A data analytics suite for exploratory predictive, and visual analysis of type 2 diabetes

Merupo, Surya Saharsha and Karri, Ganesh Reddy and Jami, Sai Tharun and Chirumamilla, Akash and Rahman, Habeeb Ur (2025) A data analytics suite for exploratory predictive, and visual analysis of type 2 diabetes. World Journal of Advanced Engineering Technology and Sciences, 15 (1). pp. 1731-1740. ISSN 2582-8266

The development of cloud, big data, and AI technologies has also created much interest in building data-driven approaches for health care, including dealing with chronic diseases such as T2D. This proposal outlines a set of data analytics for managing T2D disease, where clinical and research practitioners can determine relations between patient biomarkers and T2D correlated compliances, tendencies, and potential patient reactions to treatments. The analytics uses sophisticated data analysis methods with further potential to support clinicians and improve T2D outcomes directly, as supported by Smith & Jones [2][6]. Research Statement: Due to the significant variation in the demographics of T2D patients and how they respond to treatments, it is difficult to know the best course of action for clinicians. The data analysis review can offer information that can help manage the T2D in a personalized manner. Prior studies have shown that using big data in community health can help develop more appropriate treatment plans according to the results found, hence improving the patients’ profile. Conjecture: By establishing a range of data analytical solutions, including exploratory and predictive tools, clinicians would be better placed to make evidence-based decisions regarding t2d patient management and therapeutic interventions, hence improving overall results as observed by Patel and Reddy [5]. It extends this idea in our project by creating a full-stack data analytics solution. This suite will: Combine multiple data sources: Include data on patient demographics, laboratory tests, treatments received, and, in some cases, genomics. Utilize advanced analytics techniques: Use classification algorithms to group patients and subsequent generation of models for possible complications and response to treatment. Offer clear visualizations: Provide numerical and graphical representation of data for quick and easy analysis and aid the clinician in decision-making. Catalyzing these elements together, this suite will enable clinicians to enhance T2D management by customizing treatment protocols according to patient characteristics, as highlighted by Nguyen and Tran [2][4].