An Efficient AI-Driven Tool for Pediatric Pneumonia Detection
CWSF · 2026 Disease & Illness Bronze Medal
Overview
Pediatric Pneumonia is the leading infectious cause of death for children worldwide [1], largely due to slow or incorrect diagnosis [2]. Even with advancements in machine learning, modern AI systems struggle to detect it as they are trained on adult-only datasets. Overcoming challenges like limited data, class imbalance, and constrained hardware capabilities, I developed and optimized a deep learning model that can accurately classify pediatric pneumonia. Additionally, I created a saliency map that highlights what the model considered for its final prediction and a web interface that allows for easy upload of chest X-ray images. In comparison to modern benchmarks, this project demonstrates efficiency and reliability. If implemented in areas such as South Asia or Sub-Saharan Africa, it could save lives through faster and more accurate diagnosis.
Awards (2)
- Bronze Medal
- Selected for CWSF 2026
Competition history
- CWSF 2026
Related projects
ISEF · 2020
Using Machine Learning for Pneumonia Diagnosis
ISEF · 2019
Deployment of a Scalable Single Shot Detector (SSD) Mobile Architecture for the Localization and Classification of Pneumonia Chest Radiographs
ISEF · 2025
Convolutional Clarity: Accurate, Reliable, Explainable CNNs by Evaluating the Impact of Data Augmentation on Chest X-Ray Pneumonia Classification
ISEF · 2024
A Holistic Multi-Modal GenAI System: Early Detection and Predictive Treatment Monitoring Using Chest X-rays and Cough Audio for Tuberculosis
Closest projects by meaning, across every fair and year in the corpus.