Peter Paul Oketta

Research Interests

AI in Health, MLOps, Inclusive AI

Projects

Tuberculosis in households with infectious cases in Kampala city: Harnessing health data science for new insights on TB transmission and treatment response

The DS-I Africa-TB project is a multidisciplinary effort focused on advancing the understanding of tuberculosis transmission and treatment responses within households in Kampala City. By harnessing health data science and artificial intelligence (AI), the project seeks to uncover critical insights that could inform TB control strategies and improve patient outcomes.

Amplify Initiative

Amplify is a Google Research effort to build a global, open, and community-based platform for data collection in diverse languages and domains. By co-creating high-quality, locally grounded datasets, Amplify aims to ensure that AI innovation is inclusive, culturally relevant, and capable of addressing region-specific needs like health, education, and financial inclusion.

Enhancing Bean Crop Disease Diagnosis with Vision-Language Models: A Multitask Approach Using PaliGemma

This project explores how advanced AI can be applied to agriculture by improving the detection and monitoring of bean crop diseases such as Angular Leaf Spot (ALS) and Bean Rust. Leveraging PaliGemma, a state-of-the-art vision-language model, we developed a multitask system capable of identifying disease symptoms in bean images, answering relevant questions about plant health, and generating descriptive captions. These models were then deployed into a mobile application for real-time, in-field use. By combining object detection, visual question answering, and image captioning, this work demonstrates how vision-language models can support precision agriculture and help users make faster, data-driven decisions.

Machine Learning-based Algorithm for Automatic Screening of Pulmonary Tuberculosis using Chest X-rays in the Ugandan Population

Tuberculosis (TB) remains a pressing public health challenge in Uganda and other low- and middle-income countries, where limited diagnostic resources hinder timely detection and treatment. This project focuses on developing an AI-supported screening system that combines portable digital chest X-ray technology with machine learning models to automatically detect TB. By addressing the shortage of radiology expertise, the system aims to improve the speed, accuracy, and accessibility of TB diagnosis, ultimately reducing caseloads and saving lives.

Previous Education and Professional Experiences

Education

1. Bachelor of Science in Electrical Engineering, Makerere University, February, 2021-May, 2024

Experience

1. Research Engineer, Marconi Research and Innovations Lab, September, 2024 - Present

2. Data Science Intern, Marconi Research and Innovations Lab June 2023 – August 2023

3. Intern, Radio Planing and Optimzation, MTN Uganda July 2022 – September 2023