Skip to content

An Interpretable Machine Learning Model for the Diagnosis of Sarcopenia in Patients with Crohn's Disease

An Interpretable Machine Learning Model for the Diagnosis of Sarcopenia in Patients with Crohn's Disease

Status
Recruiting
Phases
Unknown
Study type
Observational
Source
ChiCTR
Registry ID
ChiCTR2500113065
Enrollment
Unknown
Registered
2025-11-24
Start date
2025-11-25
Completion date
Unknown
Last updated
2025-12-15

For informational purposes only — not medical advice. Sourced from public registries and may not reflect the latest updates. Terms

Conditions

Crohn's disease

Interventions

Gold Standard:Diagnosing LMM in CD patients by calculating the psoas muscle index (PMI) through a CT scan at the level of the third lumbar vertebra (L3). According to the 2019 Asian Working Group for
females: PMI < 3.6 cm²/m² (ages 18–40) or < 3.3 cm²/m² (ages 41–60).
Index test:Body Composition Analysis (Bioelectrical Impedance Analysis, BIA)

Sponsors

Xiangya Hospital Central South University
Lead Sponsor

Eligibility

Sex/Gender
All
Age
18 Years to 60 Years

Inclusion criteria

Inclusion criteria: (1) Patients diagnosed with CD according to the European Crohn's and Colitis Organization (ECCO) guidelines and aged >= 18 years; (2) Patients underwent both abdominal non-contrast computed tomography (CT) and bioelectrical impedance analysis (BIA) concurrently within 48 hours of admission.

Exclusion criteria

Exclusion criteria: (1) Baseline data missing rate >20%; (2) Presence of comorbid conditions that may cause sarcopenia (e.g., liver cirrhosis, hyperthyroidism, malignant tumors, severe infections, etc.); (3) Use of glucocorticoids or other medications that affect hydration status; (4) Pregnant or lactating women.

Design outcomes

Primary

MeasureTime frame
Low muscle mass;Accuracy;

Secondary

MeasureTime frame
Sensitivity;Specificity;Abdominal Computed Tomography;

Countries

China

Contacts

Public ContactYu Peng

Xiangya Hospital, Central South University

pengyu918@csu.edu.cn+86 139 7489 9436

Outcome results

None listed

Source: ChiCTR (via WHO ICTRP) · Data processed: Feb 4, 2026