Machine Learning for Early Detection of Hypoxic-Ischemic Brain Injury After Cardiac Arrest

Abstract

Background Establishing whether a patient who survived a cardiac arrest has suffered hypoxic-ischemic brain injury (HIBI) shortly after return of spontaneous circulation (ROSC) can be of paramount importance for informing families and identifying patients who may benefit the most from neuroprotective therapies. We hypothesize that using deep transfer learning on normal-appearing findings on head computed tomography (HCT) scans performed after ROSC would allow us to identify early evidence of HIBI. Methods We analyzed 54 adult comatose survivors of cardiac arrest for whom both an initial HCT scan, done early after ROSC, and a follow-up HCT scan were available. The initial HCT scan of each included patient was read as normal by a board-certified neuroradiologist. Deep transfer learning was used to evaluate the initial HCT scan and predict progression of HIBI on the follow-up HCT scan. A naive set of 16 additional patients were used for external validation of the model. Results The median age (interquartile range) of our cohort was 61 (16) years, and 25 (46%) patients were female. Although findings of all initial HCT scans appeared normal, follow-up HCT scans showed signs of HIBI in 29 (54%) patients (computed tomography progression). Evaluating the first HCT scan with deep transfer learning accurately predicted progression to HIBI. The deep learning score was the most significant predictor of progression (area under the receiver operating characteristic curve = 0.96 [95% confidence interval 0.91–1.00]), with a deep learning score of 0.494 having a sensitivity of 1.00, specificity of 0.88, accuracy of 0.94, and positive predictive value of 0.91. An additional assessment of an independent test set confirmed high performance (area under the receiver operating characteristic curve = 0.90 [95% confidence interval 0.74–1.00]). Conclusions Deep transfer learning used to evaluate normal-appearing findings on HCT scans obtained early after ROSC in comatose survivors of cardiac arrest accurately identifies patients who progress to show radiographic evidence of HIBI on follow-up HCT scans.

Comment on “Machine Learning for Early Detection of Hypoxic-Ischemic Brain Injury After Cardiac Arrest” Submitted by Noah Salomon Molinski et al.

“…We agree with some of their remarks, especially regarding the risk of overfitting for a data set of 54 cases, and therefore we clearly acknowledge that limitation of our article [ 1 ]. Although we have attempted to reduce the risk of overfitting in the methodology adopted, it indeed remains a possibility, particularly when considering the strong performance of our pilot data.…”

“…Lastly, we also agree that the use of explainable Artificial Intelligence tools such as heatmaps may be useful to identify specific image features that the model focuses on and understands the classification performance of. As noted in our article [ 1 ], we suspect the early signs of Hypoxic-Ischemic Brain Injury may be due to subtle changes in gray–white matter differentiation or brain edema that evade the human eye. Therefore, the output from explainable artificial intelligence tools may not necessarily be easy to interpret to a human reader.…”

Comment on “Machine Learning for Early Detection of Hypoxic‑ischemic Brain Injury After Cardiac Arrest”

“…

With great interest, we have read the article by Mansour et al [1], reporting on the use of deep transfer learning to identify early signs of hypoxic-ischemic brain injury (HIBI) on head computed tomography (HCT) scans. The authors report a very high accuracy (0.94) of their model with respect to the detection of HIBI signs on HCT scans performed within hours after the return of spontaneous circulation.

…”

“…Nonlinear methods (manifold learning), such as kernel PCA, t-distributed Stochastic Neighbor Embedding, or Multidimensional Scaling, could be applied instead. Moreover, the authors write "single-scan testing was repeated so that each of the 54 scans served as the test scan exactly one time" [1]. Although the leave-one-out cross validation described above improves model quality, the multiple repeated uses of the same data as training data can strongly facilitate overfitting.…”

“…As the authors reported that early HIBI signs were due to "subtle changes that evade the detection threshold of the human eye" [1], it would have been desirable to visualize by using heat maps or GradCAM, in which the subtle changes in the brain could start [5]. Those are important tools to plausibly illustrate the "thinking process of AI" to the readers.…”