Internet-of-things based machine learning enabled medical decision support system for prediction of health issues

Purpose The main purpose of this paper is to develop and test internet of things (IoT) based physiological parameters monitoring system. This system is implemented using different multilabel classifier (MLC) algorithms and have been used for the health status prediction and classifications. Method A...

Full description

Saved in:
Bibliographic Details
Published in:Health and technology 2023-11, Vol.13 (6), p.987-1002
Main Authors: Sahu, Manju Lata, Atulkar, Mithilesh, Ahirwal, Mitul Kumar, Ahamad, Afsar
Format: Article
Language:English
Subjects:
Algorithms
Biological and Medical Physics
Biomedical Engineering and Bioengineering
Biomedicine
Biophysics
Blood pressure
Classification
Computational Biology/Bioinformatics
Data analysis
Decision making
Decision support systems
Empowerment
Engineering
Failure analysis
Heart rate
Internet of Things
Machine learning
Medical equipment
Medical personnel
Medicine/Public Health
Monitoring systems
Original Paper
Oxygen saturation
Parameters
Physiology
R & D/Technology Policy
Respiration
Citations: Items that this one cites
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Purpose The main purpose of this paper is to develop and test internet of things (IoT) based physiological parameters monitoring system. This system is implemented using different multilabel classifier (MLC) algorithms and have been used for the health status prediction and classifications. Method A method has been proposed and developed as medical decision support system (MDSS) based on the outcome of the different MLC algorithms. The developed MDSS enables real time assistance to local and remote supervisor for in time decision better diagnosis plan Results The performance parameters and results of the different MLC algorithms has been evaluated, in terms of several, Accuracy, Precision, Recall F-measure, and MCC etc. to identify the best algorithm for classification and prediction of health status. Gradient Boost algorithm of classification outperform the other algorithm and achieved approx 94% of accuracy. Conclusions This study concludes that the developed MDSS will be very useful in remote areas to assist patient and health practitioners to predict heath status and for quick decision making in case of medical emergencies.
ISSN:2190-7188
2190-7196
DOI:10.1007/s12553-023-00790-y