Healthcare costs in the United States are soaring, with one-third of those costs being attributed to wasteful or fraudulent healthcare services. Conventional healthcare payment integrity systems lack the necessary understanding of patients, providers, and healthcare settings, making them imprecise and ineffective. To address this issue, Health at Scale has developed artificial intelligence (AI) algorithms that can identify low-value care missed by current systems. These algorithms consider historical patient information and provider practice patterns, along with up-to-date evidence and guidelines. They are intended to be used in prior authorization and claims adjudication workflows to prevent fraud and waste.
The University of Michigan Medical School, Health at Scale’s test partner, has yet to produce definitive results, but Health at Scale reports an AI response time of less than 200 milliseconds and has observed between 3% and 7% of missed spend being flagged as fraud, waste, or abuse. The accuracy of the system is attributed to the consideration of various factors, including patient and provider history, statistical similarities with other providers, and clinical nuances.
Organizations should choose a scalable anti-fraud, -waste, and -abuse system and consider additional services to maximize impact. AI and machine learning tools will likely fill this gap, providing immediate return on investment and preventing unnecessary care services, since inappropriate elective procedures contribute to rising healthcare costs and pose risks to patients. In the long-term, innovative AI-generated systems will reduce poor healthcare and protect patients from the harms of inappropriate or unnecessary services.
The ainewsarticles.com article you just read is a brief synopsis; the original article can be found here: Read the Full Article…
