A machine learning approach for early identification of patients with severe imported malaria.
Imported malaria
Machine learning
Risk factors
Severe malaria
Journal
Malaria journal
ISSN: 1475-2875
Titre abrégé: Malar J
Pays: England
ID NLM: 101139802
Informations de publication
Date de publication:
13 Feb 2024
13 Feb 2024
Historique:
received:
08
11
2023
accepted:
03
02
2024
medline:
14
2
2024
pubmed:
14
2
2024
entrez:
13
2
2024
Statut:
epublish
Résumé
The aim of this study is to design ad hoc malaria learning (ML) approaches to predict clinical outcome in all patients with imported malaria and, therefore, to identify the best clinical setting. This is a single-centre cross-sectional study, patients with confirmed malaria, consecutively hospitalized to the Lazzaro Spallanzani National Institute for Infectious Diseases, Rome, Italy from January 2007 to December 2020, were recruited. Different ML approaches were used to perform the analysis of this dataset: support vector machines, random forests, feature selection approaches and clustering analysis. A total of 259 patients with malaria were enrolled, 89.5% patients were male with a median age of 39 y/o. In 78.3% cases, Plasmodium falciparum was found. The patients were classified as severe malaria in 111 cases. From ML analyses, four parameters, AST, platelet count, total bilirubin and parasitaemia, are associated to a negative outcome. Interestingly, two of them, aminotransferase and platelet are not included in the current list of World Health Organization (WHO) criteria for defining severe malaria. In conclusion, the application of ML algorithms as a decision support tool could enable the clinicians to predict the clinical outcome of patients with malaria and consequently to optimize and personalize clinical allocation and treatment.
Sections du résumé
BACKGROUND
BACKGROUND
The aim of this study is to design ad hoc malaria learning (ML) approaches to predict clinical outcome in all patients with imported malaria and, therefore, to identify the best clinical setting.
METHODS
METHODS
This is a single-centre cross-sectional study, patients with confirmed malaria, consecutively hospitalized to the Lazzaro Spallanzani National Institute for Infectious Diseases, Rome, Italy from January 2007 to December 2020, were recruited. Different ML approaches were used to perform the analysis of this dataset: support vector machines, random forests, feature selection approaches and clustering analysis.
RESULTS
RESULTS
A total of 259 patients with malaria were enrolled, 89.5% patients were male with a median age of 39 y/o. In 78.3% cases, Plasmodium falciparum was found. The patients were classified as severe malaria in 111 cases. From ML analyses, four parameters, AST, platelet count, total bilirubin and parasitaemia, are associated to a negative outcome. Interestingly, two of them, aminotransferase and platelet are not included in the current list of World Health Organization (WHO) criteria for defining severe malaria.
CONCLUSION
CONCLUSIONS
In conclusion, the application of ML algorithms as a decision support tool could enable the clinicians to predict the clinical outcome of patients with malaria and consequently to optimize and personalize clinical allocation and treatment.
Identifiants
pubmed: 38351021
doi: 10.1186/s12936-024-04869-3
pii: 10.1186/s12936-024-04869-3
doi:
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Pagination
46Subventions
Organisme : Ministero della Salute
ID : Line1 Ricerca Corrente "Studio dei patogeni ad alto impatto sociale: emergent, da importazione, multiresistenti, negletti"
Informations de copyright
© 2024. The Author(s).
Références
European Centre for Disease Prevention and Control. Annual epidemiological report 2014-emerging and vector-borne disease. Stockholm: ECDC; 2014.
Greenberg AE, Lobel HO. Mortality from Plasmodium falciparum malaria in travelers from the United States, 1959 to 1987. Ann Intern Med. 1990;113:326–7.
doi: 10.7326/0003-4819-113-4-326
pubmed: 2197915
Rajkomar A, Jeffrey D, Kohane I. Machine learning in medicine. N Engl J Med. 2019;380:1347–58.
doi: 10.1056/NEJMra1814259
pubmed: 30943338
Valleron AJ. Data science priorities for a university hospital-based institute of infectious diseases: a viewpoint. Clin Infect Dis. 2017;65(suppl_1):S84–8.
doi: 10.1093/cid/cix351
pubmed: 28859346
Schwalbe N, Wahl B. Artificial intelligence and the future of global health. Lancet. 2020;395:1579–86.
doi: 10.1016/S0140-6736(20)30226-9
pubmed: 32416782
pmcid: 7255280
WHO. World malaria report 2023. Geneva, World Health Organization, 2023.
Cortes C, Vapnik V. Support-vector network. Mach Learn. 1995;20:273–97.
doi: 10.1007/BF00994018
Breiman L. Random forest. Mach Learn. 2001;45:5–32.
doi: 10.1023/A:1010933404324
Van deer Maaten L, Hinton G. Visualizing data using t-SNE. J Mach Learn Res. 2008;9:2579–605.
Bruneel F, Tubach F, Corne P, Megarbane B, Mira JP, Peytel E, et al. Severe imported malaria in adults (SIMA) study group Severe imported falciparum malaria: a cohort study in 400 critically ill adults. PLoS One. 2010;5:e13236.
D’Abramo A, Lepore L, Iannetta M, Gebremeskel Tekle S, Corpolongo A, Scorzolini L, Spallanzani Group for Malaria Study. Imported severe malaria and risk factors for intensive care: a single-centre retrospective analysis. PLoS ONE. 2019;1: e0225135.
doi: 10.1371/journal.pone.0225135
Kalantar-Motamed Y, Eastman RT, Guha R, Bender A. A systematic and prospectively validated approach for identifying synergistic drug combinations against malaria. Malar J. 2018;1:160.
doi: 10.1186/s12936-018-2294-5
Bernabeu M, Danziger SA, Avril M, Vaz M, Babar PH, Brazier AJ. Severe adult malaria is associated with specific PfEMP1 adhesion types and high parasite biomass. Proc Natl Acad Sci USA. 2016;113:E3270–9.
doi: 10.1073/pnas.1524294113
pubmed: 27185931
pmcid: 4988613
Cominetti O, Smith D, Hoffman F, Jallow M, Thézénas ML, Huang H. Identification of a novel clinical phenotype of severe malaria using a network-based clustering approach. Sci Rep. 2018;8:12849.
doi: 10.1038/s41598-018-31320-w
pubmed: 30150696
pmcid: 6110866
Megabiaw F, Eshetu T, Kassahun Z, Aemero M. Liver enzymes and lipid profile of malaria patients before and after antimalarial drug treatment at Dembia Primary Hospital and Teda Health Center, Northwest, Ethiopia. Res Rep Trop Med. 2022;13:11–23.
pubmed: 35370434
pmcid: 8974243
Dos-Santos JCK, Silva-Filho JL, Judice CC, Kayano ACAV, Aliberti J, Khouri R, et al. Platelet disturbances correlate with endothelial cell activation in uncomplicated Plasmodium vivax malaria. PLoS Negl Trop Dis. 2020;14: e0007656.
doi: 10.1371/journal.pntd.0007656
pubmed: 32687542
pmcid: 7392343
Punnath K, Dayanand KK, Chandrashekar VN, Achur RN, Kakkilaya SB, Ghosh SK, et al. Association between inflammatory cytokine levels and thrombocytopenia during Plasmodium falciparum and P. vivax infections in South-Western Coastal Region of India. Malar Res Treat. 2019;2019:4296523.
pubmed: 31110658
pmcid: 6487116