Machine Learning-Based Prediction of Insulin Resistance in Psoriasis Patients Emphasizing Interpretability

NCT07321288 | Active Not Recruiting

• 1 other identifier: S2025-72-01
• Study Type: observational
• Target: 1,265
• Locations: 1 country
• Sites: 1

Brief Summary

Psoriasis is a long-term inflammatory skin disease that can affect overall health. People with psoriasis have a higher risk of developing insulin resistance, a condition in which the body does not respond properly to insulin. Insulin resistance can increase the risk of diabetes, heart disease, and other serious health problems. Because insulin resistance often develops without clear symptoms, many patients are not diagnosed early. The purpose of this study is to identify which patients with psoriasis are more likely to develop insulin resistance and to create a tool that can help doctors estimate this risk for individual patients. The study will use existing medical records from two medical centers. Researchers will analyze information such as age, body weight, psoriasis severity, blood test results, other medical conditions, and medication history. Machine learning methods will be used to analyze these data and build a prediction model. The model will be designed to be easy to understand, so doctors can see which factors contribute most to insulin resistance risk. This study does not involve any new treatments or procedures. All patient information will be anonymized to protect privacy. The results may help doctors identify high-risk patients earlier and support timely monitoring and preventive care.

Conditions

Psoriasis; Insulin Resistance

Outcome Measures

Primary Outcomes (1)

• Insulin Resistance Status Assessed by the TyG Index

  Insulin resistance will be evaluated using the triglyceride-glucose (TyG) index, calculated from fasting triglyceride and fasting plasma glucose levels obtained from medical records. Participants will be classified as having insulin resistance or not based on a predefined TyG index cutoff value (TyG ≥ 8.5)

  At baseline (using existing medical record data collected between January 2015 and June 2025)

Eligibility Criteria

• Age: 18 Years+
• Sex: all
• Healthy Volunteers: No
• Age Groups: Adult (18-64), Older Adult (65+)
• Sampling Method: Non-Probability Sample

Study Population

The study population includes adult patients with psoriasis who received routine clinical care at Chinese PLA General Hospital (First Medical Center) and a collaborating center (Fourth Medical Center) in China. Participants are identified from hospital-based clinical databases and electronic medical records collected during routine dermatology practice between January 2015 and June 2025. The population represents a real-world cohort of patients with psoriasis receiving standard medical care in tertiary hospitals. Data used in this observational study are collected retrospectively, and all patient information is anonymized prior to analysis. No interventions or additional procedures are performed as part of the study.

You may qualify if:

• Adults aged 18 years or older
• Diagnosed with psoriasis (including plaque psoriasis, pustular psoriasis, erythrodermic psoriasis, or other clinically recognized subtypes), according to established clinical diagnostic guidelines
• Received medical care at Chinese PLA General Hospital (First Medical Center) or the collaborating center (Fourth Medical Center) during the study period
• Availability of complete medical records, including demographic information, relevant clinical characteristics, and laboratory data required to assess insulin resistance

You may not qualify if:

• Previous or current diagnosis of diabetes mellitus
• Presence of severe systemic diseases that may significantly affect glucose metabolism (such as malignant tumors, hyperthyroidism, or other serious endocrine disorders)
• Current or recent use of systemic medications known to affect insulin sensitivity, including:Systemic corticosteroids,Glucose-lowering medications, or Other medications with known significant effects on insulin resistance
• Pregnant or breastfeeding women
• Medical records with missing key variables required for the assessment of insulin resistance or model development

Sponsors & Collaborators

• Chinese PLA General Hospital: lead

Study Sites (1)

Chinese PLA General Hosptial

Beijing, None Selected, 100853, China

Location

MeSH Terms

Conditions

Psoriasis; Insulin Resistance

Condition Hierarchy (Ancestors)

Skin Diseases, Papulosquamous; Skin Diseases; Skin and Connective Tissue Diseases; Hyperinsulinism; Glucose Metabolism Disorders; Metabolic Diseases; Nutritional and Metabolic Diseases

Study Design

• Study Type: observational
• Observational Model: COHORT
• Time Perspective: RETROSPECTIVE
• Sponsor Type: OTHER
• Responsible Party: PRINCIPAL INVESTIGATOR
• PI Title: Resident Physician

Study Record Dates

• First Submitted: December 22, 2025
• First Posted: January 7, 2026
• Study Start: September 1, 2025
• Primary Completion (Estimated): September 1, 2026
• Study Completion (Estimated): September 1, 2026
• Last Updated: May 8, 2026

Record last verified: 2025-09

Locations

CN (1)