Diagnosing Sarcopenia with AI-Aided Ultrasound (DINOSAUR)-A Pilot Study

Abstract

Background: Sarcopenia has been recognized as a determining factor in surgical outcomes and is associated with an increased risk of postoperative complications and readmission. Diagnosis is currently based on clinical guidelines, which includes assessment of skeletal muscle mass but not quality. Ultrasound has been proposed as a useful point-of-care diagnostic tool to assess muscle quality, but no validated cut-offs for sarcopenia have been reported. Using novel automated artificial intelligence (AI) software to interpret ultrasound images may assist in mitigating the operator-dependent nature of the modality. Our study aims to evaluate the fidelity of AI-aided ultrasound as a reliable and reproducible modality to assess muscle quality and diagnose sarcopenia in surgical patients. Methods: Thirty-six adult participants from an outpatient clinic were recruited for this prospective cohort study. Sarcopenia was diagnosed according to Asian Working Group for Sarcopenia (AWGS) 2019 guidelines. Ultrasonography of the rectus femoris muscle was performed, and images were analyzed by an AI software (MuscleSound® (Version 5.69.0)) to derive muscle parameters including intramuscular adipose tissue (IMAT) as a proxy of muscle quality. A receiver operative characteristic (ROC) curve was used to assess the predictive capability of IMAT and its derivatives, with area under the curve (AUC) as a measure of overall diagnostic accuracy. To evaluate consistency between ultrasound users of different experience, intra- and inter-rater reliability of muscle ultrasound parameters was analyzed in a separate cohort using intraclass correlation coefficients (ICC) and Bland-Altman plots. Results: The median age was 69.5 years (range: 26-87), and the prevalence of sarcopenia in the cohort was 30.6%. The ROC curve plotted with IMAT index (IMAT% divided by muscle area) yielded an AUC of 0.727 (95% CI: 0.551-0.904). An optimal cut-off point of 4.827%/cm² for IMAT index was determined with a Youden's Index of 0.498. We also demonstrated that IMAT index has excellent intra-rater reliability (ICC = 0.938, CI: 0.905-0.961) and good inter-rater reliability (ICC = 0.776, CI: 0.627-0.866). In Bland-Altman plots, the limits of agreement were from -1.489 to 1.566 and -2.107 to 4.562, respectively. Discussion: IMAT index obtained via ultrasound has the potential to act as a point-of-care evaluation for sarcopenia screening and diagnosis, with good intra- and inter-rater reliability. The proposed IMAT index cut-off maximizes sensitivity for case finding, supporting its use as an easily implementable point-of-care test in the community for sarcopenia screening. Further research incorporating other ultrasound parameters of muscle quality may provide the basis for a more robust diagnostic tool to help predict surgical risk and outcomes.

Keywords: artificial intelligence; intramuscular adipose tissue; muscle quality; sarcopenia; ultrasound.

Figure 1

Typical ultrasound images obtained of the rectus femoris muscle after analysis by MuscleSound^®. (A) is a scan from a 27-year-old volunteer, and (B) is from an 85year-old patient. The pink overlay represents the muscle, yellow represents the muscle boundary and white highlights are non-contractile fibers (in color for print).

Figure 2

Receiver operating characteristic (ROC) curve for IMAT index with area under the curve. IMAT: intramuscular adipose tissue (in color for print).

Figure 3

Bland–Altman plot for IMAT index intra-rater agreement. IMAT: intramuscular adipose tissue (in color for print).

Figure 4

Bland–Altman plot for IMAT index inter-rater agreement. IMAT: intramuscular adipose tissue (in color for print).