1Department of Radio-Diagnosis, Meenakshi Medical College Hospital and Research Institute, Meenakshi Academy of Higher Education and Research
2Department of Pharmacology, Meenakshi Ammal Dental College and Hospital, Meenakshi Academy of Higher Education and Research
3Meenakshi College of Pharmacy, Meenakshi Academy of Higher Education and Research
4Meenakshi College of Nursing, Meenakshi Academy of Higher Education and Research
5Meenakshi College of Physiotherapy, Meenakshi Academy of Higher Education and Research
6Department of Radiology, Meenakshi College of Allied Health Sciences, Meenakshi Medical College Hospital & Research Institute, Meenakshi Academy of Higher Education and Research
Background: Asymptomatic valvular heart disease (VHD) poses a problem in terms of first-level risk, because the parameter parameters of conventional echocardiography do not identify the subtle myocardial dysfunction before symptoms occur. Strain imaging that is based on the use of echo provides greater sensitivity, and advanced artificial intelligence (AI) technologies can also lead to additional progress in the field of prognostic evaluation.
Objective: To determine whether left-ventricular and left-atrial strain imaging with AI-based predictive modeling has a benefit over outcome prediction in patients with asymptomatic VHD.
Method: This was a prospective cohort study that involved adults, moderate aortic or mitral disease, and preserved ejection fraction. At baseline, there was an Echocardiography and speckle-tracking strain imaging. Occurrences of clinical, imaging and biomarker data were introduced as supervised machine-learn models. The advancement to symptoms, reduction of ejection fraction and intervention necessitation within a median follow up of three years was among the primary outcomes.
Results: The combined strain-AI model had an AUC of 0.89 to predict clinical progression, which was better compared to a model constructed using the conventional echo parameters alone (AUC 0.71) or strain imaging alone (AUC 0.81). The main predictive characteristics were global longitudinal strain, left-atrial reservoir strain and subclinical diastolic abnormalities. High-risk patients had very high onset rates and earlier requirements to have their valves repaired.
Conclusion: Strain imaging with AI aids in the prediction of early outcomes in asymptomatic VHD significantly, which is why it could be used in the context of personalised warning and timely intervention design.
Keywords: Echocardiographic strain imaging, left atrial strain, early risk stratification, AI, asymptomatic valvular heart disease.
How to cite this article: Premkumar U, Vijaya TV, Karpagavalli, Sherley J, Sureshkumar S, Eswar. Echo-Derived Strain Imaging Combined With AI to Predict Outcomes in Asymptomatic Valvular Disease. Int J Drug Deliv Technol. 2026;16(10s): 132-137; DOI: 10.25258/ijddt.16.10s.19
Source of support: Nil.
Conflict of interest: None