Adrián Barreno Sánchez (adrian.barreno@alumnos.upm.es), Alberto González Delgado (alberto.gondelgado@alumnos.upm.es), Julian Elijah Politsch (julian.politsch@alumnos.upm.es), Angelo D'Angelo (angelo.dangelo@alumnos.upm.es)
This repository contains the resources of Big Data Engineering subject final project (MSc Computational Biology - Universidad Politécnica de Madrid).
All four members contributed equally, Julian did Neural Nework model, Alberto did Logistic Regression, Adrian did Random Forest Tree and Angelo did Support Vector Classification, and for that reason the evaluation should be equal for all members of the group
In this study, we aimed to utilize artificial intelligence (AI) to create a model for classifying chest X-ray images of individuals into two categories: pneumonia and healthy. With the increasing amount of medical imaging data being generated, manual interpretation by radiologists can become time-consuming and prone to errors. Our model utilizes a deep-learning algorithm, specifically convolutional neural networks (CNNs), to analyze the chest x-ray images and make predictions on the presence or absence of pneumonia. The performance of the model was evaluated using a dataset of chest X-ray images, and the results demonstrate the potential of AI in accurately classifying medical images and aiding in the diagnosis of pneumonia.
The data used in this study can be found in the following Kaggle link
Find attached a Jupyter Notebook with the script and the analysis performed.