Fautsch, Kalli

Introduction Artificial intelligence (AI), particularly large-language models like Chat Generative Pre-Trained Transformer (ChatGPT), has demonstrated potential in streamlining research methodologies. Systematic reviews and meta-analyses, often considered the pinnacle of evidence-based medicine, are inherently time-intensive and demand meticulous planning, rigorous data extraction, thorough analysis, and careful synthesis. Despite promising applications of AI, its utility in conducting systematic reviews with meta-analysis remains unclear. This study evaluated ChatGPT’s accuracy in conducting key tasks of a systematic review with meta-analysis. Methods This validation study used data from a published meta-analysis on emotional functioning after spinal cord stimulation. ChatGPT-4o performed title/abstract screening, full-text study selection, and data pooling for this systematic review with meta-analysis. Comparisons were made against human-executed steps, which were considered the gold standard. Outcomes of interest included accuracy, sensitivity, specificity, positive predictive value, and negative predictive value for screening and full-text review tasks. We also assessed for discrepancies in pooled effect estimates and forest plot generation. Results For title and abstract screening, ChatGPT achieved an accuracy of 70.4%, sensitivity of 54.9%, and specificity of 80.1%. In the full-text screening phase, accuracy was 68.4%, sensitivity 75.6%, and specificity 66.8%. ChatGPT successfully pooled data for five forest plots, achieving 100% accuracy in calculating pooled mean differences, 95% CIs, and heterogeneity estimates ( I 2 score and tau-squared values) for most outcomes, with minor discrepancies in tau-squared values (range 0.01–0.05). Forest plots showed no significant discrepancies. Conclusion ChatGPT demonstrates modest to moderate accuracy in screening and study selection tasks, but performs well in data pooling and meta-analytic calculations. These findings underscore the potential of AI to augment systematic review methodologies, while also emphasizing the need for human oversight to ensure accuracy and integrity in research workflows.

Abstract Background In predynamic or dynamic scapholunate (SL) instability, standard diagnostic imaging may not identify SL interosseous ligament (SLIL) injury, leading to delayed detection and intervention. This study describes the use of four-dimensional computed tomography (4DCT) in identifying early SLIL injury and following injured wrists to 1-year postoperatively. Description of Technique 4DCT acquires a series of three-dimensional volume data with high temporal resolution (66 ms). 4DCT-derived arthrokinematic data can be used as biomarkers of ligament integrity. Patients and Methods This study presents the use of 4DCT in a two-participant case series to assess changes in arthrokinematics following unilateral SLIL injury preoperatively and 1-year postoperatively. Patients were treated with volar ligament repair with volar capsulodesis and arthroscopic dorsal capsulodesis. Arthrokinematics were compared between uninjured, preoperative injured, and postoperative injured (repaired) wrists. Results 4DCT detected changes in interosseous distances during flexion-extension and radioulnar deviation. Generally, radioscaphoid joint distances were greatest in the uninjured wrist during flexion-extension and radioulnar deviation, and SL interval distances were smallest in the uninjured wrist during flexion-extension and radioulnar deviation. Conclusion 4DCT provides insight into carpal arthrokinematics during motion. Distances between the radioscaphoid joint and SL interval can be displayed as proximity maps or as simplified descriptive statistics to facilitate comparisons between wrists and time points. These data offer insight into areas of concern for decreased interosseous distance and increased intercarpal diastasis. This method may allow surgeons to assess whether (1) injury can be visualized during motion, (2) surgery repaired the injury, and (3) surgery restored normal carpal motion. Level of Evidence Level IV, Case series.