Mirugwe - AI Researcher & PhD Scholar Portfolio

// About

Who I Am

About Me

Some problems are too important to leave unsolved. I'm Alex Mirugwe, a PhD researcher in Artificial Intelligence at Queensland University of Technology, Australia, developing generative AI methods for unsupervised anomaly detection in medical imaging: models that learn what healthy anatomy looks like well enough to flag rare or subtle pathologies without relying on the large annotated datasets that are rarely available in real clinical practice.

This builds directly on four-plus years as a Data Scientist working at the intersection of ML and public health, where I developed and deployed models that shaped real responses to HIV, cancer, tuberculosis, and public health emergencies. That work is where the research question came from: how do you build AI that's genuinely useful when the data isn't perfect and annotations are scarce?

Always happy to connect with people working on AI for health, generative modeling, or anything at that intersection.

Core Expertise

Machine Learning

Deep Learning

NLP

Health Informatics

Medical Imaging

Geospatial Modelling

Time-Series

Data Visualization

Tech Stack

Python R SQL TensorFlow PyTorch Keras Scikit-Learn OpenCV LangChain AWS MLFlow GIT PowerBI LaTeX

Hire Me Download CV

// Resume

Experience & Education

Work Experience

July 2026 - Present

PhD Scholar

Queensland University of Technology, Australia

Researching geometry-constrained latent diffusion models for structure-preserving, unsupervised anomaly detection in medical imaging.
Developing generative methods that flag rare or subtle pathologies without depending on the large annotated datasets rarely available in real clinical practice.

March 2022 - April 2026

Data Scientist

Makerere University School of Public Health, Monitoring & Evaluation Technical Support (CDC Program)

Built a machine learning model to identify HIV patients at risk of dropping out of care or failing viral suppression, enabling proactive clinical interventions and improving patient retention and outcomes.
Designed, implemented, and deployed a deep learning algorithm for cervical cancer and TB screening, increasing diagnostic accuracy and efficiency and contributing to earlier detection and treatment across Uganda.
Developed a probabilistic patient-matching algorithm to de-duplicate HIV patient records across PEPFAR-supported facilities in Uganda, reducing duplicate entries by 4.8%.
Performed sentiment analysis on over 20,000 social media posts during the 2022 Uganda Ebola outbreak, generating actionable insights that informed public health risk communication strategies.

Jan 2022 - Feb 2024

Assistant Lecturer

Faculty of Science, Victoria University, Kampala

Delivered undergraduate and postgraduate courses in Introduction to Python, Machine Learning, Deep Learning, and Artificial Intelligence.
Designed course materials and assessments, and provided timely, constructive feedback to foster student engagement and academic growth.
Contributed to the design and review of the BSc Software Engineering and MSc Blockchain Technology curricula, ensuring academic rigour and industry relevance.

Jan 2021 - Sept 2021

Tutor

Department of Computer Science, University of Cape Town

Led and supervised laboratory sessions for undergraduate students covering core machine learning topics, including linear and logistic regression, decision trees, and support vector machines.
Prepared instructional materials and live demonstrations to deepen students' conceptual understanding and practical application of machine learning techniques.
Mentored students through coursework projects and assignments, offering targeted guidance to support academic progress.
Collaborated with faculty to develop course content, problem sets, and assessments aligned with learning objectives.

Education

July 2026 - Present

PhD in Artificial Intelligence

Queensland University of Technology, Australia

Research: Geometry-Constrained Latent Diffusion for Structure-Preserving Unsupervised Anomaly Detection in Medical Imaging

Jan 2020 - Nov 2021

MSc. Data Science

University of Cape Town, South Africa

Thesis: Automating bird detection using deep learning

Aug 2014 - June 2019

BSc. Computer Engineering

Makerere University, Uganda

Dissertation: A low-cost wireless TV audio transceiver

Online Certifications

Coursera

DataCamp

Supervised Learning in R Credit Risk Modeling EDA in Python Logistic Regression Relational Databases Data Visualization

YALI Regional Leadership Center

Climate Change Renewable Energy

// Portfolio

Featured Projects

Projects showcasing expertise in machine learning, deep learning, computer vision, and NLP, with applications in healthcare and ecology.

Published · JMIRx Med 2025

TB Detection in Chest X-Rays

Deep Learning Transfer Learning Computer Vision Medical Imaging

Comparative study of CNN architectures for tuberculosis detection in chest X-ray images using transfer learning and deep learning, achieving state-of-the-art diagnostic accuracy to support clinicians in resource-limited settings.

Read Publication

Cervical Cancer Screening

Deep Learning Medical Imaging TensorFlow

AI-powered screening tool that improved early cervical cancer detection accuracy in Uganda, enabling faster diagnosis in underserved clinical settings.

View Project

Patient Matching Algorithm

NLP Record Linkage

Reduced HIV patient data duplicates by 4.8% across Uganda's national health system.

View Project

Ebola Sentiment Analysis

NLP Deep Learning

Analyzed public sentiment during Uganda's 2022 Ebola outbreak to inform risk communication strategies.

View Project

Webcam Bird Detection

Computer Vision CNN

Automated bird species detection from webcam footage -- MSc thesis project at University of Cape Town.

View Project

Recommendation Systems

Collaborative Filtering Python

ML-based recommendation engine for personalized content delivery.

View Project

Data Encryption Suite

AES RSA Security

Implementation of AES and RSA encryption algorithms for secure healthcare data protection.

View Project

// Services

Let's Connect

Open to research collaborations, talks, and PhD networking, alongside select consultancy work.

Research Collaboration

Keen to collaborate on generative AI, anomaly detection, or ML for healthcare, as a co-author, reviewer, or sounding board.

Talks & Seminars

Available for guest lectures, seminars, and talks on generative AI, medical imaging, and applied machine learning in health.

Consultancy

Selective, part-time consulting on ML/AI systems for healthcare organizations, from model design to deployment.

Training

Comprehensive training in statistics, data analysis, and machine learning with R and Python.

// Publications

Research & Papers

01

Patient deduplication in Uganda’s electronic medical records system: a comparison of three classification algorithms 2026BMC Digital Health, vol. 4, no. 37 BMC Digital Health

02

Visit-level Prediction of Missed HIV Appointments Using Machine Learning and Transformer-Based Models in Uganda 2026BMC Medical Informatics and Decision Making, vol. 25, no. 131 BMC Med Inform

03

Secure and Efficient Federated Learning for Predictive Modeling in Resource-Constrained Healthcare Systems 2026Medinformatics, vol. 3, no. 2, 178-184 Medinformatics

04

Artificial Intelligence-Powered Multiclass Deep Learning Model for Detection of Aflatoxin-Related Defects in Ugandan Groundnuts 2026Discover Artificial Intelligence, vol. 6, no. 291 Discover AI

05

Improving Tuberculosis Detection in Chest X-Ray Images Through Transfer Learning and Deep Learning 2025JMIRx Med, Vol. 5 JMIRx Med

06

Sentiment Analysis of Social Media Data on Ebola Outbreak Using Deep Learning Classifiers 2024MDPI Life, 14, 708 MDPI

07

Cervical Cancer Screening: AI Algorithm for Automatic Diagnostic Support 2023Translational Medicine, Vol. 13, Iss. 13 ResearchGate

08

Digital Outbreak Response System: Go.Data Tool for Ebola Data Management in Uganda 2023AJPMPH, Vol. 9, No. 5 ResearchGate

09

Automating Bird Detection Based on Webcam Captured Images Using Deep Learning 2022Proc. 43rd Conf. of the South African Institute, Vol. 85, pp. 62-76 Google Scholar

10

Adoption of Artificial Intelligence in the Ugandan Health Sector: A Review 2023Preprint ResearchGate

11

Restaurant Tip Prediction Using Linear Regression 2021IJDSBDA, Vol. 1, Iss. 2, pp. 31-38 ResearchGate

// Blog

Latest Articles

Explore my latest thoughts and insights on data science and AI.

Subscribe on Substack

May 9, 2026

The Superintelligence Mockery: Why the God in the Machine has no Training Set

The claim that superintelligence is a near-term destination has no training distribution, no mechanism, no benchmark, and no precedent. This paper draws on scaling laws, data exhaustion projections, and embodied cognition to show the gap is being closed by rhetoric, not evidence.

April 25, 2026

When the Algorithm Passes the Test but Fails the Patient: A Global Reckoning with AI Evidence Standards in Clinical Diagnosis

AI diagnostic tools are cleared worldwide on benchmark accuracy alone — a metric that tells clinicians little about real-world performance. This paper argues the field has built its evidence edifice on an unstable foundation, and calls for global coordination to fix it.

April 22, 2026

Can AI Predict When an HIV Patient Will Miss Their Next Appointment?

We tested a transformer-based model on Uganda's national HIV data across 56 districts — and it flagged every at-risk patient before they disappeared from care. The results surprised us.

June 24, 2025

Why Skipping the Basics in AI Creates Pseudo-Experts

AI tools are ubiquitous, but many overlook the basics and end up with a superficial understanding. In this piece, I explain why that matters and how to build real expertise.

June 12, 2025

AI Panic: Why Strategy Must Come Before Hype

Too many teams and organizations dive into AI without a clear plan - no defined use cases, no ROI thinking, just fear of missing out. This article unpacks why hype isn't enough and what real strategy looks like.

February 17, 2025

Where is Africa in the AI Conversation?

Africa is missing from the global AI revolution. Why? What can be done? This article explores the challenges and opportunities for AI in Africa.

October 7, 2024

OpenAI's 5-Gigawatt Data Centers: Marvel or Energy Crisis?

OpenAI's ambitious proposal to build 5-to-7 massive 5-gigawatt data centers. I explore what this means for AI development, global energy use, and sustainability.

// Contact

Get in Touch

Open to research collaborations, talks, PhD networking, or select consultancy work. Reach out and let's talk.

Your message was sent successfully!

Location

QUT Gardens Point Campus, QUT S Block
Brisbane City QLD 4000, Australia

Email

mirugwealex@gmail.com
alex.mirugwe@hdr.qut.edu.au

Phone

(+256) 701 120534
(+61) 404 912 285