Efficient Prediction of Missed Clinical Appointment Using Machine Learning

Abstract

Public health and its related facilities are crucial for thriving cities and societies. The optimum utilization of health resources saves money and time, but above all, it saves precious lives. It has become even more evident in the present as the pandemic has overstretched the existing medical resources. Specific to patient appointment scheduling, the casual attitude of missing medical appointments (no-show-ups) may cause severe damage to a patient’s health. In this paper, with the help of machine learning, we analyze six million plus patient appointment records to predict a patient’s behaviors/characteristics by using ten different machine learning algorithms. For this purpose, we first extracted meaningful features from raw data using data cleaning. We applied Synthetic Minority Oversampling Technique (SMOTE), Adaptive Synthetic Sampling Method (Adasyn), and random undersampling (RUS) to balance our data. After balancing, we applied ten different machine learning algorithms, namely, random forest classifier, decision tree, logistic regression, XG Boost, gradient boosting, Adaboost Classifier, Naive Bayes, stochastic gradient descent, multilayer perceptron, and Support Vector Machine. We analyzed these results with the help of six different metrics, i.e., recall, accuracy, precision, F1-score, area under the curve, and mean square error. Our study has achieved 94% recall, 86% accuracy, 83% precision, 87% F1-score, 92% area under the curve, and 0.106 minimum mean square error. Effectiveness of presented data cleaning and feature selection is confirmed by better results in all training algorithms. Notably, recall is greater than 75%, accuracy is greater than 73%, F1-score is more significant than 75%, MSE is lesser than 0.26, and AUC is greater than 74%. The research shows that instead of individual features, combining different features helps make better predictions of a patient’s appointment status.

No-Show in Medical Appointments with Machine Learning Techniques: A Systematic Literature Review

“…The origin of the data was concentrated in nine different countries. Only the work by Qureshi et al [10] did not describe the origin of the data used. Followed by the United States, Brazil was the country of origin of eight studies, seven of which used the same dataset.…”

“…Four works [10,18,20,26] only presented the exploratory analysis of the data and the steps for the model building. However, they did not implement or discuss software and/or process management solutions that could be developed based on the study.…”

“…The results show that the most appropriate algorithms for building the models are the decision tree algorithms, either using a binary decision tree or using ensemble methods, such as Random Forest. The work by Qureshi et al [10] tested several more complex algorithms for building the model, such as the Multilayer Perceptron (MLP), but obtained satisfactory performance with the Random Forest algorithm. The choice of the final algorithm was also guided by the complexity of understanding the model built, such as the choice of decision trees against algorithms considered a black box, such as artificial neural networks.…”

Risk Prediction for the Development of Hyperuricemia: Model Development Using an Occupational Health Examination Dataset

“…The convolutional neural network (CNN) is a feedforward neural network with a deep structure that is good at mining local features of data and extracting global training features and classification and has some advantages that traditional techniques do not have [ 8 ]. XG Boost, known as eXtreme gradient boosting, achieves classification by iterative computation of classifiers, and the addition of its regular term ensures the model’s robustness and reduces the time to process features because it was good at handling missing data [ 9 ]. We established the above three HUA morbidity risk prediction models based on the medical examination data information of more than two thousand steelworkers and compared their prediction effects, aiming to select the optimal model and provide a theoretical basis for the health management of this special occupational group.…”

Retracted: Efficient Prediction of Missed Clinical Appointment Using Machine Learning

“…This article has been retracted by Hindawi following an investigation undertaken by the publisher [ 1 ]. This investigation has uncovered evidence of one or more of the following indicators of systematic manipulation of the publication process: Discrepancies in scope Discrepancies in the description of the research reported Discrepancies between the availability of data and the research described Inappropriate citations Incoherent, meaningless and/or irrelevant content included in the article Peer-review manipulation …”