A clinical decision support platform using machine learning to prevent medication-related risks and errors could result in cost savings of more than $1 million, suggests a new study from Boston-based Harvard Medical School.
In the study, published in The Joint Commission Journal on Quality and Patient Safety, researchers deployed MedAware's artificial intelligence-enabled system in outpatient clinics of Massachusetts General Hospital and Brigham and Women's Hospital, both in Boston, to retrospectively flag potential errors and adverse drug events in the data of 373,992 patients.
Based on the platform's ability to identify easily overlooked medication-related errors and prevent avoidable adverse events, the researchers concluded that, over the course of the study, had it been operational, the system would have saved the hospitals an estimated $1.3 million when extrapolated to include the full patient population. More than 90 percent of the warnings generated — two-thirds of which would not have been flagged by existing decision support systems — were determined to be accurate, and nearly 80 percent were considered clinically valid.
More articles on AI:
80% of healthcare professionals say AI has decreased burnout: 3 notes
Google is developing AI to do more with 'much less data'
Houston Methodist develops AI app to help predict severity of patient falls