Bio-RAMP is a global multidisciplinary research community at the intersection of healthcare and artificial intelligence, bringing together expertise from fields such as computer science, healthcare, data science, ethics, and policy to collaboratively explore the possibilities and limitations of using AI in healthcare while increasing the representation of minorities in biomedical AI research. Through our work, we aim to improve patient outcomes, enhance efficiency and accuracy in healthcare delivery, and promote ethical and responsible use of AI.
This infamous quote highlights a pervasive trend in artificial intelligence research today: many of the brightest minds in the field are being drawn to work on developing algorithms and models that optimize advertising campaigns, enhance user engagement, and advance trophy projects like self-driving cars and VR games, rather than tackling society’s most pressing problems and addressing challenges in healthcare, climate change, or education.
Because of the financial incentive and status at these high paying tech jobs, most grads and student projects gravitate towards these problems, drawing resources and even the rare talented researchers from underrepresented communities with real problems away from projects that could change their communities.
Engage a broad range of researchers especially those from minority/underrepresented groups
Inspire them to pursue meaningful research questions that benefit their communities, e.g target disease that affect minorities
Curate, create, or annotate novel datasets to solve these problems
Provide the resources, mentorship, and enabling environment to run experiments, develop algorithms,
Publish and/or Deploy algorithms in real world settings and make real impact.
Our research sits at the intersection of healthcare and AI
Our community is global facilitating idea sharing across continents
We promote racial diversity and prioritize communities that are underrepresented in biomedical research
We leverage machine learning methods to deliver healthcare impact
Since community problems are not uni-modal, our methods cut across modalities such as speech, text, images, and other forms of structured and unstructured data
Georgia Institute of Technology
Yale School of Management
University of San Francisco
University of lbadan
Scientist, Health AI, Amazon Web Services
Enlitic Inc, SF
Cambia Health Solutions (BlueCross BlueShield Pacific Northwest)
Insight Data Science
Tobi Olatunji is a physician turned Machine Learning Scientist focused on Clinical Natural Language Processing (NLP). He founded Intron, Africa’s first speech-powered medical record, accelerating the transition to digitized care for clinicians of all typing speeds. Intron also provides technology infrastructure and financing that eliminates technology adoption barriers. Over the past decade, he has worked as a Clinical NLP Scientist at Amazon Web Services (AWS) Health AI, Amazon, the world’s largest employer; Enlitic Inc, a Radiology AI startup in San Francisco; Cambia Health Solutions, a 100+-year-old health insurance provider in the pacific northwest; and consulted for various startups and healthcare institutions in the US and Africa. His research cuts across accented speech recognition, algorithmic bias, neural and ontology-augmented information retrieval, negation & uncertainty detection in radiology reports; Radiogenomic multi-modal models combining imaging (pathology and radiology), genomics (RNAseq), unstructured text, and cancer biomarkers to create learnable patient representations. He has published at Neurips, MIDL, EMNLP, and other machine learning conferences/workshops.
Tobi holds a Bachelor of Medicine, Bachelor of Surgery (MBBS) degree from the College of Medicine, University of Ibadan; a Master of Science in Medical Informatics from the University of San Francisco California, a Healthcare Management Certificate from Yale School of Management, and an MSc in Computer Science (c) at the Georgia Institute of Technology.
Working with us to advance the field of Machine Learning for Healthcare and expand access to deep learning applications in medicine