ObjectiveTo explore the application of Tsetlin Machine (TM) in heart beat classification. MethodsTM was used to classify the normal beats, premature ventricular contraction (PVC) and supraventricular premature beats (SPB) in the 2020 data set of China Physiological Signal Challenge. This data set consisted of the single-lead electrocardiogram data of 10 patients with arrhythmia. One patient with atrial fibrillation was excluded, and finally data of the other 9 patients were included in this study. The classification results were then analyzed. ResultsThe classification results showed that the average recognition accuracy of TM was 84.3%, and the basis of classification could be shown by the bit pattern interpretation diagram. ConclusionTM can explain the classification results when classifying heart beats. The reasonable interpretation of classification results can increase the reliability of the model and facilitate people's review and understanding.
Nowadays, lung cancer is the most common and lethal invasive tumor type in Chinese population, challenging overall health level. However, personalized early-stage treatment is currently still not widely implemented, and the choice of treatment highly depends on experience of physician. Based on deep learning and radiomics principles, deep-radiomics is important for establishing objective and promotable precision medicine plans. Among all aspects, the explainability of a model is critical for its usage in clinical practice. This paper discusses the technical aspects of explainable deep-radiomics in lung cancer, and analyzes challenges we are facing. Non-fully supervised learning methods, as a current hotspot in deep learning technology, can construct more trustworthy and practically valuable deep learning models through the co-design method of performance-interpretability. Medical artificial intelligence faces three core challenges in transitioning from the laboratory to hospitals: high-level cognitive demands, data privacy and generalization capabilities, and regulatory compliance. However, with appropriate design, non-fully supervised learning holds the greatest potential to bridge the gap between design and application, enabling broader adoption.
Polytrauma is commonly defined as multisystem trauma involving at least two body regions with an Abbreviated Injury Scale (AIS) score ≥ 3, characterized by complex pathophysiological interactions and extreme clinical heterogeneity. This study retrospectively analyzed data from 171 274 polytrauma patients in the National Trauma Data Bank (NTDB) from 2018 to 2021. Key features were selected using the eXtreme Gradient Boosting (XGBoost) algorithm. Prediction models were then developed using XGBoost, logistic regression, random forest, naive Bayes, and support vector machine, respectively. Model performance was evaluated by receiver operating characteristic (ROC) curves, calibration curves, and decision curve analysis (DCA). Subgroup standardized mortality ratio (SMR) validation and global and local interpretability analysis based on SHapley Additive exPlanations (SHAP) theory were also conducted. The results demonstrated that the XGBoost model incorporating Glasgow Coma Scale (GCS), Injury Severity Score (ISS), massive transfusion within 4 hours, respiratory support, unplanned intubation, prehospital care-limiting directives, unplanned intensive care unit (ICU) admission, sepsis, ventilator-associated pneumonia, and liver cirrhosis achieved optimal performance, with an area under the ROC curve (AUC) of 0.90. Its calibration curve closely aligned with the ideal diagonal, and decision curve analysis indicated the highest clinical net benefit across a wide range of threshold probabilities. Subgroup SMRs ranged from 1.07 to 1.18, all close to 1.0. In conclusion, the developed in-hospital mortality risk prediction model for polytrauma patients exhibits favorable discrimination and clinical net benefit, and can assist clinicians in identifying high-risk populations while providing evidence to support individualized treatment decisions.