Abstract Background Geriatric syndromes (GS) are complex conditions that affect older adults and often require multidisciplinary assessment. Natural language processing (NLP) has emerged as a promising tool for extracting relevant clinical information from unstructured text in electronic health records (EHRs). However, the application of NLP in detecting and monitoring GS remains an evolving area of research. This systematic review explores the role of NLP in the identification and analysis of GS, examining its applications, methodologies, and effectiveness. Furthermore, this review discusses the existing challenges, limitations, and future directions to advance NLP applications in the GS research. Methods We conducted a systematic literature search across ten databases to identify studies that applied NLP to GS detection. Articles were screened using predefined inclusion and exclusion criteria, and relevant studies were evaluated for quality using PROBAST. Data were extracted on study characteristics, datasets, annotation processes, NLP approaches, performance metrics, population demographics, and clinical applications. A PRISMA flow diagram was used to illustrate the study selection process. Results A total of 65 studies were included, where the majority of the studies used traditional rule-based and machine learning approaches. Publicly available datasets were scarce, and most studies used their private dataset, leading to significant variability in data sources and formats. Annotation methodologies differed across studies, with minimal shared guidelines or standards, making direct comparisons challenging. Performance metrics varied across syndromes, with F1-score, precision, and recall as the most commonly reported. Key challenges included the lack of dataset uniformity, differences in annotation practices, and the absence of external validation. Conclusion NLP has shown potential in GS analysis, particularly for the detection of syndromes and epidemiological research. However, the majority of studies only focused on one syndrome, and variability in dataset availability, annotation processes, and model performance present challenges to broader implementation. Future research should focus on improving the comprehensiveness of GS identification, dataset standardisation, enhancing model generalisability, and integrating NLP approaches into clinical workflows.
Rahman et al. (Thu,) studied this question.