Detection of malaria parasites in dried human blood spots using mid-infrared spectroscopy and logistic regression analysis
Abstract Background Epidemiological surveys of malaria currently rely on microscopy, polymerase chain reaction assays (PCR) or rapid diagnostic test kits for Plasmodium infections (RDTs). This study investigated whether mid-infrared (MIR) spectroscopy coupled with supervised machine learning could c...
Main Authors: | , , , , , , , , , , , , , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
BMC
2019-10-01
|
Series: | Malaria Journal |
Subjects: | |
Online Access: | http://link.springer.com/article/10.1186/s12936-019-2982-9 |
id |
doaj-5261c2178fc34ab48ba6aa459876859d |
---|---|
record_format |
Article |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Emmanuel P. Mwanga Elihaika G. Minja Emmanuel Mrimi Mario González Jiménez Johnson K. Swai Said Abbasi Halfan S. Ngowo Doreen J. Siria Salum Mapua Caleb Stica Marta F. Maia Ally Olotu Maggy T. Sikulu-Lord Francesco Baldini Heather M. Ferguson Klaas Wynne Prashanth Selvaraj Simon A. Babayan Fredros O. Okumu |
spellingShingle |
Emmanuel P. Mwanga Elihaika G. Minja Emmanuel Mrimi Mario González Jiménez Johnson K. Swai Said Abbasi Halfan S. Ngowo Doreen J. Siria Salum Mapua Caleb Stica Marta F. Maia Ally Olotu Maggy T. Sikulu-Lord Francesco Baldini Heather M. Ferguson Klaas Wynne Prashanth Selvaraj Simon A. Babayan Fredros O. Okumu Detection of malaria parasites in dried human blood spots using mid-infrared spectroscopy and logistic regression analysis Malaria Journal Malaria diagnosis Plasmodium Ifakara Health Institute Mid-infrared spectroscopy Dried blood spots Supervised machine learning |
author_facet |
Emmanuel P. Mwanga Elihaika G. Minja Emmanuel Mrimi Mario González Jiménez Johnson K. Swai Said Abbasi Halfan S. Ngowo Doreen J. Siria Salum Mapua Caleb Stica Marta F. Maia Ally Olotu Maggy T. Sikulu-Lord Francesco Baldini Heather M. Ferguson Klaas Wynne Prashanth Selvaraj Simon A. Babayan Fredros O. Okumu |
author_sort |
Emmanuel P. Mwanga |
title |
Detection of malaria parasites in dried human blood spots using mid-infrared spectroscopy and logistic regression analysis |
title_short |
Detection of malaria parasites in dried human blood spots using mid-infrared spectroscopy and logistic regression analysis |
title_full |
Detection of malaria parasites in dried human blood spots using mid-infrared spectroscopy and logistic regression analysis |
title_fullStr |
Detection of malaria parasites in dried human blood spots using mid-infrared spectroscopy and logistic regression analysis |
title_full_unstemmed |
Detection of malaria parasites in dried human blood spots using mid-infrared spectroscopy and logistic regression analysis |
title_sort |
detection of malaria parasites in dried human blood spots using mid-infrared spectroscopy and logistic regression analysis |
publisher |
BMC |
series |
Malaria Journal |
issn |
1475-2875 |
publishDate |
2019-10-01 |
description |
Abstract Background Epidemiological surveys of malaria currently rely on microscopy, polymerase chain reaction assays (PCR) or rapid diagnostic test kits for Plasmodium infections (RDTs). This study investigated whether mid-infrared (MIR) spectroscopy coupled with supervised machine learning could constitute an alternative method for rapid malaria screening, directly from dried human blood spots. Methods Filter papers containing dried blood spots (DBS) were obtained from a cross-sectional malaria survey in 12 wards in southeastern Tanzania in 2018/19. The DBS were scanned using attenuated total reflection-Fourier Transform Infrared (ATR-FTIR) spectrometer to obtain high-resolution MIR spectra in the range 4000 cm−1 to 500 cm−1. The spectra were cleaned to compensate for atmospheric water vapour and CO2 interference bands and used to train different classification algorithms to distinguish between malaria-positive and malaria-negative DBS papers based on PCR test results as reference. The analysis considered 296 individuals, including 123 PCR-confirmed malaria positives and 173 negatives. Model training was done using 80% of the dataset, after which the best-fitting model was optimized by bootstrapping of 80/20 train/test-stratified splits. The trained models were evaluated by predicting Plasmodium falciparum positivity in the 20% validation set of DBS. Results Logistic regression was the best-performing model. Considering PCR as reference, the models attained overall accuracies of 92% for predicting P. falciparum infections (specificity = 91.7%; sensitivity = 92.8%) and 85% for predicting mixed infections of P. falciparum and Plasmodium ovale (specificity = 85%, sensitivity = 85%) in the field-collected specimen. Conclusion These results demonstrate that mid-infrared spectroscopy coupled with supervised machine learning (MIR-ML) could be used to screen for malaria parasites in human DBS. The approach could have potential for rapid and high-throughput screening of Plasmodium in both non-clinical settings (e.g., field surveys) and clinical settings (diagnosis to aid case management). However, before the approach can be used, we need additional field validation in other study sites with different parasite populations, and in-depth evaluation of the biological basis of the MIR signals. Improving the classification algorithms, and model training on larger datasets could also improve specificity and sensitivity. The MIR-ML spectroscopy system is physically robust, low-cost, and requires minimum maintenance. |
topic |
Malaria diagnosis Plasmodium Ifakara Health Institute Mid-infrared spectroscopy Dried blood spots Supervised machine learning |
url |
http://link.springer.com/article/10.1186/s12936-019-2982-9 |
work_keys_str_mv |
AT emmanuelpmwanga detectionofmalariaparasitesindriedhumanbloodspotsusingmidinfraredspectroscopyandlogisticregressionanalysis AT elihaikagminja detectionofmalariaparasitesindriedhumanbloodspotsusingmidinfraredspectroscopyandlogisticregressionanalysis AT emmanuelmrimi detectionofmalariaparasitesindriedhumanbloodspotsusingmidinfraredspectroscopyandlogisticregressionanalysis AT mariogonzalezjimenez detectionofmalariaparasitesindriedhumanbloodspotsusingmidinfraredspectroscopyandlogisticregressionanalysis AT johnsonkswai detectionofmalariaparasitesindriedhumanbloodspotsusingmidinfraredspectroscopyandlogisticregressionanalysis AT saidabbasi detectionofmalariaparasitesindriedhumanbloodspotsusingmidinfraredspectroscopyandlogisticregressionanalysis AT halfansngowo detectionofmalariaparasitesindriedhumanbloodspotsusingmidinfraredspectroscopyandlogisticregressionanalysis AT doreenjsiria detectionofmalariaparasitesindriedhumanbloodspotsusingmidinfraredspectroscopyandlogisticregressionanalysis AT salummapua detectionofmalariaparasitesindriedhumanbloodspotsusingmidinfraredspectroscopyandlogisticregressionanalysis AT calebstica detectionofmalariaparasitesindriedhumanbloodspotsusingmidinfraredspectroscopyandlogisticregressionanalysis AT martafmaia detectionofmalariaparasitesindriedhumanbloodspotsusingmidinfraredspectroscopyandlogisticregressionanalysis AT allyolotu detectionofmalariaparasitesindriedhumanbloodspotsusingmidinfraredspectroscopyandlogisticregressionanalysis AT maggytsikululord detectionofmalariaparasitesindriedhumanbloodspotsusingmidinfraredspectroscopyandlogisticregressionanalysis AT francescobaldini detectionofmalariaparasitesindriedhumanbloodspotsusingmidinfraredspectroscopyandlogisticregressionanalysis AT heathermferguson detectionofmalariaparasitesindriedhumanbloodspotsusingmidinfraredspectroscopyandlogisticregressionanalysis AT klaaswynne detectionofmalariaparasitesindriedhumanbloodspotsusingmidinfraredspectroscopyandlogisticregressionanalysis AT prashanthselvaraj detectionofmalariaparasitesindriedhumanbloodspotsusingmidinfraredspectroscopyandlogisticregressionanalysis AT simonababayan detectionofmalariaparasitesindriedhumanbloodspotsusingmidinfraredspectroscopyandlogisticregressionanalysis AT fredrosookumu detectionofmalariaparasitesindriedhumanbloodspotsusingmidinfraredspectroscopyandlogisticregressionanalysis |
_version_ |
1724477969629446144 |
spelling |
doaj-5261c2178fc34ab48ba6aa459876859d2020-11-25T03:53:26ZengBMCMalaria Journal1475-28752019-10-0118111310.1186/s12936-019-2982-9Detection of malaria parasites in dried human blood spots using mid-infrared spectroscopy and logistic regression analysisEmmanuel P. Mwanga0Elihaika G. Minja1Emmanuel Mrimi2Mario González Jiménez3Johnson K. Swai4Said Abbasi5Halfan S. Ngowo6Doreen J. Siria7Salum Mapua8Caleb Stica9Marta F. Maia10Ally Olotu11Maggy T. Sikulu-Lord12Francesco Baldini13Heather M. Ferguson14Klaas Wynne15Prashanth Selvaraj16Simon A. Babayan17Fredros O. Okumu18Environmental Health and Ecological Sciences Department, Ifakara Health InstituteEnvironmental Health and Ecological Sciences Department, Ifakara Health InstituteEnvironmental Health and Ecological Sciences Department, Ifakara Health InstituteSchool of Chemistry, University of GlasgowEnvironmental Health and Ecological Sciences Department, Ifakara Health InstituteEnvironmental Health and Ecological Sciences Department, Ifakara Health InstituteEnvironmental Health and Ecological Sciences Department, Ifakara Health InstituteEnvironmental Health and Ecological Sciences Department, Ifakara Health InstituteEnvironmental Health and Ecological Sciences Department, Ifakara Health InstituteEnvironmental Health and Ecological Sciences Department, Ifakara Health InstituteKEMRI Wellcome Trust Research ProgrammeKEMRI Wellcome Trust Research ProgrammeSchool of Public Health, University of QueenslandInstitute of Biodiversity, Animal Health and Comparative Medicine, University of GlasgowInstitute of Biodiversity, Animal Health and Comparative Medicine, University of GlasgowSchool of Chemistry, University of GlasgowInstitute for Disease ModelingInstitute of Biodiversity, Animal Health and Comparative Medicine, University of GlasgowEnvironmental Health and Ecological Sciences Department, Ifakara Health InstituteAbstract Background Epidemiological surveys of malaria currently rely on microscopy, polymerase chain reaction assays (PCR) or rapid diagnostic test kits for Plasmodium infections (RDTs). This study investigated whether mid-infrared (MIR) spectroscopy coupled with supervised machine learning could constitute an alternative method for rapid malaria screening, directly from dried human blood spots. Methods Filter papers containing dried blood spots (DBS) were obtained from a cross-sectional malaria survey in 12 wards in southeastern Tanzania in 2018/19. The DBS were scanned using attenuated total reflection-Fourier Transform Infrared (ATR-FTIR) spectrometer to obtain high-resolution MIR spectra in the range 4000 cm−1 to 500 cm−1. The spectra were cleaned to compensate for atmospheric water vapour and CO2 interference bands and used to train different classification algorithms to distinguish between malaria-positive and malaria-negative DBS papers based on PCR test results as reference. The analysis considered 296 individuals, including 123 PCR-confirmed malaria positives and 173 negatives. Model training was done using 80% of the dataset, after which the best-fitting model was optimized by bootstrapping of 80/20 train/test-stratified splits. The trained models were evaluated by predicting Plasmodium falciparum positivity in the 20% validation set of DBS. Results Logistic regression was the best-performing model. Considering PCR as reference, the models attained overall accuracies of 92% for predicting P. falciparum infections (specificity = 91.7%; sensitivity = 92.8%) and 85% for predicting mixed infections of P. falciparum and Plasmodium ovale (specificity = 85%, sensitivity = 85%) in the field-collected specimen. Conclusion These results demonstrate that mid-infrared spectroscopy coupled with supervised machine learning (MIR-ML) could be used to screen for malaria parasites in human DBS. The approach could have potential for rapid and high-throughput screening of Plasmodium in both non-clinical settings (e.g., field surveys) and clinical settings (diagnosis to aid case management). However, before the approach can be used, we need additional field validation in other study sites with different parasite populations, and in-depth evaluation of the biological basis of the MIR signals. Improving the classification algorithms, and model training on larger datasets could also improve specificity and sensitivity. The MIR-ML spectroscopy system is physically robust, low-cost, and requires minimum maintenance.http://link.springer.com/article/10.1186/s12936-019-2982-9Malaria diagnosisPlasmodiumIfakara Health InstituteMid-infrared spectroscopyDried blood spotsSupervised machine learning |