Wali Tursun, Bolatbekov Almat, Maimaitijiang Ehesan, Salman Dilbar, Mamatjan Yasin
Department of Engineering in the Faculty of Science, Thompson Rivers University, 805 TRU Way, Kamloops, BC V2C 0C8 Canada.
Present Address: AIdMed Laboratory, Thompson Rivers University, Kamloops, Canada.
Discov Med (Cham). 2024;1(1):161. doi: 10.1007/s44337-024-00174-9. Epub 2024 Dec 17.
Cardiovascular diseases are a major cause of mortality and morbidity. Fast detection of life-threatening emergency events and an earlier start of the therapy would save many lives and reduce successive disabilities. Understanding the specific risk factors associated with heart attack and the degree of association is crucial in the clinical diagnosis. Considering the potential benefits of intelligent models in healthcare, many researchers have developed a variety of machine learning (ML)-based models to identify patients at risk of a heart attack. However, the common problem of previous works that used ML concepts was the lack of transparency in black-box models, which makes it difficult to understand how the model made the prediction. In this study, an automated smart recommender system (Explainable Artificial Intelligence) for heart attack prediction and risk stratification was developed. For the purpose, the CatBoost classifier was applied as the initial step. Then, the SHAP (SHapley Additive exPlanation) explainable algorithm was employed to determine reasons behind high or low risk classification. The recommender system can provide insights into the reasoning behind the predictions, including group-based and patient-specific explanations. In the final step, we integrated a Large Language Model (LLM) called BioMistral for chatting functionally to talk to users based on the model output as a digital doctor for consultation. Our smart recommender system achieved high accuracy in predicting a patient risk level with an average AUC of 0.88 and can explain the results transparently. Moreover, a Django-based online application that uses patient data to update medical information about an individual's heart attack risk was created. The LLM chatbot component would answer user questions about heart attacks and serve as a virtual companion on the route to heart health, our system also can locate nearby hospitals by applying Google Maps API and alert the users. The recommender system could improve patient management and lower heart attack risk while timely therapy aids in avoiding subsequent disabilities.
心血管疾病是导致死亡和发病的主要原因。快速检测危及生命的紧急事件并尽早开始治疗可以挽救许多生命并减少后续残疾。了解与心脏病发作相关的特定风险因素及其关联程度在临床诊断中至关重要。考虑到智能模型在医疗保健中的潜在益处，许多研究人员开发了各种基于机器学习（ML）的模型来识别有心脏病发作风险的患者。然而，以前使用ML概念的工作的常见问题是黑箱模型缺乏透明度，这使得很难理解模型是如何做出预测的。在本研究中，开发了一种用于心脏病发作预测和风险分层的自动化智能推荐系统（可解释人工智能）。为此，首先应用了CatBoost分类器。然后，采用SHAP（Shapley值加法解释）可解释算法来确定高风险或低风险分类背后的原因。该推荐系统可以深入了解预测背后的推理，包括基于群体和患者特定的解释。在最后一步中，我们集成了一个名为BioMistral的大语言模型（LLM），以便根据模型输出作为数字医生进行功能聊天与用户交谈以进行咨询。我们的智能推荐系统在预测患者风险水平方面取得了很高的准确率，平均AUC为0.88，并且可以透明地解释结果。此外，创建了一个基于Django的在线应用程序，该应用程序使用患者数据来更新有关个人心脏病发作风险的医疗信息。LLM聊天机器人组件将回答用户关于心脏病发作的问题，并在通往心脏健康的道路上充当虚拟伴侣，我们的系统还可以通过应用谷歌地图API定位附近的医院并提醒用户。该推荐系统可以改善患者管理并降低心脏病发作风险，而及时的治疗有助于避免后续残疾。
