Dies ist eine Übersichtsseite mit Metadaten zu dieser wissenschaftlichen Arbeit. Der vollständige Artikel ist beim Verlag verfügbar.
Integrating AI-Driven IoT Solutions for Enhanced Predictive Analytics in Healthcare a Comprehensive Study on Chronic Disease Management
0
Zitationen
6
Autoren
2024
Jahr
Abstract
The high incidence of chronic non-communicable diseases (NCDs) places a significant financial strain on public health systems. Brazil is projected to see a rise in mortality rates caused by non-communicable diseases (NCDs) by 2030. These include cancer, cardiovascular disease, respiratory illness, and diabetes. The unique challenge of managing chronic and integrated care for NCDs is well-documented. This study presents an AI-based framework for managing chronic diseases and providing digital health services globally. The suggested platform is constructed and supported by healthcare 4.0 technologies, which enable the implementation of a smart healthcare system. Among these innovations are AI-enabled cloud solutions, the internet of medical things, and wearable technology. Also included in the publication is a case study of diabetes prediction that demonstrates the platform's viability. An initial dataset was created for the research case with many attributes, including bio-impedance, skin impedance, skin temperature, pulse rate, and oxygen concentration. In this study, we investigate how the IoT and Artificial Intelligence (AI) are changing the face of illness detection in connected healthcare systems. AI has quickly become an indispensable tool in the healthcare industry, providing advanced algorithms for evaluating medical data and facilitating forecasting and decision-making. The internet of things (IoT) improves upon this by allowing web-enabled devices, such as implanted sensors and wearables, to continuously gather data. By integrating AI and IoT, smart healthcare systems improve medical procedures, patient experiences, and operational operations. Rapid and reliable disease diagnosis is made possible by combining AI-driven procedures with IoT data streams. This paper aims to overcome the limitations of traditional methods, which are typically influenced by human biases.
Ähnliche Arbeiten
Biostatistical Analysis
1996 · 35.446 Zit.
UCI Machine Learning Repository
2007 · 24.290 Zit.
An introduction to ROC analysis
2005 · 20.711 Zit.
The use of the area under the ROC curve in the evaluation of machine learning algorithms
1997 · 7.126 Zit.
A method of comparing the areas under receiver operating characteristic curves derived from the same cases.
1983 · 7.067 Zit.