Bennett L. Leventhal’s research while affiliated with University of Illinois Chicago and other places

Background This study aims to understand how secondary use of health records can be done for prediction, detection, treatment recommendations, and related tasks in clinical decision support systems. Methods Articles mentioning the secondary use of EHRs for clinical utility, specifically in prediction, detection, treatment recommendations, and related tasks in decision support were reviewed. We extracted study details, methods, tools, technologies, utility, and performance. Results We found that secondary uses of EHRs are primarily retrospective, mostly conducted using records from hospital EHRs, EHR data networks, and warehouses. EHRs vary in type and quality, making it critical to ensure their completeness and quality for clinical utility. Widely used methods include machine learning, statistics, simulation, and analytics. Secondary use of health records can be applied in any area of medicine. The selection of data, cohorts, tools, technology, and methods depends on the specific clinical utility. Conclusion The process for secondary use of health records should include three key steps: 1. Validation of the quality of EHRs, 2. Use of methods, tools, and technologies with proactive training, and 3. Multidimensional assessment of the results and their usefulness. Trial Registration : PROSPERO registration number CRD42023409582

Background Accurate assessment of mental disorders and learning disabilities is essential for timely intervention. Machine learning and feature selection techniques have potential in improving the accuracy and efficiency of mental health assessments. However, limited research has explored the use of large transdiagnostic datasets, as well as the application of these techniques in developing quick, question-based assessments. The goals of this study are to apply machine learning and feature selection techniques to a large transdiagnostic dataset featuring a high number of assessment items, and to create a tool for the streamlined creation of efficient and effective assessment using existing datasets. Methods This study uses the Healthy Brain Network (HBN) dataset to develop a tool for creation of efficient and effective machine learning-based assessment of mental disorders and learning disabilities. Feature selection algorithms were applied to identify parsimonious item subsets. Modular architecture ensures straightforward application to other datasets. Results Machine learning models trained on the HBN data exhibited improved performance over existing assessments. Using only non-proprietary assessments did not significantly impact model performance. Discussion This study demonstrates the feasibility of using existing large-scale datasets for creating accurate and efficient assessments for mental disorders and learning disabilities. The performance of the machine learning models provide estimates of the performance of the new assessments in a population similar to HBN. The modular architecture of the developed tool ensures seamless application to diverse clinical and research contexts.

Background Research suggests racial/ethnic disparities in prenatal exposure to endocrine disrupting environmental phenols (EPs) in limited populations. However, no studies have investigated racial/ethnic disparities in prenatal EP exposure across the U.S. Objectives To estimate demographic differences in prenatal urinary EPs among participants in the Environmental influences on Child Health Outcomes (ECHO) Cohort. Methods An analysis of 4006 pregnant ECHO participants was performed, with 7854 specimens collected from 1999–2020. Racial/ethnic identity was self-reported. Urinary levels of 2,4-dichlorophenol (2,4-DCP), 2,5-dichlorophenol (2,5-DCP), benzophenone-3 (BP-3), bisphenols A (BPA), F (BPF), and S (BPS), and methyl- (MePb), ethyl- (EtPb), propyl- (PrPb), and butyl- (BuPb) parabens were measured at one or more time points during pregnancy. Effect estimates were adjusted for age, pre-pregnancy body mass index, educational level, gestational age and season at urine collection, and ECHO cohort. Results Participants were classified as Hispanic of any race ( n = 1658), non-Hispanic White ( n = 1478), non-Hispanic Black ( n = 490), and non-Hispanic Other ( n = 362), which included individuals of multiple races. Urinary 2,4-DCP and 2,5-DCP concentrations were 2- to 4-fold higher among Hispanic, non-Hispanic Black, and non-Hispanic Other participants relative to non-Hispanic White participants. MePb was ~2-fold higher among non-Hispanic Black (95% confidence interval (CI): 1.7–3.1) and non-Hispanic Other (95% CI: 1.5–2.8) participants. PrPb was similarly higher among non-Hispanic Black (95% CI: 1.7–3.7) and non-Hispanic Other (95% CI: 1.3–3.1) participants. EtPb was higher among non-Hispanic Black participants (3.1-fold; 95% CI 1.7–5.8). BP-3 was lower in Hispanic (0.7-fold; 95% CI: 0.5–0.9), non-Hispanic Black (0.4-fold; 95% CI: 0.3–0.5), and non-Hispanic Other (0.5-fold; 95% CI: 0.4–0.7) participants. Urinary BuPb, BPA, BPF, and BPS were similar across groups. Impact statement This multisite, observational cohort study investigated whether there are racial and ethnic differences in prenatal exposure to endocrine disrupting environmental phenols and parabens. Among 4006 participants from multiple U.S. cohorts who provided urine specimens during pregnancy, those who self-reported a racial and ethnic identity other than non-Hispanic White had higher urinary concentrations of 2,4-dichlorophenol, 2,5-dichlorophenol, methyl paraben, ethyl paraben, and propyl paraben and lower urinary concentrations of benzophenone-3 than those reporting as non-Hispanic White. These data show differences in prenatal concentrations of endocrine disrupting environmental phenols and parabens by racial and ethnic identity.

This study addresses the challenge of predicting readmissions in Child and Adolescent Mental Health Services (CAMHS) by analyzing the predictability of readmissions over short, medium, and long term periods. Using health records spanning 35 years, which included 22,643 patients and 30,938 episodes of care, we focused on the episode of care as a central unit, defined as a referral-discharge cycle that incorporates assessments and interventions. Data pre-processing involved handling missing values, normalizing, and transforming data, while resolving issues related to overlapping episodes and correcting registration errors where possible. Readmission prediction was inferred from electronic health records (EHR), as this variable was not directly recorded. A binary classifier distinguished between readmitted and non-readmitted patients, followed by a multi-class classifier to categorize readmissions based on timeframes: short (within 6 months), medium (6 months - 2 years), and long (more than 2 years). Several predictive models were evaluated based on metrics like AUC, F1-score, precision, and recall, and the K-prototype algorithm was employed to explore similarities between episodes through clustering. The optimal binary classifier (Oversampled Gradient Boosting) achieved an AUC of 0.7005, while the multi-class classifier (Oversampled Random Forest) reached an AUC of 0.6368. The K-prototype resulted in three clusters as optimal (SI: 0.256, CI: 4473.64). Despite identifying relationships between care intensity, case complexity, and readmission risk, generalizing these findings proved difficult, partly because clinicians often avoid discharging patients likely to be readmitted. Overall, while this dataset offers insights into patient care and service patterns, predicting readmissions remains challenging, suggesting a need for improved analytical models that consider patient development, disease progression, and intervention effects.