Evidently Exec Argues AI Chart Review Boosts Case Mix Accuracy
In a Becker's Hospital Review commentary, Kai Romero, Head of Clinical Success at Evidently and a practicing hospice and palliative care physician, argues that critical patient history routinely goes unread in sprawling EHR charts, leaving clinicians and case mix index calculations missing key complexity. Romero cites Evidently's "Admit Note Silent Study," which compares AI-drafted admit notes built from the full chart against notes clinicians actually wrote, finding an average of four to five quality-impacting conditions omitted per note and case mix index gains as high as 0.1. The author also references a peer-reviewed University of Iowa Health Care study reporting a median of 4.5 missed conditions with 97% accuracy. Romero contends that AI-driven "Clinical Data Intelligence" tools can surface buried outside records, such as an old CT scan showing an undiagnosed aneurysm, before gaps in documentation affect both patient care and reimbursement.