Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{197791,
        author = {Soham Sharma and Sakshi Tamboli and Prof. Rajashree Salunke},
        title = {AnemioOS: An AI-Powered Full-Stack Diagnostic System for Anaemia Detection Using Random Forest Classification and 3D Physiological Simulation},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {11},
        pages = {7913-7917},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=197791},
        abstract = {Anaemia, characterised by a deficiency of haemoglobin (Hb) in the blood, affects more than 1.62 billion individuals worldwide and represents a major cause of disability, particularly in low- and middle-income nations. Early and accurate detection is critical, yet resource-constrained clinical environments frequently hinder timely diagnosis. This paper presents AnemioOS (Anemio (Anaemia AI Monitor and Intelligent Output System)), a full-stack intelligent diagnostic framework comprising: (i) a machine learning module based on a fine-tuned Random Forest classifier achieving 95% accuracy on a synthetically generated haematological dataset; (ii) a RESTful Flask API backend delivering real-time inference with median latency of 14 ms; and (iii) a React 18 single-page application featuring a Three.js-based three-dimensional physiological simulator with seven configurable pathology modes. The system further incorporates a natural-language medical chatbot providing contextual clinical question-answering. The dual-interface design—comprising a patient-facing Vitascan portal and a clinician-grade AnemioOS dashboard—bridges the gap between machine learning inference and clinical communication, demonstrating precision of 0.92, recall of 1.00, and F1-score of 0.96 on non-anaemic classification. This paper proposes AnemioOS as a reproducible, open-architecture platform for AI-enhanced point-of-care haematological screening.},
        keywords = {Anaemia diagnostics, Random Forest, haematological biomarkers, 3D physiological simulation, digital twin, explainable AI, full-stack machine learning, point-of-care diagnostics, Three.js, Flask, React.},
        month = {April},
        }