Larger sample sizes are needed when developing a clinical prediction model using machine learning in oncology: methodological systematic review
Biruk Tsegaye, Kym I E Snell, Lucinda Archer, Shona Kirtley, Richard D Riley, Matthew Sperrin, Ben Van Calster, Gary S. Collins, Paula Dhiman
Abstract
BACKGROUND AND OBJECTIVES: ). METHODS: , and compared this with the sample size that was used to develop the models. RESULTS: , allowing to precisely estimate the overall risk and minimize overfitting. There was a median deficit of 302 participants with the event (n = 17; range: -21,331 to 2298) when developing the ML models. An additional three out of the 17 studies met the required sample size to precisely estimate the overall risk only. CONCLUSION: . As ML models almost certainly require a larger sample size than regression models, the deficit is likely larger. We recommend that researchers consider and report their sample size and at least meet the minimum sample size required when developing a regression-based model.