Machine Learning and Malaria

A Look at Machine Learning
and Malaria.

Supervised Learning Algorithms are much like traditional statistical modeling having desired inputs of certain significance and some expected output usually based on historical output behavior pattern. This method has been used in many biological applications such as tumor detection and drug discovery. A learning algorithm under supervised learning compares actual output versus expected outputs to find errors. It then modifies the model accordingly to accommodate any errors.

Unsupervised Learning on the other hand is much less dependent on historical data sets and uses specified algorithms draw conclusion without any previously established relationships. In many other scenarios however, depending on the objectives, unsupervised learning is a prudent and cost-effective research method. Overall, key data challenges include Data Availability [labeled vs unlabeled], Data Accessibility, Data Collection Tools and Data Integrity.

Our research team is continuously and actively mapping out potential sources of data and the level of effort required to access any of these identified potential data sources. In Rwanda preliminary sources include healthcare facilities, the Rwanda Meteorology Agency, The Rwanda Ministry of Health, and more

Key points:

  • Develop a Self-Teaching Algorithm

  • Discover Hidden Relationships in Big Data

  • Design Effective Clinical Trials

Intern Support

In 2019, a group of dedicated Abphina interns played a pivotal role in the global effort to combat malaria and other vector borne diseases by harnessing the power of data science. These aspiring young professionals joined forces with Abphina to analyze vast datasets related to malaria transmission and treatment outcomes.

Leveraging their skills in data analytics, machine learning, and statistical modeling, the interns contributed to identifying patterns and trends that proved instrumental in refining malaria control strategies.

Their work not only provided valuable insights into the geographic spread of the disease but also supported the development of targeted interventions and optimized resource allocation. They were a joy to have at Abphina.