American Academy of Orthopaedic Surgeons Annual Meeting

American Academy of Orthopaedic Surgeons Annual Meeting

Source:

Lu Y, et al. Paper 069. Presented at: American Academy of Orthopaedic Surgeons Annual Meeting. Aug. 31 - Sept. 3, 2021; San Diego.

Disclosures: Schwab reports no relevant financial disclosures.
September 17, 2021
1 min read
Save

Machine learning algorithm may identify patients at risk for extended opioid use

Source:

Lu Y, et al. Paper 069. Presented at: American Academy of Orthopaedic Surgeons Annual Meeting. Aug. 31 - Sept. 3, 2021; San Diego.

Disclosures: Schwab reports no relevant financial disclosures.
You've successfully added to your alerts. You will receive an email when new content is published.

Click Here to Manage Email Alerts

We were unable to process your request. Please try again later. If you continue to have this issue please contact customerservice@slackinc.com.

SAN DIEGO — Use of a machine learning algorithm may help surgeons preoperatively identify patients at high risk for extended postoperative opioid use, according to results presented here.

Joseph H. Schwab, MD, MS, and colleagues developed five machine learning algorithms to predict extended postoperative opioid consumption among 1,504 patients who underwent shoulder arthroscopy between January 2014 and October 2019. Researchers assessed performance algorithms through discrimination, calibration and decision curve analysis.

“We chose the definition of postoperative or prolonged postoperative opioid usage as someone who is using opiates greater than 150 days after surgery, and we found that 8.8% of patients met those criteria,” Schwab, director of SORG Orthopaedic Research Group in the department of orthopedics at Massachusetts General Hospital, told Healio Orthopedics about results presented at the American Academy of Orthopaedic Surgeons Annual Meeting.

Schwab noted factors most predictive of prolonged opioid use included preoperative opioid usage, median percentage of population in the patient’s ZIP code living at the federal poverty line and high BMI. Researchers found the random forest model achieved the best performance based on discrimination, calibration and decision curve analysis.

Although the researchers have integrated the model into a web-based open-access application that is able to provide predictions and explanations, Schwab noted the model still needs to be validated. He added they also want to identify the best way to integrate the model into physicians’ workflow.

“The study needs to be validated in several other different populations and then you have to figure out how to implement these models,” Schwab said. “This is probably one of the biggest impediments to the utilization of machine learning algorithms: How do they integrate into the workflow on a daily basis?”