To develop ECG-FM, an open-weight foundation model for electrocardiogram (ECG) analysis, rigorously evaluate its performance on clinically salient tasks, and openly release it alongside a public benchmark.
Author(s): McKeen, Kaden, Masood, Sameer, Toma, Augustin, Rubin, Barry, Wang, Bo
DOI: 10.1093/jamiaopen/ooaf122
To develop a more accurate fall prediction model within the Veterans Health Administration.
Author(s): Hoover, Peter J, Blumke, Terri L, Ware, Anna D, Pillai, Malvika, Veigulis, Zachary P, Curtin, Catherine M, Osborne, Thomas F
DOI: 10.1093/jamiaopen/ooaf116
Acute chest pain is a common presentation in the emergency department, characterized by sudden onset with high morbidity and mortality. Traditional diagnostic methods, such as computed tomography (CT) and CT angiography (CTA), are often time-consuming and fail to meet the urgent need for rapid triage in emergency settings.
Author(s): Tang, Jun, Chen, Fang, Wu, Dongdong
DOI: 10.1093/jamiaopen/ooaf114
To share findings of a quality improvement initiative to capture employment status in the electronic medical record (EMR) to mitigate the potential impact of work loss on the health of patients by utilizing the results to identify eligible individuals for resources to assist return-to-work efforts.
Author(s): Breeher, Laura E, Westphal, Samantha, Green, Tammy, Abbas, Alzhraa, Cowl, Clayton T
DOI: 10.1093/jamiaopen/ooaf108
Large language models (LLMs) face challenges in inductive thematic analysis, a task requiring deep interpretive, domain-specific expertise. We evaluated the feasibility of using LLMs to replicate expert-driven thematic analysis of social media data.
Author(s): Hairston, JaMor, Ranjan, Ritvik, Lakamana, Sahithi, Spadaro, Anthony, Bozkurt, Selen, Perrone, Jeanmarie, Sarker, Abeed
DOI: 10.1093/jamiaopen/ooaf102
To develop a natural language processing (NLP) pipeline for unstructured electronic health record (EHR) data to identify symptoms and functional impacts associated with Long COVID in children.
Author(s): Bunnell, H Timothy, Reedy, Cara, Lorman, Vitaly, Jhaveri, Ravi, Rivera-Sepulveda, Andrea, Salamon, Katherine S, Patel, Payal B, Morse, Keith E, Davenport, Mattina A, Cowell, Lindsay G, Utidjian, Levon, Christakis, Dimitri A, Rao, Suchitra, Sills, Marion R, Case, Abigail, Mendonca, Eneida A, Taylor, Bradley W, Rutter, Jacqueline, Martinez, Aaron Thomas, Letts, Rebecca, Bailey, L Charles, Forrest, Christopher B, ,
DOI: 10.1093/jamiaopen/ooaf089
Type 2 diabetes (T2D) is a growing public health burden with persistent racial and ethnic disparities. . This study assessed the completeness of social determinants of health (SdoH) data for patients with T2D in Epic Cosmos, a nationwide, cross-institutional electronic health recors (EHR) database.
Author(s): Kukhareva, Polina V, O'Brien, Matthew J, Malone, Daniel C, Kawamoto, Kensaku, Gouripeddi, Ramkiran, Reddy, Deepika, Zhang, Mingyuan, Deshmukh, Vikrant G, Danks, David, Facelli, Julio C
DOI: 10.1093/jamiaopen/ooaf095
Assess time impact and provider perception of AI-generated encounter summaries.
Author(s): Silberlust, Jared, Solanki, Priyanka, Stevens, Elizabeth R, Genes, Nicholas, Lim, Edward, Sun, Kevin, Lewis, Marisa, Testa, Paul, Szerencsy, Adam
DOI: 10.1093/jamiaopen/ooaf096
Severe maternal morbidity and mortality are higher in the United States than in other high-income countries, and unacceptable disparities persist. To facilitate research on these outcomes, we developed a standardized approach for extracting perinatal data from electronic health records (EHRs).
Author(s): Stuebe, Alison M, Blanco, Randall, Horvath, Michael, Kibria, Mohammad Golam, Kucirka, Lauren, Shieh, Karl, Page, David, Gurcan, Metin N, Ed Hammond, William
DOI: 10.1093/jamiaopen/ooaf117
This study evaluates the performance of 7 synthetic data generation (SDG) methods-synthpop, avatar, copula, copulagan, ctgan, tvae, and the large language models-based tabula-for supporting pharmacogenetics (PGx) research.
Author(s): Miletic, Marko, Bollinger, Anna, Allemann, Samuel S, Sariyar, Murat
DOI: 10.1093/jamiaopen/ooaf107