AI Researcher & Healthcare Innovator
Transforming global healthcare through AI-powered diagnostics and ethical innovation. Building accessible, accurate, and affordable solutions for underserved communities.
.png)
AI researcher, ambassador, and youth healthtech entrepreneur passionate about leveraging data, evidence, and inclusive evaluation to advance global healthcare equity.
My work focuses on developing cutting-edge AI solutions that make healthcare more accessible, accurate, and affordable for everyone, especially in underserved communities across Africa and beyond. By combining deep learning expertise with a commitment to ethical AI, I'm building tools that democratize medical diagnostics.
From browser-based cancer detection to malaria screening in resource-limited settings, every project is designed with real-world impact at its core. I believe technology should adapt to people, not the other way around.
Deep learning models
Bias mitigation
TensorFlow & PyTorch
Health equity focus
Leading DAS MedHub in healthcare AI innovation
Representing Extern in ethical AI discussions
Conducting AI bias analysis in healthcare
A journey through my professional roles and contributions to healthcare AI innovation
Leading a healthtech startup focused on developing AI-powered diagnostic solutions for global healthcare challenges.
Representing Extern as a youth ambassador, engaging peers globally on ethical AI, innovation, and social impact.
Conducted AI bias analysis and risk assessments in healthcare and genomics to ensure equitable outcomes.
Leading data-driven projects, overseeing analytics and consulting initiatives that transform insights into actionable strategies.
Healthcare AI solutions with real-world impact and high accuracy rates
Medical Imaging
26 cancer types identification
Advanced deep learning model identifying 26 cancer types from histopathological and cytological images with 99.85% accuracy.
View Project
Diagnostics
Risk assessment model
Advanced AI analyzing patient medical data to predict diabetes risk, enabling early intervention and prevention strategies.
View Project.jpeg)
Medical Imaging
14 abnormalities identified
CNN analyzing chest X-rays to identify 14 different abnormalities with high precision, reducing diagnostic time.
View Project.jpeg)
Medical Imaging
Blood smear analysis
Deep learning model analyzing blood smear images to detect malaria parasites, providing rapid diagnosis in resource-limited settings.
View Project
Diagnostics
Microbiome analysis
Neural network predicting body site origin of microbiome samples with FastQ file upload support and manual feature entry.
View Project
NLP Assistant
AI health assistant
AI-powered virtual assistant helping users assess symptoms, receive preliminary health guidance, and make informed decisions.
View ProjectPeer-reviewed research advancing AI in healthcare 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.
Background: Early and accurate cancer detection remains a critical challenge in global healthcare...
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.
Revolutionizing healthcare through AI-powered diagnostics. We're making healthcare more accessible, accurate, and affordable—especially for underserved communities across Africa.
State-of-the-art ML models delivering 96-99% accuracy in disease detection
Optimized for resource-limited environments and healthcare disparities
Browser-based inference ensures patient data never leaves the device
Interested in collaborations, research opportunities, or speaking engagements? I'd love to hear from you.
divinesebukpor@gmail.com
+91 7626922236
Accra, Ghana
Typically within 24 hours