A new study by UF researchers and collaborators has found that weight loss drugs are associated with lower cancer risk.

Background: Opioid use disorder (OUD) remains a critical public health crisis in the United States. Despite widespread policy and clinical interventions, early identification of individuals at risk for developing OUD remains challenging due to limitations in traditional screening approaches and a lack of individualized risk stratification methods. Machine learning (ML) methods offer an opportunity to develop timely, high-performing, and explainable predictive models that can enhance OUD prevention strategies in clinical settings. Objective: This study aims to develop and validate an ML model using electronic health record (EHR) data to predict the 3-month risk of incident OUD among adults initiating opioid therapy and to stratify patients into clinically actionable risk groups. Methods: This prognostic modeling study used 2017‐2022 OneFlorida+ EHR data to develop and validate ML algorithms predicting 3-month incident OUD risk. We included 182,083 adults (≥18 y) without cancer, overdose, or OUD or hospice history who received ≥1 outpatient, noninjectable opioid prescription. Using 183 predictors measured in sequential 3-month intervals, we developed an elastic net, least absolute shrinkage and selection operator, gradient boosting machine (GBM), and random forest models on randomly split training, testing, and validation sets. Model performance was assessed using C-statistics, predictive values, and number needed to evaluate, with patients stratified into risk deciles for clinical applicability. Model explainability was assessed using Shapley additive explanations, and fairness was evaluated using standard metrics. We externally validated the best-performing model using an independent cohort from the 2018‐2020 UPMC (formerly University of Pittsburgh Medical Center) health system. Results: In the validation sample (n=60,694), GBM (C-statistics=0.879, 95% CI 0.874‐0.884) and elastic net (C-statistics=0.872, 95% CI 0.867‐0.877) outperformed least absolute shrinkage and selection operator (C-statistics=0.846, 95% CI 0.840‐0.851) and random forest (C-statistics=0.798, 95% CI 0.792‐0.804), with GBM model requiring the fewest predictors (n=75) for predicting 3-month incident OUD. Using the GBM algorithm to predict the subsequent 3-month OUD risk, the top decile subgroup had a positive predictive value of 3.26%, a negative predictive value of 99.8%, and a number needed to evaluate of 31. The top decile (n=6696) captured ~68% of patients with OUD. Shapley additive explanations analysis identified age, number of outpatient visits, history of back and other pain conditions, comorbidity burden, and opioid prescribing patterns as the strongest predictors of incident OUD. Fairness assessment showed an acceptable false negative rate parity across race, age, and sex. In external validation on the UPMC cohort, the GBM model maintained good discrimination (C-statistics=0.756, 95% CI 0.750‐0.762) and effective risk stratification. Conclusions: An ML algorithm predicting incident OUD derived from OneFlorida+ EHR data performed well in external validation with data using UPMC. The algorithm might be valuable for incident OUD risk prediction and stratification across health systems, with potential to inform early intervention.

"Bold perspectives, inspiring stories, and life challenges on Dammed If You Don’t—global insights with a focus on Florida's vibrant culture."

Background: Heart failure (HF) readmission rates vary across geographic regions in the United States, yet the impact of external exposome factors, such as contextual-level social determinants of health (SDoH), on adverse HF outcomes is not well understood. Objective: To examine the association between external exposome factors and the risk of HF readmission and all-cause mortality using a data-driven approach. Methods: We conducted a retrospective cohort study using electronic health records (EHR) data from the OneFlorida+ network, including patients hospitalized for HF (HHF) from 2016 to 2022. A total of 1,308 external exposome factors, covering a wide range of SDoH (e.g., economic stability, education, healthcare access, natural and built environments, and social context), were linked to patients’ EHR data based on their residential location at the county level. Patients were followed for one year after their first HHF to capture readmission and mortality events. We applied LASSO regularization to preselect candidate variables, followed by a two-phase External Exposome-Wide Association Study (ExWAS) using mixed-effects logistic regression to identify key factors associated with the composite outcome of one year HF readmission and mortality. Results: Among 63,940 HF patients (30,475 [48%] women; mean age 65 years, SD 14), higher maximum temperature in May was significantly associated with increased risk of the composite outcome (aOR: 1.04, 95% CI: 1.02–1.06; P < 0.001). Subgroup analyses showed consistent associations across age, sex, race, socioeconomic status, and rural/urban strata. Conclusions: Using a data-driven approach, we found that elevated maximum temperature in May (late spring) was significantly associated with HF readmission and mortality in Florida. Further investigations are warranted to uncover the intricate mechanisms through which extreme heat potentially influences HF outcomes. Clinical Trial: Not applicable

Amid the opioid epidemic in the United States, hepatitis C virus (HCV) infections are rising, with one-third of individuals with infection unaware due to the asymptomatic nature. This study aimed to develop and validate a machine learning (ML)-based algorithm to screen individuals at high risk of HCV infection.MethodsWe conducted prognostic modeling using the 2016–2023 OneFlorida+ database of all-payer electronic health records. The study included individuals aged ≥18 years who were tested for HCV antibodies, RNA, or genotype. We identified 275 features of HCV, including sociodemographic and clinical characteristics, during a 6-month period before the test result date. Four ML algorithms—elastic net (EN), random forest (RF), gradient boosting machine (GBM), and deep neural network (DNN)—were developed and validated to predict HCV infection. We stratified patients into deciles based on predicted risk.ResultsAmong 445 624 individuals, 11 823 (2.65%) tested positive for HCV. Training (75%) and validation (25%) samples had similar characteristics (mean, standard deviation age, 45 [16] years; 62.86% female; 54.43% White). The GBM model (C statistic, 0.916 [95% confidence interval = .911–.921]) outperformed the EN (0.885 [.879–.891]), RF (0.854 [.847–.861]), and DNN (0.908 [.903–.913]) models (P < .0001). Using the Youden index, GBM achieved 79.39% sensitivity and 89.08% specificity, identifying 1 positive HCV case per 6 tests. Among patients with HCV, 75.63% and 90.25% were captured in the top first and first to third risk deciles, respectively.ConclusionsML algorithms effectively predicted and stratified HCV infection risk, offering a promising targeted screening tool for clinical settings.

Amid the opioid epidemic in the United States, Hepatitis C virus (HCV) infections are rising, with one-third of individuals with infection unaware due to the asymptomatic nature. This study aimed to develop and validate a machine learning (ML)-based algorithm to screen individuals at high risk of HCV infection.MethodsWe conducted prognostic modeling using the 2016-2023 OneFlorida+ database of all-payer electronic health records. The study included individuals aged ≥18 years who were tested for HCV antibodies, RNA, or genotype. We identified 275 features of HCV, including sociodemographic and clinical characteristics, during a 6-month period before the test result date. Four ML algorithms—elastic net (EN), random forest (RF), gradient boosting machine (GBM), and deep neural network (DNN)—were developed and validated to predict HCV infection. We stratified patients into deciles based on predicted risk.ResultsAmong 445,624 individuals, 11,823 (2.65%) tested positive for HCV. Training (75%) and validation (25%) samples had similar characteristics (mean [SD] age, 45 [16] years; 62.86% female; 54.43% White). The GBM model (C statistic, 0.916 [95% CI, 0.911-0.921]) outperformed the EN (0.885 [0.879-0.891]), RF (0.854 [0.847-0.861]), and DNN (0.908 [0.903-0.913]) models (P<0.0001). Using the Youden index, GBM achieved 79.39% sensitivity and 89.08% specificity, identifying one positive HCV case per six tests. Among patients with HCV, 75.63% and 90.25% were captured in the top first and first to third risk deciles, respectively.ConclusionsML algorithms effectively predicted and stratified HCV infection risk, offering a promising targeted screening tool for clinical settings.

About 1 in 9 older adults over 65 has Alzheimer's disease (AD), many of whom also have multiple othe

In a target trial emulation using OneFlorida+ electronic health record data, GLP-1 receptor agonist use in adults with obesity and autoimmune disease was linked to lower hazards of pulmonary embolism,...

No description available