Skip to main content

Machine Learning for Healthcare and Life Sciences

IBM Research - Haifa

What-if Scenario Analysis for Policy Makers: Cervical Cancer in Kenya


In developed countries such as USA or Europe, cervical cancer has a low mortality rate due to new advances in screening and immunization. These new advances mean that more can be done with fewer resources in Africa as well.

Our team together with a large global team of experts in IBM, has embarked on a journey to help monitor, treat, and prevent cervical cancer in Africa. Our goal is improve monitoring and decision-making through an integrated solution addressing both policy makers and care givers. The idea is to help promote a proactive approach to public health.

Our team has developed a prototype decision support tool that blends cloud and mobile technologies with advanced analytics to gather, manage, analyze, and visualize data on cervical cancer in Kenya.

For the analytics component of the tool we developed a Dynamic Bayesian Network and used state-of-the-art machine learning algorithms to infer the correct association between Kenya demographic variables with the progression of cervical cancer and possible treatment options.

The model is then used to simulate complex 'what-if' scenarios to determine the best outcome of where to invest efforts and resources.

For more info see: movie, brochure, press release.

Contact: Lavi Shpigelman