Search AMIA.org

The study sought to characterize the evaluation of patients who present following detection of an abnormal pulse using Apple Watch.

Machine learning models trained on electronic health records have achieved high prognostic accuracy in test datasets, but little is known about their embedding into clinical workflows. We implemented a random forest-based algorithm to identify hospitalized patients at high risk for delirium, and evaluated its performance in a clinical setting.

This review summarizes past and current informatics activities at the Centers for Disease Control and Prevention National Program of Cancer Registries to inform readers about efforts to improve, standardize, and automate reporting to public health cancer registries.

The 2019 novel coronavirus disease (COVID-19) outbreak progressed rapidly from a public health (PH) emergency of international concern (World Health Organization [WHO], 30 January 2020) to a pandemic (WHO, 11 March 2020). The declaration of a national emergency in the United States (13 March 2020) necessitated the addition and modification of terminology related to COVID-19 and development of the disease's case definition. During this period, the Centers for Disease Control [...]

The genetic testing for hereditary breast cancer that is most helpful in high-risk women is underused. Our objective was to quantify the risk factors for heritable breast and ovarian cancer contained in the electronic health record (EHR), to determine how many women meet national guidelines for referral to a cancer genetics professional but have no record of a referral.

Effective, scalable de-identification of personally identifying information (PII) for information-rich clinical text is critical to support secondary use, but no method is 100% effective. The hiding-in-plain-sight (HIPS) approach attempts to solve this "residual PII problem." HIPS replaces PII tagged by a de-identification system with realistic but fictitious (resynthesized) content, making it harder to detect remaining unredacted PII.

Crowdsourced ratings have driven increased performance transparency between consumers and suppliers. While many industries have benefitted from such transparency, crowdsourced ratings have struggled to scale in the healthcare domain. In theory, interoperability services offer an ideal setting for crowdsourced ratings: costs are high, performance is variable, and information asymmetries between provider organizations (customers) and vendors offering interoperability solutions exist. Via a Cooperative Agreement between the Office of the National Coordinator [...]

We sought to predict if patients with type 2 diabetes mellitus (DM2) would develop 10 selected complications. Accurate prediction of complications could help with more targeted measures that would prevent or slow down their development.