To evaluate the current landscape of artificial intelligence (AI) and machine learning (ML) applications in predictive analytics for cervical myelopathy, focusing on diagnostic accuracy, patient stratification, surgical decision-making, and outcome prediction. A systematic search was conducted across PubMed, Embase, Scopus, and Web of Science using keywords related to cervical myelopathy and AI/ML. Studies were selected based on relevance to AI-driven predictive models in diagnosis, prognosis, and management of cervical myelopathy. Data extraction included algorithm types, validation methods, clinical applicability, and performance metrics. Qualitative synthesis was performed to identify thematic trends and methodological gaps. Out of 169 records, 41 studies met inclusion criteria. AI/ML models demonstrated high accuracy in gait analysis, hand motion tracking, and image-based diagnostics, with some achieving > 90% sensitivity and specificity. ML algorithms effectively stratified patients into phenotypic clusters and predicted surgical outcomes, including postoperative complications and opioid use. Radiomics and deep learning enhanced imaging interpretation, while ensemble models improved prognostic reliability. Despite promising results, limitations included data heterogeneity, retrospective design, and lack of standardised validation protocols. AI and ML are reshaping cervical myelopathy management by enabling precise diagnostics, personalised treatment planning, and predictive modelling. Integration of multimodal data and explainable AI frameworks is essential for clinical adoption. Future research should prioritise prospective validation, ethical safeguards, and interdisciplinary collaboration to bridge the gap between technological innovation and patient-centred care.
Rajeev et al. (Fri,) studied this question.