A Systematic Review of the Application of Computational Grounded Theory Method in Healthcare Research

The integration of computational methods with traditional qualitative research approaches has emerged as a transformative paradigm in healthcare research. Computational Grounded Theory (CGT) represents a novel methodological framework that combines the interpretive depth of grounded theory with the analytical power of computational techniques, particularly machine learning and natural language processing. This systematic review examines the application of CGT in healthcare research, synthesizing evidence from eight key studies that demonstrate the method’s utility across diverse healthcare contexts.

The primary objectives of this review are to analyze the current state of CGT application in healthcare research, evaluate the methodological approaches and computational techniques employed, identify key themes and patterns emerging from CGT studies, assess the advantages and limitations compared to traditional qualitative methods, and provide recommendations for future research and practice. Following a systematic search and narrative synthesis approach, eight papers applying CGT methods in healthcare contexts were analyzed, examining methodological frameworks, computational techniques, healthcare applications, and outcomes.

The results demonstrate diverse applications of CGT across healthcare domains including COVID-19 risk perception, medical AI adoption, mental health interventions, diabetes management, women’s health technology, online health communities, and old-age social welfare systems. Common computational techniques included Latent Dirichlet Allocation (LDA), sentiment analysis, word embeddings, and various machine learning algorithms. Studies consistently reported enhanced analytical capacity, identification of latent patterns, and novel theoretical insights as compared to traditional methods. However, challenges included technical complexity, interpretation validity, and the need for interdisciplinary expertise.

This review concludes that CGT represents a promising methodological innovation for healthcare research, offering unique capabilities for analyzing large-scale textual data while maintaining theoretical depth. The approach demonstrates particular value in understanding complex healthcare phenomena, patient experiences, and technology adoption. Future research should focus on standardizing methodological procedures, developing best practices, and expanding applications to emerging healthcare challenges.