Machine learning analysis of patients' perceptions towards generic medication in Greece: a survey-based study.

Area of Science:

• Pharmacoeconomics and Health Services Research
• Patient Behavior and Attitudes
• Health Informatics and Machine Learning

Background:

• Patient skepticism towards generic drugs hinders their market penetration in Greece.
• Understanding patient perceptions is crucial for promoting generic medication acceptance.
• Cost-saving potential of generics is acknowledged but not fully realized due to patient attitudes.

Purpose of the Study:

• To investigate Greek patients' perceptions and attitudes towards generic drugs.
• To identify factors influencing the acceptance and market penetration of generic medications.
• To predict patient willingness to switch to generic alternatives using machine learning.

Main Methods:

• A mixed-methods approach combining descriptive statistics and machine learning models.
• Analysis of survey responses from 2,617 adult participants (February 2017 - June 2021).
• Logistic Regression, Support Vector Machine, Random Forest, Gradient Boosting, and XGBoost models were optimized and compared.

Main Results:

• Healthcare providers are the primary source of information about generic drugs for patients.
• Machine learning models identified patient knowledge and healthcare professional influence as key predictors of generic drug acceptance.
• The Random Forest model achieved the highest accuracy in predicting patient willingness to switch.

Conclusions:

• Informed healthcare providers play a critical role in shaping patient attitudes towards generic drugs.
• Insights from this Greek study have global implications for improving generic drug acceptance.
• Limitations include convenience sampling and self-reported data, requiring cautious generalization.