With new $8M, MedAware uses AI to spot preventable prescription errors

By Jonah Comstock
Share

Raannana, Israel-based MedAware, which leverages machine learning algorithms to find and eliminate dangerous prescription errors, has raised $8 million. BD (Becton, Dickinson and Company), Gefen Capital, OurCrowd and Yingcheng City Fubon Technology Company all participated in the Series A round. In addition to the $8 million in venture funds, MedAware has picked up $4 million in grants from Israel’s Innovation Authority, the BIRD Foundation, and the European Commission.

Prescription errors, where a patient is prescribed the wrong medication, are unfortunately common. According to AHRQ, 5 percent of patients will encounter an adverse drug event, and roughly half of these are preventable ADEs that stem from prescription error. MedAware continuously monitors electronic health records to spot these errors, which show up as outliers in the patterns of prescribing behavior.

“MedAware was purpose built around our commitment to patient safety,” CEO Gidi Stein said in a statement. “Every catastrophic error we identify is a patient saved. Through this round of Series A funding we will be able to build on the successes we’ve achieved to date and scale our approach to protect physicians and their patients all over the world.”

The company compares its approach to the algorithms banks use to detect and prevent credit card fraud and identity theft. In both cases, quickly spotting an aberration in a pattern can safeguard against bad outcomes before they happen.

The technology has already produced some encouraging efficacy data. In a study published in January in the Journal of American Medical Informatics Association, researchers looked at five years of EHR-provided clinical data for 747,985 lives at the Brigham and Women’s Hospital and the Center for Patient Safety and Practice, plus retrospective data from Partners HealthCare BWH and Massachusetts General Hospital.

Using MedAware, researchers got alerts for over 15,000 charts, and they then looked at a sample of 300 charts and found that 75 percent of alerts were valid in identifying potentially fatal medication errors.

With the new funding, MedAware will develop additional AI-powered clinical decision support offerings. The company also plans to improve its existing algorithms to catch more kinds of errors. Other priorities include growth in the North American market and integration with more EHRs.