An update on prevention of malaria in travelers

Machine learning approach to identify malaria risk in travelers using real-world evidence

Background

Pre-travel consultation and chemoprophylaxis measures for malaria are a key component in the prevention of imported malaria in travelers. In this study we report a predictive tool for assessing personalized malaria risk in travelers based on the analysis of electronic medical records from travel consultations. The tool aims to guide physicians in the recommendation of appropriate prophylaxis prior to their trip. We also provide best-practice recommendations for pre-processing noisy and highly sparse real world evidence data.

Methods

We leveraged a large EMR dataset, containing demographic information about travelers and their destination. The data has been previously preprocessed using various strategies to handle missing and unbalanced data. We compared multiple machine learning approaches to assess the risk of malaria acquisition in travelers during their travels. Additionally, a feature importance analysis was performed using SHAP (SHapley Additive Explanations) values to identify patterns associated with malaria risk.

Results

Our study revealed that our XGB models achieved high predictive capacity (AUC >0.80). The most significant features predicting malaria infection during travel included travel destinations with low malaria risk, vaccination history, number of countries visited, age, and trip duration. Remarkably, we were able to obtain a reduced model with only five features. When comparing this model with a population of travelers recommended for malaria chemoprophylaxis, we observed that it was deemed necessary in only 40% of these travelers. This suggests that 60% received chemoprophylaxis despite having a low personalized risk of malaria.

Conclusion

We have developed an algorithmic tool that utilizes a concise survey to generate a personalized travel risk assessment, effectively minimizing the prescription of unnecessary malaria chemoprophylaxis. Through the identification of patterns linked to predictions, our model significantly enhances the efficacy of pre-travel consultations.

Evidence of malarial chemoprophylaxis among travellers who died from malaria: a systematic review and meta-analysis

BACKGROUND

Chemoprophylaxis is a prevention method for malaria during travel in malaria-endemic countries. This study aimed to collate and synthesize the evidence of malarial chemoprophylaxis among malaria death cases.

METHODS

Studies documenting malarial chemoprophylaxis related to malaria deaths were searched in PubMed, Scopus, MEDLINE, Embase, and CENTRAL until 3 July 2022. The pooled proportion of malarial chemoprophylaxis among death cases was synthesized using logit transformation and back transformation to a proportion performed using generalized linear mixed models. The pooled log odds ratio (log-OR) with a 95% confidence interval (CI) of malarial chemoprophylaxis in death cases compared to survivors were synthesized.

RESULTS

Fifty-eight studies were included in the systematic review and the meta-analysis. Of 602 pooled malaria death cases, the number of patients who took chemoprophylaxis was 187 (30%) (95% CI 22-40, P < 0.01, 58 studies), and those who took adequate chemoprophylaxis were 24 (5%) (95% CI 2-13, P < 0.01, 42 studies). A comparable log-OR of underwent chemoprophylaxis was observed between malaria death cases and survivors (P = 0.94, pooled log-OR: - 0.02, 95% CI - 0.46-0.42, I2: 0%, 17 studies). Similarly, a comparable log-OR of adequate chemoprophylaxis was identified between malaria death cases and survivors (P = 0.15, pooled log-OR: 0.83, 95% CI - 0.30-1.97, I2: 47.08%, 11 studies).

CONCLUSIONS

Among the studies where malarial chemoprophylaxis was reported, approximately 30% of malaria death cases had taken such prophylaxis. Notably, only 5% of these cases adhered fully or adequately to the recommended chemoprophylactic regimen. However, the analysis did not reveal a significant difference in the odds of malarial chemoprophylaxis between malaria death cases and survivors.

Malaria Detection Using Advanced Deep Learning Architecture

Malaria is a life-threatening disease caused by parasites that are transmitted to humans through the bites of infected mosquitoes. The early diagnosis and treatment of malaria are crucial for reducing morbidity and mortality rates, particularly in developing countries where the disease is prevalent. In this article, we present a novel convolutional neural network (CNN) architecture for detecting malaria from blood samples with a 99.68% accuracy. Our method outperforms the existing approaches in terms of both accuracy and speed, making it a promising tool for malaria diagnosis in resource-limited settings. The CNN was trained on a large dataset of blood smears and was able to accurately classify infected and uninfected samples with high sensitivity and specificity. Additionally, we present an analysis of model performance on different subtypes of malaria and discuss the implications of our findings for the use of deep learning in infectious disease diagnosis.

Diagnosis, Treatment, and Prevention of Malaria in the US: A Review

IMPORTANCE

Malaria is caused by protozoa parasites of the genus Plasmodium and is diagnosed in approximately 2000 people in the US each year who have returned from visiting regions with endemic malaria. The mortality rate from malaria is approximately 0.3% in the US and 0.26% worldwide.

OBSERVATIONS

In the US, most malaria is diagnosed in people who traveled to an endemic region. More than 80% of people diagnosed with malaria in the US acquired the infection in Africa. Of the approximately 2000 people diagnosed with malaria in the US in 2017, an estimated 82.4% were adults and about 78.6% were Black or African American. Among US residents diagnosed with malaria, 71.7% had not taken malaria chemoprophylaxis during travel. In 2017 in the US, P falciparum was the species diagnosed in approximately 79% of patients, whereas P vivax was diagnosed in an estimated 11.2% of patients. In 2017 in the US, severe malaria, defined as vital organ involvement including shock, pulmonary edema, significant bleeding, seizures, impaired consciousness, and laboratory abnormalities such as kidney impairment, acidosis, anemia, or high parasitemia, occurred in approximately 14% of patients, and an estimated 0.3% of those receiving a diagnosis of malaria in the US died. P falciparum has developed resistance to chloroquine in most regions of the world, including Africa. First-line therapy for P falciparum malaria in the US is combination therapy that includes artemisinin. If P falciparum was acquired in a known chloroquine-sensitive region such as Haiti, chloroquine remains an alternative option. When artemisinin-based combination therapies are not available, atovaquone-proguanil or quinine plus clindamycin is used for chloroquine-resistant malaria. P vivax, P ovale, P malariae, and P knowlesi are typically chloroquine sensitive, and treatment with either artemisinin-based combination therapy or chloroquine for regions with chloroquine-susceptible infections for uncomplicated malaria is recommended. For severe malaria, intravenous artesunate is first-line therapy. Treatment of mild malaria due to a chloroquine-resistant parasite consists of a combination therapy that includes artemisinin or chloroquine for chloroquine-sensitive malaria. P vivax and P ovale require additional therapy with an 8-aminoquinoline to eradicate the liver stage. Several options exist for chemoprophylaxis and selection should be based on patient characteristics and preferences.

CONCLUSIONS AND RELEVANCE

Approximately 2000 cases of malaria are diagnosed each year in the US, most commonly in travelers returning from visiting endemic areas. Prevention and treatment of malaria depend on the species and the drug sensitivity of parasites from the region of acquisition. Intravenous artesunate is first-line therapy for severe malaria.