Dataset Information

The Malaria System MicroApp: A New, Mobile Device-Based Tool for Malaria Diagnosis.

ABSTRACT: BACKGROUND:Malaria is a public health problem that affects remote areas worldwide. Climate change has contributed to the problem by allowing for the survival of Anopheles in previously uninhabited areas. As such, several groups have made developing news systems for the automated diagnosis of malaria a priority. OBJECTIVE:The objective of this study was to develop a new, automated, mobile device-based diagnostic system for malaria. The system uses Giemsa-stained peripheral blood samples combined with light microscopy to identify the Plasmodium falciparum species in the ring stage of development. METHODS:The system uses image processing and artificial intelligence techniques as well as a known face detection algorithm to identify Plasmodium parasites. The algorithm is based on integral image and haar-like features concepts, and makes use of weak classifiers with adaptive boosting learning. The search scope of the learning algorithm is reduced in the preprocessing step by removing the background around blood cells. RESULTS:As a proof of concept experiment, the tool was used on 555 malaria-positive and 777 malaria-negative previously-made slides. The accuracy of the system was, on average, 91%, meaning that for every 100 parasite-infected samples, 91 were identified correctly. CONCLUSIONS:Accessibility barriers of low-resource countries can be addressed with low-cost diagnostic tools. Our system, developed for mobile devices (mobile phones and tablets), addresses this by enabling access to health centers in remote communities, and importantly, not depending on extensive malaria expertise or expensive diagnostic detection equipment.

SUBMITTER: Oliveira AD

PROVIDER: S-EPMC5424126 | biostudies-literature | 2017 Apr

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

The Malaria System MicroApp: A New, Mobile Device-Based Tool for Malaria Diagnosis.

Oliveira Allisson Dantas AD Prats Clara C Espasa Mateu M Zarzuela Serrat Francesc F Montañola Sales Cristina C Silgado Aroa A Codina Daniel Lopez DL Arruda Mercia Eliane ME I Prat Jordi Gomez JG Albuquerque Jones J

JMIR research protocols 20170425 4

<h4>Background</h4>Malaria is a public health problem that affects remote areas worldwide. Climate change has contributed to the problem by allowing for the survival of Anopheles in previously uninhabited areas. As such, several groups have made developing news systems for the automated diagnosis of malaria a priority.<h4>Objective</h4>The objective of this study was to develop a new, automated, mobile device-based diagnostic system for malaria. The system uses Giemsa-stained peripheral blood sa ...[more]

PMID: 28442456

Similar Datasets

Project description:Background:Early and accurate diagnosis of malaria is critical to the success of malaria elimination. However, the current mainstay of malaria diagnosis in the field, such as light microscopy and rapid diagnostic tests (RDTs), have limitations due to low parasite density or mutation in diagnostic markers. Methods:We evaluated an inexpensive, robust, rapid, malaria diagnostic device, called Gazelle, that employs magneto-optical detection to identify haemozoin crystals (Hz) produced by all species of human malaria parasites in infected individuals. A beam of polarised light is passed through the lysed diluted blood sample under the influence of high (~.55T) and low magnetic fields. The difference in light transmission through the sample between the high and low magnetic fields indicates presence of Hz, suggesting possible malarial infection. A total of 300 febrile patients were screened at the malaria clinic of Indian Council of Medical Research-National Institute of Research in Tribal Health (ICMR-NIRTH), Jabalpur, India, from August 2018 to November 2018. Malaria diagnosis was done using four diagnostic methods: Gazelle, light microscopy, RDT, and malaria specific Polymerase Chain Reaction (PCR). Measures of diagnostic accuracy were compared. Findings:Out of 300 febrile patients enroled and tested for the presence of malaria parasites, 262 patient samples were included in the final analysis. The sensitivity and specificity of Gazelle was 98% and 97% in comparison to light microscopy, 82% and 99% to PCR and 78% and 99% to RDT, respectively. The results of the four diagnostic methods were comparable and statistically no significant differences in sensitivity or specificity was observed between these methods. Enhanced diagnostic accuracy of Gazelle in malaria patients with no prior history of malaria treatment was observed in this study. Interpretation:The diagnostic ability of Gazelle was comparable to light microscopy and better than RDTs even in low parasitemia and in presence of pfhrp2/3 deletion mutant parasites. Gazelle may be a novel valuable diagnostic tool in resource poor settings where (i) microscopy is not feasible and (ii) pfhrp2/3gene deleted parasite are present. Its speed, cost-efficiency, and alternative to lack of microscopists makes it an important adjunct in field settings. Funding:HemexDx, India.

Project description:BackgroundDespite the extensive implementation of control measures and achievements in morbidity reductions, malaria continues to contribute to substantial morbidity and mortality in children under-five. Innovative approaches involving the use of mobile phones have been suggested to improve health outcomes. However, evidence of its effect on reducing the prevalence of malaria is limited. This study, therefore, aimed to assess the effect of a theory-driven mHealth intervention on the prevalence of malaria among children under-five living in rural districts of Ghana.MethodsWe conducted a quasi-experimental study of a 12-month intervention using a random sample of 332 caregivers with children under-five from two rural districts, assigned to either an intervention or a control group. Caregivers in the intervention group received voice short message service (SMS) on malaria prevention based on a behavior change theory to improve their health behaviors and practice, once a week for twelve months, while caregivers in the control group received none. Pre- and post-intervention assessment of the treatment effect (ATT) on malaria in children under-five was conducted using propensity score and difference-in-difference (DiD) analyses.ResultsAmong children whose caregivers received the intervention, the prevalence of malaria decreased from 58.4% at baseline to 37.8% at endline (difference: -20.6%; 95% CI: - 31.1, - 10.1) compared with children in the control group, where a reduction of 65.0 to 59.9% (difference - 5.1%; 95% CI: - 15.5, 5.4) was observed. The treatment effect at endline revealed a statistically significant reduction in malaria prevalence (ATT: -0.214; 95% CI: - 0.36, - 0.07) compared with the baseline (ATT: -0.035; 95% CI: - 0.16, 0.09). Overall, the intervention effect showed a significant reduction in the prevalence of malaria among children under-five was positive (DiD: - 0.154; p = 0.043).ConclusionThe results of the study indicate the effectiveness of mobile phone SMS as a control tool for reducing the burden of malaria in children under-five.

Dataset Information

The Malaria System MicroApp: A New, Mobile Device-Based Tool for Malaria Diagnosis.

Publications

The Malaria System MicroApp: A New, Mobile Device-Based Tool for Malaria Diagnosis.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets