In the study, five algorithms were trained to analyze preoperative information to screen patients for the surgery, with the models combined into an ensemble classifier. When tested on the data of several thousand patients, the classifier achieved 93.4 percent accuracy in identifying suitable candidates for the operation, a level equal to that of expert ophthalmologists and significantly more successful than other existing screening methods.
Therefore, according to the study’s authors, the machine learning method serves as an effective clinical decision support tool to screen for the surgery and could ultimately lead to a reduction in postoperative complications caused by misdiagnosis.
More articles about AI:
Change Healthcare adds AI to claims management suite to predict, prevent denials
IBM, Cloudera partner to expand data management, AI solutions
Virtual drug screening initiative will use AI to find treatments for pediatric cancers
At the Becker's 11th Annual IT + Revenue Cycle Conference: The Future of AI & Digital Health, taking place September 14–17 in Chicago, healthcare executives and digital leaders from across the country will come together to explore how AI, interoperability, cybersecurity, and revenue cycle innovation are transforming care delivery, strengthening financial performance, and driving the next era of digital health. Apply for complimentary registration now.
