Improved pediatric ICU mortality prediction for respiratory diseases: machine learning and data subdivision insights.

The growing concern of pediatric mortality demands heightened preparedness in clinical settings, especially within intensive care units (ICUs). As respiratory-related admissions account for a substantial portion of pediatric illnesses, there is a pressing need to predict ICU mortality in these cases. This study based on data from 1188 patients, addresses this imperative using machine learning techniques and investigating different class balancing methods for pediatric ICU mortality prediction. This study employs the publicly accessible "Paediatric Intensive Care database" to train, validate, and test a machine learning model for predicting pediatric patient mortality. Features were ranked using three machine learning feature selection techniques, namely Random Forest, Extra Trees, and XGBoost, resulting in the selection of 16 critical features from a total of 105 features. Ten machine learning models and ensemble techniques are used to make accurate mortality predictions. To tackle the inherent class imbalance in the dataset, we applied a unique data partitioning technique to enhance the model's alignment with the data distribution. The CatBoost machine learning model achieved an area under the curve (AUC) of 72.22%, while the stacking ensemble model yielded an AUC of 60.59% for mortality prediction. The proposed subdivision technique, on the other hand, provides a significant improvement in performance metrics, with an AUC of 85.2% and an accuracy of 89.32%. These findings emphasize the potential of machine learning in enhancing pediatric mortality prediction and inform strategies for improved ICU readiness.

Machine learning-based prognostic model for 30-day mortality prediction in Sepsis-3.

BACKGROUND: Sepsis poses a critical threat to hospitalized patients, particularly those in the Intensive Care Unit (ICU). Rapid identification of Sepsis is crucial for improving survival rates. Machine learning techniques offer advantages over traditional methods for predicting outcomes. This study aimed to develop a prognostic model using a Stacking-based Meta-Classifier to predict 30-day mortality risks in Sepsis-3 patients from the MIMIC-III database. METHODS: A cohort of 4,240 Sepsis-3 patients was analyzed, with 783 experiencing 30-day mortality and 3,457 surviving. Fifteen biomarkers were selected using feature ranking methods, including Extreme Gradient Boosting (XGBoost), Random Forest, and Extra Tree, and the Logistic Regression (LR) model was used to assess their individual predictability with a fivefold cross-validation approach for the validation of the prediction. The dataset was balanced using the SMOTE-TOMEK LINK technique, and a stacking-based meta-classifier was used for 30-day mortality prediction. The SHapley Additive explanations analysis was performed to explain the model's prediction. RESULTS: Using the LR classifier, the model achieved an area under the curve or AUC score of 0.99. A nomogram provided clinical insights into the biomarkers' significance. The stacked meta-learner, LR classifier exhibited the best performance with 95.52% accuracy, 95.79% precision, 95.52% recall, 93.65% specificity, and a 95.60% F1-score. CONCLUSIONS: In conjunction with the nomogram, the proposed stacking classifier model effectively predicted 30-day mortality in Sepsis patients. This approach holds promise for early intervention and improved outcomes in treating Sepsis cases.

FPGA Implementation of Complex-Valued Neural Network for Polar-Represented Image Classification.

This proposed research explores a novel approach to image classification by deploying a complex-valued neural network (CVNN) on a Field-Programmable Gate Array (FPGA), specifically for classifying 2D images transformed into polar form. The aim of this research is to address the limitations of existing neural network models in terms of energy and resource efficiency, by exploring the potential of FPGA-based hardware acceleration in conjunction with advanced neural network architectures like CVNNs. The methodological innovation of this research lies in the Cartesian to polar transformation of 2D images, effectively reducing the input data volume required for neural network processing. Subsequent efforts focused on constructing a CVNN model optimized for FPGA implementation, emphasizing the enhancement of computational efficiency and overall performance. The experimental findings provide empirical evidence supporting the efficacy of the image classification system developed in this study. One of the developed models, CVNN_128, achieves an accuracy of 88.3% with an inference time of just 1.6 ms and a power consumption of 4.66 mW for the classification of the MNIST test dataset, which consists of 10,000 frames. While there is a slight concession in accuracy compared to recent FPGA implementations that achieve 94.43%, our model significantly excels in classification speed and power efficiency-surpassing existing models by more than a factor of 100. In conclusion, this paper demonstrates the substantial advantages of the FPGA implementation of CVNNs for image classification tasks, particularly in scenarios where speed, resource, and power consumption are critical.

Examining the disparities of anti-malarial drug consumption among children under the age of five: a study of 5 malaria-endemic countries.

BACKGROUND: Malaria is one of the most prominent illnesses affecting children, ranking as one of the key development concerns for many low- and middle-income countries (LMICs). There is not much information available on the use of anti-malarial drugs in LMICs in children under five. The study aimed to investigate disparities in anti-malarial drug consumption for malaria among children under the age of five in LMICs. METHODS: This study used recent available cross-sectional data from the Malaria Indicator Survey (MIS) datasets across five LMICs (Guinea, Kenya, Mali, Nigeria, and Sierra Leone), which covered a portion of sub-Saharan Africa. The study was carried out between January 2, 2023, and April 15, 2023, and included children under the age of five who had taken an anti-malarial drug for malaria 2 weeks before the survey date. The outcome variable was anti-malarial drug consumption, which was classified into two groups: those who had taken anti-malarial drugs and those who had not. RESULTS: In the study of LMICs, 32,397 children under five were observed, and among them, 44.1% had received anti-malarial drugs. Of the five LMICs, Kenya had the lowest (9.2%) and Mali had the highest (70.5%) percentages of anti-malarial drug consumption. Children under five with malaria are more likely to receive anti-malarial drugs if they are over 1 year old, live in rural areas, have mothers with higher education levels, and come from wealthier families. CONCLUSION: The study emphasizes the importance of developing universal coverage strategies for anti-malarial drug consumption at both the national and local levels. The study also recommends that improving availability and access to anti-malarial drugs may be necessary, as the consumption of these drugs for treating malaria in children under the age of five is shockingly low in some LMICs.

Machine learning and discriminant function analysis in the formulation of generic models for sex prediction using patella measurements.

Sex prediction from bone measurements that display sexual dimorphism is one of the most important aspects of forensic anthropology. Some bones like the skull and pelvis display distinct morphological traits that are based on shape. These morphological traits which are sexually dimorphic across different population groups have been shown to provide an acceptably high degree of accuracy in the prediction of sex. A sample of 100 patella of Mixed Ancestry South Africans (MASA) was collected from the Dart collection. Six parameters: maximum height (maxh), maximum breadth (maxw), maximum thickness (maxt), the height of articular facet (haf), lateral articular facet breadth (lafb), and medial articular facet breath (mafb) were used in this study. Stepwise and direct discriminant function analyses were performed for measurements that exhibited significant differences between male and female mean measurements, and the "leave-one-out" approach was used for validation. Moreover, we have used eight classical machine learning techniques along with feature ranking techniques to identify the best feature combinations for sex prediction. A stacking machine learning technique was trained and validated to classify the sex of the subject. Here, we have used the top performing three ML classifiers as base learners and the predictions of these models were used as inputs to different machine learning classifiers as meta learners to make the final decision. The measurements of the patella of South Africans are sexually dimorphic and this observation is consistent with previous studies on the patella of different countries. The range of average accuracies obtained for pooled multivariate discriminant function equations is 81.9-84.2%, while the stacking ML technique provides 90.8% accuracy which compares well with those presented for previous studies in other parts of the world. In conclusion, the models proposed in this study from measurements of the patella of different population groups in South Africa are useful resent with reasonably high average accuracies.

Early childhood developmental status and its associated factors in Bangladesh: a comparison of two consecutive nationally representative surveys.

BACKGROUND: Inadequate cognitive and socio-emotional development in children leads to physical and mental illness. We aimed to investigate the status of early childhood development (ECD) and its associated factors. Additionally, aimed to compare the changes of significantly associated factors using two multiple indicator cluster surveys (MICS) in Bangladesh. METHODS: We used data from the Multiple Indicator Cluster Surveys (MICS) 2012 and 2019 nationally representative surveys. A total of 17,494 children aged 36-59 months were included in the analysis. The outcome variable was ECD status: either developmentally on-track or not. We used bivariable analysis and crude and adjusted multivariable logistic models to assess the ECD status and its associated factors. RESULTS: Comparing both MICS surveys, the overall and individual domains of ECD status improved from 2012 (65.46%) to 2019 (74.86%), and the indicators of child literacy-numeracy domain improved from 21.2 to 28.8%, physical domain improved from 92.2 to 98.4%, and social-emotional domain improved from 68.4 to 72.7%. The learning approach domain was 87.5% in 2012 and increased to 91.4% in 2019. According to the adjusted logistic model in both surveys (2012 and 2019), the age of 4 years had an adjusted odds ratio (AOR) of 1.61 and 1.78 times higher developmentally on track than the age of 3. Female children were 1.42 (in 2012) and 1.44 (in 2019) times more developmentally on track than males. Compared to mothers with only primary education, children raised by mothers with secondary or higher education were 1.77 and 1.50 times more on track in their development. Moreover, Children from affluent families had 1.32- and 1.26 times higher odds- on track than those from the poorest families. Families with books had 1.50 and 1.53 times higher developmentally on track than their counterparts. CONCLUSION AND RECOMMENDATION: In summary, our study shows that the overall ECD status improved between MICS 2012 and MICS 2019. Important factors influence ECD status, including early childhood education programs, families' possession of children's books, mothers' educational level, and wealth index. The findings of our study will help making necessary public health-related initiatives in Bangladesh to improve ECD program.

IRv2-Net: A Deep Learning Framework for Enhanced Polyp Segmentation Performance Integrating InceptionResNetV2 and UNet Architecture with Test Time Augmentation Techniques.

Colorectal polyps in the colon or rectum are precancerous growths that can lead to a more severe disease called colorectal cancer. Accurate segmentation of polyps using medical imaging data is essential for effective diagnosis. However, manual segmentation by endoscopists can be time-consuming, error-prone, and expensive, leading to a high rate of missed anomalies. To solve this problem, an automated diagnostic system based on deep learning algorithms is proposed to find polyps. The proposed IRv2-Net model is developed using the UNet architecture with a pre-trained InceptionResNetV2 encoder to extract most features from the input samples. The Test Time Augmentation (TTA) technique, which utilizes the characteristics of the original, horizontal, and vertical flips, is used to gain precise boundary information and multi-scale image features. The performance of numerous state-of-the-art (SOTA) models is compared using several metrics such as accuracy, Dice Similarity Coefficients (DSC), Intersection Over Union (IoU), precision, and recall. The proposed model is tested on the Kvasir-SEG and CVC-ClinicDB datasets, demonstrating superior performance in handling unseen real-time data. It achieves the highest area coverage in the area under the Receiver Operating Characteristic (ROC-AUC) and area under Precision-Recall (AUC-PR) curves. The model exhibits excellent qualitative testing outcomes across different types of polyps, including more oversized, smaller, over-saturated, sessile, or flat polyps, within the same dataset and across different datasets. Our approach can significantly minimize the number of missed rating difficulties. Lastly, a graphical interface is developed for producing the mask in real-time. The findings of this study have potential applications in clinical colonoscopy procedures and can serve based on further research and development.

Signer-Independent Arabic Sign Language Recognition System Using Deep Learning Model.

Every one of us has a unique manner of communicating to explore the world, and such communication helps to interpret life. Sign language is the popular language of communication for hearing and speech-disabled people. When a sign language user interacts with a non-sign language user, it becomes difficult for a signer to express themselves to another person. A sign language recognition system can help a signer to interpret the sign of a non-sign language user. This study presents a sign language recognition system that is capable of recognizing Arabic Sign Language from recorded RGB videos. To achieve this, two datasets were considered, such as (1) the raw dataset and (2) the face-hand region-based segmented dataset produced from the raw dataset. Moreover, operational layer-based multi-layer perceptron "SelfMLP" is proposed in this study to build CNN-LSTM-SelfMLP models for Arabic Sign Language recognition. MobileNetV2 and ResNet18-based CNN backbones and three SelfMLPs were used to construct six different models of CNN-LSTM-SelfMLP architecture for performance comparison of Arabic Sign Language recognition. This study examined the signer-independent mode to deal with real-time application circumstances. As a result, MobileNetV2-LSTM-SelfMLP on the segmented dataset achieved the best accuracy of 87.69% with 88.57% precision, 87.69% recall, 87.72% F1 score, and 99.75% specificity. Overall, face-hand region-based segmentation and SelfMLP-infused MobileNetV2-LSTM-SelfMLP surpassed the previous findings on Arabic Sign Language recognition by 10.970% accuracy.

A Real Time Method for Distinguishing COVID-19 Utilizing 2D-CNN and Transfer Learning.

Rapid identification of COVID-19 can assist in making decisions for effective treatment and epidemic prevention. The PCR-based test is expert-dependent, is time-consuming, and has limited sensitivity. By inspecting Chest R-ray (CXR) images, COVID-19, pneumonia, and other lung infections can be detected in real time. The current, state-of-the-art literature suggests that deep learning (DL) is highly advantageous in automatic disease classification utilizing the CXR images. The goal of this study is to develop models by employing DL models for identifying COVID-19 and other lung disorders more efficiently. For this study, a dataset of 18,564 CXR images with seven disease categories was created from multiple publicly available sources. Four DL architectures including the proposed CNN model and pretrained VGG-16, VGG-19, and Inception-v3 models were applied to identify healthy and six lung diseases (fibrosis, lung opacity, viral pneumonia, bacterial pneumonia, COVID-19, and tuberculosis). Accuracy, precision, recall, f1 score, area under the curve (AUC), and testing time were used to evaluate the performance of these four models. The results demonstrated that the proposed CNN model outperformed all other DL models employed for a seven-class classification with an accuracy of 93.15% and average values for precision, recall, f1-score, and AUC of 0.9343, 0.9443, 0.9386, and 0.9939. The CNN model equally performed well when other multiclass classifications including normal and COVID-19 as the common classes were considered, yielding accuracy values of 98%, 97.49%, 97.81%, 96%, and 96.75% for two, three, four, five, and six classes, respectively. The proposed model can also identify COVID-19 with shorter training and testing times compared to other transfer learning models.

Deep Learning Framework for Liver Segmentation from T1-Weighted MRI Images.

The human liver exhibits variable characteristics and anatomical information, which is often ambiguous in radiological images. Machine learning can be of great assistance in automatically segmenting the liver in radiological images, which can be further processed for computer-aided diagnosis. Magnetic resonance imaging (MRI) is preferred by clinicians for liver pathology diagnosis over volumetric abdominal computerized tomography (CT) scans, due to their superior representation of soft tissues. The convenience of Hounsfield unit (HoU) based preprocessing in CT scans is not available in MRI, making automatic segmentation challenging for MR images. This study investigates multiple state-of-the-art segmentation networks for liver segmentation from volumetric MRI images. Here, T1-weighted (in-phase) scans are investigated using expert-labeled liver masks from a public dataset of 20 patients (647 MR slices) from the Combined Healthy Abdominal Organ Segmentation grant challenge (CHAOS). The reason for using T1-weighted images is that it demonstrates brighter fat content, thus providing enhanced images for the segmentation task. Twenty-four different state-of-the-art segmentation networks with varying depths of dense, residual, and inception encoder and decoder backbones were investigated for the task. A novel cascaded network is proposed to segment axial liver slices. The proposed framework outperforms existing approaches reported in the literature for the liver segmentation task (on the same test set) with a dice similarity coefficient (DSC) score and intersect over union (IoU) of 95.15% and 92.10%, respectively.