- Explainable temporal machine learning of multimorbidity trajectories after acute myocardial infarction: complementing clinical risk scores with mechanistic phenotypes. [Journal Article]J Am Med Inform Assoc. 2026 Aug 06. [Online ahead of print]JAMIA
- CONCLUSIONS: Explainable temporal modeling of EHR data reveals clinically interpretable, biologically grounded multimorbidity trajectories after AMI that complement established risk scores and provide a reproducible approach to mechanistic phenotyping and precision care.
- Publisher Full Text (DOI)
- REWARD-an open-source framework for identifying the unknown benefits of existing medications to inform drug discovery, development, and repurposing. [Journal Article]J Am Med Inform Assoc. 2026 Aug 06. [Online ahead of print]JAMIA
- CONCLUSIONS: The REWARD framework demonstrates how real-world evidence can be harnessed to address unmet medical needs, particularly for diseases lacking effective approved treatments. By making the REWARD analytic package open-source and accessible, we promote an open scientific approach, while maintaining best practices in pharmacoepidemiology.
- Publisher Full Text (DOI)
- Developing and evaluating human-led and large language model-assisted hybrid deductive-inductive workflows for qualitative analysis. [Journal Article]J Am Med Inform Assoc. 2026 Aug 06. [Online ahead of print]JAMIA
- CONCLUSIONS: LLMs are best positioned as analytic partners rather than autonomous coders. Transparent workflows with human-in-the-loop validation are essential for responsible AI integration in health and biomedical informatics.
- Publisher Full Text (DOI)
- CiteSure: retrieval-augmented large language models for faithful biomedical citation recommendation. [Journal Article]J Am Med Inform Assoc. 2026 Aug 04. [Online ahead of print]JAMIA
- CONCLUSIONS: Our results demonstrate that CiteSure, built on a 2-stage retrieval-augmented generation framework, effectively integrates domain-specific retrieval with LLM-based generation to achieve substantial improvements over baseline approaches. Our work underscores the importance of domain-specific adaptation in biomedical citation recommendation and provides publicly available datasets, models, and code for support future research.
- Publisher Full Text (DOI)
- Evaluating large-scale propensity score adjustment when sample size is small. [Journal Article]J Am Med Inform Assoc. 2026 Aug 04. [Online ahead of print]JAMIA
- CONCLUSIONS: LSPS models generally provide reliable bias reduction in small-sample settings, supporting their use in federated analyses. However, standard balance diagnostics may be misleading in small samples, and alternatives should be considered, such as significance checking. When LSPS fails to reduce bias adequately, additional adjustment strategies are required.
- Publisher Full Text (DOI)
- PhenoSS: phenotype semantic similarity-based approach for rare disease prediction and patient clustering. [Journal Article]
- CONCLUSIONS: PhenoSS provides a statistically interpretable framework for modeling phenotypic heterogeneity in rare disease research and is adaptable to other structured clinical vocabularies such as SNOMED-CT and ICD codes.
- Publisher Full Text (DOI)
- Tipping the balance: impact of class imbalance correction on the performance of clinical risk prediction models. [Journal Article]J Am Med Inform Assoc. 2026 Jul 30. [Online ahead of print]JAMIA
- CONCLUSIONS: Common 1:1 class-imbalance correction techniques do not improve discrimination and may substantially degrade calibration, limiting their suitability for clinical risk prediction where accurate probabilities are essential.
- Publisher Full Text (DOI)
- Who is doing informatics work in US governmental public health agencies? [Journal Article]J Am Med Inform Assoc. 2026 Jul 30. [Online ahead of print]JAMIA
- CONCLUSIONS: Achieving the goals of DM and the national Public Health Data Strategy will require developing and supporting a variety of informatics and data-centric roles in PH agencies.
- Publisher Full Text (DOI)
- Real-time EHR secure messaging to coordinate emergency department disposition for 30-day revisit patients. [Journal Article]J Am Med Inform Assoc. 2026 Jul 30. [Online ahead of print]JAMIA
- CONCLUSIONS: Real-time EHR messaging may be most effective when paired with structured care coordination models rather than deployed as a standalone alerting tool.
- Publisher Full Text (DOI)
- Veteran health information exchange volume and 30-day readmissions, avoidable hospitalizations, and in-hospital mortality: evidence from community and Veterans Health Administration direct care. [Journal Article]J Am Med Inform Assoc. 2026 Jul 28. [Online ahead of print]JAMIA
- CONCLUSIONS: Setting-specific effects may stem from asymmetric content (longitudinal histories outbound from VHA, episodic summaries inbound to VHA), asymmetric interfaces (modern community EHRs vs VHA's Joint Legacy Viewer), and HIE-enabled reclamation of community patients into VHA. More work is needed to disentangle these mechanisms.
- Publisher Full Text (DOI)
- Characterization and Validation of EHR Computable Phenotypes for Long COVID Using Patient-Reported Symptoms: Insights from the Nationwide RECOVER Program. [Journal Article]J Am Med Inform Assoc. 2026 Jul 24. [Online ahead of print]JAMIA
- CONCLUSIONS: These findings demonstrate that, using EHR data, a machine-learning model can accurately select patients with sets of self-reported LC symptoms. The model could help identify patients within a health system with the highest probability of the condition and facilitate screening, recruitment for clinical trials, and etiologic studies.
- Publisher Full Text (DOI)
- Reflections on the discipline: foundations, challenges, and future of biomedical informatics. [Journal Article]J Am Med Inform Assoc. 2026 Aug 01; 33(8):1421-1422.JAMIA
- Publisher Full Text (DOI)
- Medical code embeddings from claims-based co-occurrences: a unified semantic space for ICD-10 diagnoses and ATC medications. [Journal Article]J Am Med Inform Assoc. 2026 Jul 15. [Online ahead of print]JAMIA
- CONCLUSIONS: We release the first openly available joint ICD-10-ATC embedding space derived from real-world claims data, providing a reusable resource for biomedical informatics research.
- Publisher Full Text (DOI)
- Translating machine learning predictions into meaningful risk estimates to support clinical decisions: a post hoc analysis of chronic obstructive pulmonary disease adverse outcomes using unified auto clinical scores. [Journal Article]J Am Med Inform Assoc. 2026 Jul 15. [Online ahead of print]JAMIA
- CONCLUSIONS: In conclusion, this approach facilitates the widespread adoption of ML-driven risk assessment across diverse healthcare settings while ensuring compatibility with existing clinical guidelines and regulatory frameworks.
- Publisher Full Text (DOI)