Investigating Healthcare Centers' Willingness to Adopt Electronic Health Records: A Machine Learning Perspective

Abstract

Electronic Health Records (EHRs) are a vital component of modern healthcare systems, providing a comprehensive view of patients' medical histories and improving care coordination and patient outcomes. However, despite the potential benefits, the adoption of EHRs in healthcare centers remains a complex and challenging process. Understanding the factors that influence healthcare centers' willingness to adopt EHRs is crucial for developing effective strategies to overcome barriers to adoption and realizing the full potential of EHRs. Therefore, this study aimed to investigate the willingness of healthcare centers to adopt EHRs using advanced machine learning techniques. A sample of 150 IT personnel from different healthcare centers participated in the study. The study utilized Ensemble Voting Classifier and Stacking Classifier as classification algorithms to classify the willingness of healthcare centers to adopt EHR into three classes: i) unwilling to adopt EHR, ii) undecided, and iii) willing to adopt EHR. The results indicated that the Ensemble Voting Classifier with additional features showed the best performance among all models, achieving an accuracy of 0.82. Naive Bayes with additional features and the Ensemble Voting Classifier without additional features followed with accuracies of 0.79 and 0.69, respectively. Furthermore, the study found that healthcare centers with technical expertise were more willing to adopt EHR, while cost barriers caused unwillingness to adopt EHR. Healthcare centers with supportive infrastructure were also found to be more willing to adopt EHR. Finally, the fear of workflow disruption was identified as a cause of unwillingness to adopt EHR. This research contributes to a better understanding of the factors that influence healthcare centers' willingness to adopt EHR. These findings may inform strategies to overcome barriers to EHR adoption and improve the quality and efficiency of healthcare services.