Amyloidosis, Cardiovascular Diseases, Interstitial Lung Disease, Liver Disorders, Osteoarthritis, Osteoporosis, Peripheral Neuropathy, Pulmonary Complications, RA Complications, Renal Lesions, Rheumatoid Arthritis (RA, Sjogren's Syndrome, Thrombosis, Thyroid Diseases, Vasculitis
Conditions
Keywords
Rheumatoid Arthritis, generative AI, large language model, Rheumatoid arthritis complications
Brief summary
Generative AI (GenAI) based on large language models (LLMs) is expected to improve the diagnosis and treatment of autoimmune diseases. We are studying how GenAI may affect the diagnosis of various complications of rheumatoid arthritis (RA). In a retrospective study using RA patients' EHR records, we will quantify physician adoption of GenAI predictions for RA complications and co-existing diseases. In a prospective observational study, we will assess the feasibility of using GenAI predictions as additional clinical information to help physicians make more complete diagnoses of RA complications and co-existing diseases, including complex, uncommon, or rare conditions.
Interventions
OTHERGenerative AI prediction report for RA complications
Generative AI based on multiple large language models (LLMs) is used to predict potential complications and co-existing diseases in patients with rheumatoid arthritis using EHR data available at admission. Physicians use these AI predictions as additional information to adjust their diagnostic plans during differential diagnosis. The impact of this intervention on the final diagnoses at discharge will be measured. Before the prospective study, the adoptability of the generative AI prediction reports will be validated using EHR records from retrospective RA patients.
Sponsors
Guang'anmen Hospital of China Academy of Chinese Medical Sciences
Study design
Observational model
COHORT
Time perspective
CROSS_SECTIONAL
Eligibility
Sex/Gender
ALL
Healthy volunteers
No
Inclusion criteria
* Patients with an initial diagnosis of rheumatoid arthritis (RA). * All real-world RA inpatients admitted to our department. * Admission occurring within the real-world data study period.
Exclusion criteria
* Patients subsequently confirmed not to have RA during the study.
Design outcomes
Primary
| Measure | Time frame | Description |
|---|---|---|
| Will physicians adopt GenAI predictions in diagnosing RA complications? | Immediately after reviewing patient AI report on the day of admission. | In the routine care workflow, large language models (LLMs) are used to predict potential RA complications for each de-identified patient case and generate an AI report listing possible complications and co-existing diseases. Additional diagnostic tests are suggested to verify the predicted conditions. After reviewing the AI report, physicians immediately evaluate each disease prediction using a 5-point Likert scale (1 = complete disagreement; 2 = disagreement; 3 = neutral; 4 = agreement; 5 = complete agreement). The mean score is calculated as a measure of perceived prediction accuracy. Physicians also indicate whether each specific disease prediction could potentially be adopted or used to assist differential diagnosis (binary: 0 or 1). The percentage of positive adoption responses is calculated as a measure of potential adoption rate, or adoptability. |
Secondary
| Measure | Time frame | Description |
|---|---|---|
| To what extent are RA complication diagnoses actually affected by GenAI predictions? | Immediately after making the final diagnosis at discharge. | Before patient discharge, physicians make final diagnoses and record which diagnosed complications or co-existing diseases were influenced by GenAI prediction information for each patient. The percentage of cases in which GenAI predictions affected the final diagnosis is calculated as a measure of AI's actual impact on routine diagnostic practice. |
Countries
China
Contacts
Primary ContactQuan Jiang Guang'anmen Hospital, China Academy of Chinese Medical Science
Outcome results
None listed