Passive gravitational sedimentation of peripheral blood increases the sensitivity of microscopic detection of malaria

Comparison of capillary, venous and buffy coat blood samples in detecting Plasmodium species among malaria suspected patients attending at Hamusite health center. A cross-sectional study

Background

Both capillary and venous blood samples have been interchangeably used for the diagnosis of malaria in Ethiopia. However, Plasmodium parasites are thought to be more concentrated in capillary than in venous blood. Hence, selecting a sample source where parasites are more concentrated is indispensable approach in order to maximize the accuracy of blood film microscopy. Therefore, the present study aimed to compare the detection rate and the parasitemia level of Plasmodium species from conventional capillary and venous blood films, and buffy coat preparations.

Methods

A facility based cross-sectional study was conducted from Feburary to March 2020 among 210 febrile patients attending Hamusite health center, northwest Ethiopia. Capillary and venous blood samples were collected and buffy coat was prepared from each sample. Thin and thick blood films were prepared, stained, and examined microscopically following standard protocol. Data were analysed using Statistical Package for Social Sciences Software version 20 and Med-Calc software version 19.3.

Results

Capillary blood buffy coat (61/210, 29.0%) had significantly higher detection rate as compared to capillary (48/210, 22.9%) and venous (42/210, 20.0%) blood films (p < 0.001). However, no significant difference was observed between capillary and venous blood films (p = 0.070) in detecting Plasmodium species. The highest and the lowest mean asexual stage parasite counts were found in capillary blood buffy coat (4692.88) and venous blood (631.43) films, respectively showing significant variations (p < 0.001). Mean gametocyte count was also highest in capillary blood buffy coat (3958.44). As compared to capillary blood buffy coat, the sensitivity of venous blood buffy coat, capillary blood film and venous blood film were 73.8, 78.7, 68.9%, respectively.

Conclusion

Capillary blood buffy coat samples showed the highest sensitivity in detecting and quantitating malaria parasites that its use should be promoted in clinical settings. However, conventional capillary and venous blood films could be used interchangeably.

Analyzing Malaria Disease Using Effective Deep Learning Approach

Medical tools used to bolster decision-making by medical specialists who offer malaria treatment include image processing equipment and a computer-aided diagnostic system. Malaria images can be employed to identify and detect malaria using these methods, in order to monitor the symptoms of malaria patients, although there may be atypical cases that need more time for an assessment. This research used 7000 images of Xception, Inception-V3, ResNet-50, NasNetMobile, VGG-16 and AlexNet models for verification and analysis. These are prevalent models that classify the image precision and use a rotational method to improve the performance of validation and the training dataset with convolutional neural network models. Xception, using the state of the art activation function (Mish) and optimizer (Nadam), improved the effectiveness, as found by the outcomes of the convolutional neural model evaluation of these models for classifying the malaria disease from thin blood smear images. In terms of the performance, recall, accuracy, precision, and F1 measure, a combined score of 99.28% was achieved. Consequently, 10% of all non-dataset training and testing images were evaluated utilizing this pattern. Notable aspects for the improvement of a computer-aided diagnostic to produce an optimum malaria detection approach have been found, supported by a 98.86% accuracy level.