Abstract
As machine learning research in the field of cardiovascular imaging continues to grow, obtaining reliable model performance estimates is critical to develop reliable baselines and compare different algorithms. While the machine learning community has generally accepted methods such as k-fold stratified cross-validation (CV) to be more rigorous than single split validation, the standard research practice in medical fields is the use of single split validation techniques. This is especially concerning given the relatively small sample sizes of datasets used for cardiovascular imaging. We aim to examine how train-test split variation impacts the stability of machine learning (ML) model performance estimates in several validation techniques on two real-world cardiovascular imaging datasets: stratified split-sample validation (70/30 and 50/50 train-test splits), tenfold stratified CV, 10 × repeated tenfold stratified CV, bootstrapping (500 × repeated), and leave one out (LOO) validation. We demonstrate that split validation methods lead to the highest range in AUC and statistically significant differences in ROC curves, unlike the other aforementioned approaches. When building predictive models on relatively small data sets as is often the case in medical imaging, split-sample validation techniques can produce instability in performance estimates with variations in range over 0.15 in the AUC values, and thus any of the alternate validation methods are recommended.
Highlights
As machine learning research in the field of cardiovascular imaging continues to grow, obtaining reliable model performance estimates is critical to develop reliable baselines and compare different algorithms
These predictions are based on analyses of both nominal and numerical risk factors/features, exported as probabilistic outputs, which serve as the basis for classification
For the stratified split-sample validation techniques across all four algorithms and in both datasets (Cedars Sinai and REFINE SPECT Registry), a comparison between the ROC curves generated for the seeds with the maximum and minimum AUC revealed statistically significant results (p < 0.05) (Tables 1, 2)
Summary
As machine learning research in the field of cardiovascular imaging continues to grow, obtaining reliable model performance estimates is critical to develop reliable baselines and compare different algorithms. While the machine learning community has generally accepted methods such as k-fold stratified cross-validation (CV) to be more rigorous than single split validation, the standard research practice in medical fields is the use of single split validation techniques. This is especially concerning given the relatively small sample sizes of datasets used for cardiovascular imaging. When building predictive models on relatively small data sets as is often the case in medical imaging, split-sample validation techniques can produce instability in performance estimates with variations in range over 0.15 in the AUC values, and any of the alternate validation methods are recommended. We aimed to examine how train-test split variation impacts the measured AUC in several validation techniques, namely: split-sample validation (70/30 and 50/50 train-test splits), bootstrap validation, tenfold stratified cross-validation (CV) and 10 × repeated tenfold stratified CV
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
