P1681 - Diagnostic Accuracy of Artificial Intelligence in the Diagnosis of Liver Fibrosis: A Systematic Review and Meta Analysis

Keerthi Balaji Babu Naidu, ¹, Vinay Chandramouli Bellur, ¹, Omar Oudit, DO², Ananya Prasad, ³, Shradha Chervittara Karaveetil, ³, Deepika A, ⁴, Shreya Narayan, ⁵, Anusha Giri, ³, Pavan Kumara Kasam Shiva, ⁴, Deepak Bhat, MBBS⁶, Diya Suhas, ⁷, Vardhini Ganesh Iyer, ⁸, Disha Prashanth, ⁹, Trisha Chandra Mohan, ⁸, Druvadeep Srinivas, ¹⁰, Rishikesh R. Magaji, ⁸, Adithya Sathya narayana, MBBS¹¹, Sravani Bhavanam, ¹², Prakriti Ramamurthy, MBBS, MD¹³
1Ramaiah medical college, Bangalore, Karnataka, India; 2Brookdale University Hospital Medical Center, Brooklyn, NY; 3ramaiah medical college, Bangalore, Karnataka, India; 4bangalore medical college and research institute, Bangalore, Karnataka, India; 5Bangalore Medical College and Research Institute, Bangalore, Karnataka, India; 6M. S Ramaiah Medical College, Bangalore North, Karnataka, India; 7Bangalore Medical College, Bangalore, Karnataka, India; 8BGS Global Institute of Medical Sciences, Bangalore, Karnataka, India; 9Ramaiah Medical College, Bangalore, Karnataka, India; 10rajarajeshwari medical college & hospital, Bangalore, Karnataka, India; 11M S Ramaiah Medical College, Bangalore, Karnataka, India; 12Brookdale University Hospital Medical Center, Bangalore, Karnataka, India; 13University of Massachusetts Chan Medical School - Baystate Health, Springfield, MA

Introduction: Chronic liver disease (CLD) is a global health burden where early detection of liver fibrosis is critical for prognosis and management. Conventional methods like biopsy are invasive, while serum biomarkers often lack precision. Recent studies have demonstrated that machine learning algorithms applied to MRI data can enhance diagnostic accuracy for fibrosis detection. This meta-analysis assesses the performance of AI-based imaging tools in diagnosing liver fibrosis in CLD.

Methods: The study follows the PRISMA guidelines and multiple major medical databases were searched by creating a Boolean search string to retrieve and select articles which assessed the accuracy of Machine learning, Deep learning and Neural Network models in diagnosis of Liver Fibrosis.The R Studio package was used to evaluate the diagnostic test accuracy. The Meta, Metadata and Mada packages were utilized to evaluate Pooled Area Under Curve and Pooled Accuracy based on the imaging modality used. The heterogeneity of the studies was assessed using the I^2 test.

Results: This study included a total of 17 studies where 40073 images from 17459 patients were analysed by Artificial Intelligence Software. The pooled Area Under the Curve (AUC) Set 1 was 0.98 (I^2=0.6% ,95% CI [0.96,1.00]) and in Set 2 was 0.90 ( I^2=0.0%, 95% CI [0.84-0.96]). The Pooled accuracy was 87% (I^2=98.4%, 95% CI [0.80-0.91]); and for respective subgroups: Pooled Accuracy specifically in patients who underwent Ultrasound was 81%( I^2= 86.6%, 95%CI [0.72-0.88]), in patients undergoing CECT was 87% (I^2=98.5%, 95%CI [0.81-0.92]) and in patients who underwent MRI was 89% (I^2=97.9%, 95% CI [0.68-0.97]).

Discussion: The high pooled AUC and Accuracy highlights the efficacy of Artificial Intelligence in identifying liver fibrosis proving its role in improvement of detection and management of liver fibrosis. The highest accuracy was obtained through AI analysis of MRI images in comparison with CECT and Ultrasound images. This suggests that Machine Learning Algorithms using MRI images show highest Accuracy in the detection of Liver Fibrosis.

Disclosures:
Keerthi Balaji Babu Naidu indicated no relevant financial relationships.
Vinay Chandramouli Bellur indicated no relevant financial relationships.
Omar Oudit indicated no relevant financial relationships.
Ananya Prasad indicated no relevant financial relationships.
Shradha Chervittara Karaveetil indicated no relevant financial relationships.
Deepika A indicated no relevant financial relationships.
Shreya Narayan indicated no relevant financial relationships.
Anusha Giri indicated no relevant financial relationships.
Pavan Kumara Kasam Shiva indicated no relevant financial relationships.
Deepak Bhat indicated no relevant financial relationships.
Diya Suhas indicated no relevant financial relationships.
Vardhini Ganesh Iyer indicated no relevant financial relationships.
Disha Prashanth indicated no relevant financial relationships.
Trisha Chandra Mohan indicated no relevant financial relationships.
Druvadeep Srinivas indicated no relevant financial relationships.
Rishikesh R. Magaji indicated no relevant financial relationships.
Adithya Sathya narayana indicated no relevant financial relationships.
Sravani Bhavanam indicated no relevant financial relationships.
Prakriti Ramamurthy indicated no relevant financial relationships.

Keerthi Balaji Babu Naidu, ¹, Vinay Chandramouli Bellur, ¹, Omar Oudit, DO², Ananya Prasad, ³, Shradha Chervittara Karaveetil, ³, Deepika A, ⁴, Shreya Narayan, ⁵, Anusha Giri, ³, Pavan Kumara Kasam Shiva, ⁴, Deepak Bhat, MBBS⁶, Diya Suhas, ⁷, Vardhini Ganesh Iyer, ⁸, Disha Prashanth, ⁹, Trisha Chandra Mohan, ⁸, Druvadeep Srinivas, ¹⁰, Rishikesh R. Magaji, ⁸, Adithya Sathya narayana, MBBS¹¹, Sravani Bhavanam, ¹², Prakriti Ramamurthy, MBBS, MD¹³. P1681 - Diagnostic Accuracy of Artificial Intelligence in the Diagnosis of Liver Fibrosis: A Systematic Review and Meta Analysis, ACG 2025 Annual Scientific Meeting Abstracts. Phoenix, AZ: American College of Gastroenterology.