Imported severe malaria and risk factors for intensive care: A single-centre retrospective analysis

A machine learning approach for early identification of patients with severe imported malaria

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

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

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

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.

Diagnosis and management of malaria in the intensive care unit

Malaria is responsible for approximately three-quarters of a million deaths in humans globally each year. Most of the morbidity and mortality reported are from Sub-Saharan Africa and Asia, where the disease is endemic. In non-endemic areas, malaria is the most common cause of imported infection and is associated with significant mortality despite recent advancements and investments in elimination programs. Severe malaria often requires intensive care unit admission and can be complicated by cerebral malaria, respiratory distress, acute kidney injury, bleeding complications, and co-infection. Intensive care management includes prompt diagnosis and early initiation of effective antimalarial therapy, recognition of complications, and appropriate supportive care. However, the lack of diagnostic capacities due to limited advances in equipment, personnel, and infrastructure presents a challenge to the effective diagnosis and management of malaria. This article reviews the clinical classification, diagnosis, and management of malaria as relevant to critical care clinicians, highlighting the role of diagnostic capacity, treatment options, and supportive care.