Detection Of Malaria Parasites Research Articles

Malaria vector bionomics in Taita-Taveta County, coastal Kenya

BackgroundEstimation of the composition and densities of mosquito species populations is crucial for monitoring the epidemiology of mosquito-borne diseases and provide information on local vectors to public health officials and policy-makers. The aim of this study was to evaluate malaria vector bionomics in ecologically distinct sites in Taita-Taveta County, Kenya.MethodsAdult mosquitoes were collected using backpack aspirators and paired indoor/outdoor CDC light traps in 10 randomly selected households in six villages with distinct ecologies over a study period of 3 years. All Anopheles mosquitoes were morphotyped, and sibling species of Anopheles gambiae sensu lato (An. gambiae s.l.) were identified and separated by PCR analysis of extracted ribosomal DNA. All female anophelines were tested for sporozoite infectivity, with engorged females screened for blood-meal sources using the enzyme-linked immunosorbent assay technique. A subsample of those testing positive and those testing negative for Plasmodium in the ELISA were subjected to PCR assay.ResultsA total of eight different Anopheles species were collected both indoors and outdoors. Anopheles gambiae s.l. (82.6%, n = 5252) was the predominant species sensu lato, followed by Anopheles coustani sensu lato (An. coustani s.l.; (10.5%, n = 666) and Anopheles funestus sensu lato (An. funestus s.l.; 5.6%, n = 357). A subset of 683 mosquito samples representing An. gambiae s.l. (n = 580, approx. 11.0%) and An. funestus s.l. (n = 103, approx. 28.9%) were identified by molecular diagnostic assays into sibling species. The An. gambiae s.l. complex was composed of Anopheles arabiensis (62.5%, n = 363/580), An. gambiae sensu stricto (An. gambiae s.s.; 0.7%, n = 4/580), Anopheles merus (0.7%, n = 4/580) and Anopheles quadriannulatus (0.2%, n = 1/580), with the remaining samples (35.5%, n = 206/580) unamplified. Anopheles funestus s.l. was composed of An. rivulorum (14.6%, n = 15/103) and An. leesoni (11.6%, n = 12/103); the remaining samples were unamplified (73.8%, n = 76/103). A total of 981 samples were subjected to PCR analysis for malaria parasite detection; of these 16 (1.6%) were confirmed to be positive for Plasmodium falciparum. The overall human blood index was 0.13 (32/238).ConclusionsAnopheles gambiae, An. funestus and An. coustani are key malaria vectors in the Taveta region of Kenya, showing concurrent indoor and outdoor transmission. All of the vectors tested showed a higher propensity for bovine and goat blood than for human blood.Graphical

Knowledge, attitudes, and practices regarding malaria control among communities living in the south Cameroon forest region

ObjectiveThis study assessed knowledge, attitudes, and practices (KAP) regarding malaria among communities living in the equatorial forest region of south Cameroon. MethodsThe study was conducted in Olama and Nyabessan. Interviews were undertaken using a semi-structured questionnaire for data collection on KAP, while malaria rapid diagnostic testing, using SD BIOLINE kits, was employed for malaria parasite detection. ResultsIn total, 186 heads of households (HoH), comprising 105 (56.45%) males and 81 (43.45%) females, were interviewed. The majority of HoH demonstrated good knowledge of malaria (86.56%; n = 161) and control measures, with a high proportion of long-lasting insecticidal net (LLIN) ownership (96.8%; n = 180). More than two-thirds (81.1%; n = 151) of households owned at least one LLIN for two people. The majority of HoH (85.40%) declared visiting hospitals or clinics in cases of suspected malaria. Malaria parasite prevalence was high in the two study sites (63.9% in Nyabessan and 48.65% in Olama), and varied according to age, house type, and sleeping time. ConclusionThe study indicated that despite good knowledge of malaria, high possession and utilization of control measures by population, transmission of malaria still persist in the area. The study stress the need for implementing additional control measures to improve the fight against malaria in the area.

Evaluating the Performance of Deep Learning Frameworks for Malaria Parasite Detection Using Microscopic Images of Peripheral Blood Smears.

Malaria is a significant health concern in many third-world countries, especially for pregnant women and young children. It accounted for about 229 million cases and 600,000 mortality globally in 2019. Hence, rapid and accurate detection is vital. This study is focused on achieving three goals. The first is to develop a deep learning framework capable of automating and accurately classifying malaria parasites using microscopic images of thin and thick peripheral blood smears. The second is to report which of the two peripheral blood smears is the most appropriate for use in accurately detecting malaria parasites in peripheral blood smears. Finally, we evaluate the performance of our proposed model with commonly used transfer learning models. We proposed a convolutional neural network capable of accurately predicting the presence of malaria parasites using microscopic images of thin and thick peripheral blood smears. Model evaluation was carried out using commonly used evaluation metrics, and the outcome proved satisfactory. The proposed model performed better when thick peripheral smears were used with accuracy, precision, and sensitivity of 96.97%, 97.00%, and 97.00%. Identifying the most appropriate peripheral blood smear is vital for improved accuracy, rapid smear preparation, and rapid diagnosis of patients, especially in regions where malaria is endemic.

Two-Stage Detection of Plasmodium spp. by Combination of Recombinase Polymerase Amplification and Loop-Mediated Isothermal Amplification Assay.

We developed a combination of recombinase polymerase and loop-mediated isothermal amplification methods (RAMP) for rapid screening of five human Plasmodium spp. simultaneously. RAMP is a two-stage isothermal amplification method, which consists of a first-stage recombinase polymerase amplification and a second-stage loop-mediated isothermal amplification. Under these two isothermal conditions, five Plasmodium spp. were amplified in less than 40 minutes. We demonstrated RAMP assay with 10-fold better limit of detection than a single (loop-mediated isothermal amplification) LAMP. As compared with microscopy, RAMP assay showed 100% sensitivity (95% CI: 95.65-100.00%) and 100% specificity (95% CI: 69.15-100.00%). The end products were inspected by the color changes of neutral red. Positive reactions were indicated by pink while the negative reactions remained yellow. The combination assay established in this study can be used as a routine diagnostic method for malaria.

Comparative Assessment of the Sensitivity of Ten Commercial Rapid Diagnostic Test Kits for the Detection of Plasmodium.

Malaria is one of the most common tropical diseases encountered by members of the French military who are deployed in operations under constrained conditions in malaria-endemic areas. Blood smear microscopy—the gold standard for malaria diagnosis—is often not available in such settings, where the detection of malaria relies on rapid diagnostic tests (RDTs). Ten RDTs (from Biosynex, Carestart, Humasis, SD Bioline, and CTK Biotech), based on the detection of the Plasmodium falciparum histidine-rich protein 2 (HRP2) or lactate dehydrogenase (pLDH, PfLDH, or PvLDH), were assessed against 159 samples collected from imported malaria cases, including 79 P. falciparum, 37 P. vivax, 22 P. ovale, and 21 P. malariae parasites. Samples had been previously characterised using microscopy and real-time PCR. The overall sensitivities for the Plasmodium test ranged from 69.8% (111/159) to 95% (151/159). There was no significant difference for the specific detection of P. falciparum (96.2% to 98.7%, p = 0.845). No significant difference was found between sensitivities to P. vivax by pan LDH or pvLDH (81.1% (30/37) to 94.6% (35/37) (p = 0.845)). Some of the RDTs missed most of P. ovale and P. malariae, with sensitivities for all RDTs ranging respectively from 4.5% (1/22) to 81.8% (18/22) and 14.3% (3/21) to 95.2% (20/21). Carestart Malaria Pf/Pan (pLDH) Ag G0121, a pLDH-based RDT (PfLDH and pLDH), showed the highest sensitivities to P. falciparum (98.7%, 78/79), P. vivax (94.6%, 35/37), P. ovale (81.8%, 18/22), and P. malariae (95.2%, 20/21) and meets the requirements for military deployments in malaria-endemic areas.

Malaria parasite detection using deep learning algorithms based on (CNNs) technique

Malaria is a life-threatening disease caused by female anopheles mosquito bites that are prevalent in many regions of the world. We introduce a deep convolutional neural network (CNN) to improve malaria diagnosis accuracy using patches segmented from microscopic images of red blood cell smears. We design the automatic parasite detection in blood from Giemsa-stained smears using three CNN pre-trained models such as VGG19, ResNet50, and MobileNetV2. As the CNNs are poorly performing for small datasets, we introduce the transfer learning technique. Transfer learning involves acquiring visual features from large general datasets and resolving issues using small datasets. We use a transfer learning approach to detect and classify malaria parasites with three CNN pre-trained models. We evaluated proposed CNN models experimentally using the National Institute of Health (NIH) Malaria Dataset. Our proposed model achieves an accuracy of almost 100%.

Agreement among rapid diagnostic tests, urine malaria tests, and microscopy in malaria diagnosis of adult patients in southwestern Nigeria.

ObjectiveWe determined the malaria prevalence and ascertained the degree of agreement among rapid diagnostic tests (RDTs), urine malaria tests, and microscopy in malaria diagnosis of adults in Nigeria.MethodsThis was a cross-sectional study among 384 consenting patients recruited at a tertiary health facility in southwestern Nigeria. We used standardized interviewer-administered questionnaires to collect patients’ sociodemographic information. Venous blood samples were collected and processed for malaria parasite detection using microscopy, RDTs, and urine malaria tests. The degree of agreement was determined using Cohen’s kappa statistic.ResultsThe malaria prevalence was 58.3% (95% confidence interval [CI]: 53.0–63.1), 20.6% (95% CI: 16.6–25.0), and 54.2% (95% CI: 49.0–59.2) for microscopy, RDTs, and urine malaria test, respectively. The percent agreement between microscopy and RDTs was 50.8%; the expected agreement was 45.1% and Cohen’s kappa was 0.104. The percent agreement between microscopy and urine malaria tests was 52.1%; the expected agreement was 50.7% and Cohen’s kappa was 0.03.ConclusionThe malaria prevalence was dependent on the method of diagnosis. This study revealed that RDTs are a promising diagnostic tool for malaria in resource-limited settings. However, urine malaria test kits require further improvement in sensitivity prior to field use in malaria-endemic settings.

Malaria parasites detection and identification using object detectors based on deep neural networks: a wide comparative analysis

ABSTRACT Malaria is an infectious disease transmitted by the bite of the female Anopheles mosquito, infected by Plasmodium spp. Early diagnosis and prompt and effective treatment are needed to avoid anaemia, organ failure, and death. Manual microscopy is the primary technique used for diagnosing malaria. However, this exam is labour-intensive and requires qualified personnel. In order to alleviate these difficulties, researchers are using computer vision concepts to detect and classify cells infected by the Plasmodium spp. This paper presents a comparative study of seven object detectors based on deep neural networks. We evaluated four versions of the You Only Look Once (YOLO), Single Shot MultiBox Detector, EfficientDet, and Faster R-CNN convolutional neural networks to detect and classify the malaria parasite in six different scenarios. We used four public image datasets, and the YOLOv5 model outperformed the other evaluated models. Their results had similar performance to the state-of-the-art works demonstrating the feasibility and effectiveness of YOLOv5 to detect and classify malaria parasites in thin blood smear images with high precision and sensitivity.

Malaria Case Presentation: The Results of a Web Based Malaria Surveillance in Plateau State, Nigeria

Nigeria bears the heaviest malaria burden of any single nation in the world and has relentlessly pursued the elimination of the disease. One of the key strategies for the elimination of malaria is increasing the specificity and sensitivity of surveillance. To this end, this study sought to determine malaria transmission along an altitudinal gradient of Plateau state, central Nigeria, while examining socio- demographic factors affecting the prevalence of malaria at these sites. Three communities each at high and low elevation areas of Plateau State in central Nigeria were surveyed for incidence of malaria cases. Information on age, gender, use of long-lasting insecticide treated nets, pregnancy status in women, and, malaria severity were recorded in 1700 study subjects. Using venipuncture method, 4ml blood samples were collected in EDTA vials for laboratory analyses. Microscopy (thick and thin blood smear techniques) and Rapid Diagnostic test were used to detect malaria parasites and determine the Plasmodium species involved. Using a propriety application (ELDACAP), real time geolocation data, socioeconomic, health, and preventative status information were also collected from all 1700 respondents. Our findings showed more cases of malaria prevalence in lowland areas compared to highland areas. The main predictors of malaria incidence were age, sex, use of ITN and the presentation of symptoms. Non-net users had more prevalence of malaria compared to users, males had a higher positive frequency compared to females, and malaria was more prevalent in the younger age group compared to older group. Malaria eradication in north-central Nigeria must take into account geographic differences, cultural and social practices, previous anti-malaria preventative measures (use of ITN), as well as the presence of asymptomatic malaria carriers who serve as reservoir in the population

Automated Recognition of Plasmodium falciparum Parasites from Portable Blood Levitation Imaging.

In many malaria‐endemic regions, current detection tools are inadequate in diagnostic accuracy and accessibility. To meet the need for direct, phenotypic, and automated malaria parasite detection in field settings, a portable platform to process, image, and analyze whole blood to detect Plasmodium falciparum parasites, is developed. The liberated parasites from lysed red blood cells suspended in a magnetic field are accurately detected using this cellphone‐interfaced, battery‐operated imaging platform. A validation study is conducted at Ugandan clinics, processing 45 malaria‐negative and 36 malaria‐positive clinical samples without external infrastructure. Texture and morphology features are extracted from the sample images, and a random forest classifier is trained to assess infection status, achieving 100% sensitivity and 91% specificity against gold‐standard measurements (microscopy and polymerase chain reaction), and limit of detection of 31 parasites per µL. This rapid and user‐friendly platform enables portable parasite detection and can support malaria diagnostics, surveillance, and research in resource‐constrained environments.

Assessment of intestinal and blood protozoan infections among pregnant women visiting ante-natal care at Tafo Hospital, Ghana

IntroductionIntestinal and blood protozoans cause morbidity and mortality in both pregnant women and developing foetuses worldwide. It constitutes a major health problem in many tropical areas in Africa. This study assessed the prevalence of intestinal and blood protozoans’ parasitic load and their risk factors among pregnant women visiting antenatal care at Tafo Hospital, Ghana from November 2016 to January 2017. MethodA pilot cross-sectional study was conducted among consented pregnant women who visited antenatal care at Tafo Government Hospital, Kumasi Ghana. Structured questionnaires were administered to obtain socio-demographic data, knowledge on protozoan infections, and their risk factors among study participants. A stool sample was obtained from each participant for the microscopic examination of the intestinal protozoa. Venous blood was taken from participants for the detection of Plasmodium and Toxoplasma gondii infections. Wet mount and the faecal protozoan concentrated method were done for the identification of intestinal parasites. Blood films and serological examination for malaria rapid diagnostic tests (RDT) were done for identification of Plasmodium parasites while an Enzyme-linked immunosorbent assay (ELISA) was used for detecting the antibodies of T. gondii among participants. Data were analyzed using statistical packages for the social sciences (SPSS). ResultsThe mean age of the study participants was 27.83, and ranges from 18 to 40 years. The majority of the participants (82.2%) had never experienced stillbirth nor spontaneous abortion. Intestinal parasites were found in 36.7% of participants. Giardia lamblia (28.1%), Cryptosporidium parvum (5.3%), and Entamoeba histolytica/dispar (3.3%) were among the intestinal protozoans detected. T. gondii antibodies were detected by high levels of immunoglobulins, resulting in IgG (48.0%) and IgM (11.3%) being found among participants, with 7.3% testing positive for both IgM and IgG. The prevalence of malaria infection among the study participants was 2.7%. The consumption of raw or cooked vegetables had significant influence on their intestinal and blood protozoan infections status (p = 0.004) (OR = 0.32, CI = 0.12–0.86). There was a significant association between Hb levels and malaria (p = 0.014) and that of intestinal protozoans (p = 0.035). ConclusionThe prevalence of intestinal protozoans and blood protozoans such as T. gondii were high and therefore effective measures should be put in place to reduce the infectivity. Environmental hygiene should be improved and education by relevant agencies should be intensified on the possible transmission of intestinal and blood parasite infections given the possible role of these infections in adverse pregnancy outcomes.

Insecticide-treated eave nets and window screens for malaria control in Chalinze district, Tanzania: a study protocol for a household randomised control trial

BackgroundLong-lasting insecticidal nets (LLINs) have contributed to the reduction of malaria in sub-Saharan Africa, including Tanzania. However, they rely on daily user behaviour and high coverage which is difficult to maintain. Also, insecticide resistance among malaria vector mosquitoes is contributing to reduced efficacy of control tools. To overcome these problems, we propose to evaluate a new tool for house modification, the insecticide-treated eave nets (ITENs) in combination with insecticide-treated window screens (ITWS) incorporated with dual active ingredient (dual AI) for the control of malaria.MethodsFour hundred and fifty (450) households with intact walls, open eaves without screens or nets on the windows in Chalinze district will be eligible and recruited upon written informed consent. The households will be randomly allocated into two arms: one with ITENs and ITWS installed and the other without. Malaria parasite detection using a quantitative polymerase chain reaction (qPCR) will be conducted shortly after the long rain (June/July, 2022) as the primary outcome and shortly after the short rain (January/February, 2022) as the secondary outcome. Other secondary outcomes include clinical malaria cases, and density of malaria vectors and nuisance after the short rain and long rain. In addition, surveys will be conducted in households with ITENs and ITWS to estimate the intervention’s cost during installation, adverse effects one month after installation, and presence, fabric integrity and user acceptance six and twelve months after installation. Bioefficacy and chemical content will be evaluated twelve months after installation.DiscussionITENs and ITWS have been shown in Kenya to reduce indoor mosquito density. However, it is not known if indoor mosquito density reduction translates into reduction of malaria cases. Data from the study will measure the potential public health value of an additional intervention for malaria control at the household level in areas of mosquito insecticide resistance that does not require daily adherence.Trial registrationThe study is registered on ClinicalTrials.gov.

Prevalence of malaria and helminth infections in rural communities in northern Sierra Leone, a baseline study to inform Ebola vaccine study protocols.

Recurrent parasitic infections may influence the immune response to vaccines. In the Partnership for Research on Ebola VACcinations extended follow-UP and clinical research capacity build-UP (PREVAC-UP) study being undertaken in Mambolo, northern Sierra Leone, participants are being followed up to assess the potential impact of exposure to malaria and/or helminth infections on long-term immune response to two Ebola vaccines. To support the development of the assays that will be used in this evaluation, a parasitological survey was conducted in Mambolo between November 2019 and February 2020. Healthy individuals aged ≥1 year who were resident in Mambolo Chiefdom were selected using a stratified sampling approach and questionnaires were administered to explore their sociodemographic characteristics. Microscopy was used to detect malaria parasites, intestinal helminths and urinary schistosome infections. Rapid blood tests were used to detect infections with Onchocerca volvulus and Wuchereria bancrofti. We estimated the overall prevalence of these infections and used adjusted logistic regression models to explore risk factors for malaria and hookworm infection. Eight hundred and fifteen (815) residents, 50.9% of whom were female were surveyed. Overall, 309 (39.1%) of 791 persons tested for malaria had a positive blood slide; Plasmodium falciparum was the dominant species. Helminth infection was detected in 122 (15.0%) of 815 stool samples including three mixed infections. The helminth infections comprised 102 (12.5%) cases of hookworm, 11 (1.3%) cases of Trichuris trichiura, 10 (1.2%) cases of Schistosoma mansoni and two (0.2%) cases of Ascaris lumbricoides. Being male (OR = 2.01, 95% CI 1.15-3.50) and residing in a non-riverine community (OR = 4.02, 95%CI 2.32-6.98) were the factors associated with hookworm infection. Onchocerca volvulus and Wuchereria bancrofti infections were found in 3.3% and 0.4% of participants respectively. Malaria and hookworm are the most prevalent parasite infections and those most likely to influence long-term immune response to Ebola vaccines among the trial participants.

A new approach for malaria diagnosis in thick blood smear images

This paper presents a new approach for detecting malaria parasites in full images of thick blood smear using pixel classifiers for obtaining foreground objects and delimiting parasite-stained objects. For both processes, the HSV components were used as input variables of the following pixel classifiers: multilayer perceptron and a decision tree. The obtained patches were classified using a deep neural network with 34 layers, trained from scratch. The image dataset used was divided into sets with different parasite sizes. This enables characterizing performance metrics (accuracy, sensitivity, specificity, precision, and F1-score) for parasite detection with varying parasite sizes. The best metric values were obtained in images with large parasite sizes. For image sets 1 and 2, with large parasite sizes, precision rates of 91.71% and 93.14% were obtained. For image sets 3 and 4, with small parasite sizes, precision rates of 76.58% and 71.58% were obtained. As shown by the literature review, these results are comparable to others previously published. Nevertheless, a rigorous comparison could not be done, as different works use different datasets.

Detection of Malaria Parasites in Different Age and Gender Groups Using a Light Microscopy

Introduction: The most frequent pathogens responsible for renal failure in hospitalised patients are Staphylococcus species, particularly in those receiving hemodialysis. The aim was to isolate and identified the Staphylococcus species from hemodialysis patients. Methodology: The research was carried out between November 2021 and February 2022. This study included participants who were receiving maintenance hemodialysis for end-stage renal illness. Each patient's demographic information was gathered using a structured questionnaire that had been evaluated beforehand. Blood samples from both sexes were taken (28 males and 22 females). The blood samples were sent directly to the research lab for processing after being inoculated into the Brain Heart Infusion broth under aseptic circumstances. Gram stain and biochemical assays were used to determine the bacteria's identity. Result :Overall, there were 44 percent female patients and 56 percent male patients. Out of all the blood samples analyse, 26% of samples showed evidence of bacterial development in the Brain Heart Infusion broth. S. aureus species (62 percent), S. epidermidis (15 percent), and S. saprophyticus were the Staphylococcus species that were detected 23 percent). Conclusion According to the findings, coagulase-positive Staphylococci were the most often isolated species from hemodialysis patients who had bacteremia, but coagulase-negative strains were identified far less frequently. The findings of the current study need to be confirmed by more research. Keywords: S. aureus, Kidney Failure, Hemodialysis, Femoral Double Lumen Catheter

Explainable Transformer-Based Deep Learning Model for the Detection of Malaria Parasites from Blood Cell Images

Malaria is a life-threatening disease caused by female anopheles mosquito bites. Various plasmodium parasites spread in the victim’s blood cells and keep their life in a critical situation. If not treated at the early stage, malaria can cause even death. Microscopy is a familiar process for diagnosing malaria, collecting the victim’s blood samples, and counting the parasite and red blood cells. However, the microscopy process is time-consuming and can produce an erroneous result in some cases. With the recent success of machine learning and deep learning in medical diagnosis, it is quite possible to minimize diagnosis costs and improve overall detection accuracy compared with the traditional microscopy method. This paper proposes a multiheaded attention-based transformer model to diagnose the malaria parasite from blood cell images. To demonstrate the effectiveness of the proposed model, the gradient-weighted class activation map (Grad-CAM) technique was implemented to identify which parts of an image the proposed model paid much more attention to compared with the remaining parts by generating a heatmap image. The proposed model achieved a testing accuracy, precision, recall, f1-score, and AUC score of 96.41%, 96.99%, 95.88%, 96.44%, and 99.11%, respectively, for the original malaria parasite dataset and 99.25%, 99.08%, 99.42%, 99.25%, and 99.99%, respectively, for the modified dataset. Various hyperparameters were also finetuned to obtain optimum results, which were also compared with state-of-the-art (SOTA) methods for malaria parasite detection, and the proposed method outperformed the existing methods.

Barnacles Mating Optimizer with Deep Transfer Learning Enabled Biomedical Malaria Parasite Detection and Classification.

Biomedical engineering involves ideologies and problem-solving methods of engineering to biology and medicine. Malaria is a life-threatening illness, which has gained significant attention among researchers. Since the manual diagnosis of malaria in a clinical setting is tedious, automated tools based on computational intelligence (CI) tools have gained considerable interest. Though earlier studies were focused on the handcrafted features, the diagnostic accuracy can be boosted through deep learning (DL) methods. This study introduces a new Barnacles Mating Optimizer with Deep Transfer Learning Enabled Biomedical Malaria Parasite Detection and Classification (BMODTL-BMPC) model. The presented BMODTL-BMPC model involves the design of intelligent models for the recognition and classification of malaria parasites. Initially, the Gaussian filtering (GF) approach is employed to eradicate noise in blood smear images. Then, Graph cuts (GC) segmentation technique is applied to determine the affected regions in the blood smear images. Moreover, the barnacles mating optimizer (BMO) algorithm with the NasNetLarge model is employed for the feature extraction process. Furthermore, the extreme learning machine (ELM) classification model is employed for the identification and classification of malaria parasites. To assure the enhanced outcomes of the BMODTL-BMPC technique, a wide-ranging experimentation analysis is performed using a benchmark dataset. The experimental results show that the BMODTL-BMPC technique outperforms other recent approaches.

Field evaluation of the diagnostic performance of EasyScan GO: a digital malaria microscopy device based on machine-learning

BackgroundMicroscopic examination of Giemsa-stained blood films remains the reference standard for malaria parasite detection and quantification, but is undermined by difficulties in ensuring high-quality manual reading and inter-reader reliability. Automated parasite detection and quantification may address this issue.MethodsA multi-centre, observational study was conducted during 2018 and 2019 at 11 sites to assess the performance of the EasyScan Go, a microscopy device employing machine-learning-based image analysis. Sensitivity, specificity, accuracy of species detection and parasite density estimation were assessed with expert microscopy as the reference. Intra- and inter-device reliability of the device was also evaluated by comparing results from repeat reads on the same and two different devices. This study has been reported in accordance with the Standards for Reporting Diagnostic accuracy studies (STARD) checklist.ResultsIn total, 2250 Giemsa-stained blood films were prepared and read independently by expert microscopists and the EasyScan Go device. The diagnostic sensitivity of EasyScan Go was 91.1% (95% CI 88.9–92.7), and specificity 75.6% (95% CI 73.1–78.0). With good quality slides sensitivity was similar (89.1%, 95%CI 86.2–91.5), but specificity increased to 85.1% (95%CI 82.6–87.4). Sensitivity increased with parasitaemia rising from 57% at < 200 parasite/µL, to ≥ 90% at > 200–200,000 parasite/µL. Species were identified accurately in 93% of Plasmodium falciparum samples (kappa = 0.76, 95% CI 0.69–0.83), and in 92% of Plasmodium vivax samples (kappa = 0.73, 95% CI 0.66–0.80). Parasite density estimates by the EasyScan Go were within ± 25% of the microscopic reference counts in 23% of slides.ConclusionsThe performance of the EasyScan Go in parasite detection and species identification accuracy fulfil WHO-TDR Research Malaria Microscopy competence level 2 criteria. In terms of parasite quantification and false positive rate, it meets the level 4 WHO-TDR Research Malaria Microscopy criteria. All performance parameters were significantly affected by slide quality. Further software improvement is required to improve sensitivity at low parasitaemia and parasite density estimations.Trial registration ClinicalTrials.gov number NCT03512678.

MOLECULAR DETECTION OF THE PLASMODIUM FALCIPARUM OBTAINED FROM OUT-PATIENTS FROM SELECTED HOSPITALS IN KADUNA STATE

Molecular detection of Plasmodium falciparum based on PCR amplification is generally very specific and sensitive test for determining the species of Plasmodium present in the blood of an individual than the microscopy-based diagnosis from blood smears. Thirty-two (32) microscopic malaria positive blood samples were collected from some patients between November 2013 to March 2014 from three major hospitals.Plasmodium DNA was extracted from the 32 blood samples collected from the malaria-positive patients confirmed by microscopy and the DNA amplification was done by using Polymerase Chain Reaction (PCR). The amplified COX3 gene of each malaria isolates were further characterized using Agarose gel electrophoresis while sequence identification was performed by using GenBank’s BLAST algorithm. After the completion of the agarose gel electrophoresis the bands indicating amplified Cox3 gene by PCR was observed in four (4) plasmodium positive blood samples out of the 32 samples analyzed. Amplified band for COX3 gene was located at 300bp position on the DNA ladder on the agarose gel plate for sample 1, 9 and 24 all from Kagarko general hospital while sample 28 was from GwannaAwan general hospital. The BLAST results showed that the P. falciparum DNA sequences aligned at 98-99% similarity with those deposited in the GenBank confirming the parasite isolated from the patients were P. falciparum. The use of PCR diagnosis to compliment microscopy examination of stained blood smears in our medical centres is strongly recommended so that an accurate detection of malaria parasites in blood will help to institute proper drug therapy

Computational Methods for Automated Analysis of Malaria Parasite Using Blood Smear Images: Recent Advances.

Malaria comes under one of the dangerous diseases in many countries. It is the primary reason for most of the causalities across the world. It is presently rated as a significant cause of the high mortality rate worldwide compared with other diseases that can be reduced significantly by its earlier detection. Therefore, to facilitate the early detection/diagnosis of malaria to reduce the mortality rate, an automated computational method is required with a high accuracy rate. This study is a solid starting point for researchers who want to look into automated blood smear analysis to detect malaria. In this paper, a comprehensive review of different computer-assisted techniques has been outlined as follows: (i) acquisition of image dataset, (ii) preprocessing, (iii) segmentation of RBC, and (iv) feature extraction and selection, and (v) classification for the detection of malaria parasites using blood smear images. This study will be helpful for: (i) researchers can inspect and improve the existing computational methods for early diagnosis of malaria with a high accuracy rate that may further reduce the interobserver and intra-observer variations; (ii) microbiologists to take the second opinion from the automated computational methods for effective diagnosis of malaria; and (iii) finally, several issues remain addressed, and future work has also been discussed in this work.