Backpropagation Neural Network-Based Machine Learning Model for Prediction of Blood Urea and Glucose in CKD Patients

Prediction of mortality events of patients with acute heart failure in intensive care unit based on deep neural network

BACKGROUND

Acute heart failure (AHF) in the intensive care unit (ICU) is characterized by its criticality, rapid progression, complex and changeable condition, and its pathophysiological process involves the interaction of multiple organs and systems. This makes it difficult to predict in-hospital mortality events comprehensively and accurately. Traditional analysis methods based on statistics and machine learning suffer from insufficient model performance, poor accuracy caused by prior dependence, and difficulty in adequately considering the complex relationships between multiple risk factors. Therefore, the application of deep neural network (DNN) techniques to the specific scenario, predicting mortality events of patients with AHF under intensive care, has become a research frontier.

METHODS

This research utilized the MIMIC-IV critical care database as the primary data source and employed the synthetic minority over-sampling technique (SMOTE) to balance the dataset. Deep neural network models-backpropagation neural network (BPNN) and recurrent neural network (RNN), which are based on electronic medical record data mining, were employed to investigate the in-hospital death event judgment task of patients with AHF under intensive care. Additionally, multiple single machine learning models and ensemble learning models were constructed for comparative experiments. Moreover, we achieved various optimal performance combinations by modifying the classification threshold of deep neural network models to address the diverse real-world requirements in the ICU. Finally, we conducted an interpretable deep model using SHapley Additive exPlanations (SHAP) to uncover the most influential medical record features for each patient from the aspects of global and local interpretation.

RESULTS

In terms of model performance in this scenario, deep neural network models outperform both single machine learning models and ensemble learning models, achieving the highest Accuracy, Precision, Recall, F1 value, and Area under the ROC curve, which can reach 0.949, 0.925, 0.983, 0.953, and 0.987 respectively. SHAP value analysis revealed that the ICU scores (APSIII, OASIS, SOFA) are significantly correlated with the occurrence of in-hospital fatal events.

CONCLUSIONS

Our study underscores that DNN-based mortality event classifier offers a novel intelligent approach for forecasting and assessing the prognosis of AHF patients in the ICU. Additionally, the ICU scores stand out as the most predictive features, which implies that in the decision-making process of the models, ICU scores can provide the most crucial information, making the greatest positive or negative contribution to influence the incidence of in-hospital mortality among patients with acute heart failure.

An advanced approach for fig leaf disease detection and classification: Leveraging image processing and enhanced support vector machine methodology

In the rapidly evolving landscape of agricultural technology, image processing has emerged as a powerful tool for addressing critical agricultural challenges, with a particular focus on the identification and management of crop diseases. This study is motivated by the imperative need to enhance agricultural sustainability and productivity through precise plant health monitoring. Our primary objective is to propose an innovative approach combining support vector machine (SVM) with advanced image processing techniques to achieve precise detection and classification of fig leaf diseases. Our methodology encompasses a step-by-step process, beginning with the acquisition of digital color images of diseased leaves, followed by denoising using the mean function and enhancement through Contrast-limited adaptive histogram equalization. The subsequent stages involve segmentation through the Fuzzy C Means algorithm, feature extraction via Principal Component Analysis, and disease classification, employing Particle Swarm Optimization (PSO) in conjunction with SVM, Backpropagation Neural Network, and Random Forest algorithms. The results of our study showcase the exceptional performance of the PSO SVM algorithm in accurately classifying and detecting fig leaf disease, demonstrating its potential for practical implementation in agriculture. This innovative approach not only underscores the significance of advanced image processing techniques but also highlights their substantial contributions to sustainable agriculture and plant disease mitigation. In conclusion, the integration of image processing and SVM-based classification offers a promising avenue for advancing crop disease management, ultimately bolstering agricultural productivity and global food security.

Hybrid method for accurate starch estimation in adulterated turmeric using Vis-NIR spectroscopy

Turmeric is widely used as a health supplement and foodstuff in South East Asian countries because of its medicinal benefits. Like several other plants and peppers, turmeric is prone to exploitation because of its economic value, rising consumer need, and essential food element that adds colour and flavour. Due to this, quick and comprehensive testing processes are needed to detect adulterants in turmeric. In this study, pure turmeric powders were mixed with starch in proportions ranging from 0 to 50% with a 1% variation to obtain different combinations. Reflectance spectra of pure turmeric and starch mixed samples were recorded using a JASCO-V770 spectrometer from 400 to 2050 nm. The recorded spectra were pre-processed using a Multiplicative Scatter Correction (MSC) and Standard Normal Variate (SNV). The Savitzky-Golay (SG) filter was initially applied to these original (X), MSC, and SNV-corrected spectra. Secondly, the Extra Tree Regressor (ETR) feature selection method was employed to select the best features. Finally, principal component analysis (PCA) was used to reduce the dimension of the selected features. The stacked generalization method was applied to improve the performance of this work. Both regressors and classifier stacking techniques have been tested with different classification and regression methods. The K-Nearest Neighbours (KNN), Decision Tree (DT), and Random Forest (RF) models were used as base learners, and Logistic Regression (LRC) was used as a meta-model for classification and Linear Regression (LR) for regression analysis. The proposed method achieved the best regression performance with r2 of 0.999, Root Mean Square Error (RMSE) of 0.206, Ratio of Performance to Deviation (RPD) of 73.73, and Range Error Ratio (RER) of 480.58, whereas 100% F1 score and Matthew's Correlation Coefficient (MCC) classification performance.

Predict, diagnose, and treat chronic kidney disease with machine learning: a systematic literature review

OBJECTIVES

In this systematic review we aimed at assessing how artificial intelligence (AI), including machine learning (ML) techniques have been deployed to predict, diagnose, and treat chronic kidney disease (CKD). We systematically reviewed the available evidence on these innovative techniques to improve CKD diagnosis and patient management.

METHODS

We included English language studies retrieved from PubMed. The review is therefore to be classified as a "rapid review", since it includes one database only, and has language restrictions; the novelty and importance of the issue make missing relevant papers unlikely. We extracted 16 variables, including: main aim, studied population, data source, sample size, problem type (regression, classification), predictors used, and performance metrics. We followed the Preferred Reporting Items for Systematic Reviews (PRISMA) approach; all main steps were done in duplicate.

RESULTS

From a total of 648 studies initially retrieved, 68 articles met the inclusion criteria. Models, as reported by authors, performed well, but the reported metrics were not homogeneous across articles and therefore direct comparison was not feasible. The most common aim was prediction of prognosis, followed by diagnosis of CKD. Algorithm generalizability, and testing on diverse populations was rarely taken into account. Furthermore, the clinical evaluation and validation of the models/algorithms was perused; only a fraction of the included studies, 6 out of 68, were performed in a clinical context.

CONCLUSIONS

Machine learning is a promising tool for the prediction of risk, diagnosis, and therapy management for CKD patients. Nonetheless, future work is needed to address the interpretability, generalizability, and fairness of the models to ensure the safe application of such technologies in routine clinical practice.

Systematic analysis and prediction for disease burden of ovarian cancer attributable to hyperglycemia: a comparative study between China and the world from 1990 to 2019

Background

Ovarian cancer is one of the most common female malignancies worldwide, and metabolic factors, such as hyperglycemia, are becoming potential risk factors. This study aimed to analyze the disease burden and its changing trend of ovarian cancer attributable to hyperglycemia in the Chinese population from 1990 to 2019.

Methods

Using the data released by the Global Burden of Disease study 2019 (GBD 2019), we analyze the disease burden of ovarian cancer attributable to hyperglycemia in Chinese from 1990 to 2019 via morbidity, death, disability-adjusted life years (DALY); compare it with the global population; and predict the incidence and death trend in Chinese women for the next 10 years (2020-2029).

Results

The incidence, death cases, and DALY numbers of ovarian cancer attributable to hyperglycemia in Chinese in 2019 were 2,751, 1,758, and 44,615 person-years, respectively, with an increase of 352.5%, 356.6%, and 329.0% compared with 1990, and the growth rate was higher than the global level. The age-standardized incidence rate (ASIR), age-standardized mortality rate (ASMR), and age-standardized DALY rate (ASDR) in 2019 were 0.270/100,000, 0.164/100,000, and 4.103/100,000, respectively. Moreover, the average annual percent changes (AAPCs) were 2.3%, 2.0%, and 2.0%, respectively, all higher than the global average. The disease burden of ovarian cancer attributable to hyperglycemia increased with age, reaching a peak in the 45-75 age group. The prediction of the neural network model showed that the incidence and death of the disease would remain high and rise in the next 10 years.

Conclusion

The disease burden caused by ovarian cancer attributable to hyperglycemia in Chinese accounts for a large proportion globally, and the ASIR, ASMR, and ASDR are increasing year by year. We should continue to pay attention to the role of metabolic factors, such as hyperglycemia, in the occurrence and development of ovarian cancer, perform a good job in tertiary prevention, and strive to reduce health losses.

Cloud-based COVID-19 disease prediction system from X-Ray images using convolutional neural network on smartphone

COVID-19 has engulfed over 200 nations through human-to-human transmission, either directly or indirectly. Reverse Transcription-polymerase Chain Reaction (RT-PCR) has been endorsed as a standard COVID-19 diagnostic procedure but has caveats such as low sensitivity, the need for a skilled workforce, and is time-consuming. Coronaviruses show significant manifestation in Chest X-Ray (CX-Ray) images and, thus, can be a viable option for an alternate COVID-19 diagnostic strategy. An automatic COVID-19 detection system can be developed to detect the disease, thus reducing strain on the healthcare system. This paper discusses a real-time Convolutional Neural Network (CNN) based system for COVID-19 illness prediction from CX-Ray images on the cloud. The implemented CNN model displays exemplary results, with training accuracy being 99.94% and validation accuracy reaching 98.81%. The confusion matrix was utilized to assess the models' outcome and achieved 99% precision, 98% recall, 99% F1 score, 100% training area under the curve (AUC) and 98.3% validation AUC. The same CX-Ray dataset was also employed to predict the COVID-19 disease with deep Convolution Neural Networks (DCNN), such as ResNet50, VGG19, InceptonV3, and Xception. The prediction outcome demonstrated that the present CNN was more capable than the DCNN models. The efficient CNN model was deployed to the Platform as a Service (PaaS) cloud.

Improved Support Vector Machine and Image Processing Enabled Methodology for Detection and Classification of Grape Leaf Disease

In recent years, agricultural image processing research has been a key emphasis. Image processing techniques are used by computers to analyze images. New advancements in image capture and data processing have simplified the resolution of a wide range of agricultural concerns. Crop disease classification and identification are crucial for the agricultural industry’s technical and commercial well-being. In agriculture, image processing begins with a digital color picture of a diseased leaf. Plant health and disease detection must be monitored on a regular basis in property agriculture. Plant diseases have had a tremendous impact on civilization and the Earth as a whole. Extensions of detection strategies and classification methods try to identify and categorize each ailment that affects the plant rather than focusing on a single disease among several illnesses and symptoms. This article describes a new support vector machine and image processing-enabled approach for detecting and classifying grape leaf disease. The given architecture includes steps for image capture, denoising, enhancement, segmentation, feature extraction, classification, and detection. Image denoising is conducted using the mean function, image enhancement is performed using the CLAHE method, pictures are segmented using the fuzzy C Means algorithm, features are retrieved using PCA, and images are eventually classed using the PSO SVM, BPNN, and random forest algorithms. The accuracy of PSO SVM is higher in performing classification and detection of grape leaf diseases.

Smart deployment of IoT-TelosB service care StreamRobot using software-defined reliability optimisation design

Intelligent service care robots have increasingly been developed in mission-critical sectors such as healthcare systems, transportation, manufacturing, and environmental applications. The major drawbacks include the open-source Internet of Things (IoT) platform vulnerabilities, node failures, computational latency, and small memory capacity in IoT sensing nodes. This article provides reliable predictive analytics with the optimisation of data transmission characteristics in StreamRobot. Software-defined reliable optimisation design is applied in the system architecture. For the IoT implementation, the edge system model formulation is presented with a focus on edge cluster log-normality distribution, reliability, and equilibrium stability considerations. A real-world scenario for accurate data streams generation from in-built TelosB sensing nodes is converged at a sink-analytic dashboard. Two-phase configurations, namely off-taker and on-demand, link-state protocols are mapped for deterministic data stream offloading. An orphan reconnection trigger mechanism is used for reliable node-to-sink resilient data transmissions. Data collection is achieved, using component-based programming in the experimental testbed. Measurement parameters are derived with TelosB IoT nodes. Reliability validations on remote monitoring and prediction processes are studied considering neural constrained software-defined networking (SDN) intelligence. An OpenFlow-SDN construct is deployed to offload traffic from the edge to the fog layer. At the core, fog detection-to-cloud predictive machine learning (FD-CPML) is used to predict real-time data streams. Prediction accuracy is validated with decision tree, logistic regression, and the proposed FD-CPML. The data streams latency gave 40.00%, 33.33%, and 26.67%, respectively. Similarly, linear predictive scalability behaviour on the network plane gave 30.12%, 33.73%, and 36.15% respectively. The results show satisfactory responses in terms of reliable communication and intelligent monitoring of node failures.