Malaria is a blood disease caused by thePlasmodiumparasites transmitted through the bite of female Anopheles mosquito. Microscopists commonly examine thick and thin blood smears to diagnose disease and compute parasitemia. However, their accuracy depends on smear quality and expertise in classifying and counting parasitized and uninfected cells. Such an examination could be arduous for large-scale diagnoses resulting in poor quality. State-of-the-art image-analysis based computer-aided diagnosis (CADx) methods using machine learning (ML) techniques, applied to microscopic images of the smears using hand-engineered features demand expertise in analyzing morphological, textural, and positional variations of the region of interest (ROI). In contrast, Convolutional Neural Networks (CNN), a class of deep learning (DL) models promise highly scalable and superior results with end-to-end feature extraction and classification. Automated malaria screening using DL techniques could, therefore, serve as an effective diagnostic aid. In this study, we evaluate the performance of pre-trained CNN based DL models as feature extractors toward classifying parasitized and uninfected cells to aid in improved disease screening. We experimentally determine the optimal model layers for feature extraction from the underlying data. Statistical validation of the results demonstrates the use of pre-trained CNNs as a promising tool for feature extraction for this purpose.

Malaria remains a major burden on global health, with roughly 200 million cases worldwide and more than 400,000 deaths per year. Besides biomedical research and political efforts, modern information technology is playing a key role in many attempts at fighting the disease. One of the barriers toward a successful mortality reduction has been inadequate malaria diagnosis in particular. To improve diagnosis, image analysis software and machine learning methods have been used to quantify parasitemia in microscopic blood slides. This article gives an overview of these techniques and discusses the current developments in image analysis and machine learning for microscopic malaria diagnosis. We organize the different approaches published in the literature according to the techniques used for imaging, image preprocessing, parasite detection and cell segmentation, feature computation, and automatic cell classification. Readers will find the different techniques listed in tables, with the relevant articles cited next to them, for both thin and thick blood smear images. We also discussed the latest developments in sections devoted to deep learning and smartphone technology for future malaria diagnosis.

Emergence of artemisinin resistance in southeast Asia poses a serious threat to the global control of Plasmodium falciparum malaria. Discovery of the K13 marker has transformed approaches to the monitoring of artemisinin resistance, allowing introduction of molecular surveillance in remote areas through analysis of DNA. We aimed to assess the spread of artemisinin-resistant P falciparum in Myanmar by determining the relative prevalence of P falciparum parasites carrying K13-propeller mutations. We did this cross-sectional survey at malaria treatment centres at 55 sites in ten administrative regions in Myanmar, and in relevant border regions in Thailand and Bangladesh, between January, 2013, and September, 2014. K13 sequences from P falciparum infections were obtained mainly by passive case detection. We entered data into two geostatistical models to produce predictive maps of the estimated prevalence of mutations of the K13 propeller region across Myanmar. Overall, 371 (39%) of 940 samples carried a K13-propeller mutation. We recorded 26 different mutations, including nine mutations not described previously in southeast Asia. In seven (70%) of the ten administrative regions of Myanmar, the combined K13-mutation prevalence was more than 20%. Geospatial mapping showed that the overall prevalence of K13 mutations exceeded 10% in much of the east and north of the country. In Homalin, Sagaing Region, 25 km from the Indian border, 21 (47%) of 45 parasite samples carried K13-propeller mutations. Artemisinin resistance extends across much of Myanmar. We recorded P falciparum parasites carrying K13-propeller mutations at high prevalence next to the northwestern border with India. Appropriate therapeutic regimens should be tested urgently and implemented comprehensively if spread of artemisinin resistance to other regions is to be avoided. Wellcome Trust-Mahidol University-Oxford Tropical Medicine Research Programme and the Bill & Melinda Gates Foundation.

The emergence and spread of resistance in Plasmodium falciparum malaria to artemisinin combination therapies in the Greater Mekong subregion poses a major threat to malaria control and elimination. The current study is part of a multi-country, open-label, randomised clinical trial (TRACII, 2015-18) evaluating the efficacy, safety, and tolerability of triple artemisinin combination therapies. A very high rate of treatment failure after treatment with dihydroartemisinin-piperaquine was observed in Thailand, Cambodia, and Vietnam. The immediate public health importance of our findings prompted us to report the efficacy data on dihydroartemisinin-piperaquine and its determinants ahead of the results of the overall trial, which will be published later this year. Patients aged between 2 and 65 years presenting with uncomplicated P falciparum or mixed species malaria at seven sites in Thailand, Cambodia, and Vietnam were randomly assigned to receive dihydroartemisinin-piperaquine with or without mefloquine, as part of the TRACII trial. The primary outcome was the PCR-corrected efficacy at day 42. Next-generation sequencing was used to assess the prevalence of molecular markers associated with artemisinin resistance (kelch13 mutations, in particular Cys580Tyr) and piperaquine resistance (plasmepsin-2 and plasmepsin-3 amplifications and crt mutations). This study is registered with ClinicalTrials.gov, number NCT02453308. Between Sept 28, 2015, and Jan 18, 2018, 539 patients with acute P falciparum malaria were screened for eligibility, 292 were enrolled, and 140 received dihydroartemisinin-piperaquine. The overall Kaplan-Meier estimate of PCR-corrected efficacy of dihydroartemisinin-piperaquine at day 42 was 50·0% (95% CI 41·1-58·3). PCR-corrected efficacies for individual sites were 12·7% (2·2-33·0) in northeastern Thailand, 38·2% (15·9-60·5) in western Cambodia, 73·4% (57·0-84·3) in Ratanakiri (northeastern Cambodia), and 47·1% (33·5-59·6) in Binh Phuoc (southwestern Vietnam). Treatment failure was associated independently with plasmepsin2/3 amplification status and four mutations in the crt gene (Thr93Ser, His97Tyr, Phe145Ile, and Ile218Phe). Compared with the results of our previous TRACI trial in 2011-13, the prevalence of molecular markers of artemisinin resistance (kelch13 Cys580Tyr mutations) and piperaquine resistance (plasmepsin2/3 amplifications and crt mutations) has increased substantially in the Greater Mekong subregion in the past decade. Dihydroartemisinin-piperaquine is not treating malaria effectively across the eastern Greater Mekong subregion. A highly drug-resistant P falciparum co-lineage is evolving, acquiring new resistance mechanisms, and spreading. Accelerated elimination of P falciparum malaria in this region is needed urgently, to prevent further spread and avoid a potential global health emergency. UK Department for International Development, Wellcome Trust, Bill & Melinda Gates Foundation, Medical Research Council, and National Institutes of Health.

The global burden of lower respiratory infections (LRIs) and corresponding risk factors in children older than 5 years and adults has not been studied as comprehensively as it has been in children younger than 5 years. We assessed the burden and trends of LRIs and risk factors across all age groups by sex, for 204 countries and territories. In this analysis of data for the Global Burden of Diseases, Injuries, and Risk Factors Study (GBD) 2019, we used clinician-diagnosed pneumonia or bronchiolitis as our case definition for LRIs. We included International Classification of Diseases 9th edition codes 079.6, 466–469, 470.0, 480–482.8, 483.0–483.9, 484.1–484.2, 484.6–484.7, and 487–489 and International Classification of Diseases 10th edition codes A48.1, A70, B97.4–B97.6, J09–J15.8, J16–J16.9, J20–J21.9, J91.0, P23.0–P23.4, and U04–U04.9. We used the Cause of Death Ensemble modelling strategy to analyse 23 109 site-years of vital registration data, 825 site-years of sample vital registration data, 1766 site-years of verbal autopsy data, and 681 site-years of mortality surveillance data. We used DisMod-MR 2.1, a Bayesian meta-regression tool, to analyse age–sex-specific incidence and prevalence data identified via systematic reviews of the literature, population-based survey data, and claims and inpatient data. Additionally, we estimated age–sex-specific LRI mortality that is attributable to the independent effects of 14 risk factors. Globally, in 2019, we estimated that there were 257 million (95% uncertainty interval [UI] 240–275) LRI incident episodes in males and 232 million (217–248) in females. In the same year, LRIs accounted for 1·30 million (95% UI 1·18–1·42) male deaths and 1·20 million (1·07–1·33) female deaths. Age-standardised incidence and mortality rates were 1·17 times (95% UI 1·16–1·18) and 1·31 times (95% UI 1·23–1·41) greater in males than in females in 2019. Between 1990 and 2019, LRI incidence and mortality rates declined at different rates across age groups and an increase in LRI episodes and deaths was estimated among all adult age groups, with males aged 70 years and older having the highest increase in LRI episodes (126·0% [95% UI 121·4–131·1]) and deaths (100·0% [83·4–115·9]). During the same period, LRI episodes and deaths in children younger than 15 years were estimated to have decreased, and the greatest decline was observed for LRI deaths in males younger than 5 years (–70·7% [–77·2 to –61·8]). The leading risk factors for LRI mortality varied across age groups and sex. More than half of global LRI deaths in children younger than 5 years were attributable to child wasting (population attributable fraction [PAF] 53·0% [95% UI 37·7–61·8] in males and 56·4% [40·7–65·1] in females), and more than a quarter of LRI deaths among those aged 5–14 years were attributable to household air pollution (PAF 26·0% [95% UI 16·6–35·5] for males and PAF 25·8% [16·3–35·4] for females). PAFs of male LRI deaths attributed to smoking were 20·4% (95% UI 15·4–25·2) in those aged 15–49 years, 30·5% (24·1–36·9) in those aged 50–69 years, and 21·9% (16·8–27·3) in those aged 70 years and older. PAFs of female LRI deaths attributed to household air pollution were 21·1% (95% UI 14·5–27·9) in those aged 15–49 years and 18·2% (12·5–24·5) in those aged 50–69 years. For females aged 70 years and older, the leading risk factor, ambient particulate matter, was responsible for 11·7% (95% UI 8·2–15·8) of LRI deaths. The patterns and progress in reducing the burden of LRIs and key risk factors for mortality varied across age groups and sexes. The progress seen in children younger than 5 years was clearly a result of targeted interventions, such as vaccination and reduction of exposure to risk factors. Similar interventions for other age groups could contribute to the achievement of multiple Sustainable Development Goals targets, including promoting wellbeing at all ages and reducing health inequalities. Interventions, including addressing risk factors such as child wasting, smoking, ambient particulate matter pollution, and household air pollution, would prevent deaths and reduce health disparities. Bill & Melinda Gates Foundation.

A multidrug-resistant co-lineage of Plasmodium falciparum malaria, named KEL1/PLA1, spread across Cambodia in 2008-13, causing high rates of treatment failure with the frontline combination therapy dihydroartemisinin-piperaquine. Here, we report on the evolution and spread of KEL1/PLA1 in subsequent years. For this genomic epidemiology study, we analysed whole genome sequencing data from P falciparum clinical samples collected from patients with malaria between 2007 and 2018 from Cambodia, Laos, northeastern Thailand, and Vietnam, through the MalariaGEN P falciparum Community Project. Previously unpublished samples were provided by two large-scale multisite projects: the Tracking Artemisinin Resistance Collaboration II (TRAC2) and the Genetic Reconnaissance in the Greater Mekong Subregion (GenRe-Mekong) project. By investigating genome-wide relatedness between parasites, we inferred patterns of shared ancestry in the KEL1/PLA1 population. We analysed 1673 whole genome sequences that passed quality filters, and determined KEL1/PLA1 status in 1615. Before 2009, KEL1/PLA1 was only found in western Cambodia; by 2016-17 its prevalence had risen to higher than 50% in all of the surveyed countries except for Laos. In northeastern Thailand and Vietnam, KEL1/PLA1 exceeded 80% of the most recent P falciparum parasites. KEL1/PLA1 parasites maintained high genetic relatedness and low diversity, reflecting a recent common origin. Several subgroups of highly related parasites have recently emerged within this co-lineage, with diverse geographical distributions. The three largest of these subgroups (n=84, n=79, and n=47) mostly emerged since 2016 and were all present in Cambodia, Laos, and Vietnam. These expanding subgroups carried new mutations in the crt gene, which arose on a specific genetic background comprising multiple genomic regions. Four newly emerging crt mutations were rare in the early period and became more prevalent by 2016-17 (Thr93Ser, rising to 19·8%; His97Tyr to 11·2%; Phe145Ile to 5·5%; and Ile218Phe to 11·1%). After emerging and circulating for several years within Cambodia, the P falciparum KEL1/PLA1 co-lineage diversified into multiple subgroups and acquired new genetic features, including novel crt mutations. These subgroups have rapidly spread into neighbouring countries, suggesting enhanced fitness. These findings highlight the urgent need for elimination of this increasingly drug-resistant parasite co-lineage, and the importance of genetic surveillance in accelerating malaria elimination efforts. Wellcome Trust, Bill & Melinda Gates Foundation, UK Medical Research Council, and UK Department for International Development.