Search AMIA.org

We help identify subpopulations underrepresented in randomized clinical trials (RCTs) cohorts with respect to national, community-based or health system target populations by formulating population representativeness of RCTs as a machine learning (ML) fairness problem, deriving new representation metrics, and deploying them in easy-to-understand interactive visualization tools.

Patient-generated health data (PGHD) are important for tracking and monitoring out of clinic health events and supporting shared clinical decisions. Unstructured text as PGHD (eg, medical diary notes and transcriptions) may encapsulate rich information through narratives which can be critical to better understand a patient's condition. We propose a natural language processing (NLP) supported data synthesis pipeline for unstructured PGHD, focusing on children with special healthcare needs (CSHCN), and demonstrate [...]

We sought to cluster biological phenotypes using semantic similarity and create an easy-to-install, stable, and reproducible tool.

To characterize challenges and strategies related to algorithmic risk scoring for care management eligibility determinations.

Social determinants of health (SDH), key contributors to health, are rarely systematically measured and collected in the electronic health record (EHR). We investigate how to leverage clinical notes using novel applications of multi-label learning (MLL) to classify SDH in mental health and substance use disorder patients who frequent the emergency department.

Persons with multiple sclerosis (MS) can face a number of potential healthcare-related barriers, for which mobile health (mHealth) technology can be potentially beneficial. This review aimed to understand the frequency, current uses, and potential barriers with mHealth usage among persons with MS.

We developed COVID-19 Outbreak Simulator (https://ictr.github.io/covid19-outbreak-simulator/) to quantitatively estimate the effectiveness of preventative and interventive measures to prevent and battle COVID-19 outbreaks for specific populations.

Healthcare systems suffer from a lack of interoperability that creates "data silos," causing patient linkage and data sharing problems. Blockchain technology's unique architecture provides individuals greater control over their information and may help address some of the problems related to health data. A multidisciplinary team designed and tested a blockchain application, MediLinker, as a patient-centric identity management system.

Real-time locating systems (RTLS) enable contact tracing and hand hygiene reminders, to improve hospital safety. Successful implementation requires healthcare personnel (HCP) to carry RTLS tags continuously. We assessed for determinants of HCP's willingness to use RTLS tags during routine inpatient care, and evaluated concerns using mixed-methods analysis.

In service of particularly vulnerable populations, safety net healthcare systems must nimbly leverage health information technology (IT), including electronic health records (EHRs), to coordinate the medical and public health response to the novel coronavirus (COVID-19). Six months after the San Francisco Department of Public Health implemented a new EHR across its hospitals and citywide clinics, California declared a state of emergency in response to COVID-19. This paper describes how the [...]