No full-text available
To read the full-text of this research,
you can request a copy directly from the authors.
Explainable AI Method for Tinnitus Diagnosis via Neighbor-Augmented Knowledge Graph and Traditional Chinese Medicine: Development and Validation Study
Abstract
Background
Tinnitus diagnosis poses a challenge in otolaryngology owing to an extremely complex pathogenesis, lack of effective objectification methods, and factor-affected diagnosis. There is currently a lack of explainable auxiliary diagnostic tools for tinnitus in clinical practice.
Objective
This study aims to develop a diagnostic model using an explainable artificial intelligence (AI) method to address the issue of low accuracy in tinnitus diagnosis.
Methods
In this study, a knowledge graph–based tinnitus diagnostic method was developed by combining clinical medical knowledge with electronic medical records. Electronic medical record data from 1267 patients were integrated with traditional Chinese clinical medical knowledge to construct a tinnitus knowledge graph. Subsequently, weights were introduced, which measured patient similarity in the knowledge graph based on mutual information values. Finally, a collaborative neighbor algorithm was proposed, which scored patient similarity to obtain the recommended diagnosis. We conducted 2 group experiments and 1 case derivation to explore the effectiveness of our models and compared the models with state-of-the-art graph algorithms and other explainable machine learning models.
Results
The experimental results indicate that the method achieved 99.4% accuracy, 98.5% sensitivity, 99.6% specificity, 98.7% precision, 98.6% F1-score, and 99% area under the receiver operating characteristic curve for the inference of 5 tinnitus subtypes among 253 test patients. Additionally, it demonstrated good interpretability. The topological structure of knowledge graphs provides transparency that can explain the reasons for the similarity between patients.
Conclusions
This method provides doctors with a reliable and explainable diagnostic tool that is expected to improve tinnitus diagnosis accuracy.
... Germany followed with 14 contributions, focusing in particular on ML models and clinical decision support systems [30,33,40,42,51,53,[62][63][64][65]73,93,95]. Contributing to 12 studies, China has made significant strides in diagnostic applications using DL and predictive modeling [50,59,78,83,87,105,110,[116][117][118][119], as depicted in Figure 2. ...
... Germany followed with 14 c butions, focusing in particular on ML models and clinical decision support sy [30,33,40,42,51,53,[62][63][64][65]73,93,95]. Contributing to 12 studies, China has made signi strides in diagnostic applications using DL and predictive mod [50,59,78,83,87,105,110,[116][117][118][119], as depicted in Figure 2. Table 1 illustrates the most frequently retrieved journals and the published st designs. Ear and Hearing was the leading journal with 13 publications [24,29,3 37,50,55,57,69,86,96,97] followed by International Journal of Audiology w [26,30,32,33,42,72], both showcasing significant contributions to the field through va investigations of hearing tests, diagnostics, and therapeutic tools. ...
... In such an investigation, the prediction accuracy of the convolutional neural network system was 99.07% for the non-responder group and 98.86% for responders [84]. Also, in the field of non-pharmacological approaches to tinnitus, Yin et al. [119] implemented a machine learning model based on the knowledge graph method to identify the likelihood of response of patients with tinnitus to traditional Chinese medicine, based on clinical features and aspects derived from traditional Chinese semiology. According to the authors, such an AI model achieved high prediction performances (99.4% accuracy, 98.5% sensitivity, 99.6% specificity, and 98.7% precision, with an area under the receiver operating characteristic curve of 99%) across 253 test patients [119]. ...
The integration of artificial intelligence (AI) into medical disciplines is rapidly transforming healthcare delivery, with audiology being no exception. By synthesizing the existing literature, this review seeks to inform clinicians, researchers, and policymakers about the potential and challenges of integrating AI into audiological practice. The PubMed, Cochrane, and Google Scholar databases were searched for articles published in English from 1990 to 2024 with the following query: “(audiology) AND (“artificial intelligence” OR “machine learning” OR “deep learning”)”. The PRISMA extension for scoping reviews (PRISMA-ScR) was followed. The database research yielded 1359 results, and the selection process led to the inclusion of 104 manuscripts. The integration of AI in audiology has evolved significantly over the succeeding decades, with 87.5% of manuscripts published in the last 4 years. Most types of AI were consistently used for specific purposes, such as logistic regression and other statistical machine learning tools (e.g., support vector machine, multilayer perceptron, random forest, deep belief network, decision tree, k-nearest neighbor, or LASSO) for automated audiometry and clinical predictions; convolutional neural networks for radiological image analysis; and large language models for automatic generation of diagnostic reports. Despite the advances in AI technologies, different ethical and professional challenges are still present, underscoring the need for larger, more diverse data collection and bioethics studies in the field of audiology.
With the emergence of new classroom teaching modes such as STEM education, traditional classroom teaching and student cultivation are facing many new challenges, so this paper explores the use of knowledge mapping in teaching classrooms based on the STEM education perspective. The article first analyzes the basic theory of knowledge graphs and designs a knowledge graph architecture based on the relevant basic theory. It also proposes a personalized learning path generation and recommendation algorithm. Finally, 38 students majoring in educational technology were surveyed to test and explore the knowledge mapping approach proposed in this paper for STEM education. The results of the study indicate that the fifth and sixth groups, which utilized the personalized recommendation algorithm proposed in this paper, achieved the highest learning gains of 0.531 and 0.756, respectively.
Tinnitus is a highly prevalent condition, affecting more than 1 in 7 adults in the EU and causing negative effects on sufferers’ quality of life. In this study, we utilised data collected within the “UNITI” project, the largest EU tinnitus-related research programme. Initially, we extracted characteristics from both auditory brainstem response (ABR) and auditory middle latency response (AMLR) signals, which were derived from tinnitus patients. We then combined these features with the patients’ clinical data, and integrated them to build machine learning models for the classification of individuals and their ears according to their level of tinnitus-related distress. Several models were developed and tested on different datasets to determine the most relevant features and achieve high performances. Specifically, seven widely used classifiers were utilised on all generated datasets: random forest (RF), linear, radial, and polynomial support vector machines (SVM), naive bayes (NB), neural networks (NN), and linear discriminant analysis (LDA). Results showed that features extracted from the wavelet-scattering transformed AMLR signals were the most informative data. In combination with the 15 LASSO-selected clinical features, the SVM classifier achieved optimal performance with an AUC value, sensitivity, and specificity of 92.53%, 84.84%, and 83.04%, respectively, indicating high discrimination performance between the two groups.
Diabetic macular edema (DME) is a significant complication of diabetes that impacts the eye and is a primary contributor to vision loss in individuals with diabetes. Early control of the related risk factors is crucial to reduce the incidence of DME. Artificial intelligence (AI) clinical decision-making tools can construct disease prediction models to aid in the clinical screening of the high-risk population for early disease intervention. However, conventional machine learning and data mining techniques have limitations in predicting diseases when dealing with missing feature values. To solve this problem, a knowledge graph displays the connection relationships of multi-source and multi-domain data in the form of a semantic network to enable cross-domain modeling and queries. This approach can facilitate the personalized prediction of diseases using any number of known feature data. In this study, we proposed an improved correlation enhancement algorithm based on knowledge graph reasoning to comprehensively evaluate the factors that influence DME to achieve disease prediction. We constructed a knowledge graph based on Neo4j by preprocessing the collected clinical data and analyzing the statistical rules. Based on reasoning using the statistical rules of the knowledge graph, we used the correlation enhancement coefficient and generalized closeness degree method to enhance the model. Meanwhile, we analyzed and verified these models’ results using link prediction evaluation indicators. The disease prediction model proposed in this study achieved a precision rate of 86.21%, which is more accurate and efficient in predicting DME. Furthermore, the clinical decision support system developed using this model can facilitate personalized disease risk prediction, making it convenient for the clinical screening of a high-risk population and early disease intervention.
With the development of digital technology, machine learning has paved the way for the next generation of tinnitus diagnoses. Although machine learning has been widely applied in EEG-based tinnitus analysis, most current models are dataset-specific. Each dataset may be limited to a specific range of symptoms, overall disease severity, and demographic attributes; further, dataset formats may differ, impacting model performance. This paper proposes a side-aware meta-learning for cross-dataset tinnitus diagnosis, which can effectively classify tinnitus in subjects of divergent ages and genders from different data collection processes. Owing to the superiority of meta-learning, our method does not rely on large-scale datasets like conventional deep learning models. Moreover, we design a subject-specific training process to assist the model in fitting the data pattern of different patients or healthy people. Our method achieves a high accuracy of 73.8% in the cross-dataset classification. We conduct an extensive analysis to show the effectiveness of side information of ears in enhancing model performance and side-aware meta-learning in improving the quality of the learned features.
Importance:
To date, no systematic review has taken a meta-analytic approach to estimating the prevalence and incidence of tinnitus in the general population.
Objective:
To provide frequency estimates of tinnitus worldwide.
Data sources:
An umbrella review followed by a traditional systematic review was performed by searching PubMed-MEDLINE and Embase from inception through November 19, 2021.
Study selection:
Research data from the general population were selected, and studies based on patients or on subgroups of the population with selected lifestyle habits were excluded. No restrictions were applied according to date, age, sex, and country.
Data extraction and synthesis:
Relevant extracted information included type of study, time and location, end point, population characteristics, and tinnitus definition. The study followed the Meta-analysis of Observational Studies in Epidemiology (MOOSE) reporting guideline.
Main outcomes and measures:
Pooled prevalence estimates of any tinnitus, severe tinnitus, chronic tinnitus, and diagnosed tinnitus as well as incidence of tinnitus were obtained using random-effects meta-analytic models; heterogeneity between studies was controlled using the χ2 test, and inconsistency was measured using the I2 statistic.
Results:
Among 767 publications, 113 eligible articles published between 1972 and 2021 were identified, and prevalence estimates from 83 articles and incidence estimates from 12 articles were extracted. The pooled prevalence of any tinnitus among adults was 14.4% (95% CI, 12.6%-16.5%) and ranged from 4.1% (95% CI, 3.7%-4.4%) to 37.2% (95% CI, 34.6%-39.9%). Prevalence estimates did not significantly differ by sex (14.1% [95% CI, 11.6%-17.0%] among male individuals; 13.1% [95% CI, 10.5%-16.2%] among female individuals), but increased prevalence was associated with age (9.7% [95% CI, 7.4%-12.5%] among adults aged 18-44 years; 13.7% [95% CI, 11.0%-17.0%] among those aged 45-64 years; and 23.6% [95% CI, 19.4%-28.5%] among those aged ≥65 years; P < .001 among age groups). The pooled prevalence of severe tinnitus was 2.3% (95% CI, 1.7%-3.1%), ranging from 0.5% (95% CI, 0.3%-0.7%) to 12.6% (95% CI, 11.1%-14.1%). The pooled prevalence of chronic tinnitus was 9.8% (95% CI, 4.7%-19.3%) and the pooled prevalence of diagnosed tinnitus was 3.4% (95% CI, 2.1%-5.5%). The pooled incidence rate of any tinnitus was 1164 per 100 000 person-years (95% CI, 479-2828 per 100 000 person-years).
Conclusions and relevance:
Despite the substantial heterogeneity among studies, this comprehensive systematic review on the prevalence and incidence of tinnitus suggests that tinnitus affects more than 740 million adults globally and is perceived as a major problem by more than 120 million people, mostly aged 65 years or older. Health policy makers should consider the global burden of tinnitus, and greater effort should be devoted to boost research on tinnitus.
Tinnitus is an auditory phantom perception without external sound stimuli. This chronic perception can severely affect quality of life. Because tinnitus symptoms are highly heterogeneous, multimodal data analyses are increasingly used to gain new insights. MHealth data sources, with their particular focus on country- and season-specific differences, can provide a promising avenue for new insights. Therefore, we examined data from the TrackYourTinnitus (TYT) mHealth platform to create symptom profiles of TYT users. We used gradient boosting engines to classify momentary tinnitus and regress tinnitus loudness, using country of origin and season as features. At the daily assessment level, tinnitus loudness can be regressed with a mean absolute error rate of 7.9% points. In turn, momentary tinnitus can be classified with an F1 score of 93.79%. Both results indicate differences in the tinnitus of TYT users with respect to season and country of origin. The significance of the features was evaluated using statistical and explainable machine learning methods. It was further shown that tinnitus varies with temperature in certain countries. The results presented show that season and country of origin appear to be valuable features when combined with longitudinal mHealth data at the level of daily assessment.
The clinical informatization of traditional Chinese medicine (TCM) focuses on serving users and assisting in diagnosis. The rules of clinical knowledge play an important role in improving the TCM informatization service. However, many rules are difficult to find because of the complexity of the data in the current TCM syndrome prediction. Therefore, we proposed an end-to-end model, called Decision-making System for the Diagnosis of Syndrome (DSDS), which is based on the knowledge graph (KG) of TCM. This paper introduces the link prediction for the diagnosis of syndrome by dismantling medical records into multiple symptoms. In addition, based on the symptoms and predicted syndromes, the most relevant syndrome could be determined by the scoring and voting method in this paper. The results show that the accuracy of DSDS is 80.6%.
Background:
There is huge variability in the way that individuals with tinnitus respond to interventions. These experiential variations, together with a range of associated etiologies, contribute to tinnitus being a highly heterogeneous condition. Despite this heterogeneity, a "one size fits all" approach is taken when making management recommendations. Although there are various management approaches, not all are equally effective. Psychological approaches such as cognitive behavioral therapy have the most evidence base. Managing tinnitus is challenging due to the significant variations in tinnitus experiences and treatment successes. Tailored interventions based on individual tinnitus profiles may improve outcomes. Predictive models of treatment success are, however, lacking.
Objective:
This study aimed to use exploratory data mining techniques (ie, decision tree models) to identify the variables associated with the treatment success of internet-based cognitive behavioral therapy (ICBT) for tinnitus.
Methods:
Individuals (N=228) who underwent ICBT in 3 separate clinical trials were included in this analysis. The primary outcome variable was a reduction of 13 points in tinnitus severity, which was measured by using the Tinnitus Functional Index following the intervention. The predictor variables included demographic characteristics, tinnitus and hearing-related variables, and clinical factors (ie, anxiety, depression, insomnia, hyperacusis, hearing disability, cognitive function, and life satisfaction). Analyses were undertaken by using various exploratory machine learning algorithms to identify the most influencing variables. In total, 6 decision tree models were implemented, namely the classification and regression tree (CART), C5.0, GB, XGBoost, AdaBoost algorithm and random forest models. The Shapley additive explanations framework was applied to the two optimal decision tree models to determine relative predictor importance.
Results:
Among the six decision tree models, the CART (accuracy: mean 70.7%, SD 2.4%; sensitivity: mean 74%, SD 5.5%; specificity: mean 64%, SD 3.7%; area under the receiver operating characteristic curve [AUC]: mean 0.69, SD 0.001) and gradient boosting (accuracy: mean 71.8%, SD 1.5%; sensitivity: mean 78.3%, SD 2.8%; specificity: 58.7%, SD 4.2%; AUC: mean 0.68, SD 0.02) models were found to be the best predictive models. Although the other models had acceptable accuracy (range 56.3%-66.7%) and sensitivity (range 68.6%-77.9%), they all had relatively weak specificity (range 31.1%-50%) and AUCs (range 0.52-0.62). A higher education level was the most influencing factor for ICBT outcomes. The CART decision tree model identified 3 participant groups who had at least an 85% success probability following the undertaking of ICBT.
Conclusions:
Decision tree models, especially the CART and gradient boosting models, appeared to be promising in predicting ICBT outcomes. Their predictive power may be improved by using larger sample sizes and including a wider range of predictive factors in future studies.
Tinnitus is the chronic perception of a phantom sound with different levels of related distress. Past research has elucidated interactions of tinnitus distress with audiological, affective and further clinical variables. The influence of tinnitus distress on cognition is underinvestigated. Our study aims at investigating specific influences of tinnitus distress and further associated predictors on cognition in a cohort of n = 146 out-ward clinical tinnitus patients. Age, educational level, hearing loss, Tinnitus Questionnaire (TQ) score, tinnitus duration, speech in noise (SIN), stress, anxiety and depression, and psychological well-being were included as predictors of a machine learning regression approach (elastic net) in three models with scores of a multiple choice vocabulary test (MWT-B), or two trail-making tests (TMT-A and TMT-B), as dependent variables. TQ scores predicted lower MWT-B scores and higher TMT-B test completion time. Stress, emotional, and psychological variables were not found to be relevant predictors in all models with the exception of small positive influences of SIN and depression on TMT-B. Effect sizes were small to medium for all models and predictors. Results are indicative of specific influence of tinnitus distress on cognitive performance, especially on general or crystallized intelligence and executive functions. More research is needed at the delicate intersection of tinnitus distress and cognitive skills needed in daily functioning.
Auditory Residual Inhibition (ARI) is a temporary suppression of tinnitus that occurs in some people following the presentation of masking sounds. Differences in neural response to ARI stimuli may enable classification of tinnitus and a tailored approach to intervention in the future. In an exploratory study, we investigated the use of a brain-inspired artificial neural network to examine the effects of ARI on electroencephalographic function, as well as the predictive ability of the model. Ten tinnitus patients underwent two auditory stimulation conditions (constant and amplitude modulated broadband noise) at two time points and were then characterised as responders or non-responders, based on whether they experienced ARI or not. Using a spiking neural network model, we evaluated concurrent neural patterns generated across space and time from features of electroencephalographic data, capturing the neural dynamic changes before and after stimulation. Results indicated that the model may be used to predict the effect of auditory stimulation on tinnitus on an individual basis. This approach may aid in the development of predictive models for treatment selection.
Chronic tinnitus is a debilitating condition which affects 10–20% of adults and can severely impact their quality of life. Currently there is no objective measure of tinnitus that can be used clinically. Clinical assessment of the condition uses subjective feedback from individuals which is not always reliable. We investigated the sensitivity of functional near-infrared spectroscopy (fNIRS) to differentiate individuals with and without tinnitus and to identify fNIRS features associated with subjective ratings of tinnitus severity. We recorded fNIRS signals in the resting state and in response to auditory or visual stimuli from 25 individuals with chronic tinnitus and 21 controls matched for age and hearing loss. Severity of tinnitus was rated using the Tinnitus Handicap Inventory and subjective ratings of tinnitus loudness and annoyance were measured on a visual analogue scale. Following statistical group comparisons, machine learning methods including feature extraction and classification were applied to the fNIRS features to classify patients with tinnitus and controls and differentiate tinnitus at different severity levels. Resting state measures of connectivity between temporal regions and frontal and occipital regions were significantly higher in patients with tinnitus compared to controls. In the tinnitus group, temporal-occipital connectivity showed a significant increase with subject ratings of loudness. Also in this group, both visual and auditory evoked responses were significantly reduced in the visual and auditory regions of interest respectively. Naïve Bayes classifiers were able to classify patients with tinnitus from controls with an accuracy of 78.3%. An accuracy of 87.32% was achieved using Neural Networks to differentiate patients with slight/ mild versus moderate/ severe tinnitus. Our findings show the feasibility of using fNIRS and machine learning to develop an objective measure of tinnitus. Such a measure would greatly benefit clinicians and patients by providing a tool to objectively assess new treatments and patients’ treatment progress.
Tinnitus is a complex condition that is associated with major psychological and economic impairments – partly through various comorbidities such as depression. Understanding the interaction between tinnitus and depression may thus improve either symptom cluster’s prevention, diagnosis and treatment. In this study, we developed and validated a machine learning model to predict depression severity after outpatient therapy (T1) based on variables obtained before therapy (T0). 1,490 patients with chronic tinnitus (comorbid major depressive disorder: 52.2%) who completed a 7-day multimodal treatment encompassing tinnitus-specific components, cognitive behavioural therapy, physiotherapy and informational counselling were included. 185 variables were extracted from self-report questionnaires and socio-demographic data acquired at T0. We used 11 classification methods to train models that reliably separate between subclinical and clinical depression at T1 as measured by the general depression questionnaire. To ensure highly predictive and robust classifiers, we tuned algorithm hyperparameters in a 10-fold cross-validation scheme. To reduce model complexity and improve interpretability, we wrapped model training around an incremental feature selection mechanism that retained features that contributed to model prediction. We identified a LASSO model that included all 185 features to yield highest predictive performance (AUC = 0.87 ± 0.04). Through our feature selection wrapper, we identified a LASSO model with good trade-off between predictive performance and interpretability that used only 6 features (AUC = 0.85 ± 0.05). Thus, predictive machine learning models can lead to a better understanding of depression in tinnitus patients, and contribute to the selection of suitable therapeutic strategies and concise and valid questionnaire design for patients with chronic tinnitus with or without comorbid major depressive disorder.
Adaptation level theory of tinnitus and neuropsychological theory of tinnitus are extensively used frameworks for understanding emotional and psychological distress among tinnitus sufferers. Objective of the present study was to investigate potential associations between hearing loss, tinnitus, anxiety, depression, and stress. The Tinnitus Handicap Inventory (Newman, Jacobson, & Spitzer, 1996) and the Depression, Anxiety, Stress Scale (Lovibond & Lovibond, 1995)scales were administered to a sample of 110 tinnitus outpatients recruited from Audiology departments of Lahore and Rawalpindi hospitals. Results revealed tinnitus was positively linked with psychological problems. Additionally, it was established that tinnitus is a positive significant predictor for anxiety, stress and depression. The moderation models related to the interactions between psychological problems and hearing loss were negative significant predictors for tinnitus symptoms. Moreover, the comparative analysis between gender differences revealed a significant diversity in the levels of stress, anxiety, and depression. Results also elucidated that patients at initial stages of hearing loss were more prone towards reporting tinnitus symptoms along with emerging psychological problems.
According to previous studies, many neuroanatomical alterations have been detected in patients with tinnitus. However, the results of these studies have been inconsistent. The objective of this study was to explore the cortical/subcortical morphological neuroimaging biomarkers that may characterize idiopathic tinnitus using machine learning methods. Forty-six patients with idiopathic tinnitus and fifty-six healthy subjects were included in this study. For each subject, the gray matter volume of 61 brain regions was extracted as an original feature pool. From this feature pool, a hybrid feature selection algorithm combining the F-score and sequential forward floating selection (SFFS) methods was performed to select features. Then, the selected features were used to train a support vector machine (SVM) model. The area under the curve (AUC) and accuracy were used to assess the performance of the classification model. As a result, a combination of 13 cortical/subcortical brain regions was found to have the highest classification accuracy for effectively differentiating patients with tinnitus from healthy subjects. These brain regions include the bilateral hypothalamus, right insula, bilateral superior temporal gyrus, left rostral middle frontal gyrus, bilateral inferior temporal gyrus, right inferior parietal lobule, right transverse temporal gyrus, right middle temporal gyrus, right cingulate gyrus, and left superior frontal gyrus. The accuracy in the training and test datasets was 80.49% and 80.00%, respectively, and the AUC was 0.8586. To the best of our knowledge, this is the first study to elucidate brain morphological changes in patients with tinnitus by applying an SVM classifier. This study provides validated cortical/subcortical morphological neuroimaging biomarkers to differentiate patients with tinnitus from healthy subjects and contributes to the understanding of neuroanatomical alterations in patients with tinnitus.
Background: Audiologists, globally, are generally challenged when assessing and creating intervention plans to help patients suffering from tinnitus. Tinnitus is very common among individuals and may significantly affect one’s quality of life, especially if not addressed by health care professionals. In South Africa, there seems to be limited published studies regarding the current practices of tinnitus management by audiologists. This is mainly because of limited training and a lack of guidelines and strategies for the management of tinnitus. In particular, some participants reported being unfamiliar on how to approach the identification of tinnitus and difficulty is also encountered when counselling tinnitus patients.
Aim: The aim of this study was to describe the preparedness, perspectives and practices of audiologists who manage adult patients with tinnitus.
Method: Two hundred and forty-three registered Health Professions Council of South Africa (HPCSA) participants were involved in the study by responding to an electronic questionnaire survey. Data were collected online from Survey Monkey and were exported to Statistical Packages for the Social Sciences (SPSS) (Version 23) for statistical analysis. Data were analysed using descriptive and inferential statistics. Closed-ended questions were analysed within a quantitative framework and thematic analysis for open-ended questions that were descriptively quantified.
Results: The results of the study are presented according to the objectives. Approximately 44% of participants (44.3%) disagreed that the undergraduate university training had sufficiently prepared them to manage adult patients with tinnitus. Very few (12.3%) had the opportunity to attend specialist training on how to assess patients with tinnitus. Similarly, only 11.6% received any specialist training with regard to tinnitus intervention. With regard to its overall management, 49.4% felt adequately informed in the assessment of patients with tinnitus, while a further 39.2% rated their experience as being limited with regard to tinnitus intervention. There is no statistical significance relationship between participants’ years of experience and tinnitus intervention (p = 0.075). Most participants did not follow any standard guidelines for its management. Some participants (26.8%) reported that further education and training are required in the overall management of patients with tinnitus, while a further 17.7% required training in all areas of tinnitus.
Conclusion: The feedback relating to the study suggests that overall management of tinnitus seems to be a challenge among South African audiologists, irrespective of their years of experience. Audiologists in the study perceived that tinnitus services are limited mainly because of a lack of or limited knowledge, training and guidelines, these being affected by contextual restraints.
Tinnitus is a common but obscure auditory disease to be studied, and there are still in the lack of effective methods developed to treat tinnitus universally. Although electroencephalogram (EEG) is widely applied to the diagnosis of tinnitus, there are few machine learning methods developed to classify tinnitus patients from healthy people based on the EEG data. Moreover, there is still room for improving the classification performance due to the insufficient existing studies. Therefore, in order to improve the performance of classification based on the EEG data, we introduce a multi-view intact space learning method to characterize the EEG signals by feature extraction in a latent intact space. Considering the fact that there are only a small number of subjects available for study, we conduct the classification for valid segments of EEG data of each subject. In this way, the dataset can be enlarged and the classification performance can be improved. By combining different views of EEG data, a considerable result is achieved on classification by using Support Vector Machine classifier, with accuracy, recall, precision, F1 to be 99.23, 99.72, 98.97, 99.34% respectively. This proposed method is an effective and objective method to classify the tinnitus patients from healthy people, further researches are needed to explore the machine learning method in classification and prediction of the effectiveness of tinnitus interventions based on the EEG response of tinnitus individuals.
Network topology plays a key role in many phenomena, from the spreading of diseases to that of financial crises. Whenever the whole structure of a network is unknown, one must resort to reconstruction methods that identify the least biased ensemble of networks consistent with the partial information available. A challenging case, frequently encountered due to privacy issues in the analysis of interbank flows and Big Data, is when there is only local (node-specific) aggregate information available. For binary networks, the relevant ensemble is one where the degree (number of links) of each node is constrained to its observed value. However, for weighted networks the problem is much more complicated. While the naïve approach prescribes to constrain the strengths (total link weights) of all nodes, recent counter-intuitive results suggest that in weighted networks the degrees are often more informative than the strengths. This implies that the reconstruction of weighted networks would be significantly enhanced by the specification of both strengths and degrees, a computationally hard and bias-prone procedure. Here we solve this problem by introducing an analytical and unbiased maximum-entropy method that works in the shortest possible time and does not require the explicit generation of reconstructed samples. We consider several real-world examples and show that, while the strengths alone give poor results, the additional knowledge of the degrees yields accurately reconstructed networks. Information-theoretic criteria rigorously confirm that the degree sequence, as soon as it is non-trivial, is irreducible to the strength sequence. Our results have strong implications for the analysis of motifs and communities and whenever the reconstructed ensemble is required as a null model to detect higher-order patterns.
A Family of new measures of point and graph centrality based on early intuitions of Bavelas (1948) is introduced. These measures define centrality in terms of the degree to which a point falls on the shortest path between others and therefore has a potential for control of communication. They may be used to index centrality in any large or small network of symmetrical relations, whether connected or unconnected.
Objective: To establish the knowledge graph of “disease-syndrome-symptom-method-formula” in Treatise on Febrile Diseases (Shang Han Lun,《伤寒论》) for reducing the fuzziness and uncertainty of data, and for laying a foundation for later knowledge reasoning and its application. Methods: Under the guidance of experts in the classical formula of traditional Chinese medicine (TCM), the method of “top-down as the main, bottom-up as the auxiliary” was adopted to carry out knowledge extraction, knowledge fusion, and knowledge storage from the five aspects of the disease, syndrome, symptom, method, and formula for the original text of Treatise on Febrile Diseases, and so the knowledge graph of Treatise on Febrile Diseases was constructed. On this basis, the knowledge structure query and the knowledge relevance query were realized in a visual manner. Results: The knowledge graph of “disease-syndrome-symptom-method-formula” in the Treatise on Febrile Diseases was constructed, containing 6 469 entities and 10 911 relational triples, on which the query of entities and their relationships can be carried out and the query result can be visualized. Conclusion: The knowledge graph of Treatise on Febrile Diseases systematically realizes its digitization of the knowledge system, and improves the completeness and accuracy of the knowledge representation, and the connection between “disease-syndrome-symptom-treatment-formula”, which is conducive to the sharing and reuse of knowledge can be obtained in a clear and efficient way.
Background:
Many important clinical decisions require causal knowledge (CK) to take action. Although many causal knowledge bases for medicine have been constructed, a comprehensive evaluation based on real-world data and methods for handling potential knowledge noise are still lacking.
Objective:
The objectives of our study are three-fold: (1) propose a framework for the construction of a large-scale and high-quality causal knowledge graph (CKG); (2) design the methods for knowledge noise reduction to improve the quality of the CKG; (3) evaluate the knowledge completeness and accuracy of the CKG using real-world data.
Material and methods:
We extracted causal triples from three knowledge sources (SemMedDB, UptoDate and Churchill's Pocketbook of Differential Diagnosis) based on rules method and language model, performed ontological encoding, and then designed semantic modeling between electronic health record (EHR) data and the CKG to complete knowledge instantiation. We proposed two graph pruning strategies (co-occurrence ratio and causality ratio) to reduce the potential noise introduced by SemMedDB. Finally, the evaluation was carried out by taking the diagnostic decision support (DDS) of diabetic nephropathy (DN) as a real-world case. The data originated from a Chinese hospital EHR system from October 2010 to October 2020. The knowledge completeness and accuracy of the CKG were evaluated based on three state-of-the-art embedding methods (R-GCN, MHGRN and MedPath), the annotated clinical text and the expert review, respectively.
Results:
This graph included 153,289 concepts and 1,719,968 causal triples. A total of 1427 inpatient data were used for evaluation. Better results were achieved by combining three knowledge sources than using only SemMedDB (three models: area under the receiver operating characteristic curve (AUC): p < 0.01, F1: p < 0.01), and the graph covered 93.9% of the causal relations between diseases and diagnostic evidence recorded in clinical text. Causal relations played a vital role in all relations related to disease progression for DDS of DN (three models: AUC: p > 0.05, F1: p > 0.05), and after pruning, the knowledge accuracy of the CKG was significantly improved (three models: AUC: p < 0.01, F1: p < 0.01; expert review: average accuracy: + 5.5%).
Conclusions:
The results demonstrated that our proposed CKG could completely and accurately capture the abstract CK under the concrete EHR data, and the pruning strategies could improve the knowledge accuracy of our CKG. The CKG has the potential to be applied to the DDS of diseases.
There are many risks that may lead to serious consequences in the prescriptions. The traditional prescription risk detection methods rely on rational medication monitoring systems based on the database, which cannot cover the medication patterns, and often conflicts with clinical practice, resulting in false-reporting and under-reporting. To effectively detect the risks in prescriptions, we propose a prescription risk detection framework based on knowledge graph leveraging medical big data. Firstly, we construct a medical knowledge graph using the knowledge extracted from medical text data and historical prescriptions data. Then, based on the constructed knowledge graph, we detect the medication risk and complete the risk edges of the knowledge graph in three aspects: (1) we extract the medication usages that are consistent with both the description of the drug instructions and the historical prescriptions, and then label the risk degree in the graph. (2) we collect the medication patterns that did not conform to the instructions and extract the features leveraging knowledge graph to detect the risk of off-label drug use. (3) we represent the new drugs that lack risk information using graph model, then detect the risk of new drugs using knowledge graph completion task. Finally, we get a complete medical risk knowledge graph to detect the risk of clinical prescriptions. We use real-world prescriptions data from a tertiary hospital in Fujian Province for verification. The results show that our framework performs best among the baseline and can effectively detect the risks in the prescription.
Background
: High prevalence of hypertension and complicated medication knowledge have presented challenges to hypertension clinicians and general practitioners. Clinical decision support systems (CDSSs) are developed to aid clinicians in decision making. Current clinical knowledge is stored in fixed templates, which are not intuitive for clinicians and limit the knowledge reusability. Knowledge graphs (KGs) store knowledge in a way that is not only intuitive to humans but also processable by computers directly. However, existing medical KGs such as UMLS and CMeKG are general purpose and thus lack enough knowledge to enable hypertension medication.
Methods
: We first construct a KG specific to hypertension medication according to the Chinese hypertension guideline and then develop the corresponding CDSS to implement hypertension medication and knowledge management. Current advances in knowledge graph representation and modelling are researched and applied in the complex medical knowledge representation. Traditional knowledge representation and KG representation are innovatively combined in the storage of the KG to enable convenient knowledge management and easy application by the CDSS. Along a predefined reasoning path in the KG, the CDSS finally accomplishes the hypertension medication by applying knowledge stored in the KG. 124 health records of a hypertension Chief Physician from Beijing Anzhen Hospital, Capital Medical University, are collected to evaluate the system metrics on the single drug recommendation task.
Results and conclusion
: The proposed CDSS has functions of medication knowledge graph management and hypertension medication decision support. With elaborate design on knowledge representation, knowledge management is intuitive and convenient. By virtue of the KG, medication recommendations are highly visualized and explainable. Experiments on 124 health records with 90% guideline compliance collected from hospitals in single class recommendation task achieve 91%, 83% and 77% on recall, [email protected] and MRR metrics respectively, which demonstrates the quality of the KG and effectiveness of the system.
Tinnitus is an auditory perception in the absence of an auditory stimulus. It may be associated with acoustic trauma (eg, exposure to loud noise), chronic hearing loss, emotional stressors, or spontaneous occurrence. The psychopathological reaction to the perceived auditory stimulus is an enormous source of distress and disability for many patients with tinnitus. National health surveys estimate that nearly 10 in 100 adults experience some form of tinnitus.¹ Among workers exposed to occupational noise, the prevalence of tinnitus is 15 per 100.² Of these, tinnitus is burdensome and chronic for roughly 20 million and extreme and debilitating tinnitus for 2 million US residents.² Many patients with tinnitus report that the auditory perception impairs sleep, concentration, and cognitive function required for day-to-day functioning. Among the nearly 4.5 million US military veterans receiving service-connected compensation, 42% receive compensation for tinnitus, which makes it the most prevalent service-connected disability. The number of veterans who receive compensation due to tinnitus is nearly 60% greater than the number of veterans who receive compensation for hearing loss, which is the condition with the second most disability claims.
The Internet has become a rich and large repository of information about us as individuals. Anything from the links and text on a user’s homepage to the mailing lists the user subscribes to are reflections of social interactions a user has in the real world. In this paper we devise techniques and tools to mine this information in order to extract social networks and the exogenous factors underlying the networks’ structure. In an analysis of two data sets, from Stanford University and the Massachusetts Institute of Technology (MIT), we show that some factors are better indicators of social connections than others, and that these indicators vary between user populations. Our techniques provide potential applications in automatically inferring real world connections and discovering, labeling, and characterizing communities.
Research on entity recognition and knowledge graph construction based on TCM medical records
- Y M Yang
- Y Li
- X Zhong
Yang YM, Li Y, Zhong X. Research on entity recognition and knowledge graph construction based on TCM medical
records. J Artif Intell Pract. 2021;47(1):1-15. [doi: 10.23977/jaip.2020.040105]
BERT: pre-training of deep bidirectional transformers for language understanding
- J Devlin
- M W Chang
- K Lee
- K Toutanova
Devlin J, Chang MW, Lee K, Toutanova K. BERT: pre-training of deep bidirectional transformers for language understanding.
2019. Presented at: Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational
Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers);
- M N Minneapolis
Minneapolis,
MN. [doi: 10.18653/v1/N19-1423]
Traditional Chinese Otorhinolaryngology. Beijing, China. China Traditional Chinese Medicine Press
- P Liu
Liu P. Traditional Chinese Otorhinolaryngology. Beijing, China. China Traditional Chinese Medicine Press; 2021:90-94.
- D J Wang
- Z W Gan
Wang DJ, Gan ZW. Traditional Chinese Otorhinolaryngology. Shanghai, China. Shanghai Scientific and Technical Publishers;
1985:26-28.