Background: In sub-Saharan Africa, Plasmodium falciparum is the most prevalent species of malaria parasites. In endemic areas, malaria is mainly diagnosed using microscopy or rapid diagnostic tests (RDTs), which have limited sensitivity, and microscopic expertise is waning in non-endemic regions. Matrix-assisted laser desorption/ionization time-of-flight (MALDI-TOF) mass spectrometry (MS) is nowadays the standard method in routine microbiology laboratories for bacteria and fungi identification in high-income countries, but is rarely used for parasite detection. This study aims to employ MALDI-TOF MS for identifying malaria by distinguishing P. falciparum-positive from P. falciparum-negative sera.
Methods: Sera were obtained from 282 blood samples collected from non-febrile, asymptomatic people aged 5 to 58 years in southern Côte d'Ivoire. Infectious status and parasitaemia were determined by both RDTs and microscopy, followed by a categorization into two groups (P. falciparum-positive and P. falciparum-negative samples). MALDI-TOF MS analysis was carried out by generating protein spectra profiles from 131 Plasmodium-positive and 94 Plasmodium-negative sera as the training set. Machine learning (ML) algorithms were employed for distinguishing P. falciparum-positive from P. falciparum-negative samples. Subsequently, a subset of 57 sera (42 P. falciparum-positive and 15 P. falciparum-negative) was used as the validation set to evaluate the best two of the four models trained.
Results: MALDI-TOF MS was able to generate good-quality spectra from both P. falciparum-positive and P. falciparum-negative serum samples. High similarities between the protein spectra profiles did not allow for distinguishing the two groups using principal component analysis (PCA). When four supervised ML algorithms were tested by tenfold cross-validation, P. falciparum-positive sera were discriminated against P. falciparum-negative sera with a global accuracy ranging from 73.28% to 81.30%, while sensitivity ranged from 70.23% to 83.97%. The independent test performed with a subset of 57 serum samples showed accuracies of 85.96% and 89.47%, and sensitivities of 90.48% and 92.86%, respectively, for LightGBM and RF.
Conclusion: MALDI-TOF MS combined with ML might be applied for detection of protein profiles related to P. falciparum malaria infection in human serum samples. Additional research is warranted for further optimization such as specific biomarkers detection or using other ML models.
Keywords: Plasmodium falciparum; Machine learning (ML); Malaria identification; Matrix-assisted laser desorption/ionization-time of flight (MALDI-TOF) mass spectrometry; Serum.
© 2025. The Author(s).