Artificial Intelligence in Point-of-Care Imaging for Clinical Decision Support: Systematic Review of Diagnostic Accuracy, Task-Shifting, and Explainability.

Authors

Abstract

Artificial intelligence (AI) integrated with point-of-care (POC) imaging has emerged as a promising approach to expand diagnostic access in settings with limited specialist availability. However, no systematic review has comprehensively evaluated AI-assisted clinical decision support across multiple POC imaging modalities, assessed explainability implementation, or quantified clinical impact evidence gaps. To systematically evaluate and synthesize evidence on AI-based clinical decision support systems utilizing point-of-care imaging, with particular attention to task-shifting potential, explainability implementation, and clinical outcome evidence. We searched PubMed, Scopus, IEEE Xplore, and Web of Science (January 2018 to November 2025). We included research studies evaluating AI/machine learning systems applied to POC-capable imaging modalities in POC clinical settings with clinical decision support outputs. Two reviewers independently screened studies, extracted data across 15 domains, and assessed methodological quality using QUADAS-2. Proposed frameworks were developed to evaluate explainability implementation and clinical impact evidence. Narrative synthesis was performed due to substantial data heterogeneity. Of 2,113 records identified, 20 studies met inclusion criteria, encompassing approximately 78,296 patients across 15 countries. Studies evaluated tuberculosis (n=5), breast cancer (n=3), deep vein thrombosis (n=2), and nine other conditions using ultrasound (35%, 7/20), chest X-ray (25%, 5/20), photography-based and colposcopic imaging (15%, 3/20), fundus photography (10%, 2/20), microscopy (10%, 2/20), and dermoscopy (5%, 1/20). Median sensitivity was 92% (IQR 85.7%-98.0%), and median specificity was 90.6% (IQR 70.0%-95.7%). Task-shifting was demonstrated in 65% (13/20) of studies, with nonspecialists achieving specialist-level performance after a median of 1 hour of training. The explainable AI (XAI) implementation cascade revealed critical gaps: 75% (15/20) of studies did not mention explainability, 10% (2/20) provided explanations to users, and none evaluated whether clinicians understood explanations or whether XAI influenced decisions. The clinical impact pyramid showed 15% (3/20) of studies reported technical accuracy only, 65% (13/20) reported process outcomes, 20% (4/20) documented clinical actions, and none measured patient outcomes. Methodological quality was concerning, as 70% (14/20) of studies were at high or very high risk of bias, with verification bias (70%, 14/20) and selection bias (50%, 10/20) being the most common. The overall certainty of evidence was very low-Grading of Recommendations, Assessment, Development, and Evaluation (GRADE) ⊕◯◯◯, primarily due to risk of bias, heterogeneity, and imprecision. AI-assisted POC imaging demonstrates promising diagnostic accuracy and enables meaningful task-shifting with minimal training requirements. However, critical evidence gaps remain, including absent patient outcome measurement, inadequate explainability evaluation, regulatory misalignment, and lack of cross-context validation despite claims of global applicability. Addressing these gaps requires implementation research with patient outcome end points, rigorous XAI evaluation, and multi-context validation before widespread adoption. Limitations include restriction to English-language publications, grey literature exclusion, and heterogeneity precluding meta-analysis. This review was not prospectively registered due to time constraints.

Tags

Topics