Machine learning paired with spectroscopy to detect malaria
Researchers devised a new technique for diagnosing malaria infections that is more easily available and more reliable than current techniques and diagnostic tests. Their method relies on a technology called mid-infrared (MIR) spectroscopy, combined with machine learning.
It is important to track malaria infections both in humans and in mosquitoes so that authorities can prepare healthcare resources and manage cases.
Researchers currently rely on microscopes, PCR (polymerase chain reaction) tests, or rapid diagnostic tests to diagnose malaria, but these methods can be unreliable, be labour intensive, require many skilled people or be too expensive to implement in remote or rural areas..
This study investigated whether mid-infrared (MIR) spectroscopy technology, combined with machine learning, could be a suitable alternative method for rapid malaria screening of dried human blood spots.
The researchers obtained dried blood spots from field surveys of naturally infected individuals in a malaria-endemic community in Tanzania. They scanned the dried blood spots using a MIR spectrometer.
They analysed the dried blood spots of 296 individuals, which was made up of 123 malaria positives and 173 negatives, confirmed with PCR tests. The researchers trained a machine learning algorithm using 80% of the malaria test data, and evaluated the best models that would be suitable for predicting if a sample is positive for Plasmodium falciparum.
Researchers identified a mathematical model that was 92% accurate at predicting Plasmodium falciparum infections, and 85% accurate at predicting mixed infections of Plasmodium falciparum and Plasmodium ovale, another malaria-causing parasite.
Previous research has shown that mid-infrared (MIR) spectroscopy can be used to detect malaria parasites.This study confirmed that the technique is a reliable method for identifying malaria-infected and non-infected specimens from dried human blood spots. This is important because it means no additional reagents or pre-processing is needed for samples.
It also provides further evidence of the potential role of infrared spectroscopy and data-driven chemistry techniques, known as chemometrics, in tracking mosquito-borne diseases.
One limitation of this research is that the number of samples used was low, totalling only 296. Another is that researchers couldn’t factor in how variables such as anaemia, gender, age, and period of storage,could have affected the positivity and negativity of the blood samples.
Number of words:
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.
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.
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.
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.
This summary is a free resource intended to make African research and research that affects Africa, more accessible to non-expert global audiences. It was compiled by ScienceLink's team of professional African science communicators as part of the Masakhane MT: Decolonise Science project. ScienceLink has taken every precaution possible during the writing, editing, and fact-checking process to ensure that this summary is easy to read and understand, while accurately reporting on the facts presented in the original research paper. Note, however, that this summary has not been fact-checked or approved by the authors of the original research paper, so this summary should be used as a secondary resource. Therefore, before using, citing or republishing this summary, please verify the information presented with the original authors of the research paper, or email [email protected] for more information.