Search

Hospital-acquired pressure injuries (HAPIs) are a common and largely preventable complication in ICU patients, affecting 5–15% of cases and contributing to increased morbidity and healthcare costs. Despite standardized nursing protocols, incidence remains high, highlighting the need for more effective predictive and preventive approaches. While traditional tools like the Braden Scale offer interpretability, they lack sufficient predictive accuracy in critically ill populations. In contrast, machine learning models such as XGBoost and random forests improve prediction but function as black boxes, limiting clinical trust and actionable insight. To address this gap, this work proposes an Explainable Boosting Machine (EBM) framework trained on electronic health record (EHR) data from over 50,000 ICU admissions (2017–2023). EBMs combine strong predictive performance with interpretability by modeling feature effects through shape functions and capturing pairwise interactions. This allows identification of both global and patient-specific risk factors while maintaining transparency. The framework emphasizes modifiable factors such as repositioning frequency, nutrition, and medical device management, revealing nonlinear thresholds and interaction effects often missed by conventional methods. Overall, the proposed approach integrates accurate prediction with clear, clinically interpretable insights, enabling real-time identification of actionable risk factors for HAPI prevention. By bridging predictive modeling and nursing decision-making, it supports more targeted interventions and improved patient outcomes in critical care settings.

Adverse drug reactions (ADRs) are a major global health issue, contributing to significant morbidity, mortality, and healthcare costs. Many ADRs are detected only after widespread drug use, reflecting limitations of pre-market trials in capturing real-world patient variability. Although electronic health records (EHRs) collected between 2017 and 2023 provide rich data for post-market surveillance, they remain underused for systematic ADR detection. Current pharmacovigilance methods rely heavily on spontaneous reporting systems, which suffer from underreporting and bias, while supervised machine learning approaches require labeled ADR data that are often unavailable for rare or novel events. This paper proposes a variational autoencoder (VAE)-based unsupervised framework to detect ADR signals from multimodal EHR data, including clinical notes and laboratory results. The model learns normal patient data distributions and identifies deviations as potential safety signals without requiring labeled ADR examples. A multimodal architecture combines natural language processing of clinical notes with structured laboratory encoders, forming a shared latent space for anomaly detection based on reconstruction error. The framework enables detection of unknown ADRs by flagging abnormal patterns in patient records across large datasets from 2017 to 2023. Its unsupervised nature makes it suitable for identifying rare or previously unrecognized drug safety issues. Overall, this approach offers a scalable, proactive pharmacovigilance strategy that shifts drug safety monitoring from reactive reporting to predictive detection using routine EHR data.

Hypertension affects about 1.4 billion adults globally and is a major modifiable risk factor for cardiovascular disease. Although several first-line antihypertensive drug classes exist, randomized controlled trials typically report only average treatment effects (ATEs), which mask important variability in individual patient responses. As a result, clinical guidelines often assume a homogeneous patient population, leading to trial-and-error prescribing, delayed blood pressure control, and avoidable adverse effects. I argue that causal forest models combined with double machine learning (DML) enable reliable estimation of heterogeneous treatment effects (HTEs) from observational electronic health record data. These methods can approximate randomized trial validity while capturing clinically meaningful variation in treatment response across patients. Compared with traditional approaches, they are computationally feasible and better suited for individualized treatment assessment. Therefore, comparative effectiveness research in hypertension should move beyond ATE-focused analyses toward routine HTE estimation using causal machine learning. This shift would support more precise, data-driven prescribing and improve patient outcomes.

Telemedicine expanded rapidly in the United States during the COVID-19 public health emergency as Medicare and state Medicaid programs relaxed coverage restrictions. Diabetes affects about 37 million Americans, and key outcomes such as HbA1c, blood pressure, and LDL cholesterol are routinely tracked in electronic health records. However, the causal impact of telemedicine expansion on these outcomes remains uncertain, as simple pre–post comparisons are confounded by concurrent trends such as the pandemic and seasonal variation. Randomized policy experiments are impractical, leaving a gap in high-quality causal evidence. We argue that Bayesian structural time series (BSTS) applied to state-level EHR aggregates provides a strong alternative. BSTS constructs a synthetic counterfactual from similar states, modeling trend and seasonality to estimate what outcomes would have been without telemedicine expansion. This allows clearer separation of policy effects from underlying time dynamics and produces interpretable estimates with uncertainty bounds. Unlike difference-in-differences, BSTS does not rely on parallel trends assumptions that may be violated in this context. It offers a transparent framework for causal inference using routinely available aggregated data. Policymakers should prioritize such causal methods when evaluating whether telemedicine expansions should become permanent rather than relying on descriptive before–after analyses.

Telemedicine expanded rapidly during COVID-19 as Medicare and states relaxed long-standing restrictions. Diabetes outcomes (HbA1c, blood pressure, LDL cholesterol) are routinely tracked in EHRs, yet causal evidence that telemedicine improves these outcomes remains limited. Pre-post analyses cannot separate telemedicine effects from confounding time trends such as seasonality and pandemic-related changes, while randomized state-level policy trials are infeasible. This leaves a key evidence gap for policy decisions. Bayesian structural time series (BSTS) using state-level EHR aggregates is the most suitable approach for causal inference, constructing counterfactual outcomes from similar donor states. BSTS accounts for trends, seasonality, and autocorrelation, and uses synthetic control principles to reduce confounding. It also provides uncertainty estimates and works with routinely collected aggregate data. Policymakers should require BSTS-based evidence before making telemedicine coverage permanent. Researchers should apply these methods to existing policy variation and share data and code. States should build routine EHR-based monitoring systems for diabetes outcomes. Causal evaluation of telemedicine is feasible now using existing data and methods. Relying on pre-post studies or waiting for randomized trials delays actionable evidence needed for policy decisions.

Clinicians often need rapid, evidence-based answers that integrate patient-specific electronic health records (EHRs) with clinical guidelines, but existing decision support tools are limited in real-time personalization. While large language models (LLMs) offer strong medical reasoning, they are prone to hallucinations and lack direct access to local EHR data, making them unsafe for standalone clinical use; meanwhile, traditional retrieval systems cannot synthesize coherent, context-aware responses. This paper proposes a retrieval-augmented generation (RAG) framework that combines dual-source retrieval from both institutional EHRs and clinical guideline databases. The system includes an EHR indexer, a guideline repository, a semantic retriever, an LLM-based generator, and a safety filter for hallucination mitigation. By grounding outputs in retrieved patient data and evidence-based recommendations, the model improves factual reliability, explainability, and clinical trustworthiness. Overall, the framework enables safe, real-time clinical question answering by integrating LLM reasoning with verified medical sources, with future validation planned on public EHR and guideline datasets.

Rare diseases collectively affect over 300 million people globally, yet individual conditions are often missed due to low clinician familiarity and non-specific presenting symptoms that mimic common disorders. Supervised machine learning requires large numbers of labeled examples for training, but rare diseases have too few diagnosed cases to develop condition-specific predictive models using traditional approaches. We propose a multimodal foundation model pretrained on 10 million de-identified electronic health records (EHRs) combining clinical notes and laboratory values for zero-shot rare disease diagnosis without requiring labeled training examples. The framework comprises four components: a clinical note encoder based on a large language model, a laboratory value encoder using a time-series transformer, a multimodal fusion module with cross-attention, and a zero-shot classifier that compares patient embeddings to disease descriptions. Pretraining on large-scale EHR data enables the model to learn general medical knowledge and disease patterns, allowing diagnosis of rare conditions by recognizing manifestations even when no labeled examples of that specific disease were used for training.

Long COVID (post-acute sequelae of SARS-CoV-2 infection, PASC) affects roughly 10–30% of COVID-19 survivors and is marked by persistent symptoms such as fatigue, cognitive dysfunction (“brain fog”), shortness of breath, loss of smell, and post-exertional malaise that can last for months or years, while its underlying biological mechanisms and validated diagnostic biomarkers remain unclear. The condition is highly heterogeneous, with patients showing different recovery patterns and no clearly defined clinical subtypes, and the scarcity of labeled datasets further limits the use of supervised machine learning methods for phenotyping. To address this, we propose a self-supervised contrastive multi-view learning framework that integrates three temporal data modalities—pre-infection electronic health records, acute-phase clinical and biomarker data (e.g., CRP, ferritin, D-dimer, lymphocyte counts), and post-acute symptom trajectories—using separate encoders and a shared latent space aligned through contrastive learning without requiring phenotype labels, followed by unsupervised clustering to identify potential subtypes. By exploiting the natural temporal linkage within each patient and contrasts across patients, this approach enables data-driven discovery of long COVID phenotypes, supports early prediction of subgroup membership, and may ultimately inform personalized treatment strategies, clinical trial design, and improved understanding of disease mechanisms.

Hypertension affects over 1.4 billion adults worldwide, and antihypertensive dose titration is a common but complex clinical decision. Although electronic health records contain longitudinal data on medication adjustments and blood pressure outcomes, determining optimal individualized dosing remains challenging due to confounding in observational data, where patients receiving higher doses often have worse baseline health. We propose a transformer-based model with causal attention masking to estimate counterfactual blood pressure outcomes under alternative dose regimens. The architecture ensures temporal validity by preventing information leakage from future events and encodes medication dose changes in a continuous representation. It includes a dose encoder, outcome predictor, and counterfactual contrastive loss to distinguish between competing treatment paths. This framework learns patient-specific dose–response relationships and enables personalized predictions for antihypertensive adjustments. While it supports individualized treatment planning from observational EHR data, prospective validation is still required before clinical deployment.

Hospital discharge delays are costly, disrupt inpatient capacity, and expose patients to avoidable iatrogenic harm. Early identification of patients likely to be ready for discharge could improve patient flow and reduce operational bottlenecks. Current discharge decisions often rely on subjective judgment, fragmented documentation, and sequential review by multiple clinical teams. No single tool routinely integrates the morning snapshot of clinical readiness. This article proposes a predictive model that estimates the probability of same-day discharge readiness by 9 am. The model uses morning laboratory results, active medication orders, vital sign stability, mobility documentation, and pending consultation status. The proposed approach is a supervised classification model using gradient-boosted trees trained on historical inpatient encounters. Features would be assembled from electronic health record data available before morning rounds. Conceptually, the model would generate a calibrated discharge readiness list for clinical review. This list could help care teams focus on borderline patients and support bed-management forecasting. The model could accelerate discharge throughput while maintaining safety by surfacing hidden readiness signals. It is intended to complement, not replace, clinical judgment.

Clinical notes, problem lists, medication orders, and billing codes are core components of the electronic health record. When these components conflict, the record may become less reliable for care delivery, quality measurement, and reimbursement. Current inconsistency detection is largely manual, episodic, and dependent on documentation audits. This approach is difficult to scale across encounters, specialties, and longitudinal records. This article proposes a deep learning NLP model for detecting contradictions among clinical notes, problem lists, medication orders, and billing codes. The goal is to support continuous documentation integrity surveillance. The proposed model uses transformer-based encoders for clinical text and embedding layers for structured coded fields. Cross-attention mechanisms align concepts across EHR modules before classifying consistency relationships. Conceptually, the model could surface discrepancies such as a diagnosis documented in a note but absent from the problem list, or a billing code unsupported by physician documentation. Its output would include an inconsistency category and an interpretable explanation for clinician review. A unified NLP model for cross-module inconsistency detection could improve EHR trustworthiness, documentation quality, and clinical audit workflows. Such a system should be evaluated prospectively before operational deployment.

Care coordination failures include missed referrals, lost follow-ups, fragmented communication, and incomplete transitions between primary and specialty care. These failures can delay diagnosis, weaken continuity, and increase avoidable utilisation. Existing detection approaches often depend on manual review, retrospective audits, or simple rule-based flags. Such approaches are poorly suited to capture the relational complexity of patient, provider, referral, messaging, and encounter networks. This article develops a conceptual graph-based machine learning model for predicting care coordination failures. The model represents patient–provider referral networks enriched with follow-up status, patient message activity, specialty access delays, and provider communication patterns. The proposed approach uses a heterogeneous graph neural network in which patients and providers are nodes. Referral, encounter, and messaging relationships are represented as edges, while node and edge features encode follow-up adherence, message frequency, wait-time signals, and communication context. Conceptually, the model would identify high-risk referral edges that combine delayed access, incomplete follow-up, weak messaging activity, or limited provider communication. These predictions would support coordinator review before a referral becomes a documented care gap. A graph-based model could shift care coordination from reactive tracking toward predictive prevention. By identifying fragile referral relationships early, it could support more timely outreach and safer continuity of care.

Specialist consultation delays are a pervasive source of prolonged inpatient stays and disrupted throughput. They remain difficult to anticipate because delay risk emerges across ordering, communication, workload, and completion steps. A predictive model could support earlier recognition of consults likely to exceed expected completion windows. Existing consultation monitoring often depends on retrospective reports, manual tracking, or informal escalation. These approaches miss the opportunity to intervene while the consultation is still unfolding. A real-time model could convert consult workflow events into actionable delay forecasts. This article proposes a sequence learning model that predicts the probability of specialist consultation completion delay at the time of order entry. The model would refine this probability after each subsequent event, including messages, assignment, escalation, note drafting, and completion. The objective is conceptual model development rather than experimental evaluation. The proposed approach uses an LSTM-, GRU-, or Transformer-based architecture to ingest consultation milestones and static context. Inputs include consultation type, patient location, ordering service, specialty workload, communication logs, and escalation history. The output is a dynamically updated delay probability intended for consult workflow management. Conceptually, the model would identify high-risk consults early, such as a complex weekend consultation for a critically ill patient with no timely response from an overloaded service. It would be expected to support targeted escalation, workload redistribution, and proactive communication. No empirical performance claims are made. A sequence learning model could help hospitals move from passive consultation tracking to proactive delay management. By combining temporal workflow events with operational context, the model could support more timely specialist input and reduce avoidable length-of-stay pressure. Future evaluation should focus on safety, fairness, usability, and workflow impact.

Clinical pathways are designed to standardize inpatient care for common conditions while allowing clinically justified individualization. Deviations from these pathways are frequent and may reflect either appropriate adaptation to patient complexity or potentially harmful departure from evidence-informed practice. Current deviation detection often depends on retrospective audit, static compliance rules, or aggregate dashboards. These approaches can miss subtle temporal drift in care delivery and rarely explain why a specific patient trajectory diverged from the expected pathway. This article proposes an interpretable machine learning model for detecting clinical pathway deviations in hospitalized patients. The model focuses on order sequences, vital sign trends, laboratory monitoring frequency, and provider decision patterns as dynamic indicators of care-process variation. Conceptually, the model would compare each patient’s evolving care trajectory with learned expected pathways using sequence-comparison and outlier-detection logic. SHAP-based or attention-informed explanations would identify the specific features responsible for a deviation flag, such as delayed monitoring, omitted follow-up testing, or unusual ordering behavior. The proposed model could detect when a patient’s care trajectory diverges from an expected pathway and provide a transparent rationale for review. For example, it could flag a missing repeat troponin, a delayed antibiotic escalation, or a laboratory monitoring pattern inconsistent with the patient’s clinical state. An interpretable pathway-deviation model could shift quality monitoring from manual, sample-based review toward continuous and transparent pathway surveillance. Such a system would support real-time clinical awareness, structured audit, and organizational learning.

Repeat diagnostic imaging is a major driver of healthcare costs, radiation exposure, workflow burden, and downstream follow-up from incidental findings. Its occurrence often follows recognizable patterns shaped by prior imaging, persistent symptoms, specialist advice, recent results, and provider ordering habits. Current utilization management tools often respond after an imaging order has already been placed or rely on static appropriateness rules. They therefore miss opportunities to anticipate repeat ordering risk before the clinician reaches the final order-entry step. This manuscript proposes a sequence learning model that could predict the probability of a repeat diagnostic imaging order within a future clinical window. The model would integrate prior imaging history, symptom documentation, specialist recommendations, ordering physician behavior, and recent test results. The conceptual model would use a recurrent neural network or Transformer encoder to process temporally ordered imaging and clinical events. Structured radiology information system data would be combined with natural language processing features from clinical notes and consult documentation, physician-level ordering context, and recent laboratory or imaging-result signals. Conceptually, the model would forecast whether a repeat CT, MRI, ultrasound, or related diagnostic imaging order is likely to occur. It would also identify major contextual drivers so that the prediction could support pre-emptive review, alternative care suggestions, or guideline-aligned follow-up. A sequence learning model for repeat imaging prediction could function as a safety-and-value layer within radiology workflow. It could reduce unsupported imaging variation while preserving clinically indicated follow-up and surveillance.

Care delivery delays arise from asynchronous interactions among clinical decisions, operational constraints, staffing patterns, facility capacity, and patient communication. These delays are rarely represented within a single predictive framework that captures the hospital as a dynamic multimodal system. Existing delay prediction models often focus on one operational endpoint, such as discharge timing, transport coordination, or procedure scheduling. Such models may require extensive hand-engineered features and may not generalize across units, services, or delay types. This article proposes a conceptual multimodal foundation model for predicting care delivery delays using electronic health record events, operational logs, staff assignments, patient messages, facility capacity indicators, and service queue data. The goal is to describe a reusable model backbone that could support multiple downstream operational prediction tasks. The proposed model would use a transformer-based architecture pre-trained through self-supervised learning over heterogeneous temporal hospital data. Task-specific prediction heads could then be fine-tuned for medication delays, procedure delays, discharge delays, transport delays, and broader care progression bottlenecks. Conceptually, the model would learn a holistic representation of clinical workflow, operational pressure, staffing context, patient communication burden, and service demand. It would be expected to produce dynamic delay risk estimates that adapt to changing hospital conditions and tolerate incomplete modality availability. A multimodal foundation model could unify delay prediction across multiple operational domains. Such an approach may support proactive hospital management by transforming fragmented data streams into shared, contextualized representations of care delivery risk.