As the pace of evolution and nature of AI-based technologies outgrow traditional frameworks for evaluation, regulatory bodies are developing new models to keep up. In this News and Perspectives article, JMIR Correspondent Tejas Athni reports on the US Food and Drug Administration's (FDA's) new Technology-Enabled Meaningful Patient Outcomes (TEMPO) pilot for AI-enabled medical devices.

Mediation analysis has significantly enhanced the elucidation of underlying epigenetic mechanisms by identifying mediators that influence the effect of an exposure on an outcome. In epigenomics research, the exponential increase in the dimensionality of mediators necessitates the development of advanced high-dimensional mediation models. Here we introduce a novel Gene Set High-Dimensional Mediation Analysis (gHDMA) model to understand the gene-level mediation role of DNA methylations, building upon our previous HDMA method. We begin our analysis by applying functional principal component analysis to capture gene variation signals across regions, thereby enhancing the model's statistical power. Following this, we employ the Sure Independence Screening method, based on Wilks' $\varLambda$-test, to efficiently reduce the dimensionality to a more manageable level, enabling high-dimensional inference. Our model is distinguished by its minimal reliance on stringent assumptions about the relationship between mediators and the outcome. Extensive simulation studies, by varying the type of basis function, the nature of the outcome variable, and the dimensionality of the gene region, demonstrate the robust performance of the gHDMA model. A corroborative case study further validates the methodology's efficacy. The gHDMA model emerges as a powerful analytical tool, with an enhanced capacity to identify genes characterized by hypermethylation or hypomethylation that mediate the effects of exposure on biological outcomes.

In 2023, approximately 23,000 persons died of homicide and 49,000 persons died of suicide in the United States, according to the National Vital Statistics System. This report summarizes data from CDC's National Violent Death Reporting System (NVDRS) on violent deaths and suicides that occurred in the 50 states, the District of Columbia, and Puerto Rico in 2023.

The Consolidated Appropriations Act, 2026 (CAA 2026) introduces the most significant federal restructuring of pharmacy benefit manager (PBM) compensation to date. Effective January 2028, the act restructures Medicare Part D by effectively eliminating spread pricing, mandating the full pass-through of manufacturer remuneration, restricting PBM revenue to bona fide service fees delinked from drug prices and codifying "any willing pharmacy" network inclusivity. Similar mandates apply under the Employee Retirement Income Security Act of 1974 (ERISA) for employer-sponsored plans, though they are primarily subject to mandatory pass‑through and fiduciary reasonableness standards rather than explicit statutory delinking of service fees. Reforms to the Internal Revenue Code of 1986, the Public Health Service Act, Medicare, and ERISA aim to improve transparency and auditing for patients, payers, and the federal government while reducing incentives tied to high list prices. This transparency redefines PBM-payer engagement, reconfiguring the PBM's role within the drug supply chain. Furthermore, the CAA 2026 redistributes PBM profits to Medicare and ERISA plans, shifting the emphasis from rebate maximization to net cost savings and transferring greater financial risk to plan sponsors. This commentary examines the structural implications of these reforms for managed care pharmacy, including emerging challenges related to incentive alignment, administrative burden, and formulary design. Importantly, these implications represent early interpretations of potential downstream effects rather than finalized regulatory outcomes. Early evidence suggests that while the CAA 2026 enhances accountability, it may also introduce new distortions in pricing strategies. Managed care organizations will likely need to adapt to a data-intensive, plan-centric model of oversight as these reforms continue to evolve.

Rituximab is widely used for B‑cell malignancies and autoimmune diseases, but its pediatric safety profile requires systematic real‑world evaluation. This research mined safety signals of adverse events (AEs) linked to rituximab in pediatric patients using U.S. Food and Drug Administration Adverse Event Reporting System (FAERS) data from 2004 to 2025. A total of 2,231 pediatric AE reports involving rituximab were identified and analyzed using four disproportionality methods (ROR, PRR, BCPNN, and MGPS) for signal detection and Weibull distribution analysis for time-to-onset patterns. Results showed a balanced sex distribution in AE reports (47.7% male, 48.5% female). Most reports involved adolescents aged 12-17, with an overall increasing trend. A total of 149 positive safety signals were detected via disproportionality analysis. Several of these signals pertained to immune system - and infection‑related adverse events. Notably, the elevated signal magnitudes for certain signals were substantially confounded by indication bias, pre‑existing comorbidities, and reports associated with therapeutic failure. Stratified analyses revealed differences in the signal distribution of adverse‑event reports across age and sex subgroups. Time‑to‑onset analysis of adverse‑event reports indicated that most events documented in these reports occurred within 30 d of therapy initiation, with a median of 7 d. This study characterizes the reported safety profile of rituximab in pediatric patients based on FAERS spontaneous reports. Our findings represent exploratory signal hypotheses only and can serve as a reference for subsequent relevant investigations.

Drug overdose is a leading cause of death in the United States. Targeted community interventions and allocation of resources for reducing overdose deaths require timely and actionable data to make a meaningful public health impact. We present our work on tuning geographic-specific machine learning forecast models to predict the number of opioid-involved overdoses involving Emergency Medical Services (EMS) in Kentucky, with a focus on optimizing covariates representing measurable opioid overdose risk and protective factors. We aggregated suspected opioid-involved overdoses in EMS data into monthly totals by county between January 2017 and September 2025. We further grouped these counties into larger regions, representing Area Development Districts (ADDs), service areas for Community Mental Health Centers (CMHCs), and local health departments (LHDs). We constructed long-term time-series forecasting models (NLinear LTSF) to predict opioid-involved overdoses three months into the future. We tested the impact of using eight covariate data sources: Kentucky State Police drug seizures, Medicaid claims, community naloxone distribution, Kentucky Department of Corrections intakes and releases, social determinants of health data, location of treatment venues, and weather. We evaluated our models using both an unseen 10% test set and an expanding window strategy, where we simulated predicting historical data and retrained the model using data available for every three-month window. We embedded predictions into community-specific dashboards where end-users can select individual counties, or larger regions covered by distinct ADDs, CMHCs, or LHDs. The dashboards are integrated in Kentucky's Rapid Actionable Data for Opioid Response system designed to deliver ongoing near-real time analytics and forecasting at state and local levels.