Research · BISL
Biomedical Intelligence Systems Lab
A cloud-native, interdisciplinary research group. Biomedical informatics is its anchor, machine learning its engine, and secure, well-built software its systems layer.
Five themes, one lab.
Biomedical informatics and data-driven discovery
Clinical and genomic data turned into evidence for diagnosis and treatment.
Artificial intelligence and intelligent systems
Machine learning and deep learning models built for decisions people actually make.
Secure and trustworthy computing
Systems that protect sensitive health and institutional data.
Software systems and platform innovation
Research that ships as working software and digital platforms.
Emerging interdisciplinary innovation
Questions between disciplines that need more than one method.
- SDG 3 Good health and well-being
- SDG 4 Quality education
- SDG 9 Industry, innovation and infrastructure
- SDG 16 Peace, justice and strong institutions
Doctoral research · Rutgers · 2020
Who benefits from radiotherapy in triple-negative breast cancer?
Triple-negative breast cancer lacks the receptors that many targeted therapies rely on, so knowing who will respond to radiotherapy matters. This work read clinical features and genetic alterations together to anticipate treatment response.
Clinical associations and genetic alterations to predict radiotherapy treatment response in patients with triple-negative breast cancer. PhD dissertation, Rutgers, The State University of New Jersey.
Framework
COFIP
Comorbidity Ontological Framework for Intelligent Prediction
A knowledge-based clinical decision support framework that predicts comorbidity and generates patient-specific care plans at the point of care.
People
A founding team of ten.
Doctoral and masters researchers in biomedical informatics, machine learning, deep learning, software engineering and secure systems. Names and photos appear with each member's consent.
- Ernest Onuiri, PhDFounder and Lead
How we work
A lab without walls.
BISL runs on a distributed, cloud-native model instead of a single physical room, so members collaborate across campuses and time zones.
- Shared code and reproducible computational workflows
- A manuscript pipeline from first draft to submission
- Outputs: journal articles, conference papers, theses, software prototypes, technical reports
- Grant and collaboration opportunities tracked every week
Where the lab is going
Three phases to 2031.
From a founding team to a continental consortium for health AI in low-resource settings, each phase builds on the last.
- 01 · 2026 to 2027
Foundation
Building the lab: every thesis becomes a series of papers, with a first explainable-AI flagship and a rolling grant portfolio.
- 02 · 2027 to 2028
Scale-up
Scaling up: centre funding, postdoctoral researchers, new computational-neuroscience studies and a coherent cancer-AI research series.
- 03 · 2029 to 2031
Continental consortium
A continental consortium: multi-site African clinical data, shared benchmarks and open tools for health AI in low-resource settings.
Partner with BISL
Better science travels in networks.
Multi-site data, joint supervision and shared benchmarks are how the lab's work reaches patients. We welcome:
How credit works
Fair authorship, agreed early.
- Contribution roles are agreed at the start of every project, using the CRediT taxonomy.
- Students are first authors on work built from their thesis or project.
- Every manuscript passes two independent BISL reviews before it is submitted.
- No gift or ghost authorship. Any use of AI tools is disclosed as each journal requires.
Join the lab.
Open to MSc and PhD candidates and visiting researchers in biomedical informatics, machine learning and secure systems.