EUVIMEDEUVIMED entdecken
Crossref

IOT-ENABLED MULTI-MODAL SYMPTOM FUSION FOR REAL-TIME EARLY PREDICTION OF ALZHEIMER'S DISEASE

KALA B, P. LATHA, P. ANBUMANI, KAVIYA R, M. SANGEETHA, MANIMOZHI S

International Journal of Drug Delivery Technology · 01.07.2026 · 16 (60s)

DOI: 10.25258/ijddt.16.60s.151 ↗

Kurz gefasst

Fachartikel in der Zeitschrift International Journal of Drug Delivery Technology, online erschienen am 01.07.2026. Verfasst von KALA B und 5 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

The timely prevention of the Alzheimer disease (AD) is crucial, but the standard tests usually fail to identify the subtle cognitive, behavioral, and physiological changes in the patient. In this paper, a hybrid, IoT-based human-centered model of real-time advanced AD prediction with Multi-Mode Symptom Fusion (MMSF) is described. Materials and Methods The system constantly gathers various data on the patients such as cognitive tests, speech analysis, mood analysis, and daily activity indicator using wearables and smartphones IoT devices. The low-latency UDP communication is used to transmit data and enable synchronized multi-source streaming to a central processing unit. MMSF combines these heterogeneous signals into a single feature representation, the interdependencies between these features are very complicated and MMSF can capture this interdependency which often cannot be captured by single-modality based approaches. The fused features are analyzed using advanced machine learning algorithms to assign the patients into low, medium or high AD risk group. Continuous visualization, trend tracking, and real-time alerts are offered by an interactive dashboard of the IoT to facilitate proactive intervention.

Results

Experimental measures of simulated data reveals that in comparison to conventional unimodal evaluation methods MMSF that incorporates real time IoT monitoring performs better at prediction.

Conclusion

It is a non-invasive and proactive framework that can be scaled to provide an early detection of Alzheimer disease, allowing it to monitor the disorder on a personal level as well as intervene with the disease in time. The suggested solution will be a bridging solution that combines wearable IoT sensing, multi-modal data fusion, and predictive analytics that would bring to fruition the possibility of continuous neurodegenerative health monitoring.

Zitieren

APA

B, K., LATHA, P., ANBUMANI, P., R, K., SANGEETHA, M., & S, M. (2026). IOT-ENABLED MULTI-MODAL SYMPTOM FUSION FOR REAL-TIME EARLY PREDICTION OF ALZHEIMER'S DISEASE. International Journal of Drug Delivery Technology, 16(60s). https://doi.org/10.25258/ijddt.16.60s.151

Vancouver

B K, LATHA P, ANBUMANI P, R K, SANGEETHA M, S M. IOT-ENABLED MULTI-MODAL SYMPTOM FUSION FOR REAL-TIME EARLY PREDICTION OF ALZHEIMER'S DISEASE. International Journal of Drug Delivery Technology. 2026;16(60s). doi:10.25258/ijddt.16.60s.151

BibTeX
@article{B2026,
  author = {B, KALA and LATHA, P. and ANBUMANI, P. and R, KAVIYA and SANGEETHA, M. and S, MANIMOZHI},
  title = {IOT-ENABLED MULTI-MODAL SYMPTOM FUSION FOR REAL-TIME EARLY PREDICTION OF ALZHEIMER'S DISEASE},
  journal = {International Journal of Drug Delivery Technology},
  year = {2026},
  volume = {16},
  number = {60s},
  doi = {10.25258/ijddt.16.60s.151}
}
Kostenlos starten →