Key result
Deep learning on PET polar maps outperforms logistic regression in predicting mortality with 0.82 AUC.
Why the study?
The authors aimed to develop and prospectively evaluate an explainable deep learning network to predict all-cause mortality directly from positron emission tomography myocardial perfusion imaging flow and perfusion polar map data.
Does an explainable deep learning network improve prediction of all-cause mortality compared to established methods in patients referred for stress and rest 82 Rb positron emission tomography?
Cohort (n=4,735)
Does an explainable deep learning network improve prediction of all-cause mortality compared to established methods in patients referred for stress and rest 82 Rb positron emission tomography?
Answers are grounded in this paper and cite their sources.
A deep learning model trained directly on PET polar maps significantly improves risk stratification for all-cause mortality compared to established methods.
Background: We aim to develop an explainable deep learning (DL) network for the prediction of all-cause mortality directly from positron emission tomography myocardial perfusion imaging flow and perfusion polar map data and evaluate it using prospective testing. Methods: A total of 4735 consecutive patients referred for stress and rest 82 Rb positron emission tomography between 2010 and 2018 were followed up for all-cause mortality for 4.15 (2.24–6.3) years. DL network utilized polar maps of stress and rest perfusion, myocardial blood flow, myocardial flow reserve, and spill-over fraction combined with cardiac volumes, singular indices, and sex. Patients scanned from 2010 to 2016 were used for training and validation. The network was tested in a set of 1135 patients scanned from 2017 to 2018 to simulate prospective clinical implementation. Results: In prospective testing, the area under the receiver operating characteristic curve for all-cause mortality prediction by DL (0.82 [95% CI, 0.77–0.86]) was higher than ischemia (0.60 [95% CI, 0.54–0.66]; P <0.001), myocardial flow reserve (0.70 [95% CI, 0.64–0.76], P <0.001) or a comprehensive logistic regression model (0.75 [95% CI, 0.69–0.80], P <0.05). The highest quartile of patients by DL had an annual all-cause mortality rate of 11.87% and had a 16.8 ([95% CI, 6.12%–46.3%]; P <0.001)-fold increase in the risk of death compared with the lowest quartile patients. DL showed a 21.6% overall reclassification improvement as compared with established measures of ischemia. Conclusions: The DL model trained directly on polar maps allows improved patient risk stratification in comparison with established methods for positron emission tomography flow or perfusion assessments.
No takes yet. Share an insight, caveat, or question.
Singh et al. (2022) conducted a cohort in Patients referred for stress and rest 82 Rb positron emission tomography (n=4,735). Deep learning (DL) network vs. Ischemia, myocardial flow reserve, or comprehensive logistic regression model was evaluated on Area under the receiver operating characteristic curve for all-cause mortality prediction (95% CI 0.77-0.86, p=<0.05). A deep learning network using positron emission tomography polar maps predicted all-cause mortality with a higher AUC than a comprehensive logistic regression model.
Synapse has enriched 10 related papers. Consider them for comparative context: