Artificial Intelligence aware Knowledge Graphs and Deep Learning-Based Diagnostic Prediction Model in Healthcare

Diagnostic prediction experts use a patient’s medical history to anticipate their future diagnosis. Attention mechanisms and recurrent neural networks are typically utilized for this purpose; however, data shortages often cause complications. Additionally, healthcare information can help diagnostic prediction algorithms. This study links healthcare ideas using AI-aware, intelligent healthcare ontologies and patient visit records as an intelligent graph. Next, utilize a graph convolution module to collect geographical attributes that show patient visit healthcare code linkages. Using a multihead attention technique, visit information and healthcare knowledge are compared to predict the patient’s future health. On two open-source healthcare datasets, the suggested solution outperforms state-of-the-art diagnostic prediction algorithms and better uses IMG data.

• diagnostic prediction
• knowledge graphs
• graph convolutional networks
• multi-head attention
• medical history
• data scarcity

• 3 — Bonne santé et bien-être

• Machine Learning in Healthcare
• Artificial Intelligence in Healthcare
• Advanced Graph Neural Networks
• diagnostic prediction
• knowledge graphs
• graph convolutional networks
• multi-head attention
• medical history
• data scarcity
• Artificial Intelligence
• Health Information Management
• Computer Science
• Health Professions