International Journal of Medical Informatics

In this work, we demonstrate the unprecedented value of NIH's "All of Us Research Program" (AoURP) dataset in studying maternal morbidity and building predictive machine learning (ML) models across heterogeneous populations in the United States. We developed robust and data-driven preprocessing pipelines to curate a longitudinal, multi-site, multimodal, and demographically diverse pregnancy dataset (20,253 subjects; 27,525 pregnancy episodes) from AoURP data, using electronic health records (EHR) (Conditions, Labs, Measurements) and survey responses (Social Determinant of Health (SDoH)), focusing on 7 crucial maternal health adverse outcomes. After characterizing data quality, missingness, and heterogeneity, we performed statistical correlation analysis to identify risk factors. We subsequently developed XGBoost and sequential LSTM models to predict the adverse outcomes, reaching state-of-the-art performance for multiple outcomes. We conducted model interpretability post-hoc analysis to understand success points and fairness analysis to evaluate implications for socio-economic disparities. Four practicing physicians reviewed the set of statistically significant and ML model identified features to assess their clinical validity and novelty. Most features identified through either statistical correlations or ML feature importance analysis aligned with known clinical risk factors. Several features were identified that the ML models used but that are not currently used in clinical practice and may merit further clinical investigation. Fairness analysis revealed certain associations with SDoH and age highlight areas that warrant continued monitoring. Overall, we demonstrate that meaningful populational level patterns can be extracted, and high-performing machine learning models can be trained on this longitudinal, diverse, multi-site dataset. Important risk features, particularly novel ones identified, if validated, could inform new strategies for maternal care or enable development and validation of outcome-specific, clinically deployable ML models.

Acute kidney injury (AKI) is a frequent complication within intensive care units, with its sudden onset often missed. This is especially important because a timely window for intervention is required as delayed detection leads to progressively worse outcomes. Existing machine learning and deep learning models have contributed to closing this gap, but their complexity, requiring hundreds to thousands of features, and lack of generalisation pose a limitation that prevents them from being integrated into clinical workflows across different electronic health-record ecosystems. This study presents a 37-feature XGBoost model trained on the MIMIC-IV dataset with 5.4% positive cases, with hyperparameters optimised via Optuna and probabilities calibrated using isotonic regression, designed for transportability across clinical settings. Validation was conducted internally using a temporal patient-level split simulating prospective deployment, training on 2008-2016 data and testing on 2017-2022 data"External validation was performed on the eICU Collaborative Research Database, a multi-centre dataset spanning 208 US hospitals, using the trained model without retraining. SHAP TreeExplainer was used to provide feature-level explainability for individual predictions. Internal testing yielded an AUROC score of 0.794 for predicting AKI onset within a 12-24 hour window. External validation produced a 0.750 AUROC without retraining. Equitable discrimination was observed across gender, age, chronic kidney disease presence, race, and AKI stages on both datasets, with a 95% internal CI of 0.789-0.799 confirming the model's estimate stability. These results suggest that clinically useful prediction systems are achievable with substantially fewer features than current models require.

Objective To measure the accuracy of clinical coding, clinician review, and a locally deployed large language model (LLM) in identifying alcohol, drug, and self-harm involvement in emergency department (ED) attendances, and quantify prevalence. Design Two-phase diagnostic accuracy study. In a validation week, the identification strategies were assessed against a conflict-adjudicated reference standard (n=2,256); the LLM was then applied to n=105,096 annual attendances at the same site. Setting UK Type 1 Emergency Department treating patients [&ge;]16yrs. Main outcome measures Prevalence quantification compared with the reference standard; sensitivity, specificity, and balanced accuracy of each strategy; monthly identification rates and adjusted annual prevalence. Results The reference standard identified 12.1% of attendances as involving alcohol, drugs, or self-harm (coding 6.0%; clinician 10.0%, LLM 15.6%). LLM balanced accuracy matched or outperformed clinician review in all three domains (alcohol 0.942 v 0.930, p=0.635; drug 0.959 v 0.791, p<0.001; self-harm 0.982 v 0.908, p=0.004). Coding recorded 1.07 domains per identified patient against 1.32 in the reference standard. Adjusted annual prevalence corresponded to 12,890 domain involvements per year not identifiable in coded data. Subdomain classification found at least 81.6% of self-harm attendances required medical assessment for injury or overdose before psychiatric review. Conclusions Clinical coding identified fewer than half of presentations involving alcohol, drugs, and self-harm and rarely captured co-occurring domains; under-recording was present across a full year. A locally deployed LLM generated more complete structured data from existing clinical text within NHS infrastructure, at a scale which is not feasible for manual review.

The openEHR standard provides an open, vendor-neutral architecture for clinical data repositories (CDRs), yet its real-world deployment has not been systematically documented. We conducted a dual-perspective survey combining a vendor survey of openEHR CDR providers with a community survey of openEHR practitioners. Eleven vendor organisations reported deployments across 22 countries and over 100 institutions and health regions. A complementary community survey (n=29, 17 countries) provided context on regulatory environments, adoption drivers, and barriers. Combined, the surveys cover 28 countries, 26 of them with a reported openEHR CDR deployment. Three findings emerge: openEHR has achieved national-scale presence through two distinct channels. Through vendor-market convergence, openEHR-based systems cover the majority of regional health authorities without a national mandate, including 19 of 21 Swedish regions, 3 of 4 Norwegian health regions, and 16 of 21 Finnish wellbeing services counties. Through national health record adoption, governments have built or procured national systems on openEHR as their technical foundation, including Ireland, Malta, Greece, Jamaica and Slovenia. Across Europe, this constitutes an openEHR-based interoperability infrastructure already in place across multiple EU member states. We identified no country in which openEHR is named in binding national regulation, creating structural fragility and an unrealised opportunity for alignment with the European Health Data Space (EHDS). Second, 61% of deployments serve primary use only, and 12% support both primary and secondary use. Third, lack of openEHR-specific knowledge is the most consistent adoption barrier across all geographies and deployment tiers. Adoption is driven by practitioner need and innovation, not by regulatory mandate.

Background: Consumer use of AI chatbots for health advice is rising, yet triage safety relative to established services remains unclear. Australia's Healthdirect, a government-backed symptom checker with 2.4 million uses in FY2024-25, remains unevaluated against frontier large language models (LLMs), and whether premium subscriptions improve triage safety remains unexplored. This study compared the triage accuracy and safety of Healthdirect against six LLM configurations across ChatGPT, Claude, and Gemini, assessed whether paid subscriptions improve triage safety, and characterised each system's error patterns. Methods: Forty-five clinical vignettes from the Semigran et al. benchmark spanning emergency, non-emergent, and self-care categories (15 each) were evaluated across seven systems. Healthdirect was tested following a seven-rule interaction protocol. LLMs were evaluated using first-person patient-language prompts under free-tier and paid-tier conditions. Outcomes were triage accuracy, emergency sensitivity, under-triage, and critical misses, analysed using Cochran's Q, Bonferroni-corrected McNemar tests, Cohen's kappa, and Wilson intervals. Findings: Triage accuracy differed significantly (Cochran's Q = 36.79, p < 0.001). Healthdirect achieved 48.9% accuracy (95% CI 35.0% to 63.0%; kappa = 0.233) versus 73.3% to 86.7% for LLMs (kappa = 0.600 to 0.800). Healthdirect operated under conservative interactive defaults while LLMs received complete information in a single prompt, which may have disadvantaged Healthdirect. Emergency sensitivity was 46.7% versus 80.0% to 86.7% for LLMs. Healthdirect produced two critical misses; no LLM produced any across 270 evaluations (95% CI 0% to 1.4%). When LLMs undertriaged, they recommended GP care rather than self-care. No tier differences were significant (all p > 0.05), and most systems over-triaged self-care cases. Interpretation: Frontier LLMs demonstrated higher triage accuracy and safer error profiles than Healthdirect. All LLMs avoided critical misses; Healthdirect did not. Premium subscriptions did not significantly improve triage safety. These findings support clinical governance decisions about whether LLMs warrant formal evaluation alongside government-backed symptom checkers.

Background Computerised cognitive testing may address the global challenge in identifying cognitive changes in people living with HIV scalably and affordably. We assessed a computerised battery (CB) of cognitive tests, in a prospective cohort (CONNECT) of people with HIV in a low-income peri-urban area of Cape Town, South Africa during a national programmatic switch from efavirenz- to dolutegravir-based antiretroviral therapy (ART). Methods We recruited 170 people with HIV and 91 people without HIV (controls) (140[82%] and 41[45%] followed up). The CB and gold-standard pen&paper cognitive testing (P&P) were performed at both timepoints. Technology familiarity/use questionnaire data were also collected. We compared performance in detecting lower group-level cognitive performance associated with efavirenz treatment. Furthermore, the CB was compared to P&P in classifying individuals with low cognitive performance, correlation of global test scores and domain-level scores between batteries, and practice effects between timepoints. Exploratory principal component analysis was also performed. Results People with HIV on efavirenz at baseline had lower performance on the computerised battery than controls, {Delta}T=2.6, p=0.0047. This difference was lost after switching to dolutegravir-based ART at follow-up. CB and P&P global T were moderately correlated (R2=0.203, p<0.001), and the CB performed moderately in classification of low cognitive performance against the gold standard (AUC 0.70, sensitivity 0.52, specificity 0.76, PPV 0.40, and NPV 0.84). Selecting the first three principal components improved both classification of low cognitive performance (AUC 0.77) and correlation strength with P&P global T (R2=0.3, p<0.001). The CB did not show practice effects. Most participants owned a mobile phone (95%, 85.9% of these smartphones). Performance was better in smartphone owners ({Delta}T=1.8) and computer owners (23%, {Delta}T=1.8). Conclusions Delivering computerised cognitive testing was feasible in this low-income southern African setting. The CB showed reasonable construct validity (detecting known lower cognitive performance associated with efavirenz-ART) and may detect broad cognitive characteristics such as processing speed and accuracy. However, correlation of CB results with gold standard P&P testing was low-moderate and may limit its applicability as a diagnostic tool. This might be improved by including a wider range of cognitive domains tested in the CB, or data driven analysis. Brief CBs may fulfil an initial screening role, followed by more detailed clinical assessment.

Background. Routine service databases are attractive sources of training labels for clinical prediction models, but the processes that write those labels are rarely audited before the labels are used. In a deployed community cognitive-screening programme, we audited the routine cognitive-status label, built a matrix of twenty-four model arms over the same patients under a specialist reference standard, and measured what each supervision choice bought or cost. Methods. The study cohort is the 672 individuals whose cognitive status was recorded by a titled (attending-or-above) physician, that record being the reference standard; after holding out one institution entirely, a development panel of 642 individuals at 38 institutions. The routine cognitive-status label these individuals also carry was first audited at the operator level: for each data-entry account we counted diagnoses entered and the proportion recording any impairment, and tested a competing bulk-timestamp explanation. Twenty-four arms span the supervision choices such a programme faces: an incumbent 21-variable logistic regression; local language models (Qwen2.5-1.5B/3B, Qwen3-4B/8B) zero-shot, with chain-of-thought, fine-tuned on physician labels, on routine labels with and without decontamination, or on a proxy scale-band task; preference-optimised (DPO) and reinforcement-trained (GRPO) variants; a proprietary frontier model queried zero-shot; and knowledge distillation of that frontier model into the regression and into the local 4B, using 943 teacher-labelled records from the programme's unlabelled pool. All arms are scored out-of-fold under one five-fold split grouped on registry-resolved institution clusters (no cluster spans a fold); paired contrasts use a 2,000-draw cluster bootstrap. Results. 181 operator accounts (each entering at least 100 diagnoses with zero recorded impairments) account for 45,315 rows - 40.5% of the outcome column; recorded impairment falls monotonically with account volume (15.7% for 1-9 rows to 0.7% for 500-999); a bulk-timestamp explanation was tested and refuted, identifying the write-time column as a migration artefact. Under the specialist standard, no locally fine-tuned arm beat the incumbent regression (AUROC 0.926): physician-label SFT reached 0.924 (4B), DPO 0.881, and GRPO 0.789; the pre-registered two-stage proxy-then-RL recipe was worse than its single-stage contaminated baseline (-0.030, 95% CI -0.077 to -0.004). Chain-of-thought reduced discrimination at every size (-0.072, -0.080, -0.041 at 1.5B/3B/4B; -0.012, n.s., at 8B). The frontier model scored 0.932 (vs. regression +0.007, n.s.). The distilled 4B reached 0.940 - above the incumbent (+0.014, 0.004 to 0.031) and above its own teacher (+0.008, 0.001 to 0.017) - with near-teacher calibration; it reached the teacher's level by 50 teacher labels and changed little beyond 200. Conclusions. The audit and the arm matrix support one deployment recipe: audit the routine label at the operator level before training on it; do not expect fine-tuning, preference optimisation, or reinforcement learning on a few hundred specialist cases to beat a well-calibrated regression; and if a frontier model is available but undeployable, spend a bounded number of queries on it as a labelling instrument and distil. A companion paper uses these frozen predictions to quantify how evaluation design choices compare with model choice.

Routine childhood growth surveillance is a cornerstone of pediatric care. Growth pattern abnormalities are often early manifestations of chronic disease. Yet subtle abnormalities are frequently underrecognized, leading to diagnostic delays and avoidable morbidity. We introduce SPROUT (System for Pediatric Recognition Of Undiagnosed Trajectories), a generalized, multi-agent large language model (LLM) reasoning system designed to identify a broad spectrum of pediatric growth-related conditions from longitudinal electronic health records (EHRs) earlier than standard clinical practice. Using a large pediatric primary care EHR dataset, we developed and validated SPROUT as a two-stage system. First, a highly specific LLM screener flags concerning longitudinal growth patterns. Second, an Orchestrator module coordinates a multidisciplinary panel of LLM agents to generate a ranked differential diagnosis. To correct systemic reasoning errors, a Trainer module injects meta-knowledge into the panel via a dedicated "Learner" agent. Diagnostic capability was evaluated using a walk-forward, visit-by-visit simulation leading up to the diagnosis date. The SPROUT screener model achieved 98% (83/85) specificity and 28% (9/32) sensitivity on a gold-standard dataset of pediatric primary care patients when evaluated one year before the index date, and 100% specificity and 47% sensitivity when evaluated using longitudinal data up to the day of diagnosis. When applied to 300 control patients (i.e., healthy or undiagnosed), the screener flagged 15. Subsequent expert panel review confirmed high suspicion for undiagnosed pathology in 33% (5/15) of these cases. In chronological walk-forward validation on disease cases, the diagnostic engine identified conditions well before standard-of-care documentation. One year prior to clinical diagnosis, the system achieved sensitivities of 81% for type 1 diabetes mellitus, 56% for pituitary disorders, and 44% for celiac disease. The SPROUT multi-agent system demonstrates the ability to detect a significant portion of latent growth-related pediatric conditions months to years before current clinical standards while minimizing false positives. These results support its potential as a decision support tool for reducing diagnostic delays in pediatric care.

Background: HIV/HBV coinfection is associated with substantial liver-related morbidity and mortality, yet the impact of social vulnerability (SV) on clinical outcomes has not been systematically assessed. We evaluated associations of multidimensional SV with mortality, hepatic, virologic, and extrahepatic organ outcomes among adults with HIV/HBV. Methods: We conducted a retrospective cohort study using TriNetX data from 110 U.S. healthcare organizations (2010-2026). We propensity score matched adults with HIV/HBV with and without documented SV 1:1 (2,024 per group). SV was defined using a four-domain framework encompassing material, healthcare access and engagement, interpersonal, and psychosocial vulnerability. Results: Over 15,900 person-years, SV was associated with higher mortality (hazard ratio [HR], 2.06; 95% confidence interval [CI], 1.72-2.47), liver composite events (HR, 1.37; 95% CI, 1.07-1.76), hepatic decompensation (HR, 1.94; 95% CI, 1.39-2.70), hepatic failure (HR, 2.39; 95% CI, 1.53-3.73), HBV viremia (HR, 1.69; 95% CI, 1.32-2.16), and HIV viremia (HR, 2.05; 95% CI, 1.71-2.46). SV was also associated with major adverse cardiovascular events (HR, 1.47), chronic kidney disease (HR, 1.49), and diabetes (HR, 1.25). Multidomain SV generally showed stronger associations than single-domain SV for most hepatic and virologic outcomes, with HR ranges of 1.76-2.62 versus 1.35-1.76 for single-domain SV. Healthcare access and engagement vulnerability was most consistently associated with mortality and hepatic outcomes. Conclusions: SV was associated with mortality, hepatic disease, impaired HIV/HBV control, extrahepatic organ morbidity, and acute care utilization in adults with HIV/HBV. SV assessment may improve risk stratification and identify actionable intervention targets during HIV/HBV care.

BACKGROUND Generative AI (genAI) chart summarization tools embedded in electronic health records (EHRs) are being rapidly deployed across U.S. health systems. Although these tools represent a promising solution to alleviate cognitive burdens, their effects have not been examined in randomized-clinical trials (RCTs). METHODS In this pragmatic RCT at a single academic health system, 284 outpatient clinicians across forty-two specialties were assigned 1:1 to Epic's outpatient chart summarization tool or a usual-care control arm over 90 days, from February 23 to May 23, 2026. The primary outcome was physician task load (PTL) adapted for pre-charting. Prespecified exploratory outcomes included additional validated psychometrics as well as usability, safety, and time-based measures. Descriptive statistics included interaction and usage of the tool. RESULTS Of 74,474 AI chart summaries generated, 14.2% were interacted with by a clinician; the proportion of generated summaries interacted with declined from 21.5% in month 1 to 10.5% in month 3, and the proportion of clinicians using the tool at least once per month declined from 88.7% to 66.2%. The adjusted between-arm difference in PTL at follow-up favored the intervention arm (scale 0-400; -27.4; 95% CI, -49.4 to -5.3; P=0.02). Among the Professional Fulfillment Index (PFI; scale 0-4, lower=better) psychometrics, overall burnout (-0.20; 95% CI, -0.38 to -0.01) and work exhaustion (-0.24; 95% CI, -0.47 to -0.02) were lower in the intervention arm, with little difference in overall professional fulfillment (+0.04; 95% CI, -0.16 to 0.25). Charting time per encounter showed no significant between-arm difference during steady state (-1.2 seconds; 95% CI, -19.0 to 16.6). The net promoter score was -22, indicating that on average, clinicians did not recommend the tool. Among free-text respondents, 57.1% reported at least one concern, most commonly tool limitations or inaccurate information. No adverse patient safety events or near-misses were reported. CONCLUSION An EHR-integrated AI chart summarization tool modestly reduced physician task load and was associated with lower burnout, without time savings and against declining engagement. Sustained usage and oversight of reported inaccuracies remain open challenges.

Background: Current understanding of acute kidney injury (AKI) risk factors remains largely descriptive, offering limited precision into how specific biomarker values or physiologic thresholds influence susceptibility. We aimed to synthesize knowledge from machine learning models trained across multiple health systems to identify generalizable, value-specific risk drivers and biomarker interactions contributing to AKI risk. Methods: We analyzed electronic health records (EHRs) from 785,497 adult inpatients between 2010 and 2019 across nine U.S. academic medical centers within PCORnet. Interpretable gradient boosting machine models were independently developed at each health system to quantify predictor-outcome associations. Meta-regression was applied to integrate these site-level results, characterize nonlinear value-risk relationships, and identify bivariate interactions between predictors. Results: Meta-analysis revealed consistent, value-specific risk drivers across health systems. An increase in glucose from 100 mg/dL to 140 mg/dL was associated with a 1.46-fold higher risk of AKI. Chloride and anion gap also demonstrated elevated AKI risk with risk increases overlapping portions of their reference ranges, with anion gap showing a 1.14-fold increase across 4-12 mmol/L and chloride a 1.28-fold increase across 96-100 mEq/L. Electrolytes including potassium, calcium, and sodium showed quadratic associations with AKI risk. Bivariate meta-regression identified interactions between key predictors, highlighting pathways that jointly modulate AKI risk. Conclusion: This cross-system meta-analysis synthesizes machine learning-derived evidence into clinically interpretable knowledge, revealing how specific biomarker ranges and interactions modulate AKI risk. By moving beyond surface-level associations to quantitative, generalizable physiologic thresholds, these findings provide actionable insights to enhance risk stratification and personalized prevention in hospital care.

Artificial intelligence applied to routine electrocardiograms (ECGs) has largely focused on detecting existing disease or predicting individual cardiovascular outcomes. Whether ECGs can support prediction of multiple future diseases across organ systems remains unclear. We developed ECG-RISK, a multitask survival model for 67 incident three-character ICD-10 endpoints using ECG waveforms, demographic characteristics and routinely collected laboratory data from 86,673 MIMIC-IV patients. Discrimination was highest for heart, brain, kidney and lung endpoints, with organ-level C-indices ranging from 0.796 to 0.825, whereas liver and pancreatic endpoints showed lower discrimination. The ECG-only model achieved strong discrimination across most endpoints, whereas the incremental improvement gained by incorporating ECG and laboratory inputs beyond demographic information varied substantially across endpoints. Across the nine exploratory aggregated outcomes, Kaplan Meier curves showed clear separation among model-score tertiles. Discrimination was highest for dementia (C-index, 0.891) and heart failure (C-index, 0.857). These findings support the feasibility of ECG-based longitudinal risk prediction across multiple diseases. External validation and competing-risk analyses are required to assess generalisability and clinical utility.

Large language models perform well on medical examinations, but users routinely challenge their answers and invoke professional roles, and it is unclear what a system does when a medical credential and a stated task-specific accuracy point in opposite directions. In a factorial experiment on 480 items from four Polish specialty examination sets and three consumer large language model systems (ChatGPT, Claude, Gemini), each item and system received eleven independent conversations. Conditions crossed attributed source role (medical student, experienced specialist), stated prior accuracy on similar questions (2/10, 8/10) and suggestion correctness. The primary outcome was adoption of a prespecified incorrect option when the baseline answer matched the official key, comparing a specialist described as 2/10 with a student described as 8/10. Baseline agreement with the key was 87.2% across 15,683 analyzable conversations. The incorrect option was adopted more often from the specialist described as 2/10 than from the student described as 8/10 (10.2% vs. 7.6%; adjusted risk difference +2.82 percentage points, 95% CI +0.65 to +4.99). Estimates varied across the three systems and only one system-specific interval excluded zero. In a prespecified exploratory analysis with a shared eligibility rule, correct suggestions were adopted far more often than incorrect ones (risk difference +35.7 percentage points, 95% CI +30.8 to +40.7), indicating selective rather than indiscriminate compliance. An incorrect suggestion from a specialist with low stated accuracy was therefore slightly more influential than the same suggestion from a student with high stated accuracy, although the difference was modest and varied across systems. Agreement reached only after a user has disclosed a preferred answer should not automatically be treated as an independent second opinion, and medical large language model systems should be evaluated on how they revise answers after such disclosure, not solely on initial accuracy.

Study Objective Little is known about where in hospital care for multiple long-term conditions (MLTC) is delivered. We aimed to describe pathways of care (ward transfers) and outcomes for people admitted to hospital for unscheduled care by MLTC status and other key sociodemographic characteristics. Design and setting Analysis of routinely-collected electronic health records from a large acute UK hospital. Participants Adult unscheduled care admissions from 1st July 2018 to 30th June 2019. The presence of two or more of 59 long-term conditions was ascertained using ICD-10 codes from previous hospital discharges. Main outcome measures Markov state transition probabilities were derived for ward moves and compared for MLTC vs no MLTC, age, sex, ethnicity and neighbourhood deprivation. Outcomes (length of stay, death, readmission, move from definitive ward) and time spent in emergency and assessment departments were compared between subgroups. Results A total of 33,252 adults, mean age 56.0 (SD 21.9) years were analysed; 14,834 (42.4%) had MLTC. People with MLTC were more likely to die in hospital (4.2 vs 1.9%, p<0.001), transfer to internal medicine wards or older peoples medicine wards, were less likely to transfer to surgical wards, had longer median length of stay (1.83 vs 0.69 days, p<0.001), stayed longer in acute medical units (15.5 vs 9.6 hours, p<0.001), and were more likely to move from their definitive ward (18.2 vs 16.4%, p=0.002). Conclusion Unscheduled hospital care pathways are complex and differ for people with MLTC, who have worse outcomes and may be less likely to receive optimal care.

Automatic coding from clinical notes has been studied extensively for International Classification of Diseases (ICD) codes, yet broad Current Procedural Terminology (CPT) and Healthcare Common Procedure Coding System (HCPCS) recommendation remains comparatively underexplored. Existing studies often focus on one specialty, a limited code vocabulary, or a single model family, leaving it unclear how different artificial intelligence (AI) paradigms perform under a common, clinically meaningful evaluation. We formulate CPT and HCPCS coding as an AI-assisted recommendation task in which a physician or professional coder reviews a short, ranked list of candidate codes supported by the clinical note. Using operative notes from Vanderbilt University Medical Center (VUMC) and discharge summaries from Medical Information Mart for Intensive Care IV (MIMIC-IV), we compare lexical retrieval, Clinical-Longformer, GPT-5.6-Sol, MedGemma-27B, and an inspectable agentic-style retrieve-and-verify system under a controlled review budget. Micro-averaged recall within a fixed number of recommendations measures whether reference codes reach the reviewable list; micro-F1 is reported only where reference labels are sufficiently complete. Zero-shot GPT-5.6-Sol achieves the highest recall within five and ten candidates: 0.717 and 0.800 on VUMC and lower-bound values of 0.689 and 0.738 on MIMIC-IV. The retrieve-and-verify system reaches 0.695 and 0.784 on VUMC and lower-bound values of 0.575 and 0.657 on MIMIC-IV, with a candidate-linked evidence window attached to each retained recommendation. Diagnostic analyses reveal distinct failure sources, including output-length underfilling, confusion among closely related codes, out-of-knowledge-base generation, and incomplete evidence support. These findings establish a systematic evaluation framework for procedure-code recommendation and identify practical requirements for future systems that are accurate, review-efficient, and grounded in clinical evidence.

Background. A primary constraint on the capacity of EMS programs to meet industry demand is psychomotor instruction and verification, requiring direct observation of each student by a qualified evaluator. Whether AI video analysis can relieve it is untested; none has been applied to EMS skill examination or compared with human examiners. Objective. To quantify human EMS evaluator inter-rater reliability and evaluate an AI video-analysis platform against it. Methods. In a prospective, fully crossed study, five certified EMS evaluators and an AI platform independently scored identical video-recorded EMT performances of cervical collar application (n=15), bag-valve-mask (BVM) ventilation (n=14), and medical assessment (n=15) on dichotomous checklists with critical-failure criteria. Agreement was assessed at item, score, and decision levels using Fleiss' kappa, Krippendorff's alpha, Gwet's AC1, and ICC(2,1)/ICC(2,k). Results. Human item agreement was moderate (kappa 0.409 to 0.467), as was single-rater reliability (ICC(2,1) 0.539 to 0.694), against good panel reliability (ICC(2,k) 0.854 to 0.919). Recorded pass/fail agreement was fair (kappa 0.297 to 0.388) and critical-failure agreement near zero for two skills (kappa 0.028, 0.119). AI alignment tracked rubric observability rather than task complexity: r = 0.857 (collar, exceeding every human), -0.173 (BVM), 0.664 (medical), and it was most lenient on two skills. Conclusions. Human evaluators are an imperfect standard, especially on critical failures. The AI was a legitimate additional rater where checklist items were discrete and visually verifiable, but not where credit required judging continuous quantities such as ventilation rate, volume, or suction duration. Defensible uses are formative and archival, not summative. These results reflect an early, non-specialist configuration: a baseline, not a limit.

Improvements in data availability, sharing, and integration, together with the development of explainable artificial intelligence (XAI) techniques, are advancing precision medicine for pediatric cancer by facilitating diagnosis, biomarker discovery, and drug development. Data sharing commons and initiatives like the Childhood Cancer Data Initiative (CCDI) provide access to pediatric-specific genomic and clinical data cohorts and improve data availability for pediatric cancer research. Based on CCDI, a scalable AI platform, Graph Artificial Intelligence for Pediatric Oncology (GAIPO), integrates various data modalities from bulk and single-cell omics data to clinical information. Such multi-modal data facilitates the training and development of advanced XAI models for pediatric cancers. We then developed an end-to-end multi-modality framework, PCGS, for pediatric cancer by incorporating omics-specific representation learning via GNN models with cross-attention fusion and multi-objective learning for downstream tasks such as classification, clustering, and survival analysis. This framework outperforms previous supervised multi-omics integration baseline approaches based on glioma and Wilms tumor cohorts and enables GNN model explainability via Shapley value-based feature attribution approaches to explain the contributions of gene-level features across various biomedical tasks, including classification and survival. Given specific background samples (e.g., age groups, sex, grades) as baselines, this explainable GNN model estimates and ranks the importance scores for input features from each omics modality. It identifies background-specific key features for biomarker discovery, risk group identification, and survival analysis in glioma and Wilms tumor, with potential applicability to other pediatric cancers.

Background: Traditional real-world studies comparing SGLT2 and DPP4 inhibitors on renal outcomes rely on propensity score matching, which causes high-dimensional data loss. We used causal machine learning (Causal ML) to unmask heterogeneous treatment effects in diabetic kidney disease (DKD). Methods: Using data from 4,588 patients within the Japanese J-CKD-DB-Ex registry, we implemented a doubly robust (DR) learning framework (Linear DR-learner with XGBoost) to compare SGLT2 and DPP4 inhibitors. Outcomes included the chronic eGFR slope and a composite renal endpoint ([&ge;] 50% eGFR decline or end-stage kidney disease). Heterogeneity was explored via causal SHAP and decision trees. Results: At the population level, SGLT2 inhibitors modestly slowed chronic eGFR decline (average treatment effect [ATE] = 0.14 [95% CI: -0.86, 1.15] mL/min/1.73m^2/year) and reduced composite endpoint risk by 9% (ATE: -0.09 [-0.11, -0.08]) versus DPP4 inhibitors. However, individual-level counterfactual analysis suggested that for the chronic eGFR slope, non-glinide users with stable pre-treatment trajectories who were also taking ACE inhibitors had a greater benefit from SGLT2 inhibitors (ATE: 2.95 [-0.68, 6.58]). Conversely, glinide users with steep pre-treatment decline had a greater benefit from DPP4 inhibitors (ATE: -8.98 [-16.11, -1.85]). For composite renal events, SGLT2 inhibitors had a 28% absolute risk reduction within the algorithmically identified high-risk subgroup (eGFR [&le;] 28.1 mL/min/1.73 m^2 and positive proteinuria; ATE: -0.28 [-0.33, -0.23]). Even non-proteinuric decliners demonstrated a 8% risk reduction with SGLT2 inhibitors (ATE: -0.08 [-0.10, -0.06]). Conclusion: Causal ML advances precision medicine in DKD, shifting from uniform prescribing to individualized, data-driven therapy targeting distinct intrarenal pathways.

Introduction Postoperative analgesic management after minimally invasive cardiac surgery (MICS) should facilitate early recovery while providing adequate pain control. However, direct evidence comparing postoperative remifentanil- and fentanyl-based analgesic strategies after MICS remains limited. We compared these strategies and explored their associations with postoperative recovery, postoperative nausea and vomiting (PONV), and pain management. Methods This retrospective single-center observational cohort study included patients who underwent MICS via a right mini-thoracotomy between January 2023 and June 2026. Patients were categorized according to postoperative remifentanil- or fentanyl-based analgesia in the intensive care unit. Outcomes included time to extubation, PONV, postoperative pain assessed using the numerical rating scale (NRS), additional analgesic use, and intensive care unit length of stay. Multivariable logistic regression examined the association between postoperative opioid strategy and PONV, adjusting for age, sex, and smoking history. Results PONV occurred less frequently in the remifentanil group than in the fentanyl group (20.6% vs 45.0%, P = 0.004), and this association remained significant after adjustment (adjusted odds ratio, 0.23; 95% confidence interval, 0.10-0.56; P = 0.001). Time to extubation was shorter with remifentanil (median, 179 [interquartile range, 134-240.5] vs 247 [190.2-276.5] min; P < 0.001). In contrast, NRS pain scores on postoperative day 0 were higher with remifentanil (3 [1-6] vs 1 [0-2]; P < 0.001), and additional analgesics were used more frequently (80.6% vs 33.3%; P < 0.001). Pain scores on postoperative day 1 did not differ significantly between groups. Conclusion Postoperative remifentanil-based analgesia after MICS was associated with less PONV and earlier extubation but also with greater early postoperative pain and more frequent additional analgesic use than fentanyl-based analgesia. Appropriate transition to longer-acting analgesics with multimodal analgesia may help preserve the potential benefits of remifentanil while maintaining adequate postoperative pain control.

Background: Immunochemotherapy (ICT) is considered standard in regards to care for small-cell lung cancer (SCLC) in extensive stages, yet reliable biomarkers for treatment response remain elusive. While previous univariate analyses suggest specific peripheral lymphocyte subsets correlate with survival, the systemic immune response involves complex, multivariate interactions that require advanced analytical approaches. Methods: This paper analysed high-dimensional flow cytometry data from 32 patients with stage IV SCLC treated with carboplatin, etoposide, and atezolizumab. Peripheral blood was analysed at baseline (V0) and longitudinally during treatment. To identify potential early predictive biomarkers and mitigate sample attrition in later cycles, we focused on baseline and measurements after two cycles of ICT (V1). We employed a rigorous machine learning framework utilising nested cross-validation, bootstrapping, and permutation-based statistical testing to evaluate eleven different regression and survival models. Results: Under model-appropriate metrics, regressors did not generalise (R2 <0); conversely, censoring-aware Random Survival Forests (RSF) successfully extracted robust prognostic signatures. Baseline immune profiles (V0) achieved a concordance index (C-index) of 0.66 (p= 0.015), while dynamic changes from V0 to V1 ({triangleup}V) achieved a C-index of 0.65 (p= 0.022). Crucially, absolute values measured after two cycles of ICT (V1) yielded no significant signal (p= 0.445). Feature importance analysis confirmed the prognostic value of Th17 normalisation and identified Naive Regulatory T cells and Memory B cells as candidate components. Conclusion: Machine learning validation confirms a predictive signal in the peripheral immune profile of SCLC patients. Early dynamic shifts in the balance between regulatory and effector immune arms are associated with prognosis, contrasting with the lack of signal in absolute counts after two cycles of ICT. These findings establish a proof of concept for multivariate liquid biopsy immune profiling, warranting confirmation in larger cohorts and highlighting the necessity of integrating systemic and tumour-intrinsic data.