Key result
Adding clinical data to CT radiomics ML models improves aldosterone source prediction to AUC 0.67.
Why the study?
The study aimed to investigate an integrated diagnostics approach to predict the source of aldosterone overproduction in primary hyperaldosteronism.
Does an integrated machine learning model combining clinical parameters and CT-based radiomics improve the prediction of the source of aldosterone overproduction in patients with primary hyperaldosteronism compared to radiomics alone?
Cohort (n=269)
No
Does an integrated machine learning model combining clinical parameters and CT-based radiomics improve the prediction of the source of aldosterone overproduction in patients with primary hyperaldosteronism compared to radiomics alone?
Effect estimate: ROC AUC 0.67 (95% CI 0.57-0.77)
Absolute Event Rate: 0.67% vs 0.56%
Integrating clinical parameters with CT-based radiomics in a machine learning model improves the non-invasive subtyping and lateralization of primary hyperaldosteronism compared to using radiomics alone.
May aid non-invasive subtyping in primary aldosteronism; leaves open prospective outcome validation before practice change.
Objectives: The aim of this study was to investigate an integrated diagnostics approach for prediction of the source of aldosterone overproduction in primary hyperaldosteronism (PA). Methods: 269 patients from the prospective German Conn Registry with PA were included in this study. After segmentation of adrenal glands in native CT images, radiomic features were calculated. The study population consisted of a training (n = 215) and a validation (n = 54) cohort. The k = 25 best radiomic features, selected using maximum-relevance minimum-redundancy (MRMR) feature selection, were used to train a baseline random forest model to predict the result of AVS from imaging alone. In a second step, clinical parameters were integrated. Model performance was assessed via area under the receiver operating characteristic curve (ROC AUC). Permutation feature importance was used to assess the predictive value of selected features. Results: Radiomics features alone allowed only for moderate discrimination of the location of aldosterone overproduction with a ROC AUC of 0.57 for unilateral left (UL), 0.61 for unilateral right (UR), and 0.50 for bilateral (BI) aldosterone overproduction (total 0.56, 95% CI: 0.45-0.65). Integration of clinical parameters into the model substantially improved ROC AUC values (0.61 UL, 0.68 UR, and 0.73 for BI, total 0.67, 95% CI: 0.57-0.77). According to permutation feature importance, lowest potassium value at baseline and saline infusion test (SIT) were the two most important features. Conclusion: Integration of clinical parameters into a radiomics machine learning model improves prediction of the source of aldosterone overproduction and subtyping in patients with PA.
No takes yet. Share an insight, caveat, or question.
Mansour et al. (2023) conducted a cohort in Primary hyperaldosteronism (n=269). Integrated clinical and radiomics machine learning model vs. Radiomics machine learning model alone was evaluated on Prediction of the source of aldosterone overproduction (total ROC AUC) (ROC AUC 0.67, 95% CI 0.57-0.77). Integration of clinical parameters into a CT-based radiomics machine learning model improved the prediction of the source of aldosterone overproduction, increasing the total ROC AUC from 0.56 to 0.67.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: