Multi-label chain clustering-classification and regression predictive models for patient punctuality and turnaround time in outpatient primary care settings

Abstract

This study develops two multi-label chain machine learning predictive models to anticipate patient punctuality and turnaround time. The first model uses an integrated model of clustering and classification where the check-in, service, and checkout times are clustered into three categories using the K-means algorithm. Then, patient punctuality and established clusters are used to develop a multi-label chain predictive model that utilizes Logistic Regression, Multi-Layer Perceptron, and tree-based classifiers. The second model predicts patient punctuality and turnaround time using a multi-label chain regression model that utilizes Linear Regression, Huber Regressor, ADR Regression, Multi-Layer Perceptron, and tree-based regressors. It was found that a patient’s age is a key driver for both patient punctuality and turnaround time. Also, there is a significant association between patient punctuality and turnaround time. The first proposed model predicted the punctuality and turnaround time with an average best F1-score of about 70.4% and 71.9%, respectively. The second model produced acceptable results with the best average R-squared of 0.67 for punctuality and 0.68 for turnaround time. The models can reduce the complexity and time of predicting several numerical outputs, enhance the interpretation of the results, and improve the understanding of the results by non-technical staff.

Keywords:

• Machine learning
• multi-label classification
• primary care
• predictive model
• punctuality
• regression
• turnaround time

Additional information

Funding

This work was supported in part by a research grant from Finger Lakes Community Health to Binghamton University.