A Washington State University initiative helped a Spokane home health care agency ensure its patients’ medication lists were in proper order and reduced hospitalizations of high-risk heart-failure patients by more than half over a 10-week period.

Doctors often must make critical decisions in minutes, relying on incomplete information. While electronic health records contain vast amounts of patient data, much of it remains difficult to interpret quickly—especially for patients with rare diseases or unusual symptoms. Now, researchers at the Icahn School of Medicine at Mount Sinai and collaborators have developed an artificial intelligence system, called InfEHR, that links unconnected medical events over time, creating a diagnostic web that reveals hidden patterns. Published in the September 26 online issue of Nature Communications, the study shows that Inference on Electronic Health Records (InfEHR) transforms millions of scattered data points into actionable, patient-specific diagnostic insights.

Iron-deficiency anemia is a common condition marked by tiredness, headaches or ice cravings. But the oral iron supplements used to treat it can leave behind excess iron that causes inflammation and an upset stomach. A new supplement reported in ACS Applied Materials & Interfaces combines iron, prebiotics and probiotics. In trials, the treatment successfully restored blood iron levels in anemic mice without initiating an inflammatory response or throwing off the balance of the gut microbiota.