Journal Of The American Medical Informatics Association[JOURNAL]
Sun
200 papers
Digital divide in clinical and operational artificial intelligence adoption and implementation stages: US hospital diffusion patterns and AI deserts.
Vo A, Tao Y, Sundrup R … +3 more , Mishra AN, Wu D, Nathan LS
J Am Med Inform Assoc · 2026 Jul · PMID 42386166 · Publisher ↗
OBJECTIVES: We examine how hospital characteristics relate to clinical and operational artificial intelligence (AI) adoption and implementation stages and characterize AI deserts and spatial clustering patterns to highli...
OBJECTIVES: We examine how hospital characteristics relate to clinical and operational artificial intelligence (AI) adoption and implementation stages and characterize AI deserts and spatial clustering patterns to highlight place-based AI access gaps among United States (US) hospitals. MATERIALS AND METHODS: We used the 2024 American Hospital Association Annual Survey data from 2720 hospitals with at least one AI response. We applied logistic regression models to examine the associations between hospital characteristics and AI adoption, local indicators of spatial association to identify local clusters, and distance analyses to locate AI desert hospitals (ie, geographically isolated nonadopters located >50 miles from the nearest AI adopters). RESULTS: We found that system membership, larger bed size, and nurse staffing intensity are positively associated with clinical and operational AI adoption and implementation stages, whereas rural location, for-profit ownership, and physician intensity are negatively associated with them. Teaching status is more strongly associated with clinical AI, while system membership is more positively associated with operational AI. Although 68.0% of hospitals adopted ≥1 clinical AI functionalities and 60.7% adopted ≥1 operational AI functionalities, 12.1% of clinical and 13.2% of operational non-adopters are classified as AI desert hospitals. DISCUSSION: AI deserts reveal regional implementation gaps; sustained diffusion requires building shared regional capacity rather than relying only on hospital-level incentives. Policy implications to emerging divides may include tracking implementation stage, providing domain-specific support, and funding regional partnerships. CONCLUSION: US hospital AI diffusion is uneven and spatially structured. AI deserts mark regional gaps in access to AI-adopting hospitals.
Extending the fundamental theorem of biomedical informatics: a proposal and illustrative examples.
Bakken S
J Am Med Inform Assoc · 2026 Jul · PMID 42378657 · Full text
Abstract loading — click title to view on PubMed.
Human factors methods for designing safe health information technology: what do the experts think?
Awad S, Begg R, Loveday T … +2 more , Baillie A, Baysari MT
J Am Med Inform Assoc · 2026 Jun · PMID 42366129 · Publisher ↗
OBJECTIVE: Human Factors (HF) methods have potential to ensure the design of health information technology (HIT) is safe and usable, but limited research has examined what HF methods have been applied or could be applied...
OBJECTIVE: Human Factors (HF) methods have potential to ensure the design of health information technology (HIT) is safe and usable, but limited research has examined what HF methods have been applied or could be applied to HIT. This study aimed to identify key HF and safety analysis methods used and/or recommended by HF experts working in healthcare or non-healthcare industries that may be suitable for supporting the design, redesign and configuration of HIT. MATERIALS AND METHODS: We ran semi-structured interviews with 21 HF experts working across health and non-health industries to identify key HF and safety analysis methods used and/or recommended for supporting the design, redesign and configuration of HITs. RESULTS: Forty-seven HF methods across 11 method categories were reported by HF experts. Non-health participants reported a wider range of Human Error Identification and Risk Assessment Methods and were the only cohort to report workload assessment methods. Both health and non-health participants described their approaches for selecting methods and recommended that methods be applied flexibly. DISCUSSION: This study highlights the need to uplift HF capability by teaching methods to system designers, particularly where access to HF experts is limited and undertaking efforts to learn from HF practice in safety-critical industries outside of healthcare. CONCLUSION: Further work is required to integrate HF methods and approaches, especially those focused on safety, into the work of HIT designers.
Equity-by-design for socially assistive robots as digital health tools.
Kachouie R, Barton B
J Am Med Inform Assoc · 2026 Jun · PMID 42364080 · Publisher ↗
OBJECTIVES: To propose an equity-by-design agenda for socially assistive robots (SARs) as embodied digital health informatics interventions. MATERIALS AND METHODS: We developed this Perspective via a purposive narrative...
OBJECTIVES: To propose an equity-by-design agenda for socially assistive robots (SARs) as embodied digital health informatics interventions. MATERIALS AND METHODS: We developed this Perspective via a purposive narrative synthesis of SARs healthcare studies, digital health equity, informatics governance, and human-robot interaction ethics/equity, integrating care- and technology-ethics to derive a 3-level equity framework. RESULTS: We outline equity requirements at product (user), institutional (meso), and policy/evaluation (macro) levels and operationalize them as a checklist covering co-design, accessibility, privacy, data governance, equitable access and financing, and equity-oriented evaluation. DISCUSSION: Applying equity-by-design to SARs highlights how embodied sensing, workflow fit and organizational readiness, and governance/reimbursement incentives determine who benefits, which risks are borne, and whether deployments narrow or widen digital divides. CONCLUSION: Treating SARs as embodied informatics interventions and operationalizing equity across micro (product), meso (institution), and macro (policy) levels can guide designers, informatics teams, providers, and payers toward deployments that are safe, acceptable, and just.
Orchestrator multi-agent clinical decision support system for secondary headache diagnosis in primary care.
Wu X, Zhang H, Garduno-Rapp NE … +6 more , Rousseau JF, Thakkallapally M, Ji Y, Visweswaran S, Peng Y, Wang Y
J Am Med Inform Assoc · 2026 Jun · PMID 42364078 · Publisher ↗
OBJECTIVE: Secondary headaches require urgent recognition due to potentially devastating consequences if untreated. Despite established clinical "red flag" criteria, identifying patients needing immediate evaluation rema...
OBJECTIVE: Secondary headaches require urgent recognition due to potentially devastating consequences if untreated. Despite established clinical "red flag" criteria, identifying patients needing immediate evaluation remains challenging in primary care. This study developed and evaluated a large language model (LLM)-based multi-agent clinical decision support system for interpretable secondary headache diagnosis. MATERIALS AND METHODS: We first established 7 clinically relevant secondary headache red flag domains through manual review and synthesis of clinical guidelines. Based on these domains, we designed an LLM-based system using an orchestrator-specialist multi-agent architecture that decomposes diagnostic reasoning into 7 guideline-aligned agents corresponding to key red flag features. Each agent generates structured, evidence-grounded reasoning, coordinated by a central orchestrator. The system was evaluated on 90 expert-validated secondary headache cases and compared with a single-LLM baseline under 2 prompting strategies: question-based prompting (QPrompt) and guideline-based prompting (GPrompt). Five open-source LLMs (Qwen-8b, Qwen-14b, Qwen-30b, GPT-OSS-20b, and Llama-3.1-8b) were tested. RESULTS: The orchestrated multi-agent system with GPrompt achieved the highest red flag classification performance across models, measured by F1 score. Performance gains were consistent and more pronounced in smaller LLMs, suggesting that structured reasoning improves efficiency and accuracy beyond prompt engineering alone. The framework also produced transparent and guideline-aligned intermediate reasoning. DISCUSSION: Decomposing clinical reasoning into specialized agents enhances interpretability and diagnostic reliability compared with monolithic LLM approaches. Multi-agent orchestration provides a clinically aligned framework for explainable decision support. CONCLUSION: An orchestrator-specialist multi-agent LLM framework improves secondary headache diagnosis accuracy and transparency, supporting the development of explainable AI systems for time-constrained clinical decision-making in primary care.
CUI-Curate: a GraphRAG-based framework for automated clinical concept curation for NLP applications.
Blake V, Novak J, Miller M … +2 more , Ooi SY, Gallego B
J Am Med Inform Assoc · 2026 Jun · PMID 42350271 · Publisher ↗
BACKGROUND: Clinical named entity recognition tools commonly map free text to Unified Medical Language System (UMLS) Concept Unique Identifiers (CUIs). For many downstream tasks, however, the clinically meaningful unit i...
BACKGROUND: Clinical named entity recognition tools commonly map free text to Unified Medical Language System (UMLS) Concept Unique Identifiers (CUIs). For many downstream tasks, however, the clinically meaningful unit is not a single CUI but a concept set comprising related synonyms, subtypes, and associated concepts. Constructing these sets is labour-intensive, inconsistently performed, and poorly supported by existing tools. METHODS: We present CUI-Curate, a graph-based retrieval-augmented-generation (GraphRAG) framework for automated UMLS concept set curation. A UMLS knowledge graph was constructed and embedded for semantic retrieval. Candidate CUIs were retrieved using graph-based expansion and then filtered and classified using large language models (GPT-5 and Qwen3-32B). The framework was evaluated on five lexically heterogeneous clinical concepts against manually curated concept sets and gold-standard concept sets. RESULTS: CUI-Curate produced substantially larger and more complete concept sets than the manual benchmarks. A single retrieval configuration across concepts achieved high recall of definitive concepts with manageable candidate sets. GPT-5 outperformed manual curation for all concepts and retained at least 95% of definitive gold-standard CUIs, while Qwen3-32B achieved comparable but slightly lower performance. Many missed concepts were not observed in 10,000 MIMIC-III notes. CUI-Curate infrastructure and end-to-end processing were inexpensive and stable across runs. CONCLUSIONS: CUI-Curate offers a scalable, reproducible, and cost-efficient approach for generating clinician-reviewable UMLS concept sets tailored to clinical natural language processing and phenotyping applications.
Malfunctions in distributed clinical decision support: 3 cases from a multi‑component clinical decision support system.
Thayer JG, Shaeffer GP, Fiks AG … +6 more , Jenssen BP, Ramachandran J, Karavite D, Nabi-Burza E, Winickoff JP, Grundmeier RW
J Am Med Inform Assoc · 2026 Jun · PMID 42350266 · Publisher ↗
INTRODUCTION: Clinical decision support (CDS) is increasingly delivered through distributed architectures that connect electronic health record (EHR) workflows to external services and community partners. While these des...
INTRODUCTION: Clinical decision support (CDS) is increasingly delivered through distributed architectures that connect electronic health record (EHR) workflows to external services and community partners. While these designs enable rapid deployment and interoperability, they also introduce new failure modes that can silently disrupt time‑sensitive care processes. Practical, real‑world descriptions of these distributed CDS malfunctions remain limited. CASE REPORT: We describe 3 malfunctions in a distributed CDS system used to support smoking cessation referrals. The issues reflected common distributed‑system failure modes, including clock drift, timing‑related data availability problems, and asynchronous processing across partner systems. CONCLUSION AND RECOMMENDATIONS: Given the implications software architecture can have on distributed systems, it is critical to expand the definition of what constitutes the CDS system to include components outside the EHR, including those of third-party partners system. Further, monitoring techniques for distributed systems may also require multiple methods to account for differences in how each component can fail.
The importance of clinical context in evaluating algorithmic fairness: insights from a medication adherence prediction algorithm.
Mukhopadhyay A, Zhao Y, Chunara R … +4 more , Kronish IM, Lawrence S, Blecker S, Adhikari S
J Am Med Inform Assoc · 2026 Jun · PMID 42350262 · Publisher ↗
OBJECTIVE: Using AI algorithms can exacerbate health disparities if care or resources are allocated away from underserved populations. We evaluated an algorithm for its potential to worsen health disparities across diffe...
OBJECTIVE: Using AI algorithms can exacerbate health disparities if care or resources are allocated away from underserved populations. We evaluated an algorithm for its potential to worsen health disparities across different clinical use cases. MATERIALS AND METHODS: This was a retrospective study of patients with heart failure (HF) at an academic health system using an algorithm that predicts pharmacy fill nonadherence to evidence-based HF medications. We compared prediction performance metrics (accuracy, false positive rate, false negative rate), using rate-ratios (RRs), between subgroups with and without known HF care disparities: below vs above median neighborhood-level socioeconomic status (nSES) and Black vs White race. Results were then applied to 3 hypothetical clinical use cases. RESULTS: Among 34 697 patients (13% Black, 10% Hispanic, 65% White), algorithm accuracy was similar across nSES and racial subgroups. The algorithm assigned more false positives for medication nonadherence among low vs high nSES (RR [95%CI] 1.50 [1.44-1.56]) and Black vs White (2.05 [1.92-2.19]) subgroups. The algorithm also assigned fewer false negatives (0.63 [0.59-0.67]) to Black vs White subgroups. When applied to 3 hypothetical use cases, worsening of existing disparities was pertinent for clinical applications where false positives could be particularly harmful (e.g, if predictions of nonadherence prompted lower treatment priority). DISCUSSION: Although accuracy was similar across demographic groups, differences in false positive and false negative rates revealed that the same prediction may worsen disparities in some use cases, but not others. CONCLUSION: Evaluation of predictions in the context of clinical use is essential to avoid unintentionally worsening inequities.
Patient and carer perceptions and experiences of technology-facilitated appointment reminders in healthcare: a scoping review.
Rousaki A, Jones D, Dowding D … +1 more , Gasteiger N
J Am Med Inform Assoc · 2026 Jun · PMID 42341159 · Publisher ↗
BACKGROUND AND AIM: Missed healthcare appointments, or "Did Not Attends" (DNAs), pose challenges for healthcare systems. Technology-facilitated reminder systems, such as SMS and phone calls are often implemented to impro...
BACKGROUND AND AIM: Missed healthcare appointments, or "Did Not Attends" (DNAs), pose challenges for healthcare systems. Technology-facilitated reminder systems, such as SMS and phone calls are often implemented to improve attendance. This scoping review aimed to map the evidence on patient and carer perspectives and experiences of technology-enabled appointment reminders in healthcare and, secondly, examine how equity-relevant characteristics were reported. METHODS: A scoping review which searched EMBASE, MEDLINE, PsycINFO, Web of Science, Scopus, and EBSCO from September to October 2025 for studies published between 2010 and 2025. Studies examining patient or informal/unpaid carer perceptions and experiences of technology-based reminder systems were included. Equity-relevant dimensions were examined using the PROGRESS-Plus framework. Data were extracted and summarised using a structured form; with findings synthesised thematically. RESULTS: A total of 45 studies were included. Most focused on patient perspectives, with comparatively fewer centered specifically on carers. The majority were cross-sectional surveys, with fewer longitudinal and theory-informed designs. SMS reminders were the most studied modality, followed by phone calls and app-based notifications. Patients and carers reported high satisfaction. Recurring barriers included digital exclusion, language challenges, confidentiality concerns, and socio-economic inequalities. Equity reporting across studies was inconsistent, with many studies describing sociodemographic characteristics without examining how they influenced engagement with reminder systems. CONCLUSIONS: Technology-enabled appointment reminders are widely perceived as useful. Digital exclusion, privacy, language, and trust-related barriers limit engagement and access. Greater user involvement is needed to ensure reminder systems support, rather than reproduce, healthcare inequalities. Future research and implementation efforts should prioritise equity-informed design and evaluation.
Charting the future of ACMI: a report from the 2025 ACMI symposium.
Foraker R, Grando A, Alexander GL … +5 more , Cato K, Kharrazi H, Embi P, Matheny ME, Payne PRO
J Am Med Inform Assoc · 2026 Jun · PMID 42340859 · Publisher ↗
The 2025 American College of Medical Informatics (ACMI) Symposium, themed Charting the Future of ACMI, provided a forum for fellows to reflect on the 2020-2025 ACMI Strategic Plan and define future priorities. Discussion...
The 2025 American College of Medical Informatics (ACMI) Symposium, themed Charting the Future of ACMI, provided a forum for fellows to reflect on the 2020-2025 ACMI Strategic Plan and define future priorities. Discussions centered on: (1) mobilizing ACMI's expertise to guide the responsible use of artificial intelligence (AI) in medical informatics, (2) advancing informatics education and mentorship across career stages, and (3) strengthening local, national, and global interdisciplinary partnerships. Proposed actions include establishing an AI Task Force, developing an online Education Resource Library, expanding structured mentorship, and cultivating strategic partnerships with relevant informatics, engineering, and clinical organizations. Fellows also identified cross-cutting challenges, including financial pressures, competition with alternative convening spaces, and the need to engage emerging leaders. By addressing these challenges while advancing its strategic imperatives, ACMI aims to serve as a trusted compass for the informatics community.
A comparison of Fast Healthcare Interoperability Resources and Observational Medical Mutcomes Partnership electronic health record data within the All of Us Research Program.
Patterson J, Minto E, Beaton M … +5 more , Anand A, Velez M, Harris P, Hripcsak G, Natarajan K
J Am Med Inform Assoc · 2026 Jun · PMID 42334204 · Publisher ↗
OBJECTIVE: This study compares the contents of two data standards; the Observational Medical Outcomes Partnership (OMOP) and Fast Healthcare Interoperability Resources (FHIR), highlighting their strength and weaknesses a...
OBJECTIVE: This study compares the contents of two data standards; the Observational Medical Outcomes Partnership (OMOP) and Fast Healthcare Interoperability Resources (FHIR), highlighting their strength and weaknesses and serve as an initial step toward understanding how each standard supports secondary data analysis. MATERIALS AND METHODS: Participant electronic health record data in both OMOP and FHIR formats from the All of Us Research Program (AoURP) were compared, including codeable event volume, healthcare encounters, and person timelines. A phenotype-based assessment was also conducted using Type-II Diabetes Mellitus (T2DM). RESULTS: Among 29 512 participants identified with overlapping FHIR and OMOP data, Median codeable event counts were comparable between FHIR and OMOP within the Measurement (OMOP = 846; FHIR = 832), Drug (OMOP = 92; FHIR = 90), and Observation (OMOP = 65; FHIR = 100) domains, but were higher in OMOP within the Condition (OMOP = 258; FHIR = 11) and Procedure (OMOP = 72; FHIR = 4) domains. Within the T2DM cohort, OMOP contained more data, except for medications. Very few participants had encounters in FHIR (1.5%) relative to OMOP (97.0%). On average, only 15.9% of visit dates overlapped in both standards, with most visit dates occurring only in OMOP (65.3%) or only FHIR (18.4%). DISCUSSION: Data in OMOP showed a higher volume of observation and procedure codeable events, reported encounters, and T2DM symptoms, complications, and comorbidities. FHIR data was able to capture data across multiple providers and health systems. CONCLUSION: Based on AoURP data, both standards were shown to support healthcare data capture, although OMOP shows greater utility for research purposes as its extract, transform, and load process enables more flexible data capture relative to extracting data from FHIR payloads. FHIR, however, captures patient-level data from beyond the health system and can thus be used to supplement OMOP.
Effect of use of ambient listening technology on patient-reported communication and satisfaction ratings.
Taylor SL, Aizenberg D, Jost M … +3 more , Ren Y, Lyles CR, Adams JY
J Am Med Inform Assoc · 2026 Jun · PMID 42334196 · Publisher ↗
OBJECTIVES: Evaluate the impact of ambient listening AI scribe technology for drafting notes on patient-reported communication and satisfaction ratings of their physician during ambulatory visits. MATERIALS AND METHODS:...
OBJECTIVES: Evaluate the impact of ambient listening AI scribe technology for drafting notes on patient-reported communication and satisfaction ratings of their physician during ambulatory visits. MATERIALS AND METHODS: We conducted a pilot (April-August 2024) during which 31 physicians across multiple specialties could use an AI scribe during ambulatory visits. Patient surveys from AI-scribe supported visits were compared with pre-pilot surveys in the previous 12 months, and to 125 control physicians, following a difference-in-differences approach. Logistic regression evaluated change in the odds of receiving the highest score for 5 questions, focused on patient ratings of communication (4 items) and overall satisfaction with their physician (1 item). RESULTS: Among 31 917 surveys (7164 pilot; 24 753 control), patient ratings were high. The pre-post change in communication and satisfaction scores did not differ significantly between pilot and control physicians. However, for 3 questions (concern provider showed, explanation provider gave, and likelihood of recommending their provider), ratings increased for pilot physicians while declining for controls without reaching statistical significance. DISCUSSION: We did not find evidence of AI scribes worsening or enhancing patient experiences. Continued evaluation is warranted to ensure positive patient experiences as AI tools expand in clinical care.
Digital health technology burden and frustration among patients with multimorbidity.
Chen H, Ye J
J Am Med Inform Assoc · 2026 Jun · PMID 42334194 · Publisher ↗
OBJECTIVES: This study aimed to characterize patterns of digital health technology (DHT) use and examine the relationships between multimorbidity, DHT adoption, and user-reported frustration, with a focus on identifying...
OBJECTIVES: This study aimed to characterize patterns of digital health technology (DHT) use and examine the relationships between multimorbidity, DHT adoption, and user-reported frustration, with a focus on identifying socioeconomic and phenotypic determinants of digital health burden. MATERIALS AND METHODS: A cross-sectional analysis was conducted using nationally representative public data from Health Information National Trends Survey (HINTS) 7. Adults with at least one chronic condition were included (N = 3753). The outcomes were the number of DHTs used and frustration with digital tools. Multivariable logistic regression models were employed, adjusting for sociodemographic and clinical variables. Phenotypic subgroup analyses were conducted based on multimorbidity, DHT use, and frustration patterns. RESULTS: Among 3753 participants, 46.9% had multimorbidity. Participants with multimorbidity reported using a greater number of DHTs on average (mean = 3.9 vs 3.6, P < .001) compared to those with a single condition, yet exhibited significantly higher rates of frustration with digital tasks (61.2% vs 54.1%, P < .001). Both higher income and educational groups were associated with lower odds of frustration. Greater DHT use was also independently associated with reduced frustration (OR = 0.78, 95% CI: 0.71-0.87, P < .01). Phenotypic subgroup analysis further identified individuals with multimorbidity and low DHT versatility as the most vulnerable profile, characterized by older age, lower socioeconomic status, and the highest frustration prevalence (60.3%). CONCLUSION: While individuals with multimorbidity use more DHTs, they experience greater frustration, particularly those with lower socioeconomic status. However, higher engagement with DHTs (as measured by number of technology types adopted) is associated with lower frustration, suggesting that technology proficiency may mitigate burden. Targeted, equity-conscious interventions, including competency-based digital literacy programs, simplified user-centered design, and structural supports addressing device access and connectivity, are needed to reduce digital health burden and improve outcomes for patients living with multiple chronic conditions.
Benchmarking information extraction of physical activity from electronic health record with large language models: an natural language processing pipeline and comparative evaluation.
Yang H, Niu Z, Li M … +9 more , Zhou H, Xiao Y, Zhou S, Zhan Z, Liu Y, Liu S, Tignanelli CJ, Melton GB, Zhang R
J Am Med Inform Assoc · 2026 Jun · PMID 42329045 · Publisher ↗
OBJECTIVES: We aimed to develop a data model and a natural language processing (NLP) pipeline for representing physical activity (PA) in Electronic Health Records (EHRs), and to evaluate transformer- and Large Language M...
OBJECTIVES: We aimed to develop a data model and a natural language processing (NLP) pipeline for representing physical activity (PA) in Electronic Health Records (EHRs), and to evaluate transformer- and Large Language Model (LLM)-based classifiers for sentence-level PA attribute classification. MATERIALS AND METHODS: We analyzed PA documentation across three patient cohorts (cancer, COVID, and Alzheimer's disease) using structured and unstructured EHR data. A conceptual schema was developed to represent PA and its linguistic attributes. Five BERT models and three modern LLMs (Llama3-8B, MedAlpaca-13B, and PMC-Llama-13B) were evaluated for classifying PA attributes (binary status, negation, exclusion, and an eleven-class Category) on pre-extracted PA-related sentences. RESULTS: Clinical notes were a richer source of PA information than structured ICD or SDoH data. On binary tasks, the best BERT model reached F1 0.619 (Exclusion); with Supervised Fine-Tuning (SFT), Llama3-8B reached F1 0.689 (Exclusion). On the 11-class Category task, performance was modest (best macro-F1 0.262, ROC-AUC 0.803, by Llama3-8B). DISCUSSION: In-Context Learning (ICL) was highly variable: while Llama3-8B-ICL achieved the best ROC-AUC on Category, the domain-specific MedAlpaca-13B and PMC-LLaMA-13B essentially failed. These results, together with sparsely represented PA elements (Amount, Frequency, Assessment) and the absence of a downstream evaluation, position this work as an initial proof of feasibility, with supervised domain adaptation still required for reliable clinical PA extraction. CONCLUSION: We contribute a PA data model, annotation schema, and a working NLP pipeline with a BERT/LLM benchmark for sentence-level PA attribute classification. The pipeline supports future end-to-end PA extraction and downstream applications such as phenotyping, risk prediction, and cohort identification.
Role of electronic health record in stigma experiences, trust, and care decisions by women with history of pregnancy and substance use disorder: a qualitative study of perceptions of clinical note language.
Davis ME, Sharma M, Ancker JS … +2 more , Pathak J, Sharko M
J Am Med Inform Assoc · 2026 Jun · PMID 42319960 · Publisher ↗
OBJECTIVES: Stigma impacts outcomes across stigmatizing conditions, including substance use disorders (SUDs). Recent policy changes give patients rapid access to clinical notes in the electronic health record (EHR), whic...
OBJECTIVES: Stigma impacts outcomes across stigmatizing conditions, including substance use disorders (SUDs). Recent policy changes give patients rapid access to clinical notes in the electronic health record (EHR), which may include stigmatizing language. The objective of this study was to assess the perspectives of women with history of pregnancy and SUDs on typical language used in clinical notes. MATERIALS AND METHODS: Women with a history of pregnancy and SUD were recruited through an online crowd-sourcing platform. Respondents viewed examples of clinical language and answered survey questions about perceived stigma. An inductive approach was used to analyze open-text responses, and themes were developed. RESULTS: Three hundred seventy survey respondents wrote a response to at least one open-text question. Thematic analysis yielded 4 major themes: (1) anticipation of future stigma facilitated by EHR documentation can affect patients' care decisions for themselves and their babies; (2) documented SUD history could have short- and long-term effects on patients' experience of stigma and discrimination, especially in labor and delivery; (3) phrases using "denies" and quotes within quotation marks could be perceived as stigmatizing and decrease trust in providers; (4) nonstigmatizing language and acknowledgement of recovery in notes can facilitate positive experiences for patients, but patients want more acknowledgement of recovery and positive language. CONCLUSION: Electronic health record documentation can modulate stigma experiences for women during and after pregnancy through stigmatizing language in clinical notes and facilitating discrimination, decreasing trust in providers and negatively impacting health outcomes. Raising providers' awareness of nonstigmatizing and positive language or implementing technology to prompt nonstigmatizing terminology could contribute to positive experiences among women with a history of pregnancy and SUD.
OMOP common data model transformation: leveraging a nationwide.
Haderlein TP, Der-Martirosian C, Bensken WP … +1 more , Schuff R
J Am Med Inform Assoc · 2026 Jun · PMID 42319147 · Publisher ↗
OBJECTIVE: To demonstrate a large-scale EHR data transformation to the Observational Medical Outcomes Partnership (OMOP) Common Data model in the OCHIN network to support AI/ML analyses within the AIM-AHEAD national rese...
OBJECTIVE: To demonstrate a large-scale EHR data transformation to the Observational Medical Outcomes Partnership (OMOP) Common Data model in the OCHIN network to support AI/ML analyses within the AIM-AHEAD national research consortium. We highlight customized workflows and infrastructure development processes designed to support OCHIN database use by AI/ML researchers of varied academic backgrounds and skillsets. MATERIALS AND METHODS: Automated and manual mappings were used to ingest and transform OCHIN's i2b2-formatted database to the OMOP Common Data Model. RESULTS: 360 million encounters across 10+ million OCHIN patients were mapped over the course of a single calendar year, with custom concepts created to represent social drivers of health. DISCUSSION: The successful transformation of the OCHIN Research Data Warehouse benefitted from incorporating both customized and legacy data workflows. CONCLUSION: OCHIN's efforts will facilitate parallel analyses across AIM-AHEAD datasets and support AI/ML model representativeness of affected populations.
Synthesized annotation guidelines are knowledge-lite boosters for clinical information extraction.
Hsu E, Ugbala M, Kookal KK … +4 more , Zouaidi K, Rider NL, Walji MF, Roberts K
J Am Med Inform Assoc · 2026 Jun · PMID 42315965 · Publisher ↗
OBJECTIVE: Generative information extraction using large language models (LLMs), particularly through prompting combined with few-shot learning, has become a popular method. In many ways such prompts with examples resemb...
OBJECTIVE: Generative information extraction using large language models (LLMs), particularly through prompting combined with few-shot learning, has become a popular method. In many ways such prompts with examples resemble the annotation guidelines long used for manual labeling of data for information extraction, and indeed studies have demonstrated the direct use of these guidelines as effective prompts. However, constructing annotation guidelines is both labor- and knowledge-intensive. Instead, this paper proposes to leverage LLMs' impressive ability to automatically create such annotation guidelines. MATERIALS AND METHODS: Specifically, we propose a zero-shot hierarchical prompt engineering method that harvests the knowledge summarization and text generation capacity of LLMs to synthesize annotation guidelines to improve downstream LLMs while requiring minimal human input. RESULTS: Zero-shot clinical named entity recognition benchmarks, 2012 i2b2 EVENT, 2012 i2b2 TIMEX, 2014 i2b2, and 2018 n2c2 showed improvements of 0.2% to 25.86% for Llama 3.1 and 5.82% to 16.13% for GPT-OSS in strict F1 scores from the no-guideline baseline. The LLM-synthesized guidelines showed equivalent or better performance compared to human-written guidelines by 0.23% to 10.00% in most tasks. DISCUSSION: LLMs generate high-quality annotation guidelines following a consistent pattern (eg, title, entity types, examples) without human guidance, indicating that a representation of such a concept has been encoded during the pre-training. Nuances in definitions, however, still require adjustment by researchers to align with the project. CONCLUSION: This study proposes a novel hierarchical prompt engineering method that requires minimal knowledge transfer from a human expert and is applicable to multiple biomedical domains.
Prospectively evaluating the environmental impacts of digital health applications: a case study and recommendations.
Morand C, Névéol A, Tsopra R … +4 more , Tropeano AI, de Chambine S, Klinguer C, Ligozat AL
J Am Med Inform Assoc · 2026 Jun · PMID 42315963 · Publisher ↗
OBJECTIVES: To leverage the evaluation of the environmental impact of the Direct AP-HP/Lorah e-referral service offered in Paris (France) hospitals to create recommendations for evaluating the impact of digital health se...
OBJECTIVES: To leverage the evaluation of the environmental impact of the Direct AP-HP/Lorah e-referral service offered in Paris (France) hospitals to create recommendations for evaluating the impact of digital health services. MATERIALS AND METHODS: We review the tools and methods currently available to measure the carbon footprint and electricity consumption of digital services in the context of Life Cycle Assessment (LCA) for a comprehensive evaluation. We use the recent deployment of a telemedicine communication service at a major French hospital as a case study to understand the practical implications of conducting an impact study. Three-deployment scenarii are considered: current usage, double usage and maximum capacity. RESULTS: The bulk of the carbon footprint of the Direct AP-HP/Lorah service is due to servers vs network and user terminals in all scenarios considered. Computing hardware production impacts was instrumental in the overall impact assessment, as embodied impact represent 45% of Carbon footprint and the most of Metallic resource depletion. Recommendations for further studies notably include adequate anticipation of service usage and data collection. DISCUSSION: The environmental impact of the new telemedicine service could be assessed in sufficient level of details to provide decision makers with an adequate comparison of the service with alternative email communication. CONCLUSION: The recommendations derived from this use case should facilitate adequate impact data collection for future studies.
Translation readiness of model-based synthetic tabular data in healthcare: a systematic review and governance audit.
Castagno S, Subramanian A, Epanomeritakis IE … +5 more , Gompels B, McDonnell S, Birch M, van der Schaar M, McCaskie A
J Am Med Inform Assoc · 2026 Jun · PMID 42315134 · Publisher ↗
OBJECTIVES: To evaluate the clinical applications and translation readiness of model-based synthetic tabular data in healthcare, and identify gaps in governance reporting that may hinder translation. MATERIALS AND METHOD...
OBJECTIVES: To evaluate the clinical applications and translation readiness of model-based synthetic tabular data in healthcare, and identify gaps in governance reporting that may hinder translation. MATERIALS AND METHODS: We systematically searched Ovid MEDLINE and Embase (2010-August 2025; PROSPERO: CRD42025635514) for studies that generated and applied model-based synthetic tabular data in clinical contexts. Screening used a "human-in-the-loop" large language model workflow alongside independent manual review, achieving 100% sensitivity for included studies. Unlike prior reviews focused primarily on evaluation methodology, we mapped use-cases and deployment paradigms, and audited translation-readiness reporting using a predefined governance framework (validation depth, privacy, fairness, regulatory alignment). RESULTS: Thirty-seven studies (2019-2025) were included. GANs predominated; other approaches included VAEs, diffusion models, LLM-based synthesis, and Bayesian networks. Dataset augmentation was the primary application, often improving downstream model performance for rare outcomes. Emerging applications included synthetic control cohorts and algorithmic bias mitigation. Translation-readiness reporting was limited: 34/37 studies (92%) relied solely on internal validation, 9/37 (24%) used formal privacy models, 6/37 (16%) reported explicit fairness evaluations, and 6/37 (16%) addressed regulatory alignment. Few studies distinguished "no-release" from "delayed-release" paradigms. DISCUSSION: A systemic gap exists between methodological innovation and deployment-readiness reporting. Model-based synthetic data show clear value for augmentation and class balancing, but inconsistent reporting of validation, privacy, fairness, and regulatory considerations limits confidence in clinical deployment. CONCLUSION: We propose TRUST-SD (Transparency and Reporting for Utility, Safety, and Translation of Synthetic Data), an author-derived, preliminary, evidence-informed reporting checklist spanning 7 domains, as a starting point for community refinement and consensus-building.
GAT-BiGRU: explainable multi-task temporal graph learning for glucose forecasting, hypoglycemia risk, and counterfactual insulin adjustment.
Sarwar MA, Maqsood S, Belousovienė E … +1 more , Maskeliūnas R
J Am Med Inform Assoc · 2026 Jun · PMID 42314749 · Publisher ↗
BACKGROUND: People with type 1 diabetes mellitus (T1DM) show glucose variability driven by insulin dosing, meals, activity, and circadian rhythms. Many deep learning approaches treat glucose forecasting and hypoglycemia...
BACKGROUND: People with type 1 diabetes mellitus (T1DM) show glucose variability driven by insulin dosing, meals, activity, and circadian rhythms. Many deep learning approaches treat glucose forecasting and hypoglycemia detection as separate tasks and provide limited transparency. OBJECTIVE: We developed an explainable, multi-task temporal graph framework that jointly predicts glucose trajectories and hypoglycemia risk at 30 and 60 minute horizons, and provides bounded, patient-specific insulin adjustment recommendations. METHODS: Temporal GAT-BiGRU transforms multimodal continuous glucose monitoring (CGM) time series into a temporal k-neighborhood graph, with each time point represented as a feature-enriched node. A graph-attention encoder performs multi-head message passing over history edges, while an attention-based BiGRU captures longer dependencies. We evaluated OhioT1DM and BrisT1D using hypoglycemia and predicted Time in Range (TIR) metrics. A prediction-driven counterfactual module retrospectively generates bounded basal/bolus adjustments using patient-specific Insulin-to-Carbohydrate Ratio (ICR) and Insulin Sensitivity Factor (ISF); interpretability is supported via GNNExplainer. RESULTS: On OhioT1DM, Temporal GAT-BiGRU achieved hypoglycemia precision-recall area under the curve (PR-AUC) 0.93, mean absolute error (MAE) 9.40 mg/dL, root mean square error (RMSE) 15.8 mg/dL, mean absolute relative difference (MARD) 6.01%, and predicted TIR 71.39%. On BrisT1D, performance remained strong with PR-AUC 0.98, MAE 9.36 mg/dL, RMSE 15.3 mg/dL, MARD 7.55%, and predicted TIR 64.78%. The insulin module generated bounded, subject-specific recommendations, typically suggesting ∼10% basal increases with individualized meal-bolus updates. CONCLUSIONS: Temporal GAT-BiGRU provides accurate glucose prediction through temporal graph reasoning, sequence modeling, and interpretable explanations. It supports personalized decision support and closed-loop glucose management systems.
About
- Frequency
- Sun
- Papers found
- 200
- RSS feed
- Subscribe