METHODS: Vector data from various sources were used to create distribution maps from 1957 to 2021. A predictive statistical model utilizing logistic regression was developed using significant environmental factors. Interpolation maps were created using the inverse distance weighted (IDW) method and overlaid with the corresponding environmental variables.
RESULTS: Based on the IDW analysis, high vector abundances were found in the southwestern part of Sarawak, the northern region of Pahang and the northwestern part of Sabah. However, most parts of Johor, Sabah, Perlis, Penang, Kelantan and Terengganu had low vector abundance. The accuracy test indicated that the model predicted sampling and non-sampling areas with 75.3% overall accuracy. The selected environmental variables were entered into the regression model based on their significant values. In addition to the presence of water bodies, elevation, temperature, forest loss and forest cover were included in the final model since these were significantly correlated. Anopheles mosquitoes were mainly distributed in Peninsular Malaysia (Titiwangsa range, central and northern parts), Sabah (Kudat, West Coast, Interior and Tawau division) and Sarawak (Kapit, Miri, and Limbang). The predicted Anopheles mosquito density was lower in the southern part of Peninsular Malaysia, the Sandakan Division of Sabah and the western region of Sarawak.
CONCLUSION: The study offers insight into the distribution of the Leucosphyrus Group of Anopheles mosquitoes in Malaysia. Additionally, the accompanying predictive vector map correlates well with cases of P. knowlesi malaria. This research is crucial in informing and supporting future efforts by healthcare professionals to develop effective malaria control interventions.
METHODS/FINDINGS: A total of 550 children participated, comprising 520 (94.5%) school children aged 7 to 12 years old, 30 (5.5%) young children aged 1 to 6 years old, 254 (46.2%) boys and 296 (53.8%) girls. Of the 550 children, 26.2% were anaemic, 54.9% iron deficient and 16.9% had iron deficiency anaemia (IDA). The overall prevalence of helminths was 76.5% comprising Trichuris trichiura (71.5%), Ascaris lumbricoides (41.6%) and hookworm infection (13.5%). It was observed that iron deficiency was significantly higher in girls (p = 0.032) compared to boys. Univariate analysis demonstrated that low level of mother's education (OR = 2.52; 95% CI = 1.38-4.60; p = 0.002), non working parents (OR = 2.18; 95% CI = 2.06-2.31; p = 0.013), low household income (OR = 2.02; 95% CI = 1.14-3.59; p = 0.015), T. trichiura (OR = 2.15; 95% CI = 1.21-3.81; p = 0.008) and A. lumbricoides infections (OR = 1.63; 95% CI = 1.04-2.55; p = 0.032) were significantly associated with the high prevalence of IDA. Multivariate analysis confirmed that low level of mother's education (OR = 1.48; 95 CI% = 1.33-2.58; p<0.001) was a significant predictor for IDA in these children.
CONCLUSION: It is crucial that a comprehensive primary health care programme for these communities that includes periodic de-worming, nutrition supplement, improved household economy, education, sanitation status and personal hygiene are taken into consideration to improve the nutritional status of these children.
METHODS: Three object detection networks of DL algorithms, namely SSD-MobileNetV2, EfficientDet, and YOLOv4, were developed to automatically detect Escherichia coli (E. coli) bacteria from microscopic images. The multi-task DL framework is developed to classify the bacteria according to their respective growth stages, which include rod-shaped cells, dividing cells, and microcolonies. Data preprocessing steps were carried out before training the object detection models, including image augmentation, image annotation, and data splitting. The performance of the DL techniques is evaluated using the quantitative assessment method based on mean average precision (mAP), precision, recall, and F1-score. The performance metrics of the models were compared and analysed. The best DL model was then selected to perform multi-task object detections in identifying rod-shaped cells, dividing cells, and microcolonies.
RESULTS: The output of the test images generated from the three proposed DL models displayed high detection accuracy, with YOLOv4 achieving the highest confidence score range of detection and being able to create different coloured bounding boxes for different growth stages of E. coli bacteria. In terms of statistical analysis, among the three proposed models, YOLOv4 demonstrates superior performance, achieving the highest mAP of 98% with the highest precision, recall, and F1-score of 86%, 97%, and 91%, respectively.
CONCLUSIONS: This study has demonstrated the effectiveness, potential, and applicability of DL approaches in multi-task bacterial image analysis, focusing on automating the detection and classification of bacteria from microscopic images. The proposed models can output images with bounding boxes surrounding each detected E. coli bacteria, labelled with their growth stage and confidence level of detection. All proposed object detection models have achieved promising results, with YOLOv4 outperforming the other models.
METHODS: The YOLOv4 model is modified using direct layer pruning and backbone replacement. The primary objective of layer pruning is the removal and individual analysis of residual blocks within the C3, C4 and C5 (C3-C5) Res-block bodies of the backbone architecture's C3-C5 Res-block bodies. The CSP-DarkNet53 backbone is simultaneously replaced for enhanced feature extraction with a shallower ResNet50 network. The performance metrics of the models are compared and analysed.
RESULTS: The modified models outperform the original YOLOv4 model. The YOLOv4-RC3_4 model with residual blocks pruned from the C3 and C4 Res-block body achieves the highest mean accuracy precision (mAP) of 90.70%. This mAP is > 9% higher than that of the original model, saving approximately 22% of the billion floating point operations (B-FLOPS) and 23 MB in size. The findings indicate that the YOLOv4-RC3_4 model also performs better, with an increase of 9.27% in detecting the infected cells upon pruning the redundant layers from the C3 Res-block bodies of the CSP-DarkeNet53 backbone.
CONCLUSIONS: The results of this study highlight the use of the YOLOv4 model for detecting infected red blood cells. Pruning the residual blocks from the Res-block bodies helps to determine which Res-block bodies contribute the most and least, respectively, to the model's performance. Our method has the potential to revolutionise malaria diagnosis and pave the way for novel deep learning-based bioinformatics solutions. Developing an effective and automated process for diagnosing malaria will considerably contribute to global efforts to combat this debilitating disease. We have shown that removing undesirable residual blocks can reduce the size of the model and its computational complexity without compromising its precision.
METHODS: Samples were subjected to microscopy examination and serological test (only for Strongyloides). Speciation for parasites on microscopy-positive samples and seropositive samples for Strongyloides were further determined via polymerase chain reaction. SPSS was used for statistical analysis.
RESULTS: A total of 294 stool and blood samples each were successfully collected, involving 131 HIV positive and 163 HIV negative adult male inmates whose age ranged from 21 to 69-years-old. Overall prevalence showed 26.5% was positive for various IPIs. The IPIs detected included Blastocystis sp., Strongyloides stercoralis, Entamoeba spp., Cryptosporidium spp., Giardia spp., and Trichuris trichiura. Comparatively, the rate of IPIs was slightly higher among the HIV positive inmates (27.5%) than HIV negative inmates (25.8%). Interestingly, seropositivity for S. stercoralis was more predominant in HIV negative inmates (10.4%) compared to HIV-infected inmates (6.9%), however these findings were not statistically significant. Polymerase chain reaction (PCR) confirmed the presence of Blastocystis, Strongyloides, Entamoeba histolytica and E. dispar.
CONCLUSIONS: These data will enable the health care providers and prison management staff to understand the trend and epidemiological situations in HIV/parasitic co-infections in a prison. This information will further assist in providing evidence-based guidance to improve prevention, control and management strategies of IPIs co-infections among both HIV positive and HIV negative inmates in a prison environment.