Search AMIA.org

[This corrects the article DOI: 10.1093/jamiaopen/ooac073.].

One challenge that arises when analyzing mobile health (mHealth) data is that updates to the proprietary algorithms that process these data can change apparent patterns. Since the timings of these updates are not publicized, an analytic approach is necessary to determine whether changes in mHealth data are due to lifestyle behaviors or algorithmic updates. Existing methods for identifying changepoints do not consider multiple types of changepoints, may require prespecifying the [...]

To evaluate the feasibility, accuracy, and interoperability of a natural language processing (NLP) system that extracts diagnostic assertions of pneumonia in different clinical notes and institutions.

In case of sudden-onset disasters (SODs), the World Health Organization deploys specialized emergency medical teams (EMTs); yet, the coordination and operation of such teams pose significant challenges. One issue is the lack of digital information systems and standards. We developed a highly customizable and scalable electronic medical record (EMR) system, tailored to EMT requirements, called the "Emergency Medical Team Operating System" (EOS). EOS was successfully tested through 9 realistic clinical [...]

[This corrects the article DOI: 10.1093/jamiaopen/ooac036.].

Hypertension has long been recognized as one of the most important predisposing factors for cardiovascular diseases and mortality. In recent years, machine learning methods have shown potential in diagnostic and predictive approaches in chronic diseases. Electronic health records (EHRs) have emerged as a reliable source of longitudinal data. The aim of this study is to predict the onset of hypertension using modern deep learning (DL) architectures, specifically long short-term memory [...]

Despite smartphone ownership becoming ubiquitous, it is unclear whether and where disparities persist in experience using health apps. In 2 diverse samples of adults with type 2 diabetes collected 2017-2018 and 2020-2021, we examined adjusted disparities in smartphone ownership and health app use by age, gender, race, education, annual household income, health insurance status, health literacy, and hemoglobin A1c. In the earlier sample (N = 422), 87% owned a smartphone and 49% [...]

To develop a free, vendor-neutral software suite, the American College of Radiology (ACR) Connect, which serves as a platform for democratizing artificial intelligence (AI) for all individuals and institutions.

To demonstrate the utility of growthcleanr, an anthropometric data cleaning method designed for electronic health records (EHR).

To carry out exhaustive data-driven computations for the performance of noninvasive vital signs heart rate (HR), respiratory rate (RR), peripheral oxygen saturation (SpO2), and temperature (Temp), considered both independently and in all possible combinations, for early detection of sepsis.