Pre-processing Approach Research Articles

Insightful Clinical Assistance for Anemia Prediction with Data Analysis and Explainable AI

Anemia among young people has positive correlation with susceptibility and impede cognitive development. As per WHO 2019 statistics global prevalence rate of anemia is 33 percent. This work aims to predict anemia with inferences to identify the root cause of anemia. Prediction is done with machine learning algorithms with proper pre-processing, data normalization, and class imbalance approaches. Explainable AI, a transparent model, is used to enhance the prediction which enables to draw inferences. LGM Boost learning model prediction has a 91% accuracy and explainable AI framework predictions of most contributing attribute is accurate when compared to other models. This approach helps healthcare professionals make informed decisions on the most optimal treatment for anemia.

Deep learning innovations in South Korean maritime navigation: Enhancing vessel trajectories prediction with AIS data.

Predicting ship trajectories can effectively forecast navigation trends and enable the orderly management of ships, which holds immense significance for maritime traffic safety. This paper introduces a novel ship trajectory prediction method utilizing Convolutional Neural Network (CNN), Deep Neural Network (DNN), Long Short-Term Memory (LSTM), and Gated Recurrent Unit (GRU). Our research comprises two main parts: the first involves preprocessing the large raw AIS dataset to extract features, and the second focuses on trajectory prediction. We emphasize a specialized preprocessing approach tailored for AIS data, including advanced filtering techniques to remove outliers and erroneous data points, and the incorporation of contextual information such as environmental conditions and ship-specific characteristics. Our deep learning models utilize trajectory data sourced from the Automatic Identification System (AIS) to train and learn regular patterns within ship trajectory data, enabling them to predict trajectories for the next hour. Experimental results reveal that CNN has substantially reduced the Mean Absolute Error (MAE) and Mean Square Error (MSE) of ship trajectory prediction, showcasing superior performance compared to other deep learning algorithms. Additionally, a comparative analysis with other models-Recurrent Neural Network (RNN), GRU, LSTM, and DBS-LSTM-using metrics such as Average Displacement Error (ADE), Final Displacement Error (FDE), and Non-Linear ADE (NL-ADE), demonstrates our method's robustness and accuracy. Our approach not only cleans the data but also enriches it, providing a robust foundation for subsequent deep learning applications in ship trajectory prediction. This improvement effectively enhances the accuracy of trajectory prediction, promising advancements in maritime traffic safety.

Two-Person Intuitionistic Neutrosophic Soft Games with Harris Hawks Optimizer based Tweets Classification on NLP Applications

With the widespread usage of social media in our day-to-day lives, it becomes a platform for persons to express and share their feelings, views, thoughts, and opinions. Recognizing emotions has numerous applications extending from dynamic advertisement to behavior analyses. People express their emotional state in a language that is often complemented by figures of speech and ambiguity, making it problematic even for human beings to understand. Categorizing tweets is a dynamic application of NLP, allowing the scrutiny of topical discussions, user opinions, and trends in real-time. Leveraging techniques such as word embeddings, machine learning, and text preprocessing approaches, tweet classification enables tasks like spam detection, sentiment analysis, and topic modeling. This ability assists companies in understanding client feedback and allows policymakers and researchers to track emerging issues and gauge public opinion on social networking media. This study presents a Two-Person Intuitionistic Neutrosophic Soft Games with Harris Hawks Optimizer (TINSG-HHO) based Tweets Classification on NLP Applications. The purpose of the TINSG-HHO technique is to detect the existence of different kinds of emotions or sentiments in the tweets. The TINSG-HHO technique begins with preprocessing of tweets to convert them into useful format. Then, FastText embedding represents words as contextual similarities, dense vectors, and capturing semantic nuances. Leveraging the embedding, the Neutrosophic classification model proficiently handles vagueness and uncertainty intrinsic in deceptive content detection tasks. Moreover, the HHO technique enhances the parameter of the Neutrosophic classifier, improving its generalization capabilities and performance. Based on the hunting strategy of Harris's hawks, HHO discovers the parameter range to search for optimum configurations for the classifier. Experimental evaluations carried out on different datasets illustrate the effectiveness of the DCRM in precisely detecting the deceptive content

Prediction of Diabetes Using Diverse Ensemble Learning Classifiers

Diabetes is classified as a chronic disorder characterized by elevated blood glucose levels resulting from insufficient insulin synthesis or inadequate responsiveness of body cells to insulin. The prevailing protocol at healthcare facilities involves the acquisition of necessary data for the diagnosis of diabetes through a range of diagnostic procedures, followed by the administration of treatment in accordance with the outcomes of those tests. The task of generating precise outcomes using diabetes prediction models is challenging due to limited data availability and the existence of outliers. This study presents a proposed prediction model for diabetes that involves preprocessing techniques applied to the raw data, followed by the utilization of Ensemble Classifiers. The Ensemble Classifiers consist of a combination of catboost, LDA, LR, Random Forest, and GBC. By employing pre-processing approaches and ensemble methodologies, we have achieved improved performance i.e. 90.62% accuracy. The weights of ML models are evaluated using their Area Under Curve (AUC) and receiver operating characteristic curve (ROC) results. This proposed approach helps for clinical trials and help to take precautions at early stage of diabetes.

The Impact of Hepatitis Disease in Pre-processing Approach Using Fuzzy with May-Fly Optimization and Ensemble Classification

The Impact of Hepatitis Disease in Pre-processing Approach Using Fuzzy with May-Fly Optimization and Ensemble Classification

Fuzzy decision-making framework for explainable golden multi-machine learning models for real-time adversarial attack detection in Vehicular Ad-hoc Networks

This paper addresses various issues in the literature concerning adversarial attack detection in Vehicular Ad-hoc Networks (VANETs). These issues include the failure to consider both normal and adversarial attack perspectives simultaneously in Machine Learning (ML) model development, the lack of diversity preprocessing techniques for VANETs communication datasets, the inadequate selection guidelines for real-time adversarial attack detection models, and the limited emphasis on explainability in adversarial attack detection. In this study, we propose an original fuzzy decision-making framework that incorporates multiple fusion standpoints. Our framework aims to evaluate multi-ML models for real-time adversarial attack detection in VANETs, focusing on three stages. The first stage involves identifying and preprocessing Dedicated Short-Range Communication (DSRC) data using standard and fusion preprocessing approaches. Two communication scenarios, normal and jammed, are considered, resulting in two DSRC datasets. In the second stage, we develop multi-ML models based on the DSRC datasets using standard preprocessing and feature fusion preprocessing for dataset-1 and dataset-2, respectively. The third stage evaluates the multi-ML models using a fuzzy decision-making approach based on the Fuzzy Decision by Opinion Score Method (FDOSM) and an adversarial attack decision fusion matrix. The External Fusion Decision (EFD) settings of the FDOSM address individual ranking variance, provide a unique rank and select the best model. Experimental results demonstrate that the K-Nearest Neighbors Algorithm (kNN) model achieves the highest explain score of 0.2048 in dataset-1 using standard preprocessing, while the Random Forest (RF) model applied to dataset-2 using fusion preprocessing emerges as the most robust and golden model against adversarial attacks, with a score of 0.1819. This finding suggests that the fusion preprocessing approach using Principal Component Analysis (PCA) is more suitable for addressing normal and adversarial attack perspectives. Furthermore, our fuzzy framework undergoes evaluation in terms of systematic rank, sensitivity analysis, explainability analysis, and comparison analysis. Overall, this framework provides valuable insights for researchers and practitioners in VANETs, informing the execution, selection, and interpretation of multi-ML models to tackle adversarial attack detection problems effectively. The new fuzzy framework demonstrates that multi-ML models based on feature fusion preprocessing are more effective.

Enhancing LOCA Breach Size Diagnosis with Fundamental Deep Learning Models and Optimized Dataset Construction

In nuclear power plants, the loss-of-coolant accident (LOCA) stands out as the most prevalent and consequential incident. Accurate breach size diagnosis is crucial for the mitigation of LOCAs, and identifying the cause of an accident can prevent catastrophic consequences. Traditional methods mostly focus on combining model algorithms and utilize intricate composite model neural network architectures. However, it is crucial to investigate whether greater complexity necessarily leads to better performance. In addition, the consideration of the impact of dataset construction and data preprocessing on model performance is also needed for model building. This paper proposes a framework named DeepLOCA-Lattice to experiment with different preprocessing approaches to fundamental deep learning models for a comprehensive analysis of the diagnosis of LOCA breach size. The DeepLOCA-Lattice involves data preprocessing via the lattice algorithm and equal-interval partitioning and deep-learning-based models, including the multi-layer perceptron (MLP), recurrent neural networks (RNNs), convolutional neural networks (CNNs), and the transformer model in LOCA breach size diagnosis. After conducting rigorous ablation experiments, we have discovered that even rudimentary foundational models can achieve accuracy rates that exceed 90%. This is a significant improvement when compared to the previous models, which yield an accuracy rate of lower than 50%. The results interestingly demonstrate the superior performance and efficacy of the fundamental deep learning model, with an effective dataset construction approach. It elucidates the presence of a complex interplay among diagnostic scales, sliding window size, and sliding stride. Furthermore, our investigation reveals that the model attains its highest accuracy within the discussed range when utilizing a smaller sliding stride size and a longer sliding window length. This study could furnish valuable insights for constructing models for LOCA breach size estimation.

Variation in Botanical Reference Materials: Similarity of Actaea Racemosa Analyzed by Flow Injection Mass Spectrometry.

Botanical reference materials (BRMs) generally account for the species, cultivar, and year and location of harvest that result in variability in the chemical composition that may lead to statistically significant differences using chemometric methods. To compare the chemical composition of five species of Actaea root BRMs, four herbal sources of A. racemosa root BRMs, and A. racemosa BRMS, and commercial roots and supplements using chemometric methods and selected pre-processing approaches. Samples were analyzed by flow injection mass spectrometry (FIMS), principal component analysis (PCA), and factorial multivariate analysis of variance (mANOVA). Statistically significant (P = 0.05) compositional differences were found between three genera (Actaea, Panax, and Ginkgo), five species of Actaea (A. racemosa, A. cimicifuga, A. dahurica, A. pachypoda, and A. rubra) root BRMs, four herbal sources of A. racemosa root BRMs, and A. racemosa BRMS and commercial roots and supplements. The variability of 6% of the BRM variables was found to be quantitatively conserved and reduced the compositional differences between the four sources of root BRMs. Compositional overlap of A. racemosa and other Actaea BRMs was influenced by variation in technical repeats, pre-processing methods, selection of variables, and selection of confidence limits. Sensitivity ranged from 94 to 97% and specificity ranged from 21 to 89% for the pre-processing protocols tested. Environmental, genetic, and chemometric factors can influence discrimination between species and authentic botanical reference materials. Frequency distribution plots derived from soft independent modeling of class analogy provide excellent means for understanding the impact of experimental factors.

MNCLCDA: predicting circRNA-drug sensitivity associations by using mixed neighbourhood information and contrastive learning

BackgroundcircRNAs play an important role in drug resistance and cancer development. Recently, many studies have shown that the expressions of circRNAs in human cells can affect the sensitivity of cells to therapeutic drugs, thus significantly influencing the therapeutic effects of these drugs. Traditional biomedical experiments required to verify this sensitivity relationship are not only time-consuming but also expensive. Hence, the development of an efficient computational approach that can accurately predict the novel associations between drug sensitivities and circRNAs is a crucial and pressing need.MethodsIn this research, we present a novel computational framework called MNCLCDA, which aims to predict the potential associations between drug sensitivities and circRNAs to assist with medical research. First, MNCLCDA quantifies the similarity between the given drug and circRNA using drug structure information, circRNA gene sequence information, and GIP kernel information. Due to the existence of noise in similarity information, we employ a preprocessing approach based on random walk with restart for similarity networks to efficiently capture the useful features of circRNAs and drugs. Second, we use a mixed neighbourhood graph convolutional network to obtain the neighbourhood information of nodes. Then, a graph-based contrastive learning method is used to enhance the robustness of the model, and finally, a double Laplace-regularized least-squares method is used to predict potential circRNA-drug associations through the kernel matrices in the circRNA and drug spaces.ResultsNumerous experimental results show that MNCLCDA outperforms six other advanced methods. In addition, the excellent performance of our proposed model in case studies illustrates that MNCLCDA also has the ability to predict the associations between drug sensitivity and circRNA in practical situations.ConclusionsAfter a large number of experiments, it is illustrated that MNCLCDA is an efficient tool for predicting the potential associations between drug sensitivities and circRNAs, thereby can provide some guidance for clinical trials.

Segmentation of Dynamic Total-Body [18F]-FDG PET Images Using Unsupervised Clustering.

Clustering time activity curves of PET images have been used to separate clinically relevant areas of the brain or tumours. However, PET image segmentation in multiorgan level is much less studied due to the available total-body data being limited to animal studies. Now, the new PET scanners providing the opportunity to acquire total-body PET scans also from humans are becoming more common, which opens plenty of new clinically interesting opportunities. Therefore, organ-level segmentation of PET images has important applications, yet it lacks sufficient research. In this proof of concept study, we evaluate if the previously used segmentation approaches are suitable for segmenting dynamic human total-body PET images in organ level. Our focus is on general-purpose unsupervised methods that are independent of external data and can be used for all tracers, organisms, and health conditions. Additional anatomical image modalities, such as CT or MRI, are not used, but the segmentation is done purely based on the dynamic PET images. The tested methods are commonly used building blocks of the more sophisticated methods rather than final methods as such, and our goal is to evaluate if these basic tools are suited for the arising human total-body PET image segmentation. First, we excluded methods that were computationally too demanding for the large datasets from human total-body PET scanners. These criteria filtered out most of the commonly used approaches, leaving only two clustering methods, k-means and Gaussian mixture model (GMM), for further analyses. We combined k-means with two different preprocessing approaches, namely, principal component analysis (PCA) and independent component analysis (ICA). Then, we selected a suitable number of clusters using 10 images. Finally, we tested how well the usable approaches segment the remaining PET images in organ level, highlight the best approaches together with their limitations, and discuss how further research could tackle the observed shortcomings. In this study, we utilised 40 total-body [18F] fluorodeoxyglucose PET images of rats to mimic the coming large human PET images and a few actual human total-body images to ensure that our conclusions from the rat data generalise to the human data. Our results show that ICA combined with k-means has weaker performance than the other two computationally usable approaches and that certain organs are easier to segment than others. While GMM performed sufficiently, it was by far the slowest one among the tested approaches, making k-means combined with PCA the most promising candidate for further development. However, even with the best methods, the mean Jaccard index was slightly below 0.5 for the easiest tested organ and below 0.2 for the most challenging organ. Thus, we conclude that there is a lack of accurate and computationally light general-purpose segmentation method that can analyse dynamic total-body PET images.

A COMPARISON OF PRE-PROCESSING APPROACHES FOR REMOTELY SENSED TIME SERIES CLASSIFICATION BASED ON FUNCTIONAL ANALYSIS

Abstract. Satellite remote sensing has gained a key role for vegetation mapping distribution. Given the availability of multi-temporal satellite data, seasonal variations in vegetation dynamics can be used trough time series analysis for vegetation distribution mapping. These types of data have a very high variability within them and are subjected by artifacts. Therefore, a pre-processing phase must be performed to properly detect outliers, for data smoothing process and to correctly interpolate the data. In this work, we compare four pre-processing approaches for functional analysis on 4-years of remotely sensed images, resulting in four time series datasets. The methodologies presented are the results of the combination of two outlier detection methods, namely tsclean and boxplot functions in R and two discrete data smoothing approaches (Generalized Additive Model ”GAM” on daily and aggregated data). The approaches proposed are: tsclean-GAM on aggregated data (M01), boxplot-GAM on aggregated data (M02), tsclean-GAM on daily data (M03), boxplot-GAM on daily data (M04). Our results prove that the approach which involves tsclean function and GAM applied to daily data (M03) is ameliorative to the logic of the procedure and leads to better model performance in terms of Overall Accuracy (OA) which is always among the highest when compared with the others obtained from the other three different approaches.

Applying Dynamic U-Value Measurements for State Forecasting in Buildings

Abstract In the present day, monitoring and automated control stand as pivotal factors for the energy-efficient and comfortable operation of buildings. As the demand for indoor climate control grows, building management systems have become more intricate, making their control challenging due to the increasing number of controllable elements. Replacing manual human analysis of complex systems can be achieved through the utilization of algorithms like model-based control. It is important to note that performance of this method usually relies on the accuracy of neural network-based building state forecasts. Studying the internal dynamics of climate as influenced by temperature changes necessitates a brief record of measurements, whereas evaluating structural modifications through moisture transfer demands data covering a more extended period. Neural networks such as Long Short-Term Memory have the potential to lose information within lengthy time-series data, and the intricate nature of moisture transfer further adds complexity to the task of approximating functions, ultimately leading to a reduction in energy efficiency. In order to improve the precision of indoor climate predictions, our suggestion involves not only assessing changes in temperature but also considering alterations in U-values triggered by temperature variations and moisture transfer. Our preliminary assessment of the influence of U-value, conducted through numerical simulations using WUFI6, exposes variations of up to 10 % of U-value in certain scenarios. Dealing with these computations in real time using physical models proves to be demanding due to computational requirements and limited data availability. To tackle this issue, we present an innovative preprocessing approach for on-the-fly evaluation of U-values. Empirical trials involving three years of monitoring data indicate that the suggested technique led to an approximate 8 % reduction in the average mean squared error of climate predictions based on neural network models, in specific instances.

A Natural-Language-Processing-Based Method for the Clustering and Analysis of Movie Reviews and Classification by Genre

Reclassification of massive datasets acquired through different approaches, such as web scraping, is a big challenge to demonstrate the effectiveness of a machine learning model. Notably, there is a strong influence of the quality of the dataset used for training those models. Thus, we propose a threshold algorithm as an efficient method to remove stopwords. This method employs an unsupervised classification technique, such as K-means, to accurately categorize user reviews from the IMDb dataset into their most suitable categories, generating a well-balanced dataset. Analysis of the performance of the algorithm revealed a notable influence of the text vectorization method used concerning the generation of clusters when assessing various preprocessing approaches. Moreover, the algorithm demonstrated that the word embedding technique and the removal of stopwords to retrieve the clustered text significantly impacted the categorization. The proposed method involves confirming the presence of a suggested stopword within each review across various genres. Upon satisfying this condition, the method assesses if the word’s frequency exceeds a predefined threshold. The threshold algorithm yielded a mapping genre success above 80% compared to precompiled lists and a Zipf’s law-based method. In addition, we employed the mini-batch K-means method for the clustering formation of each differently preprocessed dataset. This approach enabled us to reclassify reviews more coherently. Summing up, our methodology categorizes sparsely labeled data into meaningful clusters, in particular, by using a combination of the proposed stopword removal method and TF-IDF. The reclassified and balanced datasets showed a significant improvement, achieving 94% accuracy compared to the original dataset.

Multi-omics fusion with soft labeling for enhanced prediction of distant metastasis in nasopharyngeal carcinoma patients after radiotherapy

Omics fusion has emerged as a crucial preprocessing approach in medical image processing, significantly assisting several studies. One of the challenges encountered in integrating omics data is the unpredictability arising from disparities in data sources and medical imaging equipment. Due to these differences, the distribution of omics futures exhibits spatial heterogeneity, diminishing their capacity to enhance subsequent tasks. To overcome this challenge and facilitate the integration of their joint application to specific medical objectives, this study aims to develop a fusion methodology for nasopharyngeal carcinoma (NPC) distant metastasis prediction to mitigate the disparities inherent in omics data. The multi-kernel late-fusion method can reduce the impact of these differences by mapping the features using the most suiTable single-kernel function and then combining them in a high-dimensional space that can effectively represent the data. The proposed approach in this study employs a distinctive framework incorporating a label-softening technique alongside a multi-kernel-based Radial basis function (RBF) neural network to address these limitations. An efficient representation of the data may be achieved by utilizing the multi-kernel to map the inherent features and then merging them in a space with many dimensions. However, the inflexibility of label fitting poses a constraint on using multi-kernel late-fusion methods in complex NPC datasets, hence affecting the efficacy of general classifiers in dealing with high-dimensional characteristics. The label softening increases the disparity between the two cohorts, providing a more flexible structure for allocating labels. The proposed model is evaluated on multi-omics datasets, and the results demonstrate its strength and effectiveness in predicting distant metastasis of NPC patients.

Opening the envelope: Efficient envelope-based PPG denoising algorithm

Photoplethysmography (PPG) signals obtained from the skin’s surface offer valuable insights into blood volume fluctuations. With the rising interest in continuous non-invasive physiological monitoring, PPG has garnered significant attention. However, PPG signals are often affected by various forms of noise, impeding reliable feature extraction. Robust data pre-processing approaches are vital for both retrospective and real-time analysis. Existing denoising methods, including recent machine learning techniques, often suffer from implementation challenges, computational inefficiency, and limited interpretability. Addressing this challenge, we propose a novel PPG denoising algorithm. The algorithm was evaluated using a dataset representing approximately 81,015.99 min or 1360.27 h of PPG data collected from 31 patients. The evaluation involved the calculation and analysis of five key metrics: Signal-to-Noise Ratio (SNR), Variance, Total Variation (TV), Shannon entropy, and Instances-per-second (IPS). Our results demonstrate a notable increase in SNR after denoising, indicating effective noise reduction while preserving signal content. Variance and TV values showed a reduction post-denoising, suggesting smoother and less variable signals, validating the noise suppression efficacy. Additionally, Shannon entropy exhibited a decrease after denoising, indicating successful noise reduction and enhanced signal regularity. The nonparametric Wilcoxon signed-rank test (a = 0.05) was employed to assess the statistical significance of the observed differences of these metrics before and after denoising. Furthermore, the computational speed analysis revealed the EPDA’s potential for efficient processing of large datasets and real-time applications. This comprehensive evaluation approach allows for a thorough understanding of the EPDA’s effectiveness in denoising PPG data, fostering advancements in non-invasive physiological monitoring and promoting the broader adoption of PPG-based healthcare technologies.

Forecasting performance of machine learning, time series, and hybrid methods for low‐ and high‐frequency time series

One of the main objectives of the time series analysis is forecasting, so both Machine Learning methods and statistical methods have been proposed in the literature. In this study, we compare the forecasting performance of some of these approaches. In addition to traditional forecasting methods, which are the Naive and Seasonal Naive Methods, S/ARIMA, Exponential Smoothing, TBATS, Bayesian Exponential Smoothing Models with Trend Modifications and STL Decomposition, the forecasts are also obtained using seven different machine learning methods, which are Random Forest, Support Vector Regression, XGBoosting, BNN, RNN, LSTM, and FFNN, and the hybridization of both statistical time series and machine learning methods. The data set is selected proportionally from various time domains in M4 Competition data set. Thereby, we aim to create a forecasting guide by considering different preprocessing approaches, methods, and data sets having various time domains. After the experiment, the performance and impact of all methods are discussed. Therefore, most of the best models are mainly selected from machine learning methods for forecasting. Moreover, the forecasting performance of the model is affected by both the time frequency and forecast horizon. Lastly, the study suggests that the hybrid approach is not always the best model for forecasting. Hence, this study provides guidelines to understand which method will perform better at different time series frequencies.

Ensemble Classification Model for Brain Tumor Detection

Abstract: Brain tumor analysis is essential in timely diagnosis and effective treatment to cure patients. The growth of abnormal cells in the brain is the cause of brain tumors, which can lead to cancer. Brain tumors occur due to uncontrolled and rapid cell growth. If not treated at an initial phase, it may lead to death. The variations in tumor location, shape, and size pose a major challenge for brain tumor detection. The aim of this survey is to provide a comprehensive literature on brain tumor detection through magnetic resonance imaging to help the researchers. In this framework based on deep learning, magnetic resonance images (MRIs) are used to identify and categorize brain tumors. In the first step, we propose a preprocessing approach to work only on a small portion of the image rather than the entire image. These little portions of the images provide a very quick and precise brain tumor prognosis, which aids in giving patients the right treatment. The radiologist can make speedy conclusions thanks to these predictions. In the proposed work, A self-defined artificial neural network (ANN) and a network of convolution neural networks (CNN) are used in the proposed work to detect the presence of brain tumors, and their performance is examined

Applying machine learning models to breast cancer prediction problem

Cancer has become the number one killer of human life and health. Therefore, a model that can predict cancer is able to help doctors to diagnose whether a patient has cancer or not, which can boost the accuracy of the diagnosis and enhance diagnostic efficiency, thus reducing the chance of misdiagnosis and other situations. This paper focuses on breast cancer prediction and adopted three machine learning based methods, including logistic regression, K-Nearest Neighbor, and decision tree models to build automatic solutions and investigate which model is more suitable for such a simple prediction problem. In this study, the detailed features, data collection and pre-processing approaches are presented to better understand such medical data. Then extensive experiments show that the accuracy scores of the three models are 97.08%, 94.89%, and 93.43%, respectively. Through comparison, it is concluded that the logistic regression model achieves the best performance for the breast cancer prediction task.

Machine learning risk estimation and prediction of death in continuing care facilities using administrative data

In this study, we aimed to identify the factors that were associated with mortality among continuing care residents in Alberta, during the coronavirus disease 2019 (COVID-19) pandemic. We achieved this by leveraging and linking various administrative datasets together. Then, we examined pre-processing methods in terms of prediction performance. Finally, we developed several machine learning models and compared the results of these models in terms of performance. We conducted a retrospective cohort study of all continuing care residents in Alberta, Canada, from March 1, 2020, to March 31, 2021. We used a univariable and a multivariable logistic regression (LR) model to identify predictive factors of 60-day all-cause mortality by estimating odds ratios (ORs) with a 95% confidence interval. To determine the best sensitivity–specificity cut-off point, the Youden index was employed. We developed several machine learning models to determine the best model regarding performance. In this cohort study, increased age, male sex, symptoms, previous admissions, and some specific comorbidities were associated with increased mortality. Machine learning and pre-processing approaches offer a potentially valuable method for improving risk prediction for mortality, but more work is needed to show improvement beyond standard risk factors.

A Lightweight Diabetic Retinopathy Detection Model Using a Deep-Learning Technique.

Diabetic retinopathy (DR) is a severe complication of diabetes. It affects a large portion of the population of the Kingdom of Saudi Arabia. Existing systems assist clinicians in treating DR patients. However, these systems entail significantly high computational costs. In addition, dataset imbalances may lead existing DR detection systems to produce false positive outcomes. Therefore, the author intended to develop a lightweight deep-learning (DL)-based DR-severity grading system that could be used with limited computational resources. The proposed model followed an image pre-processing approach to overcome the noise and artifacts found in fundus images. A feature extraction process using the You Only Look Once (Yolo) V7 technique was suggested. It was used to provide feature sets. The author employed a tailored quantum marine predator algorithm (QMPA) for selecting appropriate features. A hyperparameter-optimized MobileNet V3 model was utilized for predicting severity levels using images. The author generalized the proposed model using the APTOS and EyePacs datasets. The APTOS dataset contained 5590 fundus images, whereas the EyePacs dataset included 35,100 images. The outcome of the comparative analysis revealed that the proposed model achieved an accuracy of 98.0 and 98.4 and an F1 Score of 93.7 and 93.1 in the APTOS and EyePacs datasets, respectively. In terms of computational complexity, the proposed DR model required fewer parameters, fewer floating-point operations (FLOPs), a lower learning rate, and less training time to learn the key patterns of the fundus images. The lightweight nature of the proposed model can allow healthcare centers to serve patients in remote locations. The proposed model can be implemented as a mobile application to support clinicians in treating DR patients. In the future, the author will focus on improving the proposed model's efficiency to detect DR from low-quality fundus images.