Prevalence and treatment encounters for fecal, urinary, and double incontinence in community-dwelling adults using electronic health record data

Diversity in clinical Trials: The example of systemic lupus erythematosus.

Claims-based analyses can suffer from residual and unmeasured confounding due to factors that are poorly captured in claims. Some of these factors may be measured in other data sources, such as in structured fields of electronic health records (EHR), for example, laboratory test results, or in free-text physician notes. We conducted a proof-of-principle study to demonstrate a process for evaluating the potential risk of confounding-factors poorly captured in claims data but measurable in the EHR as part of drug safety surveillance activities. In future practical applications, this approach could be used along with other sensitivity analyses to evaluate potential residual confounding (e.g., E-values, negative controls). We used claims-EHR linked data from the Mass General Brigham site of the US Food and Drug Administration's (FDA) Sentinel Real World Evidence Data Enterprise. We extracted a cohort that was previously used in a prototypical Sentinel claims-based query that compared initiators of sacubitril-valsartan vs. angiotensin-converting enzyme inhibitors or angiotensin receptor blockers on the risk of angioedema. In this cohort, we used EHR data to characterize angioedema risk factors poorly captured in claims and observed that claims-based proxies balanced most risk factors that were measurable only in EHR data. While quantitative bias analysis methods can be used to adjust for residual confounding using external information on magnitude and direction of bias, this was deemed unnecessary for this example due to the observed balance achieved on risk factors for angioedema measured in the EHR. A robust linked EHR-claims data infrastructure is crucial for routine application of these methods to evaluate and mitigate residual confounding in drug safety surveillance studies.

Machine learning prediction of positive urine cultures in an academic pediatric emergency department (ED).

Estimate renal cell carcinoma recurrence rates using electronic health records.

To develop and externally validate a bio-ecological model for early screening of developmental coordination disorder (DCD) using maternal and environmental risk factors from electronic health records, aimed at improving early detection in children under 5 years. This was a prospective study that examined data from 150 948 preschool children in China. Perinatal and sociodemographic predictors were integrated using logistic regression and random forest algorithms. The model was internally validated on split training and testing subsets and externally validated on an independent clinical sample of 1359 children aged 3 to 10 years, including confirmed diagnoses of DCD. Model performance was evaluated using the area under the curve (AUC), sensitivity, specificity, and accuracy. In the group aged 3 to 5 years, the model achieved an AUC of 0.70, sensitivity of 71.43%, accuracy of 77.61%, and specificity of 78.00%. In the group aged 6 to 10 years, performance was moderate (AUC = 0.58; sensitivity = 54.88%; accuracy = 61.50%; specificity = 62.28%). This bio-ecological model offers a scalable, cost-effective tool to support the early identification of DCD using electronic health record data. It performs well in early childhood and maintains moderate accuracy in older children, supporting its utility for longer-term risk prediction. The model could enhance existing screening systems by enabling earlier triage and intervention. Further validation across diverse health care settings is warranted.

Although drug shortages for outpatient chronic conditions commonly occur, population-level data on how they impact patients' ability to refill prescriptions is scarce. We sought to identify distinct patterns of refill adherence following drug shortages and patient- and prescription-level factors associated with adherence trajectories reflecting potential shortage-related treatment disruption. We retrospectively analyzed panel data assembled from 2017 to 2020 Veterans Health Administration (VHA) electronic health record data. Patients were included if they were baseline users of medications subject to a shortage within VHA. Group-based trajectory modeling was applied to users' monthly proportion of days covered (PDC) values from 6-months before to 6-months after the reported drug supply chain disruption. Patient demographics and medication characteristics were compared between identified trajectory groups using multivariable logistic regression. Among 1.5 million episodes of medication use (representing 1.3 million unique Veterans) for 29 medications in shortage in VHA, 6.3% were for female patients and the mean age was 66.4 ± 12.8 years. A 4-group trajectory model had the best fit: High Adherence (69.2% of observations), Moderate Adherence (14.1%), Potential Shortage-Related Disruption (8.5%), and Pre-Shortage Disruption (8.3%). Drug characteristics (drug class, number of manufacturers) were more strongly associated than patient characteristics with having Potential Shortage-Related Treatment Disruption vs. High Adherence. We identified 4 trajectories of refill adherence for medications subject to VHA drug shortages, with 8.5% of users of affected drugs exhibiting a trajectory consistent with shortage-related treatment disruption. Drug characteristics may modify whether drug shortages lead to treatment disruption in VHA.

The incremental value of liquid biopsy in the initial evaluation of patients with metastatic non-small cell lung cancer undergoing tissue-based molecular testing.

Assessing Concordance of Cancer Registry Data and Electronic Health Record Data in Metastatic Cancer: a Cohort Study of Patients with Colorectal Liver Metastasis in a U.S. Integrated Health System.

Artificial intelligence (AI) has the potential of reshaping GI oncology by enabling more nuanced interpretation of complex clinical, imaging, and molecular data, while supporting more timely and patient-centered decisions. This article synthesizes perspectives across the GI cancer continuum, beginning with a framework for context-aware AI that emphasizes metadata, multimodal integration, and lifecycle quality and safety as foundations for trustworthy tools that clarify, rather than conceal, uncertainty. Next, AI in endoscopy is highlighted as an example in clinic practice, focusing on computer-aided detection and diagnosis systems that not only increase adenoma detection rates but also raise questions about surveillance burden, real-world effectiveness, and the balance between skill enhancement and potential deskilling of endoscopists. Another section explores how AI can help GI oncologists design, prioritize, and implement highly innovative clinical trials-particularly multi-omic and imaging-driven approaches-while envisioning a future in which far more patients participate in trials that align with their goals and values. The final section reviews emerging AI-enabled clinical trial matching pipelines, including large language model-based retrieval and prescreening tools that operate on real-world electronic health record and protocol data, and discusses challenges related to bias, privacy, explainability, and workflow integration. Together, these contributions argue that the greatest impact of AI in GI oncology will come from deliberately aligning technical capabilities with highly relevant patient-centered clinical questions, ethical governance, and implementation strategies that expand access to trials and improve outcomes for patients with GI malignancies.

Latent tuberculosis infection care cascade outcomes in primary care clinics in the tuberculosis epidemiologic studies consortium-III.

Electronic Health Record (EHR) data are increasingly used in cancer research, yet the fidelity of this data when exchanged between systems remains poorly quantified. This study investigated the agreement in essential biomarker data after they are passed from the EHR into the cancer registry and Fast Healthcare Interoperability Resources (FHIR) extracts. This single-institution retrospective study compared demographics and 6 biomarkers from 30 lung cancer patients seen between July 2020 and July 2022. Manual review from the EHR served as the gold standard, with concordance tested between the source EHR, Institutional Cancer Registry, and FHIR exports. Demographics showed high concordance across databases. In contrast, biomarker data present in the source EHR were missing in 80%-100% of FHIR extracts. The demographic registry variables were highly concordant. This study reports a significant loss in biomarker data availability across real-world data (RWD) sources. Results underscore critical gaps in RWD extraction or exchange methods and highlight risks of relying on RWD without validation.

How representative are electronic health records? A record linkage study using individual-level census data.

This study assessed the impact of implementing an admission discharge registered nurse (RN-AD) on five inpatient units at an acute care, 718-bed Magnet®-designated, academic, and Level I trauma center on throughput pressures, nurse staffing ratios, and increased workload. To assess the impact of implementing RN-ADs, the authors conducted a nonequivalent pre/post quasi-experimental study utilizing electronic health record data (discharge time, admission date, discharge date) and standardized patient experience survey scores. Predata were collected from August 2016 to July 2017, and postdata were collected from August 2017 to July 2018. Of the 19 114 patient encounters examined, length of stay decreased, discharge before noon increased, and patient experience scores increased; nurses also noted a positive impact on patient discharge. Implementation of an RN-AD role was associated with improvements in length of stay, earlier discharge timing, patient experience, and nurse satisfaction. These findings suggest that dedicated admission and discharge nurse support may be an effective workforce strategy to improve patient flow while reducing the operational burden on bedside nurses.

Diabetes care requires frequent and high-stakes decisions that must be made in the setting of substantial day-to-day physiologic variability. The growing availability of continuous glucose monitoring, connected insulin delivery devices and longitudinal electronic health record data has created an opportunity for algorithm-enabled tools that can synthesise high-frequency data, reduce cognitive burden for patients and clinicians, and support safer and more consistent decision-making. In this review, artificial intelligence (AI) is used broadly to describe computational systems that generate predictions, recommendations or automation from clinical data. We distinguish between algorithmic automation and control methods that underpin many currently deployed automated insulin delivery (AID) systems and machine learning-based models, including deep learning and large language models (LLMs), that are increasingly used for pattern recognition, risk prediction and natural language applications. This distinction is clinically relevant because evidence standards, safety risks and governance needs vary substantially across these categories. This narrative review summarises current and emerging applications of AI in diabetes care with an emphasis on clinical readiness, strength of evidence and implementation considerations. We highlight established applications in AID, emerging approaches that seek greater autonomy and interoperability and newer tools such as LLMs, wearables and digital twin frameworks, focusing on where evidence is strongest, where risks are highest and what safeguards are required for responsible clinical use.

Factors associated with discharge to skilled nursing despite a clinical recommendation for inpatient rehabilitation.

Hypertensive disorders in pregnancy (HDP) affect 16% of births in the United States. In this pilot study, we conducted a preliminary evaluation of natural language processing (NLP) in extracting signs and symptoms (SS) of HDP from clinical notes within electronic health records (EHRs). This retrospective observational pilot study used EHR data from patients admitted for labor and birth (N = 83,003 clinical notes from 17,775 patients). Four SS categories were extracted: elevated blood pressure, neurological, renal, and hepatic/hematologic. Five machine learning models and ClinicalBERT were trained and tested using five-fold cross-validation. The best-performing model was applied to the full dataset. Bivariate analyses were performed to examine (1) differences in HDP diagnoses based on ICD-10 codes (gestational hypertension, preeclampsia, and eclampsia) by SS documentation and (2) differences in SS documentation by patient race and ethnicity. XGBoost demonstrated the highest macro-average F1-score (0.75). Elevated blood pressure showed the highest F1-score (0.87), followed by neurological SS (0.77). In the full dataset, 24.3% of clinical notes and 42.3% of patients had documentation of at least one SS category. A higher proportion of HDP diagnoses was observed with an increased number of SS categories documented (p < .001). A higher proportion of non-Hispanic Black patients had documentation of SS across all categories. NLP can extract SS with moderate accuracy, supporting feasibility for larger-scale extraction. Findings also highlight differences in SS documentation by patient race and ethnicity. Future research is needed to improve NLP performance, including expanding annotated data.

In the delivery room, newborn respiratory failure precedes cardiac failure, emphasizing the importance of effective ventilation. Face masks for ventilation may cause air leakage around the mask with subsequent suboptimal lung pressure, and intubation requires skilled providers. Laryngeal mask airways (LMA) may provide a more stable airway interface, with improved seal and more consistent ventilation that is less dependent on provider technique. An evaluation of the feasibility, acceptability, and initial outcomes of implementing the laryngeal mask airway as the first-line approach for ventilation in late preterm and term infants was conducted in a high-resource, urban safety-net hospital with a level III neonatal intensive care unit (NICU). The LMA was introduced and promoted as the firstline for delivery room ventilation in infants ≥35 weeks gestational age and ≥1.5 kg from August 2023 to August 2024. Implementation was supported by comprehensive training, survey feedback, and multidisciplinary involvement. The program evaluation spanned a 2-year period from August 2022 to August 2024. Feasibility and acceptability data were collected via provider surveys, and neonatal outcomes were compared pre- and post-implementation from electronic health record data. During implementation, LMAswereused as first-line in 58.7% of eligible neonates indicated for delivery room ventilation. Provider surveys showed increased knowledge and confidence in LMA use after education and high comfortability with LMA implementation in the delivery room. NICU admission rates, delivery room endotracheal intubations, chest compressions, and epinephrine use were similar across groups. Providers across experience levels successfully inserted LMAsafter brief training. LMA as first-line ventilation yielded similar outcomes to face mask in an urban safety-net hospital. Future research should explore broader applicability.

Monitoring Patient Blood Management (PBM) practices against evidence-based standards is essential for quality improvement; however, current approaches are limited. In the UK, perioperative tranexamic acid (TXA) use is a national quality standard, yet monitoring relies on manual audit cycles that are resource-intensive and limited in scope. We evaluated whether an audit could be automated using routinely collected electronic health record (EHR) data. We performed a retrospective study at a tertiary NHS center using linked perioperative and transfusion datasets. Automated compliance indicators were constructed using coded procedures (denominator) and digitally documented TXA administration from WHO Surgical Safety Checklists and electronic prescribing records (numerator). A structured validation framework assessed data extractability, completeness, denominator coverage, coding accuracy, and concordance between electronic sources. Outputs were assessed by specialty and procedure and compared with contemporaneous manual audit findings. Between July-September 2025, 800 eligible procedures were identified. Comparison with an independent dataset demonstrated procedural coverage of 96.2% and miscoding rate of 3.9%. Overall automated TXA compliance was 86.3%. Concordance between WHO checklist and electronic prescription was 74.2%, with explainable discordance patterns. Substantial inter-specialty variation was identified, ranging from 98.2% (trauma and orthopedics) to 0% (vascular surgery). Compared with October-December 2024, overall compliance increased by 7.6%. Automated EHR-based audit of perioperative TXA compliance is feasible and demonstrates good validity. Structured validation confirmed data reliability, and full-population extraction revealed granular specialty- and procedure-level variation, likely undetectable by manual audits, supporting its wider evaluation as a continuous PBM quality monitoring tool.

Social determinants of health (SDoH) are critical drivers of health outcomes but are often underdocumented in structured electronic health record (EHR) data. Instead, SDoH are more commonly recorded in unstructured clinical notes, and unlocking this information could have far-reaching implications for advancing population health research and informing clinical decision-making. This study develops and systematically evaluates cost-efficient methods for extracting SDoH information from unstructured clinical text using rule-based natural language processing (NLP) and large language model (LLM)-based approaches. We constructed a gold-standard annotated corpus comprising clinical text segments from 171 patients in the Mass General Brigham Research Patient Data Registry, covering 7 SDoH domain categories and 23 subcategories. A rule-based system (RBS) was developed and evaluated alongside 7 OpenAI GPT models (GPT-4o, 4.1, 4.1-mini, o4-mini, GPT-5, GPT-5-mini, and o3) under zero-shot and few-shot settings using multiple prompting strategies. We additionally implemented late-fusion ensemble approaches that combined outputs from rule- and LLM-based methods. Performance was assessed using precision, recall, and F1-score, alongside qualitative error analysis. The RBS achieved high precision for SDoH domain categories (0.96) but substantially lower recall (0.68). GPT-based models consistently outperformed the RBS in overall recall and F1-scores. The best domain-level performance was observed for GPT-5 and GPT-5-mini in few-shot settings (F1-score=0.89), while o4-mini achieved the highest subcategory-level performance (F1-score=0.88). A late-fusion ensemble integrating RBS and GPT outputs further improved domain-level performance (F1-score=0.92), with balanced precision (0.93) and recall (0.90), but did not improve subcategory-level performance. Recent GPT models with advanced reasoning capabilities, including the newly released mini models (eg, o4-mini and GPT-5-mini), demonstrated strong performance for SDoH extraction without task-specific fine-tuning and consistently outperformed the rule-based NLP system. Integrating rule- and LLM-based methods via late fusion further enhanced domain-level extraction performance. Our results demonstrate a cost-efficient framework for the accurate identification of SDoH from clinical text, facilitating downstream population health research and clinical informatics applications.