Artificial intelligence might help increase the chance that people with risky drinking patterns or alcohol use disorder (AUD) will get the outreach and support they need. This is important because only 10% of people with AUD get help each year. In a new study, U-M researchers used a natural language processing tool to analyze the full text of notes, comments, and screening scores in anonymous electronic primary care health records of 133,000 patients. While traditional methods suggested 820 of the patients had risky alcohol use or AUD, the AI tool identified more than 47,500 other patients whose records showed some sign of risky drinking.
