人工智能辅助肌肉超声检查在评估营养不良风险患者的炎症和肌肉质量中的应用

Artificial Intelligence-Assisted Muscular Ultrasonography for Assessing Inflammation and Muscle Mass in Patients at Risk of Malnutrition.

作者信息

López-Gómez Juan José, Estévez-Asensio Lucía, Cebriá Ángela, Izaola-Jauregui Olatz, Pérez López Paloma, González-Gutiérrez Jaime, Primo-Martín David, Jiménez-Sahagún Rebeca, Gómez-Hoyos Emilia, Rico-Bargues Daniel, Godoy Eduardo Jorge, De Luis-Román Daniel A

机构信息

Servicio de Endocrinología y Nutrición, Hospital Clínico Universitario de Valladolid, 47003 Valladolid, Spain.

Centro de Investigación en Endocrinología y Nutrición, Universidad de Valladolid, 47003 Valladolid, Spain.

出版信息

Nutrients. 2025 May 9;17(10):1620. doi: 10.3390/nu17101620.

DOI:10.3390/nu17101620

PMID:40431361

Abstract

BACKGROUND

Malnutrition, influenced by inflammation, is associated with muscle depletion and body composition changes. This study aimed to evaluate muscle mass and quality using Artificial Intelligence (AI)-enhanced ultrasonography in patients with inflammation.

METHODS

This observational, cross-sectional study included 502 malnourished patients, assessed through anthropometry, electrical bioimpedanciometry, and ultrasonography of the quadriceps rectus femoris (QRF). AI-assisted ultrasonography was used to segment regions of interest (ROI) from transversal QRF images to measure muscle thickness (RFMT) and area (RFMA), while a Multi-Otsu algorithm was used to extract biomarkers for muscle mass (MiT) and fat mass (FatiT). Inflammation was defined as C-reactive protein (CRP) levels above 3 mg/L.

RESULTS

The results showed a mean patient age of 63.72 (15.95) years, with malnutrition present in 82.3% and inflammation in 44.8%. Oncological diseases were prevalent (46.8%). The 44.8% of patients with inflammation (CRP > 3) exhibited reduced RFMA (2.91 (1.11) vs. 3.20 (1.19) cm, < 0.01) and RFMT (0.94 (0.28) vs. 1.01 (0.30) cm, < 0.01). Muscle quality was reduced, with lower MiT (45.32 (9.98%) vs. 49.10 (1.22%), < 0.01) and higher FatiT (40.03 (6.72%) vs. 37.58 (5.63%), < 0.01). Adjusted for age and sex, inflammation increased the risks of low muscle area (OR = 1.59, CI: 1.10-2.31), low MiT (OR = 1.49, CI: 1.04-2.15), and high FatiT (OR = 1.44, CI: 1.00-2.06).

CONCLUSIONS

AI-assisted ultrasonography revealed that malnourished patients with inflammation had reduced muscle area, thickness, and quality (higher fat content and lower muscle percentage). Elevated inflammation levels were associated with increased risks of poor muscle metrics. Future research should focus on exploring the impact of inflammation on muscles across various patient groups and developing AI-driven biomarkers to enhance the diagnosis, monitoring, and treatment of malnutrition and sarcopenia.

摘要

背景

受炎症影响的营养不良与肌肉消耗和身体成分变化有关。本研究旨在使用人工智能（AI）增强超声评估炎症患者的肌肉质量和品质。

方法

这项观察性横断面研究纳入了502名营养不良患者，通过人体测量、生物电阻抗分析法和股直肌（QRF）超声进行评估。使用AI辅助超声从QRF横向图像中分割出感兴趣区域（ROI），以测量肌肉厚度（RFMT）和面积（RFMA），同时使用多阈值算法提取肌肉质量（MiT）和脂肪质量（FatiT）的生物标志物。炎症定义为C反应蛋白（CRP）水平高于3mg/L。

结果

结果显示患者平均年龄为63.72（15.95）岁，82.3%存在营养不良，44.8%存在炎症。肿瘤性疾病较为普遍（46.8%）。44.8%的炎症患者（CRP>3）表现出RFMA降低（2.91（1.11）对3.20（1.19）cm，<0.01）和RFMT降低（0.94（0.28）对1.01（0.30）cm，<0.01）。肌肉品质降低，MiT较低（45.32（9.98%）对49.10（1.22%），<0.01），FatiT较高（40.03（6.72%）对37.58（5.63%），<0.01）。在调整年龄和性别后，炎症增加了低肌肉面积（OR=1.59，CI：1.10-2.31）、低MiT（OR=1.49，CI：1.04-2.15）和高FatiT（OR=1.44，CI：1.00-2.06）的风险。