Through a deep plunge into the advancements in medical technology for cardiovascular research, Ketan Gupta: a research scientist at the University of The Cumberlands in the United States, discovered an artificial intelligence-based machine learning model that decodes the determinants of cardiac abnormalities to predict the onset of cardiac arrest at early stages and also interpret its prospect with accuracy.
Cardiovascular conditions are a severe concern in all age groups and surge the fatality rate if not diagnosed and treated on time. The complexity of estimating cardiac arrest at the initial stages is challenging and develops a confusion gap for physicians to distinguish normal chest pain from cardiac arrest. In this mixed confusion, patients are provided with palliative care, which standalone is insufficient to win the battle of the life-threatening condition. With this aforementioned thought, Ketan’s research brought a ray of hope to the medical and healthcare practitioners to identify critical parameters that may be a potential cause of cardiac arrest at earlier stages. According to the doctors, this research is paramount, which triggers an alarm to the physicians to focus on specific parameters in a considerable amount of time before the situation gets out of control.
According to Ketan, the uniqueness of this study relies on lab experiments using statistical analysis and simulation models in conjunction with Fourier Transform Infrared Spectroscopy techniques to uncover hidden patterns for image processing. The strength of this model is to unravel accurate velocity patterns and recognize objects from various angles, even if the data remains inconsistent or mislaid. The model was trained and tested on multiple machine learning algorithms based on critical and large datasets to determine the performance, followed by implementing neural networks. Ketan says, the innovative model has shown consistent and accurate results in identifying the severity of cardiac arrest based on factors such as the patient’s age, ejection fraction or fibrillation of the heart ventricle, and the patient’s follow-up time with the physician. The model also incorporates natural language processing (NLP) techniques that allow physicians to feed real-time unstructured data by voice command in the algorithm during cardiac surgeries. This unique functionality enables cardiologists to investigate emergencies and take immediate action to improve the survival rate of patients.
Ketan is accoladed with awards and recognition for his scientific contribution to the research community, highlighting his excellence level. Kudos to Ketan Gupta for his outstanding research and for demonstrating the power of machine learning in medical science.
