Authors : Vrinda Garg; Nitin Kumar Sharma; Prapti; Anubhav Garg; Manish Kumar Sharma

Volume/Issue : Volume 11 - 2026, Issue 3 - March

Google Scholar : https://tinyurl.com/kfyt47e8

Scribd : https://tinyurl.com/3ar83zxz

DOI : https://doi.org/10.38124/ijisrt/26mar724

Note : A published paper may take 4-5 working days from the publication date to appear in PlumX Metrics, Semantic Scholar, and ResearchGate.

Abstract : Medical imaging is a very important part of the medical diagnosis system, yet sometimes there are chances of errors and inaccuracies in the examination by the radiologist because of the workload and limited resources and availability of the doctors(radiologist). We are Introducing a AI- powered Health care diagnosis system that will examine the X-ray/ CTscans reports that will help the doctor to examine the reports carefully with the help of the machine learning and deep learning technologies (CNNs, Grad-CAM). In this model we use Random Forest to predict, process and examine the chest conditions and for classifying the radiographs it uses Convolutional Neural Network (ResNet-18). For the visual representation have also used Gradient-weighted Class Activation Mapping (Grad-CAM). The system is made by using MERN stack, FastAPI, Docker to provide real time interface to the users for quick and real time results to the end user. We have performedmultiple experimental tests on public datasets most of the data from Kaggle the model has achieved ≈ 96% in detecting pneumonia, while the blood report data by ≈ 89% which makes it a system that detects lung diseases and combines blood reports for better accuracy and results (in real-time).

Keywords : Machine Learning, Datasets, Random Forest, Grad-CAM, Pneumonia, Convolutional Neural Network

References :

1. A. C. V. Aravinda et al., “Leveraging compact convolutional transformers for enhanced COVID-19 detection in chest X-rays: a grad-CAM visualization approach,” Frontiers in Big Data, vol. 7, Article 1489020, 2024. doi:10.3389/fdata.2024.1489020.
2. F. Alshanketi et al., “Pneumonia Detection from Chest X-Ray Images Using Deep Learning and Transfer Learning for Imbalanced Datasets,” J. Imaging Inform. Med., vol. 38, no. 4, pp. 2021–2040, Aug. 2025. doi:10.1007/s10278-024-01334-0.
3. J. Tang et al., “Fusion of X-Ray Images and Clinical Data for a Multimodal Deep Learning Prediction Model of Osteoporosis: Algorithm Development and Validation Study,” J. Med. Internet Res. Med. Inform., vol. 13, e70738, 2025. doi:10.2196/70738.
4. H. Zhang and K. Ogasawara, “Grad-CAM-Based Explainable Artificial Intelligence Related to Medical Text Processing,” Bioengineering, vol. 10, no. 9, 1070, 2023. doi:10.3390/bioengineering10091070.
5. C. Guan et al., “A machine learning-based model for assessing community-acquired pneumonia severity using routine blood tests,” Frontiers in Cellular and Infection Microbiology, vol. 15, Article 1605502, Jan. 2026. doi:10.3389/fcimb.2025.1605502. [6] Z. H. Wang et al., “Machine learning-based model for assessing community-acquired pneumonia severity using routine blood tests,” Diagnostics (Basel), 2026. [PMID:41602115].
6. Z. H. Wang et al., “Machine learning-based model for assessing community-acquired pneumonia severity using routine blood tests,” Diagnostics (Basel), 2026. [PMID:41602115].
7. R. R. Selvaraju et al., “Grad-CAM: Visual explanations from deep networks via gradient-based localization,” Int. J. Comput. Vis., vol. 128, pp. 336–359, 2020. (Grad-CAM original paper)