Saved in:
Bibliographic Details
Main Authors: Thomas, Teena, Devis, Jinson
Format: Recurso digital
Language:English
Published: Zenodo 2025
Online Access:https://doi.org/10.5281/zenodo.15354909
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866902064677781504
author Thomas, Teena
Devis, Jinson
author_facet Thomas, Teena
Devis, Jinson
contents <h3><span><span lang="EN-US">Abstract -</span></span> <span><span lang="EN-US">This research introduces a new predictive system that is made to assess the level of iron deficiency in donors based on hemoglobin, through machine learning methods. This system employs the World Health Organization (WHO) guidelines and uses a Random Forest classifier to classify users into four categories of severity: severe, moderate, mild and normal. The platform allows donors to receive instant feedback of their iron deficiency status, suggested dietary recommendations for iron improvement, and access their health history, thereby improving monitoring efforts, safely can donate, and manage iron deficiency more efficiently. The state of being informed and advised will also help keep donors healthy, while limiting donor deferrals related to iron status, contributing to the sustainability of blood programs long term. Overall, the use of machine learning in conjunction with a web platform for health and nutritional recommendations is a highly innovative advancement using Artificial Intelligence (AI) in blood donor health management. The system collects hemoglobin level readings and additional health data from blood donors, trains a Random Forest classifier using previously collected historical blood donor data, with the WHO guidelines, and integrates the model within a web platform built on Django for real time status predictions. The donor inputs their health data for their current health status, and the website will instantaneously provide a single classification of current iron deficiency status, or not, and a recommendation for dietary improvement. The model essentially provides the donor with a real time feedback loop of knowledge about their health, advising on dietary recommendations to maintain optimal iron levels, thereby importing the donor's eligibility for future donations. Overall, the use of a machine learning based recommendation system, alongside a donor centric web platform, produces a positive outcome for blood donors while improving the overall efficiency and blood donation program safety.</span></span></h3>
format Recurso digital
id zenodo_https___doi_org_10_5281_zenodo_15354909
institution Zenodo
language eng
publishDate 2025
publisher Zenodo
record_format zenodo
spellingShingle AI-Enhanced Iron Status Monitoring & Diet Recommendation System
Thomas, Teena
Devis, Jinson
<h3><span><span lang="EN-US">Abstract -</span></span> <span><span lang="EN-US">This research introduces a new predictive system that is made to assess the level of iron deficiency in donors based on hemoglobin, through machine learning methods. This system employs the World Health Organization (WHO) guidelines and uses a Random Forest classifier to classify users into four categories of severity: severe, moderate, mild and normal. The platform allows donors to receive instant feedback of their iron deficiency status, suggested dietary recommendations for iron improvement, and access their health history, thereby improving monitoring efforts, safely can donate, and manage iron deficiency more efficiently. The state of being informed and advised will also help keep donors healthy, while limiting donor deferrals related to iron status, contributing to the sustainability of blood programs long term. Overall, the use of machine learning in conjunction with a web platform for health and nutritional recommendations is a highly innovative advancement using Artificial Intelligence (AI) in blood donor health management. The system collects hemoglobin level readings and additional health data from blood donors, trains a Random Forest classifier using previously collected historical blood donor data, with the WHO guidelines, and integrates the model within a web platform built on Django for real time status predictions. The donor inputs their health data for their current health status, and the website will instantaneously provide a single classification of current iron deficiency status, or not, and a recommendation for dietary improvement. The model essentially provides the donor with a real time feedback loop of knowledge about their health, advising on dietary recommendations to maintain optimal iron levels, thereby importing the donor's eligibility for future donations. Overall, the use of a machine learning based recommendation system, alongside a donor centric web platform, produces a positive outcome for blood donors while improving the overall efficiency and blood donation program safety.</span></span></h3>
title AI-Enhanced Iron Status Monitoring & Diet Recommendation System
url https://doi.org/10.5281/zenodo.15354909