Submitted
2025 Global Health Challenge

Mpoxdetection.ai

Team Leader
WHO-Kazakhstan- Lavrentyev Artem
Our solution, Mpoxdetection.ai, is an AI-powered tool designed to diagnose skin diseases, including mpox, directly from images taken with a smartphone. The system uses a trained convolutional neural network (CNN) to analyze pictures of skin lesions and classify them into categories such as mpox, measles, chickenpox, and others. The AI model processes the images and provides results within seconds, making...
What is the name of your organization?
Mpoxdetection.ai
What is the name of your solution?
Mpoxdetection.ai
Provide a one-line summary or tagline for your solution.
The Mpoxdetection.ai is an AI-based solution helping to diagnost skin deseases with 95% accuracy, accessible via a Telegram-bot and web platform
In what city, town, or region is your solution team headquartered?
Алматы, Казахстан
In what country is your solution team headquartered?
KAZ
What type of organization is your solution team?
Nonprofit
Film your elevator pitch.
What specific problem are you solving?
The problem we’re tackling with Mpoxdetection.ai is the lack of accessible, affordable, and timely diagnostic tools for diseases like mpox, especially in underserved regions. Traditional diagnostic methods, like PCR testing, can be expensive, time-consuming, and out of reach for many people, particularly in rural areas of countries like Kazakhstan. This leaves communities vulnerable to late diagnoses and delayed treatments. Globally, the outbreak of mpox in 2022 highlighted just how crucial early detection is, with cases spreading rapidly due to delayed diagnoses. In regions where healthcare access is limited, like rural Africa and Central Asia, rapid, inexpensive detection is a game-changer. Our AI-driven solution offers a scalable and cost-effective alternative—using smartphone images to detect skin diseases. This project could impact millions, helping to catch diseases early and prevent outbreaks. By addressing this gap in healthcare, we aim to provide a solution that’s not just effective but also accessible for the most at-risk communities.
What is your solution?
Our solution, Mpoxdetection.ai, is an AI-powered tool designed to diagnose skin diseases, including mpox, directly from images taken with a smartphone. The system uses a trained convolutional neural network (CNN) to analyze pictures of skin lesions and classify them into categories such as mpox, measles, chickenpox, and others. The AI model processes the images and provides results within seconds, making it accessible, fast, and user-friendly, even for healthcare providers with limited resources. Built on TensorFlow and Keras frameworks, the system is scalable and can be integrated into existing healthcare infrastructures or used on smartphones for remote consultations. By offering accurate, low-cost diagnoses without the need for expensive lab equipment, this tool helps bridge the gap in early disease detection in underserved communities, particularly in rural areas where traditional diagnostics like PCR tests are out of reach.
Who does your solution serve, and in what ways will the solution impact their lives?
Our solution serves underserved communities in rural and remote areas, particularly in countries like Kazakhstan, Africa, and Central Asia, where healthcare access is limited. These communities often lack access to expensive diagnostic tests like PCR, which delays the diagnosis and treatment of infectious diseases like mpox. Mpoxdetection.ai provides these communities with an accessible, low-cost alternative to traditional diagnostic methods, allowing healthcare providers to quickly diagnose and treat diseases using just a smartphone. By offering rapid, accurate diagnoses, our solution empowers individuals and healthcare professionals to take timely action, preventing outbreaks and improving public health outcomes. Our solution has the potential to directly improve millions of lives by addressing healthcare disparities and providing much-needed diagnostic tools in resource-constrained settings.
Solution Team:
WHO-Kazakhstan- Lavrentyev Artem
WHO-Kazakhstan- Lavrentyev Artem