AI can make better clinical decisions than humans


Type I Error Rate (SMD = 0) and Power (SMD = 1 to 5) Across Standardized Mean Differences for Each Method of Analysis Note. CDC: conservative dual-criteria, SGD: stochastic gradient descent, SVC: support vector classifier, SMD: standardized mean difference. Credit: DOI: 10.1002/jaba.863
Type I Error Rate (SMD = 0) and Power (SMD = 1 to 5) Across Standardized Mean Differences for Each Method of Analysis Note. CDC: conservative dual-criteria, SGD: stochastic gradient descent, SVC: support vector classifier, SMD: standardized mean difference. Credit: DOI: 10.1002/jaba.863

It's an old adage and there is no harm in getting a second opinion. But what if that second opinion could be generated by a computer, using artificial intelligence? Would it come up with better treatment recommendations than your professional proposes? A pair of Canadian mental-health researchers believe it can.


In a study published in the Journal of Applied Behavior Analysis, Marc Lanovaz of Université de Montréal and Kieva Hranchuk of St. Lawrence College, in Ontario, make a case for using AI in treating behavioral problems.


Lanovaz, an associate professor who heads the Applied Behavioral Research Lab at UdeM's School of Psychoeducation said, medical and educational professionals frequently disagree on the effectiveness of behavioral interventions, which may cause people to receive inadequate treatment.


To find a better way, Lanovaz and Hranchuk, a professor of behavioral science and behavioral psychology at St. Lawrence, compiled simulated data from 1,024 individuals receiving treatment for behavioral issues. The researchers then compared the treatment conclusions drawn in each case by five doctoral-level behavior analysts with those produced by a computer model the two academics developed using machine learning.


Lanovaz said, the five professionals only came to the same conclusions approximately 75 percent of the time. More importantly, machine learning produced fewer decision-making errors than did all the professionals. Given these very positive results, the next step would be to integrate our models in an app that could automatically make decisions or provide feedback about how the treatment is progressing.


The goal, the researchers believe, should be to use machine learning to facilitate the work of professionals, not actually replace them, while also making treatment decisions more consistent and predictable.


Lanovaz said, for example, doctors could someday use the technology to help them decide whether to continue or terminate the treatment of people with disorders as varied as autism, ADHD, anxiety, and depression. Individualized clinical and educational decision-making is one of the cornerstones of psychological and behavioral treatment. Our study may thus lead to better treatment options for the millions of individuals who receive these types of services worldwide.


Journal Information: Marc J. Lanovaz et al, Machine learning to analyze single‐case graphs: A comparison to visual inspection, Journal of Applied Behavior Analysis (2021). DOI: 10.1002/jaba.863

2 views0 comments

Recent Posts

See All