Tony Okeke, 20, winner of the 2018 edition of the Nigerian National Petroleum Corporation, NNPC, National Science Quiz Competition, presently studying Biomedical Engineering in Drexel University, Philadelphia, Pennsylvania, USA, collaborated with five other international students (four Nigerians and one Indian) to develop an Artificial Intelligence (AI) Medical Assistance App, which they named ‘Meddibia’.
Okeke’s team, named, ‘Team Meddibia’, comprises Okeke, Dishika Goel, Elochukwu Enwerem, Dalu Okonkwo, Michael Moemeke and Victor Uzo.
Grow your business with us
The team’s project, ‘Meddibia’, was one of the ten AI projects that won at the Philly Codefest 2023, a contest that took place in Philadelphia, Pennsylvania, USA during the 10th year of the software and hardware hackathon hosted by College of Computing & Informatics, Drexel University, Philadelphia.
Explaining how difficult it was for the panel of judges to determine the winners, Dave Raiken, Assistant Director of Operations, said the 46 teams that took part, presented great technical projects that aligned with the theme: AI Everywhere— that is, “real-world, scalable software and hardware solutions to improve and expand artificial intelligence’s positive societal impacts.”
Presenting their project on behalf of his team, Okeke explained: “The inspiration behind our latest project came from a deep desire to improve the accessibility of medical care for people living in rural areas. As developers from third-world countries, we understood all too well the struggles faced by those who lack access to proper medical facilities. Our team wanted to create a solution that would bridge the gap between these individuals and medical professionals, so we set out to create an app that would allow users to receive medical advice and diagnoses using machine learning models.”
Meddibia is a personal AI health assistant that puts greater control over health in the hands of users living in rural communities. With it, users can describe their symptoms to a chat assistant and receive a likely diagnosis, along with more information about their diagnosis and symptoms. Additionally, it enables users to get diagnosis for skin conditions and aberrations by simply taking a picture of the affected area. This feature is especially important for those with limited access to healthcare professionals or specialized facilities. By providing personalized care and making it easier to manage health conditions, Meddibia empowers users to take control of their health and improve their quality of life.
To accurately identify skin conditions, the team experimented with various pre-trained models, including VGG16 and EfficientNet, to extract features from images from the dermnet dataset. They then trained and evaluated deep neural network classifiers, ultimately selecting a model with approximately 70% accuracy. For symptom identification, they employed GPT-3, a state-of-the-art language model, to preprocess natural language input from users into symptom labels, which served as input to our machine-learning model. This approach resulted in about 87% accuracy in predicting disease labels. To further assist users, and used GPT-3 to provide helpful descriptions of the predicted disease. The app’s backend was built using Flask API and deployed on Heroku, while the cross-platform frontend was developed using Flutter, making our app easily accessible to users across multiple devices.
About The Author