Evaluation of the Rennes Universal Measurement Method (RUMM), an artificial intelligence application for hand joint angle assessment.

Abstract

Although goniometric measurement is considered the gold standard for the measurement of digital range of motion, visual estimation is often employed due to its simplicity despite being inconsistent with recommended guidelines. We evaluated the Rennes Universal Measurement Method, an innovative tool employing artificial intelligence to concurrently analyse hand joint angles based on a single photograph. We found a strong correlation between the goniometric method and the photograph-based approach (Spearman correlation coefficient 0.7). The mean standard error of measurement was -1° (SD 17°). Regarding reproducibility with different photographic angles, an excellent intraclass correlation coefficient of 0.9 was noted. The tool had a processing time of less than 0.1 s per hand, while traditional goniometric methods took 20-30 s per finger. Combining simplicity, high reproducibility and good inter-rater reliability, this is a potentially useful tool that can be used to monitor patient progress in place of traditional goniometry.