A deep learning approach for facility patient attendance prediction based on medical booking data
Francesco Piccialli1, Salvatore Cuomo2, Danilo Crisci2
1Department of Mathematics and Applications "R. Caccioppoli", University of Naples Federico II, 80126, Naples, Italy. francesco.piccialli@unina.it.
Scientific Reports
|September 5, 2020
Summary
This study introduces a Deep Learning (DL) model to predict patient medical facility access within two months. The Temporal Convolutional Neural Network (TCNN) analyzes booking data for intelligent healthcare insights.
Area of Science:
- Health Informatics
- Artificial Intelligence in Healthcare
- Machine Learning Applications
Background:
- Data-driven methodologies are crucial for personalized and intelligent healthcare systems.
- Machine Learning (ML) algorithms can enhance healthcare quality through smart services.
- Analyzing patient clinical history is a promising research area.
Purpose of the Study:
- To develop a predictive model for patient access to medical facilities.
- To apply Deep Learning (DL) for forecasting patient appointments within a two-month timeframe.
- To extract valuable knowledge on patients, medical staff, and healthcare structures.
Main Methods:
- Analysis of millions of medical booking records from Campania, Italy.
- Development of a structured Temporal Convolutional Neural Network (TCNN).
- Utilizing TCNN to extract temporal patterns from patient administrative medical history.
Main Results:
- A predictive model was successfully developed using a TCNN approach.
- The methodology demonstrated effectiveness in predicting patient facility access.
- The study presents a novel application of TCNN for multi-label classification in healthcare.
Conclusions:
- The proposed TCNN methodology is effective for predicting patient healthcare utilization.
- This approach offers a novel application of DL in administrative healthcare data analysis.
- The findings contribute to the development of intelligent healthcare systems.
