Researchers have used machine learning, a type of artificial intelligence, to develop a prediction model for the early diagnosis of opioid use disorder. The advance is described in Pharmacology Research & Perspectives. The model was generated from information in a commercial claim database from 2006 through 2018 of 10 million medical insurance claims from 550,000 patient records. It relied on data such as demographics, chronic conditions, diagnoses and procedures, and medication prescriptions. The tool led to a diagnosis of opioid use disorder that was on average 14.4 months earlier than it was diagnosed clinically.

Researchers have used machine learning, a type of artificial intelligence, to develop a prediction model for the early diagnosis of opioid use disorder.

Following is a transcript of the video. Rishab Jain: It all started in the summer of 2017 when I went to visit my brother in Boston, and there I learned about some research that was happening, and the surprisingly low statistics about pancreatic cancer, like its survival rate. My name is Rishab Jain. I'm in 8th grade, 13 years old, from Portland, Oregon, and I created an artificial intelligence-based tool called PCDLS Net to improve pancreas tracking during a treatment called radiotherapy for pancreatic cancer. The five-year survival rate of pancreatic cancer is around 9%, and the 10-year survival rate is around 1%, which is extremely low, and these survival rates have not improved significantly in the past 40 years, so currently, pancreatic cancer is detected in a late stage, and by then, doctors try to use radiotherapy to help treat it, but most of the time, it's not effective enough, so I got inspired to do some research on this because I'm a big programmer, and I like artificial intelligence, so I wondered if I could combine my knowledge in the two areas to help solve the problem, and I created an artificial intelligence-based tool called PCDLS Net to improve pancreas tracking during a treatment called radiotherapy for pancreatic cancer.