Development and Initial Validation of a Frontline Health Worker mHealth Assessment Platform (MEDSINC®) for Children 2-60 Months of Age

Development and Validation of Manually Modified and Supervised Machine Learning Clinical Assessment Algorithms for Malaria in Nigerian Children

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.

Performance of five pulse oximeters to detect hypoxaemia as an indicator of severe illness in children under five by frontline health workers in low resource settings - A prospective, multicentre, single-blinded, trial in Cambodia, Ethiopia, South Sudan, and Uganda

BACKGROUND

Low blood oxygen saturation (SpO₂), or hypoxaemia, is an indicator of severe illness in children. Pulse oximetry is a globally accepted, non-invasive method to identify hypoxaemia, but rarely available outside higher-level facilities in resource-constrained countries. This study aims to evaluate the performance of different types of pulse oximeters amongst frontline health workers in Cambodia, Ethiopia, South Sudan, and Uganda.

METHODS

Five pulse oximeters (POx) which passed laboratory testing, out of an initial 32 potential pulse oximeters, were evaluated by frontline health workers for performance, defined as agreement between the SpO₂ measurements of the test device and the reference standard. The study protocol is registered with the Australia New Zealand Clinical Trials Registry (Ref: ACTRrn12615000348550).

FINDINGS

Two finger-tip pulse oximeters (Contec and Devon), two handheld pulse oximeters (Lifebox and Utech), and one phone pulse oximeter (Masimo) passed the laboratory testing. They were evaluated for performance on 1,313 children under five years old by 207 frontline health workers between February and May 2015. Phone and handheld pulse oximeters had greater overall agreement with the reference standard (56%; 95% CI 0.52 - 0.60 to 68%; 95% CI 0.65 - 0.71) than the finger-tip POx (31%; 95% CI 0.26 to 0.36 and 47%; 95% CI 0.42 to 0.52). Fingertip POx performance was substantially lower in the 0-2 month olds; having just 17% and 25% agreement. The finger-tip devices more often underreported SpO₂ readings (mean difference -7.9%; 95%CI -8.6,-7.2 and -3.9%; 95%CI -4.4,-3.4), and therefore over diagnosed hypoxaemia in the children assessed.

INTERPRETATION

While the Masimo phone pulse oximeter performed best, all handheld POx with age-specific probes performed well in the hands of frontline health workers, further highlighting their suitability as a screening tool of severe illness. The poor performance of the fingertip POx suggests they should not be used in children under five by frontline health workers. It is essential that POx are performance tested on children in routine settings (in vivo), not only in laboratories or controlled settings (in vitro), before being introduced at scale.

FUNDING

Bill & Melinda Gates Foundation [OPP1054367].

The effects of mobile health on emergency care in low- and middle-income countries: A systematic review and narrative synthesis

BACKGROUND

In resource-constrained settings, mobile health (mHealth) has varied applications. While there is strong evidence for its use in chronic disease management, the applications of mHealth for management of acute illness in low- and middle-income countries (LMICs) are not as well described. This review systematically explores current available evidence on the effectiveness of mHealth interventions at improving health outcomes in emergency care settings in LMICs.

METHODS

A systematic search of the literature was performed in accordance with PRISMA guidelines, utilizing seven electronic databases and manual searches to identify peer-reviewed literature containing each of three search elements: mHealth, emergency care (EC), and LMICs. Articles quality was assessed using the Grading of Recommendations Assessment, Development and Evaluation (GRADE) criteria.

RESULTS

After removing duplicates, 6498 studies met initial search criteria; 108 were eligible for full text review and 46 met criteria for inclusion. Thirty-six pertained to routine emergency care, and 10 involved complex humanitarian emergencies. Based on the GRADE criteria, 15 studies were rated as "Very Low" quality, 24 as "Low" quality, 6 as "Moderate" quality, and 1 as "High" quality. Eight studied data collection, 9 studied decision support, 15 studied direct patient care, and 14 studied health training. All 46 studies reported positive impacts of mHealth on EC in LMICs.

CONCLUSIONS

Mobile health interventions can be effective in improving provider-focused and patient-centered outcomes in both routine and complex EC settings. Future investigations focusing on patient-centered outcomes are needed to further validate these findings.

Community health worker-based mobile health (mHealth) approaches for improving management and caregiver knowledge of common childhood infections: A systematic review

Background

Children in lower middle-income countries (LMICs) are more at risk of dying, than those in High Income Countries (HICs), due to highly prevalent deadly yet preventable childhood infections. Alongside concerns about the incidence of these infections, there has been a renewed interest in involving community health workers (CHWs) in various public health programs. However, as CHWs are increasingly asked to take on different tasks there is a risk that their workload may become unmanageable. One solution to help reduce this burden is the use of mobile health (mHealth) technology in the community through behaviour change. Considering there are various CHWs based mHealth approaches on illness management and education, therefore, we aimed to appraise the available literature on effectiveness of these mHealth approaches for caregivers to improve knowledge and management about common under-five childhood infections with respect to behaviour change.

Methods

We searched six databases between October to December 2019 using subject heading (Mesh) and free text terms in title or abstract in US English. We included multiple study types of children under-five or their caregivers who have been counselled, educated, or provided any health care service by CHWs for any common paediatric infectious diseases using mHealth. We excluded articles published prior to 1990 and those including mHealth technology not coming under the WHO definition. A data extraction sheet was developed and titles, abstracts, and selected full text were reviewed by two reviewers. Quality assessment was done using JBI tools.

Results

We included 23 articles involving around 300 000 individuals with eight types of study designs. 20 studies were conducted in Africa, two in Asia, and one in Latin America mainly on pneumonia or respiratory tract infections followed by malaria and diarrhoea in children. The most common types of Health approaches were mobile applications for decision support, text message reminders and use of electronic health record systems. None of the studies employed the use of any behaviour change model or any theoretical framework for selection of models in their studies.

Conclusions

Coupling mhealth with CHWs has the potential to benefit communities in improving management of illnesses in children under-five. High quality evidence on impact of such interventions on behaviour is relatively sparse and further studies should be conducted using theoretically informed behaviour change frameworks/models.

Registration

PROPSERO Registration number: CRD42018117679