Search AMIA.org

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.

Synthetic data may provide a solution to researchers who wish to generate and share data in support of precision healthcare. Recent advances in data synthesis enable the creation and analysis of synthetic derivatives as if they were the original data; this process has significant advantages over data deidentification.

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.

Laboratory Information Systems (LIS) and data visualization techniques have untapped potential in anatomic pathology laboratories. Pre-built functionalities of LIS do not address all the needs of a modern histology laboratory. For instance, "Go live" is not the end of LIS customization, but just the beginning. After closely evaluating various histology lab workflows, we implemented several custom data analytics dashboards and additional LIS functionalities to monitor and address weaknesses. Herein, we [...]

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.

We developed a mobile application and secure patient data storage platform, FDA MyStudies, to address privacy, engagement, and extensibility challenges in mobile clinical research. The system extends the capabilities of the mobile frameworks Apple ResearchKit and ResearchStack through an intuitive front-end application and secure storage environment that can support health research studies. The platform supports single or multisite studies via role-based access and can be implemented within highly secure data [...]

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 [...]

The UK Biobank (UKB) is making primary care electronic health records (EHRs) for 500 000 participants available for COVID-19-related research. Data are extracted from four sources, recorded using five clinical terminologies and stored in different schemas. The aims of our research were to: (a) develop a semi-supervised approach for bootstrapping EHR phenotyping algorithms in UKB EHR, and (b) to evaluate our approach by implementing and evaluating phenotypes for 31 common biomarkers.

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.

Accurate estimations of the seroprevalence of antibodies to severe acute respiratory syndrome coronavirus 2 need to properly consider the specificity and sensitivity of the antibody tests. In addition, prior knowledge of the extent of viral infection in a population may also be important for adjusting the estimation of seroprevalence. For this purpose, we have developed a Bayesian approach that can incorporate the variabilities of specificity and sensitivity of the antibody [...]