Related Experiment Video
Updated: Jul 25, 2026
A Multi-detection Assay for Malaria Transmitting Mosquitoes
Published on: February 28, 2015
Development and Validation of Manually Modified and Supervised Machine Learning Clinical Assessment Algorithms for
Megan McLaughlin1, Karell G Pellé2, Samuel V Scarpino3,4,5
1THINKMD, Burlington, VT, United States.
Insights
Improving malaria diagnosis in children under five is crucial. New machine learning algorithms integrated with mobile health platforms and rapid diagnostic tests enhance accuracy in identifying malaria risk in febrile children.
Area of Science:
- Digital Health
- Infectious Disease Epidemiology
- Machine Learning in Healthcare
Background:
- Malaria disproportionately affects children under five, accounting for 67% of global deaths.
- World Health Organization (WHO) protocols (iCCM, IMCI) aid frontline health workers in malaria risk assessment.
- Existing paper-based or mobile health (mHealth) tools require enhanced accuracy for point-of-care diagnostics.
Purpose of the Study:
- To improve the accuracy of malaria risk assessment protocols for febrile children.
- To integrate malaria rapid diagnostic test (mRDT) data into an mHealth platform (THINKMD) for algorithm refinement.
- To develop novel supervised machine learning (ML) algorithms for malaria risk prediction.
Main Methods:
- Embedded mRDT workflow into the THINKMD mHealth platform for comparative analysis.
- Utilized paired clinical data from 555 children in Kano, Nigeria, for ML model training and testing.
- Developed supervised ML random forest algorithms using 80% training and 20% testing data splits.
Main Results:
- New ML-based algorithms demonstrated improved sensitivity (60%) and specificity (79%).
- Positive Predictive Value (PPV) and Negative Predictive Value (NPV) were 76% and 65%, respectively.
- Significant improvement over initial THINKMD IMCI-based algorithms was observed.
Conclusions:
- Combining mRDT data with mHealth clinical assessments enhances malaria diagnosis accuracy.
- ML algorithms can effectively identify malaria and non-malaria febrile illnesses in children.
- Digital health platforms integrated with diagnostic data offer a promising approach to combat childhood malaria.
Abstract:
It is currently estimated that 67% of malaria deaths occur in children under-five years (WHO, 2020). To improve the identification of children at clinical risk for malaria, the WHO developed community (iCCM) and clinic-based (IMCI) protocols for frontline health workers using paper-based forms or digital mobile health (mHealth) platforms. To investigate improving the accuracy of these point-of-care clinical risk assessment protocols for malaria in febrile children, we embedded a malaria rapid diagnostic test (mRDT) workflow into THINKMD's (IMCI) mHealth clinical risk assessment platform. This allowed us to perform a comparative analysis of THINKMD-generated malaria risk assessments with mRDT truth data to guide modification of THINKMD algorithms, as well as develop new supervised machine learning (ML) malaria risk algorithms. We utilized paired clinical data and malaria risk assessments acquired from over 555 children presenting to 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. Supervised ML random forest algorithms were generated using 80% of our field-based data as the ML training set and 20% to test our new ML logic. New ML-based malaria algorithms showed an increased sensitivity and specificity of 60 and 79%, and PPV and NPV of 76 and 65%, respectively over THINKD initial IMCI-based algorithms. These results demonstrate 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.
