Background: Malaria elimination strategies in the Republic of Korea (ROK) have decreased malaria incidence but face challenges due to delayed case detection and response. To improve this, machine learning models for predicting malaria, focusing on high-risk areas, have been developed. Methods: The study targeted the northern region of ROK, near the demilitarized zone, using a 1-km grid to identify areas for prediction. Grid cells without residential buildings were excluded, leaving 8,425 cells. The prediction was based on whether at least one malaria case was reported in each grid cell per month, using spatial data of patient locations. Four algorithms were used: gradient boosted (GBM), generalized linear (GLM), extreme gradient boosted (XGB), and ensemble models, incorporating environmental, sociodemographic, and meteorological data as predictors. The models were trained with data from May to October (2019–2021) and tested with data from May to October 2022. Model performance was evaluated using the area under the receiver operating characteristic curve (AUROC). Results: The AUROC of the prediction models performed excellently (GBM = 0.9243, GLM = 0.9060, XGB = 0.9180, and ensemble model = 0.9301). Previous malaria risk, population size, and meteorological factors influenced the model most in GBM and XGB. Conclusion Machine-learning models with properly preprocessed malaria case data can provide reliable predictions. Additional predictors, such as mosquito density, should be included in future studies to improve the performance of models.

An understanding of the knowledges, attitudes and perceptions of different populations is key for public health policy makers. Here, a survey was performed on knowledge, attitudes, and perceptions about malaria diagnosis, prevention, control, and treatment. The 407 survey participants included both uninfected inhabitants and patients from 2 cities (Gimpo- and Paju-si) of Northern Gyeonggi-do, known as high-risk areas for vivax malaria. We used community-based study design and non-probability sampling method using the primary data. Association between variables were tested using χ2-tests. In general, the information on malaria reported by the participants in this study was unsystematic and included inaccurate details. The knowledge of malaria symptoms, identified as headache, chills and fever, was high, but the surveyed community lacks knowledge of the specific medications used for malaria treatment, with a large number of respondents having no knowledge of any form of medication. Survey questions with high correct answer rates included questions about easy treatment of malaria in Korea, the high daytime activity of malaria-borne mosquitoes, and the infection risk posed by outdoor activities. However, a large portion of the respondents was unable to provide simple medical and biological information about the disease. This study aimed to comprehensively evaluate the knowledge, attitude, and practical behavior of the surveyed community with respect to malaria and the implications reported here could be applicable to other malaria endemic areas in Korea.

Since 1993, vivax malaria has been recognized as a public health burden in Korea. Despite of pan-governmental malaria-control efforts and the dramatic reduction in the burden of this disease over the last 10 years, vivax malaria has not been well controlled and has remained continuously endemic. We focused interviewed and examined the charts of 28 confirmed vivax malaria patients given malarial therapy for whom daily records were kept from Gimpo-si, Gyeonggido of Korea. Various epidemiological characteristics of vivax malaria, including the incubation period, medication used, and recurrence, and an evaluation of the parasitic characteristics from the focused interviews of patients from this region are described here. Most of the participants indicated the 3 most common symptoms of malaria (headache, chills and fever). Of the 28 cases, 2 experienced a second attack and there were 17 and 11 cases with short- and long-term incubation periods, respectively, yielding a short-term to long-term ratio of 1.5. Based on the parasitemia stages, most of the participants were tested at 5 to 7 days (11 cases) and 7 to 15 days (11 cases) after initial wave of asexual parasites. In conclusion, public health authorities should consider developing management measures to decrease the time lag for diagnosis and drafting unified and robust guidelines for drug use for malaria and drawing up unified and robust guidelines on the use of medication for malaria. It also suggests that routine monitoring, surveillance, and precise medical surveys in high-risk vivax malaria endemic areas are pivotal to controlling this persistent public disease and finally eliminating it from Korea.

Vivax malaria incidence in Korea is now decreased and showing a low plateau. Nowadays, vivax malaria in Korea is expected to be successfully eliminated with anti-malaria chemotherapy, primaquine, and vector control. The glucose-6-phosphate dehydrogenase (G6PD) deficiency is associated with potential hemolytic anemia after primaquine administration. This inborn disorder has a pivotal polymorphism with genetic variants and is the most prevalent X-chromosome-linked disorder. The prevalence of G6PD deficiency was previously reported negligible in Korea. As the population of multicultural families pertaining marriage immigrants and their adolescents increases, it is necessary to check G6PD deficiency for them prior to primaquine treatment for vivax malaria. The prevalence of G6PD variants and G6PD deficiency in multicultural families was performed in 7 counties and 2 cities of Jeollanam-do (Province), Gyeonggi-do, and Gangwon-do. A total of 733 blood samples of multicultural family participants were subjected to test the phenotypic and genetic G6PD deficiency status using G6PD enzyme activity quantitation kit and PCR-based G6PD genotyping kit. The G6PD phenotypic deficiency was observed in 7.8% of male adolescent participants and 3.2% of materfamilias population. Based on the PCR-based genotyping, we observed total 35 participants carrying the mutated alleles. It is proposed that primaquine prescription should seriously be considered prior to malaria treatment.