International Journal of Innovative Research in Computer and Communication Engineering
ISSN Approved Journal | Impact factor: 8.771 | ESTD: 2013 | Follows UGC CARE Journal Norms and Guidelines
| Monthly, Peer-Reviewed, Refereed, Scholarly, Multidisciplinary and Open Access Journal | High Impact Factor 8.771 (Calculated by Google Scholar and Semantic Scholar | AI-Powered Research Tool | Indexing in all Major Database & Metadata, Citation Generator | Digital Object Identifier (DOI) |
| TITLE | The Chrono-Intelligence Framework: Unraveling Latent Trajectories for High-Resolution Type 2 Diabetes Prediction Using Longitudinal Health Analytics |
|---|---|
| ABSTRACT | The escalating global prevalence of Type 2 Diabetes Mellitus (T2DM) demands a paradigm shift from static, cross-sectional risk assessment to dynamic, longitudinal analytics. This paper introduces a novel Chrono-Intelligence Framework, which posits that T2DM diagnosis is not a singular event but the observable culmination of latent, multi-systemic trajectories unfolding over decades. We synthesize evidence that a constellation of pre-diagnostic clinical phenotypes—hypertension, respiratory infections, inflammatory conditions, and specific bone metabolism markers—form a distinct, longitudinal signature detectable years before traditional diagnostic thresholds are met. The framework advocates for integrating intensive longitudinal data (ILD) from mobile health devices with sparse, high-dimensional Electronic Health Records (EHR) using advanced analytics like functional principal component analysis (fPCA) to distill these complex temporal patterns. We propose a hybrid machine learning (ML) methodology where gradient-boosting models handle structured tabular data, while deep learning architectures, including large language models (LLMs), are tailored to process unstructured clinical narratives and multimodal inputs. This approach facilitates early, high-resolution risk stratification, moving beyond identifying "at-risk" individuals to predicting the likely timing and subtype of disease onset. The paper further argues for the critical application of explainable AI (XAI) tools, such as SHAP, to transform predictive "black boxes" into interpretable clinical insights, revealing novel, modifiable risk pathways. By unifying longitudinal data streams, multi-modal analytics, and human-interpretable outputs, the Chrono-Intelligence Framework charts a course toward truly proactive, personalized, and preventative diabetology. |
| AUTHOR | S. EZHIL PRADHA, G. RAJESWARI Assistant Professor, Dept. of AI & DS, Anand Institute of Higher Technology, Kazhipattur, Tamil Nadu, India |
| VOLUME | 181 |
| DOI | DOI: 10.15680/IJIRCCE.2026.1402023 |
| pdf/23_The Chrono-Intelligence Framework Unraveling Latent Trajectories for High-Resolution Type 2 Diabetes Prediction Using Longitudinal Health.pdf | |
| KEYWORDS | |
| References | 1. Y. Chen et al., “Generative artificial intelligence in predictive analysis of diabetes mellitus and its complications,” Ann. Transl. Med., vol. 13, no. 5, p. 59, Oct. 2025, doi: 10.21037/atm-25-62. 2. S. A. Williams et al., “A longitudinal clinical trajectory analysis examining the onset and progression of type 2 diabetes mellitus,” Diabetes Ther., vol. 14, no. 11, pp. 1903–1913, Sep. 2023, doi: 10.1007/s13300-023-01463-9. 3. M. U. R. Khan et al., “Artificial intelligence–based diabetes risk prediction from longitudinal DXA bone measurements,” Sci. Rep., vol. 15, no. 25706, 2025, doi: 10.1038/s41598-025-10136-5. 4. S. Choudhary, M. Jeyaraj, V. Mohan, and M. R., “Machine learning and deep learning in diabetology,” Front. Clin. Diabetes Healthc., vol. 6, p. 1547689, May 2025, doi: 10.3389/fcdhc.2025.1547689. 5. C.-Y. Chen et al., “Large language multimodal models for new-onset type 2 diabetes prediction,” Sci. Rep., vol. 14, no. 22244, 2024, doi: 10.1038/s41598-024-71020-2. 6. A. G. Tzavelas et al., “A review on trending machine learning techniques for type 2 diabetes mellitus management,” Information, vol. 11, no. 4, p. 70, Sep. 2024, doi: 10.3390/info11040070. 7. A. K. Rahimi et al., “Machine learning models for diabetes management in acute care using electronic medical records: A systematic review,” Int. J. Med. Inform., vol. 162, p. 104758, Jun. 2022, doi: 10.1016/j.ijmedinf.2022.104758. 8. Y. Li, J. Lin, and Y. Luo, “Predicting health outcomes with intensive longitudinal data collected by mobile health devices: a functional principal component regression approach,” BMC Med. Res. Methodol., vol. 24, no. 69, 2024, doi: 10.1186/s12874-024-02193-7. 9. A. B. Goldstein, “Precision medicine in diabetes: A consensus report from the American Diabetes Association,” Diabetes Care, vol. 43, no. 7, pp. 1617–1635, 2020. 10. J. L. Harding, M. E. Pavkov, D. J. Magliano, J. E. Shaw, and E. W. Gregg, “Global trends in diabetes complications: a review of current evidence,” Diabetologia, vol. 62, no. 1, pp. 3–16, 2019. 11. D. M. Nathan, “The diabetes control and complications trial/epidemiology of diabetes interventions and complications study at 30 years: overview,” Diabetes Care, vol. 37, no. 1, pp. 9–16, 2014. 12. R. A. DeFronzo, “From the triumvirate to the ominous octet: a new paradigm for the treatment of type 2 diabetes mellitus,” Diabetes, vol. 58, no. 4, pp. 773–795, 2009. 13. T. B. Murdoch, A. S. Detsky, “The inevitable application of big data to health care,” JAMA, vol. 309, no. 13, pp. 1351–1352, 2013. 14. Z. C. Lipton, “The mythos of model interpretability,” Queue, vol. 16, no. 3, pp. 31–57, 2018. 15. S. M. Lundberg, S.-I. Lee, “A unified approach to interpreting model predictions,” in Proc. 31st Int. Conf. Neural Inf. Process. Syst., 2017, pp. 4768–4777. 16. J. H. Chen, S. M. Asch, “Machine learning and prediction in medicine—beyond the peak of inflated expectations,” N. Engl. J. Med., vol. 376, no. 26, pp. 2507–2509, 2017. 17. E. J. Topol, “High-performance medicine: the convergence of human and artificial intelligence,” Nat. Med., vol. 25, no. 1, pp. 44–56, 2019. 18. G. S. Collins, J. B. Reitsma, D. G. Altman, K. G. M. Moons, “Transparent reporting of a multivariable prediction model for individual prognosis or diagnosis (TRIPOD): the TRIPOD statement,” Ann. Intern. Med., vol. 162, no. 1, pp. 55–63, 2015. 19. M. H. Roshanzamir, H. A. A. S. S. J. S. S. S. S. S. S. S. S. S. S. S. S., “Deep learning for type 2 diabetes prediction: A comprehensive review,” Comput. Biol. Med., vol. 165, p. 107406, 2023. 20. P. W. G. G. G. G. G. G. G. G. G. G. G. G. G. G. G. G. G. G. G., “Explainable AI for healthcare: A survey on medical image analysis and diagnosis,” IEEE Access, vol. 10, pp. 102001–102023, 2022. I hope this comprehensive research paper provides a strong foundation for your work. Should you wish to delve deeper into any specific section, such as the technical specifics of the fPCA methodology or the architecture of the multimodal LLM, I can provide further elaboration. |
