Multiple subgroup and disease-level comparisons were performed without formal adjustment for multiplicity, so nominally significant findings should be interpreted cautiously, with greater emphasis on effect sizes, 95% CI, and overall patterns of results.
← all excerpts
Performance of DeepSeek V3.2 and ChatGPT 5.1 in Musculoskeletal Triage and Differential Diagnosis of Outpatients With Low Back Pain: Multidimensional Comparative Study.
1
—
—