Search AMIA.org

This study aims to develop and evaluate a trustworthy and ethical-by-design machine learning (ML) framework for predicting 5-year cancer survival across 10 Surveillance, Epidemiology, and End Results (SEER) cancer types. We assessed ML model(s) performance across localized, regional, and distant stages while examining ML fairness, ML explainability, and the added value of social determinants of health (SDOH) as features. The goal is to advance clinically interpretable and equity-centered survival prediction [...]

To develop a large-language-model (LLM)-centric workflow flow extraction and migration of clinician-documented colonoscopy recall recommendations from unstructured reports and letters during an enterprise-wide electronic health record (EHR) transition.

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.

In the absence of standardized measures, researchers have struggled to define meaningful use of telehealth (care received via video or telephone). We evaluated a novel Telehealth Engagement Measure (TEM) that quantifies an individual's telehealth use, including telephone (TEM-t) and video (TEM-v), as a percentage of total care received.

To use bibliometric methods to deeply analyze the application of WeChat in China's mHealth field, outline its research panorama, and clarify research frontiers.

Patient portals support health management, yet enrollment remains low. This study evaluated whether timely email nudges increase patient portal enrollment compared with usual system portal invitations, whether message framing influences enrollment, and whether patients nudged to enroll go on to engage with the portal at similar rates as those who enroll organically.

Computable phenotypes derived from electronic health records (EHRs) are central to clinical research and quality reporting. Although large language models (LLMs) can extract clinically rich information from unstructured notes, routine application to all patients is computationally expensive. We evaluated whether uncertainty-guided selective use of LLMs can improve phenotyping accuracy while preserving scalability.

Patients with rare diseases often face long delays before receiving a diagnosis. Using electronic health records for automated phenotyping and diagnosis of rare diseases is a promising approach but can be challenging because critical information is often recorded in unstructured notes rather than structured fields. This systematic review synthesizes the current literature applying natural language processing (NLP) and large language models (LLMs) for rare disease phenotyping and diagnosis from clinical [...]

To examine real-world barriers to implementing federated learning in healthcare and highlight the organizational, regulatory, and socio-technical factors often overlooked in technical research.

We report on findings from a meeting convened by the American College of Medical Informatics (ACMI) to characterize aspects of the patient experience that could be improved using informatics.