support: family size, proximity of support, and social involvement. The Chinese version of 10‐item center for epidemiologic studies depression scale was used as a measurement tool for depressive symptoms. The findings demonstrate that small family size, living with a spouse, frequency of contact with children, and a number of social activities have significant effects on depressive symptoms. For all aspects of social support, the influence on depressive symptoms is not significantly different between urban and rural areas. Family support, especially the support of a spouse is crucial to prevent depression. This study also identifies the vital effect of social activity and encourages the government to improve public services, especially in rural areas.
Frailty, a syndrome characterized by an exaggerated decline in function and reserve of multiple physiological systems, is common in older patients with heart failure (HF) and is associated with worse clinical and patient-reported outcomes. Although several detailed assessment tools have been developed and validated in the geriatric population, they are cumbersome, not validated in patients with HF, and not commonly used in routine management of patients with HF. More recently, there has been an increasing interest in developing simple frailty screening tools that could efficiently and quickly identify frail patients with HF in routine clinical settings. As the burden and recognition of frailty in older patients with HF increase, a more comprehensive approach to management is needed that targets deficits across multiple domains, including physical function and medical, cognitive, and social domains. Such a multidomain approach is critical to address the unique, multidimensional challenges to the care of these high-risk patients and to improve their functional status, quality of life, and long-term clinical outcomes. This review discusses the burden of frailty, the conceptual underpinnings of frailty in older patients with HF, and potential strategies for the assessment, screening, and management of frailty in this vulnerable patient population.
Objective:
Recognizing frailty, also known as clinical geriatric syndrome in the elderly that is characterized by high vulnerability and low resilience, and its extensive influence in clinical practice is challenging. This study aims to develop a social frailty prediction system based on machine learning approaches in order to identify the social frailty status of the elders in order to advance appropriate social services provision.
Materials and methods:
This cross-sectional study enrolled and collected information from 595 community-dwelling seniors aged 65+. Fourteen predictors established from questionnaires and electronic medical records were used to predict the social frailty of participants. Bagged classification and regression trees, model average neural network, random forest, C5.0, eXtreme gradient boosting, and stochastic gradient boosting were used to build the predictive model in use. Performance was compared using accuracy, kappa, area under receiver operating characteristic curve, sensitivity, and specificity. The frailty predictive system was web-based and built upon representational state transfer application program interfaces.
Results:
C5.0 achieved the best overall performance than remaining learners, and was adopted as the base learner for the social frailty prediction system. In terms of the area under receiver operating characteristic curve (AUC), health literacy (AUC = 0.68) was found to be the most important variable for predicting one's social frailty, followed by comorbidity (AUC = 0.67), religious participation (AUC = 0.67), physical activity (AUC = 0.66), and geriatric depression score (AUC = 0.62).
Conclusions:
Results suggest that a combination of such data that is both available and unavailable from electronic medical records is predictive of the social frailty of an elderly population.
Background:
Engaging in regular physical activity has a beneficial impact on both physical health and on subjective health indicators. The aims of this study were (i) to assess the association between physical activity levels and self-reported health status in European adolescents and (ii) to identify any differences in the distribution of adolescents reporting good health between active and inactive subjects across urban areas. The study sample comprised 13 783 15-year olds from 21 urban areas across Europe who participated in the European Urban Health Indicators System Part 2 youth survey in 2010/11. Data collected on physical activity levels, self-rated health status and covariates including gender, BMI, socioeconomic status and sedentary behaviour were analyzed in a multivariable logistic regression model. High levels of physical activity (OR: 1.607, 95% CI: 1.245-2.074, P < 0.001) were associated with self-rated 'good health' across the cohort as a whole. All cities except Iasi showed a positive association between high levels of physical activity and good health. This was significant in four cases: Amsterdam, Cardiff, Greater Manchester and Merseyside ( P = 0.035, 0.016, 0.010 and 0.049, respectively). Only 13.3% of the cohort met the current WHO physical activity level recommendations. High levels of physical activity are positively associated with self-rated 'good health' status in European adolescents. Alarming levels of physical inactivity make it a priority to encourage greater engagement in physical activity. Promotion of physical activity should be specifically tailored to each urban area.
OBJECTIVES: Cognitive frailty, a condition describing the simultaneous presence of physical frailty and mild cognitive impairment, has been recently defined by an international consensus group. We estimated the predictive role of a "reversible" cognitive frailty model on incident dementia, its subtypes, and all-cause mortality in nondemented older individuals. We verified if vascular risk factors or depressive symptoms could modify this predictive role.
DESIGN: Longitudinal population-based study with 3.5- and 7-year of median follow-up.
SETTING: Eight Italian municipalities included in the Italian Longitudinal Study on Aging.
PARTICIPANTS: In 2150 older individuals from the Italian Longitudinal Study on Aging, we operationalized reversible cognitive frailty with the presence of physical frailty and pre-mild cognitive impairment subjective cognitive decline, diagnosed with a self-report measure based on item 14 of the Geriatric Depression Scale.
MEASUREMENTS: Incidence of dementia, its subtypes, and all-cause mortality.
RESULTS: Over a 3.5-year follow-up, participants with reversible cognitive frailty showed an increased risk of overall dementia [hazard ratio (HR) 2.30, 95% confidence interval (CI) 1.02-5.18], particularly vascular dementia (VaD), and all-cause mortality (HR 1.74, 95% CI 1.07-2.83). Over a 7-year follow-up, participants with reversible cognitive frailty showed an increased risk of overall dementia (HR 2.12, 95% CI 1.12-4.03), particularly VaD, and all-cause mortality (HR 1.39, 95% CI 1.03-2.00). Vascular risk factors and depressive symptoms did not have any effect modifier on the relationship between reversible cognitive frailty and incident dementia and all-cause mortality.
CONCLUSIONS: A model of reversible cognitive frailty was a short- and long-term predictor of all-cause mortality and overall dementia, particularly VaD. The absence of vascular risk factors and depressive symptoms did not modify the predictive role of reversible cognitive frailty on these outcomes.
The decision curve is a graphical summary recently proposed for assessing the potential clinical impact of risk prediction biomarkers or risk models for recommending treatment or intervention. It was applied recently in an article in Journal of Clinical Oncology to measure the impact of using a genomic risk model for deciding on adjuvant radiation therapy for prostate cancer treated with radical prostatectomy. We illustrate the use of decision curves for evaluating clinical- and biomarker-based models for predicting a man's risk of prostate cancer, which could be used to guide the decision to biopsy. Decision curves are grounded in a decision-theoretical framework that accounts for both the benefits of intervention and the costs of intervention to a patient who cannot benefit. Decision curves are thus an improvement over purely mathematical measures of performance such as the area under the receiver operating characteristic curve. However, there are challenges in using and interpreting decision curves appropriately. We caution that decision curves cannot be used to identify the optimal risk threshold for recommending intervention. We discuss the use of decision curves for miscalibrated risk models. Finally, we emphasize that a decision curve shows the performance of a risk model in a population in which every patient has the same expected benefit and cost of intervention. If every patient has a personal benefit and cost, then the curves are not useful. If subpopulations have different benefits and costs, subpopulation-specific decision curves should be used. As a companion to this article, we released an R software package called DecisionCurve for making decision curves and related graphics.
Purpose:
To develop and validate a radiomics nomogram for preoperative prediction of lymph node (LN) metastasis in patients with colorectal cancer (CRC).
Patients and methods:
The prediction model was developed in a primary cohort that consisted of 326 patients with clinicopathologically confirmed CRC, and data was gathered from January 2007 to April 2010. Radiomic features were extracted from portal venous-phase computed tomography (CT) of CRC. Lasso regression model was used for data dimension reduction, feature selection, and radiomics signature building. Multivariable logistic regression analysis was used to develop the predicting model, we incorporated the radiomics signature, CT-reported LN status, and independent clinicopathologic risk factors, and this was presented with a radiomics nomogram. The performance of the nomogram was assessed with respect to its calibration, discrimination, and clinical usefulness. Internal validation was assessed. An independent validation cohort contained 200 consecutive patients from May 2010 to December 2011.
Results:
The radiomics signature, which consisted of 24 selected features, was significantly associated with LN status (P < .001 for both primary and validation cohorts). Predictors contained in the individualized prediction nomogram included the radiomics signature, CT-reported LN status, and carcinoembryonic antigen level. Addition of histologic grade to the nomogram failed to show incremental prognostic value. The model showed good discrimination, with a C-index of 0.736 (C-index, 0.759 and 0.766 through internal validation), and good calibration. Application of the nomogram in the validation cohort still gave good discrimination (C-index, 0.778 [95% CI, 0.769 to 0.787]) and good calibration. Decision curve analysis demonstrated that the radiomics nomogram was clinically useful.
Conclusion:
This study presents a radiomics nomogram that incorporates the radiomics signature, CT-reported LN status, and clinical risk factors, which can be conveniently used to facilitate the preoperative individualized prediction of LN metastasis in patients with CRC.
From the reviews of the First Edition."An interesting, useful, and well-written book on logistic regression models . . . Hosmer and Lemeshow have used very little mathematics, have presented difficult concepts heuristically and through illustrative examples, and have included references."—Choice"Well written, clearly organized, and comprehensive . . . the authors carefully walk the reader through the estimation of interpretation of coefficients from a wide variety of logistic regression models . . . their careful explication of the quantitative re-expression of coefficients from these various models is excellent."—Contemporary Sociology"An extremely well-written book that will certainly prove an invaluable acquisition to the practicing statistician who finds other literature on analysis of discrete data hard to follow or heavily theoretical."—The StatisticianIn this revised and updated edition of their popular book, David Hosmer and Stanley Lemeshow continue to provide an amazingly accessible introduction to the logistic regression model while incorporating advances of the last decade, including a variety of software packages for the analysis of data sets. Hosmer and Lemeshow extend the discussion from biostatistics and epidemiology to cutting-edge applications in data mining and machine learning, guiding readers step-by-step through the use of modeling techniques for dichotomous data in diverse fields. Ample new topics and expanded discussions of existing material are accompanied by a wealth of real-world examples-with extensive data sets available over the Internet.
A great many tools have been developed for supervised classification, ranging from early methods such as linear discriminant analysis through to modern developments such as neural networks and support vector machines. A large number of comparative studies have been conducted in attempts to establish the relative superiority of these methods. This paper argues that these comparisons often fail to take into account important aspects of real problems, so that the apparent superiority of more sophisticated methods may be something of an illusion. In particular, simple methods typically yield performance almost as good as more sophisticated methods, to the extent that the difference in performance may be swamped by other sources of uncertainty that generally are not considered in the classical supervised classification paradigm.
BACKGROUND
As the definitional formula for population attributable fraction is not usually directly usable in applications, separate estimation formulas are required. However, most epidemiology textbooks limit their coverage to Levin's formula, based on the (dichotomous) distribution of the exposure of interest in the population. Few present or explain Miettinen's formula, based on the distribution of the exposure in the cases; and even fewer present the corresponding formulas for situations with more than two levels of exposure. Thus, many health researchers and public health practitioners are unaware of, or are not confident in their use of, these formulas, particularly when they involve several exposure levels, or confounding factors.
METHODS/RESULTS
A heuristic approach, coupled with pictorial representations, is offered to help understand and interconnect the structures behind the Levin and Miettinen formulas. The pictorial representation shows how to deal correctly with several exposure levels, and why a commonly used approach is incorrect. Correct and incorrect approaches are also presented for situations where estimates must be aggregated over strata of a confounding factor.
Several vascular risk factors are associated with dementia. We sought to develop a simple method for the prediction of the risk of late-life dementia in people of middle age on the basis of their risk profiles.
Data were used from the population-based CAIDE study, which included 1409 individuals who were studied in midlife and re-examined 20 years later for signs of dementia. Several midlife vascular risk factors were studied to create the scoring tool. The score values were estimated on the basis of beta coefficients and the dementia risk score was the sum of these individual scores (range 0-15).
Occurrence of dementia during the 20 years of follow-up was 4%. Future dementia was significantly predicted by high age (> or = 47 years), low education (< 10 years), hypertension, hypercholesterolaemia, and obesity. The dementia risk score predicted dementia well (area under curve 0.77; 95% CI 0.71-0.83). The risk of dementia according to the categories of the dementia risk score was 1.0% for those with a score of 0-5, 1.9% for a score of 6-7, 4.2% for a score of 8-9, 7.4% for a score of 10-11, and 16.4% for a score of 12-15. When the cut-off of 9 points or more was applied the sensitivity was 0.77, the specificity was 0.63, and the negative predictive value was 0.98.
The dementia risk score is a novel approach for the prediction of dementia risk, but should be validated and further improved to increase its predictive value. This approach highlights the role of vascular factors in the development of dementia and could help to identify individuals who might benefit from intensive lifestyle consultations and pharmacological interventions.