Mission
To democratize medical diagnostics through AI, ensuring that every community—regardless of geography or resources—has access to accurate, affordable healthcare solutions.
Available for collaborations
Hello, I'm Divine Sebukpor
AI Founder & Healthcare Innovator
Transforming global healthcare through AI-powered diagnostics and ethical innovation. Building accessible, accurate, and affordable solutions for underserved communities.
.png)
0+AI Models
0%Accuracy
0+Countries
0stBrowser Framework
Bridging AI Innovation
with Global Healthcare
AI researcher, ambassador, and youth healthtech entrepreneur passionate about leveraging data, evidence, and inclusive evaluation to advance global healthcare equity.
Vision
A world where AI eliminates healthcare disparities and early disease detection is universal.
Impact
Browser-based diagnostics reaching underserved communities across Africa and beyond.
Core Values
Ethical AI by design
Privacy-first architecture
Accessibility for all
Evidence-based innovation
Key Expertise
AI Diagnostics
Deep learning models for medical imaging and predictive analytics
Ethical AI
Bias mitigation and fairness frameworks for healthcare ML
Machine Learning
TensorFlow, PyTorch, and browser-based inference with TensorFlow.js
Global Health
Health equity focus with resource-limited setting optimization
Research
Peer-reviewed publications in AI diagnostics and precision medicine
Entrepreneurship
Building and scaling healthtech ventures from concept to deployment
Professional Experience
A journey through roles shaping the future of healthcare AI
Founder (CEO) & AI Researcher
DAS medhub
Leading a healthtech startup focused on developing AI-powered diagnostic solutions for global healthcare challenges.
- Designed and deployed AI-powered diagnostic models for diabetes, pneumonia, malaria, and multi-cancer detection
- Integrated Large Language Models (LLMs) for patient symptom assessment
- Built partnerships to drive AI adoption in African healthcare systems
- Secured funding and grants for research and development initiatives
TensorFlow.jsPythonReactLLMsDeep Learning
Ambassador
Extern
Representing Extern as a youth ambassador, engaging peers globally on ethical AI, innovation, and social impact.
- Engage peers globally on ethical AI, innovation, and social impact
- Support initiatives to elevate youth perspectives in research
- Organize workshops on responsible AI development
- Collaborate with international organizations on ethical AI standards
Public SpeakingEthicsCommunity
Research Analyst
NRG Group / Extern
Conducted AI bias analysis and risk assessments in healthcare and genomics to ensure equitable outcomes.
- Conducted AI bias analysis in healthcare and genomics
- Contributed to ethical frameworks and mitigation strategies
- Developed auditing tools for identifying bias in ML models
AI AuditingGenomicsFairness Metrics
Project Manager
Andeda – Data Analysis & Consulting
Leading data-driven projects, overseeing analytics and consulting initiatives that transform insights into actionable strategies.
- Manage cross-functional teams to deliver projects on time
- Collaborate with clients to define requirements and objectives
- Oversee end-to-end project lifecycle from data to visualization
- Present findings to executives enabling data-driven decisions
Data AnalyticsConsultingLeadership
AI Projects
Healthcare AI solutions with real-world impact and high accuracy rates
Multi-Cancer Detection
Problem: Early cancer detection requires expensive infrastructure and specialized pathologists, limiting access in underserved regions.
Solution: Browser-based framework using depthwise separable convolutions to identify 26 cancer types from histopathological images with client-side inference.
130K+Images Trained
26Cancer Types
100%Top-5 Accuracy
TensorFlow.jsXceptionGrad-CAMPython
Diabetes Prediction
Problem: Diabetes often goes undiagnosed until complications arise, particularly in communities with limited screening access.
Solution: Advanced AI analyzing patient medical data to predict diabetes risk, enabling early intervention and prevention strategies.
96%Accuracy
Real-timeAssessment
Scikit-learnPandasFlask
.jpeg)
Chest Abnormality Detection
Problem: Radiologist shortages in developing nations lead to delayed diagnosis of critical chest conditions.
Solution: CNN analyzing chest X-rays to identify 14 different abnormalities with high precision, reducing diagnostic time.
14Abnormalities
<2sInference
CNNTensorFlowDICOM
.jpeg)
Malaria Detection
Problem: Malaria diagnosis in rural Africa depends on scarce microscopists, causing treatment delays.
Solution: Deep learning model analyzing blood smear images to detect malaria parasites, providing rapid diagnosis in resource-limited settings.
97%Accuracy
RapidScreening
CNNOpenCVMobile-Optimized
BioTrace
Problem: Microbiome analysis requires specialized labs and is inaccessible for point-of-care diagnostics.
Solution: Neural network predicting body site origin of microbiome samples with FastQ file upload support and manual feature entry.
99%Accuracy
FastQUpload
Neural NetworksBioPythonGenomics
Rose Symptoms Assessment
Problem: Patients in remote areas lack immediate access to preliminary health guidance before seeing a doctor.
Solution: AI-powered virtual assistant helping users assess symptoms, receive preliminary health guidance, and make informed decisions.
LLMPowered
24/7Available
LLMNLPReact
Advancing AI in Healthcare
Pioneering research at the intersection of deep learning, medical diagnostics, and ethical AI
Deep Learning for Diagnostics
Developing novel architectures using depthwise separable convolutions and attention mechanisms to achieve state-of-the-art accuracy in multi-class medical image classification while maintaining computational efficiency for edge deployment.
Ethical AI & Bias Mitigation
Investigating algorithmic fairness in healthcare AI across diverse populations. Creating auditing frameworks and mitigation strategies to ensure equitable diagnostic outcomes regardless of race, geography, or socioeconomic status.
Privacy-Preserving AI
Pioneering browser-based inference using TensorFlow.js to eliminate data transmission risks. Patient data never leaves the device, enabling HIPAA-compliant diagnostics without infrastructure overhead.
Global Health Equity
Designing AI systems specifically optimized for resource-limited settings. From low-bandwidth model compression to offline-first architectures, ensuring cutting-edge diagnostics reach the communities that need them most.
Achievements
Milestones marking the impact of our work in healthcare AI
99.85% Top-1 Accuracy
Multi-cancer classification framework achieving near-perfect diagnostic accuracy across 26 cancer types
100% Top-5 Accuracy
Unprecedented performance in ranking correct cancer type within top 5 predictions
MDPI Diagnostics Publication
Peer-reviewed research published in leading open-access diagnostics journal
First Browser-Based Framework
World's first fully client-side multi-cancer deep learning diagnostic system
Privacy-First Design
Zero-data-leakage architecture ensuring complete patient confidentiality
Youth Ambassador
Recognized by Extern for leadership in ethical AI advocacy and youth engagement
Publications
Peer-reviewed research advancing AI in healthcare diagnostics
MDPI Diagnostics
2025
Browser-Based Multi-Cancer Classification Framework Using Depthwise Separable Convolutions for Precision Diagnostics
Background
Early and accurate cancer detection remains a critical challenge in global healthcare. Deep learning has shown strong diagnostic potential, yet widespread adoption is limited by dependence on high-performance hardware, centralized servers, and data-privacy risks.
Methods
This study introduces a browser-based multi-cancer classification framework that performs real-time, client-side inference using TensorFlow.js—eliminating the need for external servers or specialized GPUs. The proposed model fine-tunes the Xception architecture, leveraging depthwise separable convolutions for efficient feature extraction, on a large multi-cancer dataset of over 130,000 histopathological and cytological images spanning 26 cancer types.
Results
The model achieved a Top-1 accuracy of 99.85% and Top-5 accuracy of 100%, surpassing all comparators while maintaining lightweight computational requirements. Grad-CAM visualizations confirmed that predictions were guided by histopathologically relevant regions, reinforcing interpretability and clinical trust.
Conclusions
This work represents the first fully browser-deployable, privacy-preserving deep learning framework for multi-cancer diagnosis, demonstrating that high-accuracy AI can be achieved without infrastructure overhead.
Featured Venture
DAS medhub
Revolutionizing healthcare through AI-powered diagnostics. We're making healthcare more accessible, accurate, and affordable—especially for underserved communities across Africa.
Visit DAS medhubAI-Powered Diagnostics
State-of-the-art machine learning models delivering 96–99% accuracy in disease detection. From cancer classification to symptom assessment, every model is rigorously validated on diverse datasets.
Built for Africa & Beyond
Optimized for resource-limited environments and healthcare disparities. Our browser-based approach means no installation, no expensive hardware, and no reliance on constant internet connectivity.
Privacy-First Design
Browser-based inference ensures patient data never leaves the device. Zero server dependency means zero data leakage risk—full HIPAA compliance by architecture, not just policy.
Ready to transform healthcare?
Join us in making AI diagnostics accessible to every community.
Explore the PlatformLet's Work Together
Interested in collaborations, research opportunities, or speaking engagements? I'd love to hear from you.
Available for new projects