![Development and Validation of Manually Modified and Supervised Machine Learning Clinical Assessment Algorithms for Malaria in Nigerian Children Development and Validation of Manually Modified and Supervised Machine Learning Clinical Assessment Algorithms for Malaria in Nigerian Children](https://thinkmd.org/wp-content/uploads/2022/03/Development-and-Validation-of-Manually-Modified-and-Supervised-Machine-Learning-Clinical-Assessment-Algorithms-for-Malaria-in-Nigerian-Children.jpg)
Research article in frontiers in Artificial Intelligence by THINKMD. Development and Validation of Manually Modified and Supervised Machine Learning Clinical Assessment Algorithms for Malaria in Nigerian Children that investigates improving the accuracy of point-of-care clinical risk assessment protocols for malaria in febrile children.
Key take-aways:
- With approximately 67% of malaria deaths occurring in children under-five, the WHO developed community (ICCM) and clinic-based (IMCI) protocols for FHWs to improve the identification of children at clinical risk for malaria
- To investigate opportunities to improve the accuracy of the protocols for malaria in febrile children, a malaria rapid diagnostic test (mRDT) workflow was embedded into THINKMD’s IMCI clinical risk assessment platform.
- Paired clinical data and malaria risk assessments acquired from over 555 children presenting five health clinics in Kano, Nigeria to train ML algorithms to identify malaria cases using symptom and location data as well as confirmatory mRDT results
- The results show that combining mRDT “truth” data with digital mHealth platform clinical assessments and clinical data can improve identification of children with malaria/non-malaria attributable febrile illnesses