Woodruff Health Sciences Center

Data-driven subtyping of type 2 diabetes has not been translated into clinical practice due to the lack of routine fasting glucose and insulin measurements. We aimed to identify type 2 diabetes subtypes in clinical settings using electronic health records and study their epidemiology. We identified 727,076 adults (≥18 years) with newly diagnosed type 2 diabetes from Epic Cosmos research platform data across all 50 states and the District of Columbia between 2012 and 2023. Classification models developed in cohort studies were applied to study the sociodemographic distribution of subtypes. Cox proportional hazards regression models, adjusted for age and sex, were used to assess the rates of microvascular complications (retinopathy, neuropathy and nephropathy) and macrovascular complications (severe atherosclerotic cardiovascular disease [ASCVD], other ASCVD and heart failure). Among newly diagnosed individuals (mean age 64.4 years [SD 13.3], 52% female), 21.6% were classified as having severe insulin-deficient diabetes (SIDD), 23.8% were classified as having mild obesity-related diabetes (MOD), 40.9% were classified as having mild age-related diabetes and 13.7% were classified as having the mixed subtype. Compared with those classified as having MOD, individuals classified as having SIDD had higher HRs for retinopathy (HR 2.83; 95% CI 2.73, 2.93), neuropathy (HR 1.57; 95% CI 1.54, 1.60), nephropathy (HR 1.34; 95% CI 1.32, 1.37), severe ASCVD (HR 1.49; 95% CI 1.46, 1.53), other ASCVD (HR 1.23; 95% CI 1.21, 1.25) and heart failure (HR 1.17; 95% CI 1.15, 1.20). SIDD and MOD were more prevalent among Hispanics (28.4% and 30.1%, respectively) and non-Hispanic Black people (25.5% and 30.0%, respectively) compared with non-Hispanic White people (20.1% and 21.6%, respectively), and were also more prevalent in the District of Columbia and Utah, respectively, compared with the rest of the country. Individuals with different type 2 diabetes subtypes, identified through electronic health records, differ in terms of their risk of vascular complications. These findings support leveraging routine electronic health record data to improve the characterisation of patient heterogeneity at the time of diabetes diagnosis.

Obstetric anesthesia is an important subspecialty of anesthesia requiring specialized training to meet the distinctive needs of maternal care. Variations in obstetric anesthesia education create deficiencies for some nurse anesthesiologists upon graduation. The purpose of this study was to evaluate incorporating dedicated obstetric anesthesia rotation for nurse anesthesia residents at a northeastern university, focusing on training outcomes, preparedness, and perceptions of obstetric anesthesia as a subspecialty. Certified registered nurse anesthetists (CRNAs) graduated between 2018 and 2023 received a survey. Two groups were analyzed: with and without the obstetric rotation. The survey assessed clinical experience, obstetric anesthesia preparedness, and perceptions of obstetric anesthesia as a specialty using Likert-scale questions and open-ended feedback. Numerical data were analyzed using descriptive statistics, paired t-tests, and graphical representation. CRNAs with the obstetric rotation reported significantly fewer challenges meeting minimum epidural requirements, higher confidence in managing obstetric cases, and greater recognition of the importance of the training. In contrast, CRNAs without the rotation highlighted deficiencies in epidural training. An obstetric rotation is important to instill the confidence necessary for CRNAs to achieve full scope of practice capabilities. In addition to an obstetric specialty rotation, recommendations include advocacy for CRNA training, a focus on obstetric anesthesia subspecialty development, and access for educators to resources assisting in creating this rotation.

The environmental persistence of per- and polyfluoroalkyl substances (PFAS) necessitates new remediation technologies, yet the vast chemical space makes traditional exploration methods for understanding degradation-relevant properties intractable. Rational design of PFAS degradation strategies requires accurate prediction of three critical molecular properties: bond dissociation energies (BDEs) to govern kinetics, polarizability to control catalytic interactions, and thermodynamic stability to govern reaction feasibility. Guided by theoretically-rooted principles, we identify that global properties (polarizability, stability) require spatially-informed features (3D electron density patterns), while bond-specific properties are governed by topological features (atomic connectivity). We developed two distinct physics-informed ML workflows implementing this principle: For global properties, two-point spatial correlations were compressed via Principal Component Analysis (PCA) and input to a Gaussian Process Regression (GPR) model. For local properties, a graph-based feature scheme was coupled with a Random Forest (RF) algorithm. Both workflows demonstrated strong predictive performance (GPR R2 ≈ 0.92 for polarizability; R2 ≈ 0.97 for enthalpy; RF R2 ≈ 0.87 for BDE) across multiple datasets, establishing robust Structure-Property linkages for PFAS. These physics-informed models provide a foundational capability for rapid, high-throughput screening of the vast PFAS library, enabling prioritization of candidate molecules and bonding motifs for subsequent experimental and process-level remediation studies, rather than constituting complete remediation workflows by themselves.

The blood-brain barrier (BBB) renders the delivery of nanomedicine in the brain ineffective and the detection of circulating disease-related DNA from the brain unreliable. Here, we demonstrate that microbubble-enhanced focused ultrasound (MB-FUS) mediated BBB opening, supported by large-data models predict sonication regimens for safe and effective BBB opening. Importantly, a closed-loop MB-FUS controller augmented by machine learning (ML-CL) expands the treatment window, as compared to conventional controllers, by persistently and proactively maximizing the BBB permeability while preventing tissue damage. By successfully scaling up from mice to rats and from healthy to diseased brains (glioma), ML-CL rendered the BBB permeable to large nanoparticles and markedly improved the release and detection of reporter gene DNA from tumors in blood. Together, our findings reveal the potential of data-driven feedback to support the development of next-generation AI-powered ultrasound systems for safe, robust, and efficient nanotheranostic targeting and treatment of brain diseases.

BackgroundAtrial fibrillation (AF) ablation is an effective treatment for reducing episodes and improving quality of life in patients with AF. However, long-term AF-free rates after AF ablation are inconsistent across the population, ranging from 50% to 75%. Patient selection relies on individual clinical assessment, highlighting a critical gap in population-level predictive analytics. While existing risk scores (eg, CHADS₂ [congestive heart failure, hypertension, age ≥75 years, diabetes mellitus, and stroke], CHA₂DS₂-VASc [congestive heart failure, hypertension, age ≥75 years, diabetes mellitus, stroke, vascular disease, age, and sex category], CAAP-AF [coronary artery disease, left atrial diameter, age, AF, antiarrhythmic drugs, and female sex category]) have been applied to predict AF ablation outcomes, their performance in administrative claims data remains unclear. Leveraging large administrative claims databases represents an opportunity to develop standardized, scalable prediction models that could inform population health management and resource allocation at a national level.ObjectiveThis study utilizes machine learning (ML) models on claims data to explore if integrating International Classification of Diseases (ICD) billing codes outperforms traditional stroke and AF risk scores in predicting 1-year AF ablation outcomes.MethodsWe analyzed claims data from the Merative MarketScan Research Medicare database (2013‐2020) to identify 14,521 patients who underwent AF ablation. To predict 1-year AF-free outcomes, we developed logistic regression and extreme gradient boosting (XGBoost) models using demographic characteristics, comorbidity indices, and ICD diagnostic codes from the 2 years preceding ablation. Model predictions were compared with claims-based implementations of established risk scores—CHADS2, CHA2DS2-VASc, and a modified CAAP-AF (without left atrial diameter and the number of failed antiarrhythmic drugs). The ML models were also assessed on subgroups of patients with paroxysmal AF, persistent AF, and both AF and atrial flutter from October 2015 onward.ResultsAmong 14,521 patients (mean age 71.5, SD 5.31 y; n=5800, 39.94% female), AF ablation success occurred in 54.01% (n=7843). XGBoost achieved areas under the receiver operating characteristic curve (AUCs) of 0.528, 0.521, and 0.529 for the whole, female, and male AF ablation groups, respectively, and better discrimination than CHADS2, CHA2DS2-VASc, and the modified CAAP-AF in all AF ablation groups (whole population, female, and male). While CHA2DS2-VASc and the modified CAAP-AF showed higher recall (>0.798), their precision (<0.540) was lower than XGBoost (0.552‐0.556). In subgroup analyses of International Classification of Disease, Tenth Revision (ICD-10) patients (n=7646), the models incorporating ICD codes demonstrated better performance than those using only demographic and comorbidity data across most AF subtypes, with the highest AUC (0.544) observed in patients with paroxysmal AF.ConclusionsWhile the ML models achieved statistically significant improvements over claim-based implementations of established clinical risk scores (AUC 0.528‐0.544 vs 0.498‐0.505), the modest predictive performance highlights challenges in predicting procedural outcomes using administrative data that lack key clinical variables (eg, left atrial size and medication details). Our findings establish that while standardized outcome prediction using nationally available administrative data is technically feasible, current performance is insufficient for clinical decision-making and better suited for health system quality monitoring and comparative effectiveness research applications.

Patients prescribed second-generation antipsychotics (SGA) are at risk of antipsychotic induced weight gain (AIWG). The objective was to estimate weight changes after prescription of incretin-based weight loss medications by category of expected AIWG: high (olanzapine, clozapine), intermediate (risperidone, quetiapine, paliperidone) and low (e.g., asenapine, aripiprazole). We conducted a retrospective cohort study using electronic health records (June 2021-December 2023) from Epic Cosmos for adults (≥18 years) without diabetes, prescribed SGA, and eligible for incretin-based weight loss medications. We studied changes in weight (kg) and the probability of at least 5% weight loss after 6 months of prescription of incretin-based medications by categories of AIWG. The analytic sample (n = 66,574) were aged 51.9 years (SD: 17.7), with average BMI of 39.5 kg/m2 (SD: 7.7). Those prescribed incretin-based medications lost -2.17 kg (95% CI: -2.49, -1.84), and were 1.71 (95% CI: 1.63, 1.80) times more likely to achieve 5% weight loss, relative to those who didn't receive prescriptions. Weight loss was greater among those prescribed SGAs of low AIWG (-3.02 kg, 95% CI: -3.29, -2.74), relative to those prescribed high AIWG (-1.33 kg, 95% CI: -2.04, -0.62). Semaglutide and tirzepatide induce weight loss among those prescribed SGAs, with lower effectiveness in those prescribed higher AIWG SGAs.

This pilot study used metabolomics to provide insights into metabolic alterations of integrase strand transfer inhibitor (INSTI)-associated weight gain among women with HIV. The study included 33 virally suppressed women with HIV who switched to or added an INSTI. Plasma samples collected 6-12 months pre- (visit 1) and 1-6 months post-INSTI add/switch (visit 2) were analyzed with liquid chromatography-mass spectrometry-based high-resolution metabolomics. The baseline plasma metabolome and changes in metabolomic signatures (from visit 1 to visit 2) were compared in women who experienced ≥5% weight gain (n = 18) over 1-2 years vs those who maintained/lost body weight (n = 15). Median age was 53 (Q1 47, Q3 55) years, 94% were Black, and baseline body mass index was 34.2 (Q1 30.6, Q3 38.5) kg/m 2 . The median weight change was +9.20 kg (Q1-Q3 6.77-15.13 kg) and -0.68 kg (Q1-Q3 -5.14 to 0.00 kg) for the weight gain vs maintained/lost weight groups, respectively. A total of 820 metabolites spanning 9 enriched metabolic pathways, including amino acid (eg, tryptophan) and micronutrient pathways (eg, vitamin E) differed between weight groups before INSTI use ( P < 0.05). A total of 1147 metabolites spanning 10 enriched pathways, particularly lipid pathways, exhibited a significant group x time interaction effect ( P < 0.05), with an overall pattern of decreased free fatty acids over time among women who gained weight. Several metabolic pathways at baseline and within 6 months were associated with weight gain in women initiating INSTIs. Acute changes in lipid metabolism after INSTI initiation provide potential insights into the pathophysiology of weight gain in this population.