Researchers combined the Columbia Suicide Severity Rating Scale, a six-item questionnaire, with the Vanderbilt Suicide Attempt and Ideation Likelihood, a machine learning algorithm, to analyze 120,398 patient visits from June 2019 to September 2020.
For every patient visit, the algorithm generated risk scores based on information in the patient’s EHR.
Researchers found that suicide predictions improved when these two methods were combined.
“Results of our study show integrating clinician-led screening with algorithms improves suicide attempt prediction — even if those algorithms were never trained with face-to-face screening in the first place,” said Drew Wilimitis, statistical analyst at Vanderbilt University Medical Center. “This study is a perfect example of the idea that smart humans plus machines are better than either one alone.”
