AI-Powered Echocardiogram Analysis for Predicting Future Heart Failure in Asymptomatic Diabetic Patients
Main Article Content
Abstract
Background: Heart failure is a major complication of type 2 diabetes mellitus and may develop silently through subclinical myocardial dysfunction before overt symptoms appear. Conventional echocardiography can identify structural and functional abnormalities, but subtle changes in myocardial deformation and diastolic function may be under-recognized in routine practice. Artificial intelligence-assisted echocardiographic analysis may improve early risk stratification by integrating multidimensional imaging parameters. Objective: To determine whether AI-assisted echocardiographic-guided care improves short-term markers of subclinical cardiac dysfunction compared with standard echocardiographic care in asymptomatic adults with type 2 diabetes mellitus. Methods: A parallel-group randomized controlled trial was conducted over six months in the Islamabad-Rawalpindi region. Seventy-eight asymptomatic adults with type 2 diabetes mellitus were randomized equally to AI-assisted echocardiographic-guided care or standard echocardiographic care. The active intervention period lasted 12 weeks. The final complete-case analysis included 72 participants. Primary outcomes were global longitudinal strain and E/e′ ratio; secondary outcomes included left ventricular ejection fraction, HbA1c, and newly detected subclinical dysfunction. Results: At 12 weeks, the AI-assisted group showed better global longitudinal strain than standard care (-18.9 ± 2.1 vs -16.7 ± 2.4; p<0.001), lower E/e′ ratio (9.8 ± 1.9 vs 12.1 ± 2.3; p<0.001), and higher LVEF (58.6 ± 5.2 vs 55.9 ± 5.7; p=0.02). Newly detected subclinical dysfunction occurred in 4/36 versus 11/36 participants, respectively. Conclusion: AI-assisted echocardiographic-guided care improved short-term markers of subclinical cardiac dysfunction in asymptomatic patients with type 2 diabetes, supporting its potential role in early cardiovascular risk stratification.
Article Details
Section
This work is licensed under a Creative Commons Attribution 4.0 International License.
How to Cite
References
1. Saeed I, Hashmi MU, Khalid M, Ramzan H, Ibrahim M, Baig MF, et al. The role of artificial intelligence in heart failure diagnostics, risk prediction, and therapeutic strategies: a comprehensive review. 2025;17(7).
2. Kaur N. Cardiovascular disease in type 2 diabetes mellitus: a precision medicine approach applying artificial intelligence for heart failure and mortality prediction. University of Glasgow; 2025.
3. Lee SH, Park JH. The role of echocardiography in evaluating cardiovascular diseases in patients with diabetes mellitus. 2023;47(4):470-83.
4. Medhi D, Kamidi SR, Sree KPM, Shaikh S, Rasheed S, Murichathil AHT, et al. Artificial intelligence and its role in diagnosing heart failure: a narrative review. 2024;16(5):e59661.
5. Rana N, Sharma K, Sharma A. Diagnostic strategies using AI and ML in cardiovascular diseases: challenges and future perspectives. In: Deep Learning and Computer Vision: Models and Biomedical Applications. Vol. 1. Springer; 2025. p. 135-65.
6. Ioannou M, Karelas D, Kalesi AE, Parpas G, Papanastasiou CA, Papadopoulos CH, et al. The contribution of echocardiography to the diagnosis and prognosis stratification of diabetic cardiomyopathy. 2025;15(20):2587.
7. Ikram S, Umar U, Abassi ZW, Khan SHU, Ahmed Z, Bibi A, et al. Artificial intelligence in cardiovascular disease prediction and management: current status and future directions. 2025;12(1).
8. Khan MS, Arshad MS, Greene SJ, Van Spall HG, Pandey A, Vemulapalli S, et al. Artificial intelligence and heart failure: a state-of-the-art review. 2023;25(9):1507-25.
9. Burhanuddin M, Ahmed Z, Hamza A, Zeeshan M, Rehman FA, Gillani SHM, et al. Early detection of diabetic cardiomyopathy using speckle tracking echocardiography: a systematic review. 2025;17(9).
10. Li YH, Wang CC, Hung CL, Wu YW, Hsu CH, Tsou YL, et al. 2024 guidelines of the Taiwan Society of Cardiology for the diagnosis and treatment of heart failure with preserved ejection fraction. 2024;40(2):148.
11. Nanayakkara N, Huang ML, La Gerche A, Kaye DM, Cooper ME, Esler MD, et al. Effects of empagliflozin on cardiac function and cardiorespiratory fitness in people with type 2 diabetes: a randomised controlled trial. 2026;12(1):14.
12. Berezina TA, Berezin OO, Novikov EV, Berezin AE. Low levels of adropin predicted new incidents of atrial fibrillation in patients with heart failure with preserved ejection fraction. 2025;15(8):1171.
13. O’Neill T, Kang P, Hagendorff A, Tayal B. The clinical applications of left atrial strain: a comprehensive review. 2024;60(5):693.
14. Halabi A, Marwick TH. The heart in diabetic hypertensive patients. In: Blood Pressure Disorders in Diabetes Mellitus. Springer; 2023. p. 195-215.
15. Javadi N, Bismee NN, Abbas MT, Scalia IG, Pereyra M, Baba Ali N, et al. Left atrial strain: state of the art and clinical implications. 2024;14(11):1093.
16. Li Z, Li X, Huang W, Gao Z, Zhang P, He C, et al. Echocardiographic insights into cardiovascular autonomic dysfunction in Parkinson’s disease. 2026;16(1):146-58.
17. Bashirov AJ. Journal of Osh State University. Medicine. 4(1):9.
18. Grigorescu ED, Lăcătușu CM, Floria M, Cazac GD, Onofriescu A, Sauciuc LA, et al. Effects of incretin-based treatment on the diastolic dysfunction in patients with uncontrolled type 2 diabetes mellitus: a prospective study with 1-year follow-up. 2023;13(17):2817.