Multi-objective learning and explanation for stroke risk assessment in Shanxi province

Abstract

Stroke is the leading cause of death in China (Zhou et al. in The Lancet, 2019). A dataset from Shanxi Province is analyzed to predict the risk of patients at four states (low/medium/high/attack) and to estimate transition probabilities between various states via a SHAP DeepExplainer. To handle the issues related to an imbalanced sample set, the quadratic interactive deep model (QIDeep) was first proposed by flexible selection and appending of quadratic interactive features. The experimental results showed that the QIDeep model with 3 interactive features achieved the state-of-the-art accuracy 83.33%(95% CI (83.14%; 83.52%)). Blood pressure, physical inactivity, smoking, weight, and total cholesterol are the top five most important features. For the sake of high recall in the attack state, stroke occurrence prediction is considered an auxiliary objective in multi-objective learning. The prediction accuracy was improved, while the recall of the attack state was increased by 17.79% (to 82.06%) compared to QIDeep (from 71.49%) with the same features. The prediction model and analysis tool in this paper provided not only a prediction method but also an attribution explanation of the risk states and transition direction of each patient, a valuable tool for doctors to analyze and diagnose the disease.

An Optimization Precise Model of Stroke Data to Improve Stroke Prediction

“…Some approaches include Risk assessment models: These models can help identify individuals who are at a higher risk of stroke based on their age, sex, lifestyle factors, medical history, and other risk factors. They can also help predict the likelihood of stroke and inform preventive strategies [20].…”

Intelligent Stroke Disease Prediction Model Using Deep Learning Approaches

“…Zheng et al [ 6 ] employed six machine learning methods to predict the risk of stroke, the best predictions were obtained using random forest for experimental from 233 patients, and they found that cerebral infarction, PM 8, and drinking are independent risk factors for stroke. Ma et al [ 7 ] researched multiobjective learning and explanation for stroke risk assessment and adopted the quadratic interactive deep model to solve the problem of sample imbalance to improve the prediction accuracy. Chen and Sawam [ 8 ] investigated the use of wearable devices to monitor risk factors for stroke and analyzed the trend of combining wearable devices and machine learning algorithms to build stroke risk prediction systems.…”