EUVIMEDEUVIMED entdecken
Crossref

AI-Driven Predictive Analytics for Chronic Disease Prevention Using Electronic Health Records and Iot-Enabled Patient Monitoring

Atish Peshattiwar, Shahnazeer C K, Prof. Kishore Hn, T. Prab, Prof. Faiz Aman, Dr. K. Kiran Kuma

International Journal of Drug Delivery Technology · 25.05.2026 · 16 (32s)

DOI: 10.25258/ijddt.16.32s.31 ↗

Kurz gefasst

Fachartikel in der Zeitschrift International Journal of Drug Delivery Technology, online erschienen am 25.05.2026. Verfasst von Atish Peshattiwar und 5 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Cardiovascular disorders, diabetes, respiratory diseases, and other chronic diseases are one of the most prevalent causes of death worldwide, causing the need to develop both proactive and data-driven healthcare solutions. Conventional diagnostic systems are largely reactive and usually not able to identify risks of disease at an early stage. As such, artificial intelligence now combined with Electronic Health Records (EHR) and IoT-powered patient monitoring systems is one of the promising methods of early chronic disease prediction and prevention. This paper suggests an artificial intelligence-based predictive analytics system that integrates past clinical data and current physiological indicators to improve risk assessment of diseases. The methodology is based on the gathering of heterogeneous data in EHR repositories and IoT devices and then preprocessing to clean and normalize data and feature engineering. The machine learning and deep learning models such as the Random Forest and Long Short-Term Memory (LSTM) networks are created to analyze both time-series and the static data as well. All the models are trained and tested on conventional evaluation metrics like accuracy, precision, recall, F1-score, and Area Under the Curve (AUC). The experimental outcomes confirm that the framework proposed can attain the accuracy of about 95%, and the precision and recall values are more than 92% and 95% percent, respectively. IoT data embedded into the predictive performance enhances the predictive performance by almost 10 percent, whereas the model has an AUC score of approximately 0.97, which represents good classification capabilities. Also, risk stratification is effective to identify low, medium, and high-risk patients and justify specific actions.

Zitieren

APA

Peshattiwar, A., K, S. C., Hn, P. K., Prab, T., Aman, P. F., & Kuma, D. K. K. (2026). AI-Driven Predictive Analytics for Chronic Disease Prevention Using Electronic Health Records and Iot-Enabled Patient Monitoring. International Journal of Drug Delivery Technology, 16(32s). https://doi.org/10.25258/ijddt.16.32s.31

Vancouver

Peshattiwar A, K SC, Hn PK, Prab T, Aman PF, Kuma DKK. AI-Driven Predictive Analytics for Chronic Disease Prevention Using Electronic Health Records and Iot-Enabled Patient Monitoring. International Journal of Drug Delivery Technology. 2026;16(32s). doi:10.25258/ijddt.16.32s.31

BibTeX
@article{Peshattiwar2026,
  author = {Peshattiwar, Atish and K, Shahnazeer C and Hn, Prof. Kishore and Prab, T. and Aman, Prof. Faiz and Kuma, Dr. K. Kiran},
  title = {AI-Driven Predictive Analytics for Chronic Disease Prevention Using Electronic Health Records and Iot-Enabled Patient Monitoring},
  journal = {International Journal of Drug Delivery Technology},
  year = {2026},
  volume = {16},
  number = {32s},
  doi = {10.25258/ijddt.16.32s.31}
}
Kostenlos starten →