An interpretable neural network for outcome prediction in traumatic brain injury.

BACKGROUND: Traumatic Brain Injury (TBI) is a common condition with potentially severe long-term complications, the prediction of which remains challenging. Machine learning (ML) methods have been used previously to help physicians predict long-term outcomes of TBI so that appropriate treatment plans can be adopted. However, many ML techniques are "black box": it is difficult for humans to understand the decisions made by the model, with post-hoc explanations only identifying isolated relevant factors rather than combinations of factors. Moreover, such models often rely on many variables, some of which might not be available at the time of hospitalization. METHODS: In this study, we apply an interpretable neural network model based on tropical geometry to predict unfavorable outcomes at six months from hospitalization in TBI patients, based on information available at the time of admission. RESULTS: The proposed method is compared to established machine learning methods-XGBoost, Random Forest, and SVM-achieving comparable performance in terms of area under the receiver operating characteristic curve (AUC)-0.799 for the proposed method vs. 0.810 for the best black box model. Moreover, the proposed method allows for the extraction of simple, human-understandable rules that explain the model's predictions and can be used as general guidelines by clinicians to inform treatment decisions. CONCLUSIONS: The classification results for the proposed model are comparable with those of traditional ML methods. However, our model is interpretable, and it allows the extraction of intelligible rules. These rules can be used to determine relevant factors in assessing TBI outcomes and can be used in situations when not all necessary factors are known to inform the full model's decision.

A Comparison of Interpretable Machine Learning Approaches to Identify Outpatient Clinical Phenotypes Predictive of First Acute Myocardial Infarction.

BACKGROUND: Acute myocardial infarctions are deadly to patients and burdensome to healthcare systems. Most recorded infarctions are patients' first, occur out of the hospital, and often are not accompanied by cardiac comorbidities. The clinical manifestations of the underlying pathophysiology leading to an infarction are not fully understood and little effort exists to use explainable machine learning to learn predictive clinical phenotypes before hospitalization is needed. METHODS: We extracted outpatient electronic health record data for 2641 case and 5287 matched-control patients, all without pre-existing cardiac diagnoses, from the Michigan Medicine Health System. We compare six different interpretable, feature extraction approaches, including temporal computational phenotyping, and train seven interpretable machine learning models to predict the onset of first acute myocardial infarction within six months. RESULTS: Using temporal computational phenotypes significantly improved the model performance compared to alternative approaches. The mean cross-validation test set performance exhibited area under the receiver operating characteristic curve values as high as 0.674. The most consistently predictive phenotypes of a future infarction include back pain, cardiometabolic syndrome, family history of cardiovascular diseases, and high blood pressure. CONCLUSIONS: Computational phenotyping of longitudinal health records can improve classifier performance and identify predictive clinical concepts. State-of-the-art interpretable machine learning approaches can augment acute myocardial infarction risk assessment and prioritize potential risk factors for further investigation and validation.

Predicting need for heart failure advanced therapies using an interpretable tropical geometry-based fuzzy neural network.

BACKGROUND: Timely referral for advanced therapies (i.e., heart transplantation, left ventricular assist device) is critical for ensuring optimal outcomes for heart failure patients. Using electronic health records, our goal was to use data from a single hospitalization to develop an interpretable clinical decision-making system for predicting the need for advanced therapies at the subsequent hospitalization. METHODS: Michigan Medicine heart failure patients from 2013-2021 with a left ventricular ejection fraction ≤ 35% and at least two heart failure hospitalizations within one year were used to train an interpretable machine learning model constructed using fuzzy logic and tropical geometry. Clinical knowledge was used to initialize the model. The performance and robustness of the model were evaluated with the mean and standard deviation of the area under the receiver operating curve (AUC), the area under the precision-recall curve (AUPRC), and the F1 score of the ensemble. We inferred membership functions from the model for continuous clinical variables, extracted decision rules, and then evaluated their relative importance. RESULTS: The model was trained and validated using data from 557 heart failure hospitalizations from 300 patients, of whom 193 received advanced therapies. The mean (standard deviation) of AUC, AUPRC, and F1 scores of the proposed model initialized with clinical knowledge was 0.747 (0.080), 0.642 (0.080), and 0.569 (0.067), respectively, showing superior predictive performance or increased interpretability over other machine learning methods. The model learned critical risk factors predicting the need for advanced therapies in the subsequent hospitalization. Furthermore, our model displayed transparent rule sets composed of these critical concepts to justify the prediction. CONCLUSION: These results demonstrate the ability to successfully predict the need for advanced heart failure therapies by generating transparent and accessible clinical rules although further research is needed to prospectively validate the risk factors identified by the model.