AI Healthcare Research Laboratory

Research for prospective detection, diagnosis, and intervention

The main goal of this research group is to deploy AI technologies for prospective detection, diagnosis, and to recommend interventions. This group is a hub of interdisciplinary researchers developing healthcare technology solutions, performing user behavior analysis, and creating recommender systems. We are drawn together by our conviction to exchange knowledge between methods developers and application-driven researchers. In our active projects, we handle and analyze large, diverse, and time-sensitive data sets, especially in the biomedical field. We collaborate with biomedical researchers, different types of doctors, and medical specialists to address technical and non-technical research issues. We analyze data from cardiovascular patients, create algorithms for malaria detection, and develop models for patient health states and early warning systems. Our work is a part of the broader field of data-driven medicine, where we utilize machine learning to leverage clinical data, generating new biomedical insights and building precise predictive models for disease outcomes and treatment efficacy.

Primary investigator

Carine Mukamakuza

Assistant Teaching Professor

Carine Pierrette Mukamakuza holds a bachelor's and master's degree in computer science from Central South University, China. She completed her Ph.D. studies at Vienna Technical University in the Vienna Ph.D. School of Informatics.

Mukamakuza is a lecturer, researcher, and entrepreneur. Her research focuses on digital healthcare solutions, business intelligence, data science (specifically machine learning, where she has centered her attention on recommender systems), online social network behavior, and personalization. Using publicly available datasets, she has investigated the extent to which social connections influence user rating behavior over time. Driven by her interest in digital healthcare solutions, Mukamakuza is creating a digital detection project. She is currently focused on Rwanda as a case study, and her long-term goals for the interface are much broader where she envisions creating a system that could be utilized across countries in Africa, and across diseases. Overall, her goal is to construct an effective data management system that has wide usability and high reliability.

View Mukamakuza's full bio

Office: D108 Regional ICT Center of Excellence Bldg

Phone: +250.781.986076

Email: cmukamak@andrew.cmu.edu

Google Scholar: Carine Mukamakuza

▲ Back to the top

Guest speaker events

Affiliated faculty

Vijayakumar Bhagavatula

U.A. and Helen Whitaker Professor

Email: kumar@ece.cmu.edu

View Bhagavatula's bio

▲ Back to the top

Research team

Mona Aman

Research Associate (MS EAI)

Research interests: Foundation models, multimodal clinical AI , self-supervised learning , uncertainty quantification, efficient and trustworthy ML for healthcare
Email: amona@andrew.cmu.edu

Chol Buol

Research Associate (MS EAI)

Research interests: Explainable and trustworthy AI, AI applications in health-care (especially in low resource environments)
Email: sbuol@andrew.cmu.edu

Kevin Harerimana

Research Associate (MS EAI)

Research interests: Lightweight deep learning model for medical imaging
Email: kharerim@andrew.cmu.edu

Ahmed Tahiru Issah

Research Associate (MS EAI)

Research interests: Medical imaging; medical data to build robust and interpretable diagnostic tools; practical clinical application, with an emphasis on solutions that scale to low-resource healthcare environments
Email: aissah@andrew.cmu.edu

Ahmed Tahiru Issah's website

Martha Kachweka

Research Associate (MSIT)

Research interests: Application of AI in healthcare, particularly in disease prediction and early diagnosis
Email: mkachwek@andrew.cmu.edu

Alain Destin Nishimwe Karasira

Research Associate (MSIT)

Research interests: Application of AI in healthcare
Email: anishimw@andrew.cmu.edu

Damilare Emmanuel Olatunji

Research Associate (MS EAI)

Research interests: Health systems (distributed), medical Imaging, ML (applied), and multi-agent design
Email: dolatunji@andrew.cmu.edu

Idaya Seidu

Research Associate (MSIT)

Research interests: AI for Healthcare, with a focus on human-centered design; explainable and trustworthy AI; the engineering of context-aware distributed systems for social impact
Email: iseidu@andrew.cmu.edu

Idaya Seidu's portfolio

Godbright Nixon Uisso

Research Associate (MSIT)

Research interests: Building practical, application-level AI systems that are reliable, usable, and ready for real world deployment
Email: guisso@andrew.cmu.edu

Julius Dona Zannu

Research Associate (MSIT)

Research interests: Designing and deploying scalable software/AI systems that integrate machine learning and large language models with robust cloud-native architectures
Email: jzannu@andrew.cmu.edu

Past students

Eugenia Mawuenya Akpo (currently a Ph.D. Student at King’s College London)
Yamlak Asrat Bogale (currently a Ph.D. Student, Indiana University, Indianapolis)
Chukwuemeka Malachi Ugwu (currently a Ph.D. student at Stevens Institute of Technology)
Eric Maniraguha (current position: Research Engineer, CMU-Africa)

▲ Back to the top

About

"My passion for healthcare research stems from a deep desire to improve lives. Witnessing the impact of limited healthcare resources firsthand has fueled my commitment to this field. This drive, coupled with a fascination for technology, led me to explore how information and communication technology (ICT) can revolutionize healthcare delivery.

For aspiring ICT experts in the field of health, especially women, my advice is to embrace your unique viewpoints and champion them. The ability to see challenges from different angles is a powerful asset in this field. Seek mentorship, build strong networks and leverage your skills to make a significant impact. Remember, you are not just building technology, you are shaping the future of healthcare delivery. By harnessing the power of ICT, we can create a more equitable and and accessible healthcare system for all."

-Carine Mukamakuza

▲ Back to the top

Projects

research image showing connection between data management system, repository, public, and medical centers

Digital malaria control for the developing world

This project aims to transform the way healthcare providers can prevent, diagnose, and treat malaria in the hardest-hit regions. Malaria remains a pressing public health concern, especially in resource-constrained settings, so the project holds immense promise as it harnesses digital technologies like artificial intelligence (AI) and machine learning (ML).

At its core, the project seeks to revolutionize the traditional approach to diagnosing malaria by leveraging advanced AI and ML algorithms. By integrating these technologies with microscopy—a widely used method for malaria diagnosis—the project aims to automate and streamline diagnoses. This automation will ensure they are accurate and reliable, which are critical factors in effectively managing disease.

Furthermore, this project represents a significant advancement in diagnosing malaria by incorporating a recommender system.

Powered by AI, this system analyzes diagnostic data and patient information to generate personalized treatment recommendations. It tailors treatment plans to individual patients based on their unique characteristics and the specifics of their malaria infection, which enhances the precision and effectiveness of treatment strategies.

Collaborator and funding agency: The African Engineering and Technology Network (Afretec) and the Upanzi Network

research image showing how cardiac health is assessed

AI systems for cardiovascular disease screening in Africa

This project aims to revolutionize how cardiac health is assessed by simultaneously acquiring and analyzing electrocardiogram (ECG) and phonocardiogram (PCG) signals. It aims to understand in detail how cardiac activity functions, as well as to establish a secure, anonymized database of cardiovascular clinical profiles. The project addresses the challenges faced by individuals with cardiovascular disease in Rwanda, such as limited access to essential services and a lack of cardiologists. The study employs an artificial intelligence (AI) model for analyzing ECG and PCG signals, utilizing advanced algorithms like convolutional neural networks (CNNs) and long short-term memory (LSTM) networks. This approach aims to significantly improve how cardiovascular diseases are diagnosed and treated, particularly in resource-limited settings like Rwanda. The project also formed a team of clinical experts in congenital heart defects (CHD) to provide valuable insights on various aspects related to cardiovascular screening tools.

Collaborator and funding agency: Rwanda Biomedical Center

▲ Back to the top

A student looking into a microscope — Data Collection of malaria-infected Giemsa-stained blood smear slides by the team at the AI Healthcare Research Lab.

A man standing in front of his poster — Poster presentation of accepted paper at the AIMedHealth Bridge at the 40th Annual AAAI Conference on Artificial Intelligence, AAAI 2026 which was held in Singapore.

Two students in front of a powerpoint presentation — Poster Presentation at the African HealthTech Summit 2025 held at the Kigali Convention Center, Rwanda. The team presented a poster titled “End to End AI System for Malaria Diagnosis”

Two students in front of their poster — Afritech Poster Presentation

Three women on a panel — Malaria Diagnosis Training Workshop in collaboration with Rwandan Biomedical Centre (RBC) at Musanze, in October 2025.

A student giving the thumbs up in front of his poster — Presentation of a research paper at the AAAI conference ’26 Singapore

desks with microscopes — AI Healthcare Research Laboratory at CMU-Africa

Courses

In Mukamakuza's teaching, she focuses on fostering inclusivity within the context of CMU-Africa. This involves the establishment of a learning environment characterized by fairness, equal access, and opportunities for all students to thrive and develop. The diverse student population, which encompasses variations in education, language, culture, and professional skills, necessitates the creation of an inclusive atmosphere that nurtures a sense of belonging.

In addition to the below list, Mukamakuza advises the independent studies projects focused on AI and healthcare. Please note that Mukamakuza teaches 04-701 in the spring semester, only.

Course	Course Name	Location	Units	Semester Offered
04-611	Strategic Use of Digital Information in Enterprise	Africa	12	Fall
04-613	ICT Business Economics and Finance	Africa	12	Spring
04-652	Artificial Intelligence System Design	Africa	12	Spring
04-654	Introduction to Probabilistic Graphical Model	Africa	12	Fall
04-655	Artificial Intelligence for Engineers	Africa	12	Fall
04-701	Research Methods in Engineering	Africa	6	Fall, Spring
04-761	Recommender Systems	Africa	12	Fall

▲ Back to the top

Publications

2026

T. Issah and C. Mukamakuza, “Bridging the gap in malaria diagnostics: An attention-centric YOLO framework with species-specific augmentation for tiny parasite detection in low-resource settings,” Proceedings of The Second AAAI Bridge Program on AI for Medicine and Healthcare, PMLR, vol. 317, pp. 141–149, 2025.
https://proceedings.mlr.press/v317/issah26a.html

Link to paper:C. Buol, J. Zannu, C. P. Mukamakuza, D. E. Olatunji, and V. Bhagavatula, “Architecture-aware explainability in ECG analysis: A case study of aortic stenosis detection with ResNet18, LSTM and ViT-MAE ECG,” Proceedings of The Second AAAI Bridge Program on AI for Medicine and Healthcare, PMLR, vol. 317, pp. 67–75, 2025.
https://proceedings.mlr.press/v317/buol26a.html

Aman, G. Uiso, C. Mukamakuza, and V. Bhagavatula, “A systematic comparison of data representations for transformer-based ECG arrhythmia classification,” Proceedings of The Second AAAI Bridge Program on AI for Medicine and Healthcare, PMLR, vol. 317, pp. 37–45, 2025.
https://proceedings.mlr.press/v317/aman26a.html

2025

E. Olatunji, J. D. Zannu, C. P. Mukamakuza, G. N. Uiso, M. M. M. Aman, J. B. Thuo, C. Buol, N. T. Ghogomu, and E. Umubyeyi, “Machine learning-based analysis of ECG and PCG signals for rheumatic heart disease detection: A scoping review (2015–2025),” Computer Methods and Programs in Biomedicine Update, vol. 9, pp. 100228–100228, Dec. 2025
https://www.sciencedirect.com/science/article/pii/S2666990025000539

2024

C. M. Ugwu, C. Pierrette Mukamakuza and E. Tuyishimire, "ECG-Signals-based Heartbeat Classification: A Comparative Study of Artificial Neural Network and Support Vector Machine Classifiers," 2024 IEEE 22nd World Symposium on Applied Machine Intelligence and Informatics (SAMI), Stará Lesná, Slovakia, 2024, pp. 000217-000222, doi: 10.1109/SAMI60510.2024.10432834.

Akpo, E.M., Mukamakuza, C.P., Tuyishimire, E. (2024). Binary Segmentation of Malaria Parasites Using U-Net Segmentation Approach: A Case of Rwanda. In: Yang, XS., Sherratt, S., Dey, N., Joshi, A. (eds) Proceedings of Ninth International Congress on Information and Communication Technology. ICICT 2024 2024. Lecture Notes in Networks and Systems, vol 1011. Springer, Singapore. https://doi.org/10.1007/978-981-97-4581-4_12

Karasira, A.D.N., Mukamakuza, C.P., Tuyishimire, E. (2024). The Use of YOLOv5 as a Malaria Detection Model for the Developing World. In: Yang, XS., Sherratt, S., Dey, N., Joshi, A. (eds) Proceedings of Ninth International Congress on Information and Communication Technology. ICICT 2024 2024. Lecture Notes in Networks and Systems, vol 1002. Springer, Singapore. https://doi.org/10.1007/978-981-97-3299-9_50

Bogale, Y., Mukamakuza, C.P., Tuyishimire, E. (2024). Intelligent Malaria Detection and Species Classification: A Case of Rwanda. In: Yang, XS., Sherratt, S., Dey, N., Joshi, A. (eds) Proceedings of Ninth International Congress on Information and Communication Technology. ICICT 2024 2024. Lecture Notes in Networks and Systems, vol 1002. Springer, Singapore. https://doi.org/10.1007/978-981-97-3299-9_41

P. Mukamakuza, A. D. N. Karasira, E. M. Akpo, Y. A. Bogale, P. Fasouli, and M. Salem, “A comparative analysis of deep learning models for malaria Plasmodium classification,” Proceedings of the 31st IEEE International Conference on Electronics, Circuits and Systems (ICECS), Nancy, France, 2024. https://ieeexplore.ieee.org/abstract/document/10848723

2023

Mary, H. R., Mukamakuza, C. P., & Tuyishimire, E. (2023). A Data Management Model for Malaria Control: A Case of Rwanda. In 2023 IEEE AFRICON. 2023 IEEE AFRICON. IEEE. https://doi.org/10.1109/africon55910.2023.10293671

Tuyishimire, E., Mukamakuza, C. P., Mbituyumuremy, A., Brown, T. X., Iradukunda, D., Phuti, O., & Mary, H. R. (2023). IT-Aided Forecasting Model for Malaria Spread for the Developing World. In 2023 Conference on Information Communications Technology and Society (ICTAS). 2023 Conference on Information Communications Technology and Society (ICTAS). IEEE. https://doi.org/10.1109/ictas56421.2023.10082725

S. Umuhoza and C. Mukamakuza, “SVM model-based digital system for malaria screening and parasite monitoring,” Proceedings of the IEEE Third International Conference on Signal, Control and Communication (SCC), Hammamet, Tunisia, 2023.

2020

Sacharidis, D., Mukamakuza, C. P., & Werthner, H. (2020). Fairness and Diversity in Social-Based Recommender Systems. In Adjunct Publication of the 28th ACM Conference on User Modeling, Adaptation and Personalization. UMAP ’20: 28th ACM Conference on User Modeling, Adaptation and Personalization. ACM. https://doi.org/10.1145/3386392.3397603

2019

Mukamakuza, C. P., Sacharidis, D., & Werthner, H. (2019). The Role of Activity and Similarity in Rating and Social Behavior in Social Recommender Systems. In International Journal on Artificial Intelligence Tools (Vol. 28, Issue 06, p. 1960004). World Scientific Pub Co Pte Lt. https://doi.org/10.1142/s0218213019600042

Mukamakuza, C. P., Sacharidis, D., & Werthner, H. (2019). The Impact of Social Connections in Personalization. In Adjunct Publication of the 27th Conference on User Modeling, Adaptation and Personalization. UMAP ’19: 27th Conference on User Modeling, Adaptation and Personalization. ACM. https://doi.org/10.1145/3314183.3323675

2018

Mukamakuza, C., Sacharidis, D., & Werthner, H. (2018). Mining User Behavior in Social Recommender Systems. In Proceedings of the 8th International Conference on Web Intelligence, Mining and Semantics. WIMS ’18: 8th International Conference on Web Intelligence, Mining and Semantics. ACM. https://doi.org/10.1145/3227609.3227651

2017

Mukamakuza, C. P. (2017). Analyzing the Impact of Social Connections on Rating Behavior in Social Recommender Systems. In Proceedings of the 25th Conference on User Modeling, Adaptation and Personalization. UMAP ’17: 25th Conference on User Modeling, Adaptation and Personalization. ACM. https://doi.org/10.1145/3079628.3079706

2014

Dukuzumuremyi, J. P., Zou, B., Mukamakuza, C. P., Hanyurwimfura, D., & Masabo, E. (2014). Discrete Cosine Coefficients as Images features for Fire Detection based on Computer Vision. In Journal of Computers (Vol. 9, Issue 2). International Academy Publishing (IAP). https://doi.org/10.4304/jcp.9.2.295-300

▲ Back to the top