A multi-granularity convolutional neural network model with temporal information and attention mechanism for efficient diabetes medical cost prediction

• Published in: Computers in biology and medicine 2022-12, Vol.151 (Pt A), p.106246-106246, Article 106246
• Main Authors: Luo, Min, Wang, Yi-ting, Wang, Xiao-kang, Hou, Wen-hui, Huang, Rui-lu, Liu, Ye, Wang, Jian-qiang
• Format: Article
• Language: English
• Subjects: Artificial neural networks; Attention mechanism; Chronic illnesses; Convolutional neural network; Deep Learning; Diabetes; Diabetes Mellitus; Embedding; Health care; Humans; Machine learning; Medical research; Multi-granularity embedding; Neural networks; Neural Networks, Computer; Patients; Representations; Sparsity; t-SNE; Time series
• ISSN: 0010-4825; 1879-0534
• DOI: 10.1016/j.compbiomed.2022.106246

As the cost of diabetes treatment continues to grow, it is critical to accurately predict the medical costs of diabetes. Most medical cost studies based on convolutional neural networks (CNNs) ignore the importance of multi-granularity information of medical concepts and time interval characteristics of patients' multiple visit sequences, which reflect the frequency of patient visits and the severity of the disease. Therefore, this paper proposes a new end-to-end deep neural network structure, MST-CNN, for medical cost prediction. The MST-CNN model improves the representation quality of medical concepts by constructing a multi-granularity embedding model of medical concepts and incorporates a time interval vector to accurately measure the frequency of patient visits and form an accurate representation of medical events. Moreover, the MST-CNN model integrates a channel attention mechanism to adaptively adjust the channel weights to focus on significant medical features. The MST-CNN model systematically addresses the problem of deep learning models for temporal data representation. A case study and three comparative experiments are conducted using data collected from Pingjiang County. Through experiments, the methods used in the proposed model are analyzed, and the super contribution of the model performance is demonstrated. •A practical deep learning medical cost prediction model is established.•t-SNE is utilized to perform medical concept embedding representation visualization.•A multi-granularity model is developed to improve the quality of medical concept representation.•Attention mechanism is used to improve the performance of the model.•Interesting findings provide some guidance for future research and practical problems.