Search AMIA.org

Prediction of post-transplant health outcomes and identification of key factors remain important issues for pediatric transplant teams and researchers. Outcomes research has generally relied on general linear modeling or similar techniques offering limited predictive validity. Thus far, data-driven modeling and machine learning (ML) approaches have had limited application and success in pediatric transplant outcomes research. The purpose of the current study was to examine ML models predicting post-transplant hospitalization in [...]

Patient information can be retrieved more efficiently in electronic medical record (EMR) systems by using machine learning models that predict which information a physician will seek in a clinical context. However, information-seeking behavior varies across EMR users. To explicitly account for this variability, we derived hierarchical models and compared their performance to nonhierarchical models in identifying relevant patient information in intensive care unit (ICU) cases.

The study aimed to develop simplified diagnostic models for identifying girls with central precocious puberty (CPP), without the expensive and cumbersome gonadotropin-releasing hormone (GnRH) stimulation test, which is the gold standard for CPP diagnosis.

Observational medical databases, such as electronic health records and insurance claims, track the healthcare trajectory of millions of individuals. These databases provide real-world longitudinal information on large cohorts of patients and their medication prescription history. We present an easy-to-customize framework that systematically analyzes such databases to identify new indications for on-market prescription drugs.

Expert abstraction of acute toxicities is critical in oncology research but is labor-intensive and variable. We assessed the accuracy of a natural language processing (NLP) pipeline to extract symptoms from clinical notes compared to physicians.

A common research task in COVID-19 studies often involves the prevalence estimation of certain medical outcomes. Although point estimates with confidence intervals are typically obtained, a better approach is to estimate the entire posterior probability distribution of the prevalence, which can be easily accomplished with a standard Bayesian approach using binomial likelihood and its conjugate beta prior distribution. Using two recently published COVID-19 data sets, we performed Bayesian analysis to [...]

We developed an application (https://rush-covid19.herokuapp.com/) to aid US hospitals in planning their response to the ongoing Coronavirus Disease 2019 (COVID-19) pandemic.

Learning health systems that conduct embedded research require infrastructure for the seamless adoption of clinical interventions; this infrastructure should integrate with electronic health record (EHR) systems and enable the use of existing data. As purchasers of EHR systems, and as critical partners, sponsors, and consumers of embedded research, healthcare organizations should advocate for EHR system functionality and data standards that will increase the capacity for embedded research in clinical settings [...]

Electronic health record (EHR) optimization has been identified as a best practice to reduce burnout and improve user satisfaction; however, measuring success can be challenging. The goal of this manuscript is to describe the limitations of measuring optimizations and opportunities to combine assessments for a more comprehensive evaluation of optimization outcomes. The authors review lessons from 3 U.S. healthcare institutions that presented their experiences and recommendations at the American Medical [...]

Event notification systems are an approach to health information exchange (HIE) that notifies end-users of patient interactions with the healthcare system through real-time automated alerts. We examined associations between organizational capabilities and perceptions of event notification system use.