Detection of cortical arousals in sleep using multimodal wearable sensors and machine learning

What is the central question of this study? A transcranial magnetic stimulation (TMS)-induced twitch applied on isolated single breaths over the motor cortex somatotopic representation of the tongue briefly recruits submental muscles and improves airflow dynamics of flow-limited respiratory cycles without arousing sleep apnoea patients. However, the mechanical impact of the TMS-induced twitch applied during consecutive breathing cycles on airflow dynamics remains unknown. What is the main finding and what is its importance? Our results show that application of TMS with the stimulator output set at the sleep submental motor threshold intensity on consecutive respiratory cycles increases inspiratory flow and reduces the turbulent airflow component. These results indicate an improvement of airflow pattern after two single consecutive TMS-induced twitches without arousing sleep apnoea patients. Transcranial magnetic stimulation (TMS)-induced twitches applied on isolated breaths briefly recruit upper airway dilator muscles and improve airflow and inspiratory volume without arousing apnoeic patients from sleep, but the effects of applying such twitches consecutively on airflow dynamics is unknown. The objective of this study was to quantify the effects of five consecutive TMS-induced twitches applied on sleep-induced obstructive hypopnoeic breaths in 10 obstructive sleep apnoea patients. Submental muscle motor threshold (SUBMT) and motor-evoked potential were measured during wakefulness and sleep. The TMS-induced twitches were applied during stable non-rapid eye movement (NREM) sleep, at the beginning of inspiration of consecutive flow-limited respiratory cycles, with the stimulator output set at sleep SUBMT. Maximal inspiratory flow, inspiratory volume, inspiratory time, shifts of electroencephalogram frequency and pulse rate variability were assessed. During sleep, SUBMT increased (wakefulness, 25.3 ± 4.9%; NREM sleep, 27.0 ± 6.2%; P = 0.02). During each series of stimulations there was a rise in maximal inspiratory flow (from 306.7 ± 123.2 to 359.8 ± 154.1 ml s(-1); P = 0.0002) and in inspiratory volume (from 346.1 ± 128.1 to 414.9 ± 171.2 ml; P = 0.02) without differences in thoraco-abdominal efforts and inspiratory time. These responses were observed in the absence of arousals and ceased immediately after TMS interruption. Transcranial magnetic stimulation-induced cortical and/or autonomic arousal was observed in 30.2% of all series of stimulation. Consecutive twitch TMS of submental muscles may lead to arousals in a minority of patients but can be applied on consecutive respiratory cycles during sleep and can significantly improve maximal inspiratory flow and inspiratory volume of flow-limited cycles.

EEG beta power and heart rate variability describe the association between cortical and autonomic arousals across sleep.

Low nuclear grade ductal carcinoma in situ (DCIS) patients can adopt proactive management strategies to avoid unnecessary surgical resection. Different personalized treatment modalities may be selected based on the expression status of molecular markers, which is also predictive of different outcomes and risks of recurrence. DCIS ultrasound findings are mostly non mass lesions, making it difficult to determine boundaries. Currently, studies have shown that models based on deep learning radiomics (DLR) have advantages in automatic recognition of tumor contours. Machine learning models based on clinical imaging features can explain the importance of imaging features. The available ultrasound data of 349 patients with pure DCIS confirmed by surgical pathology [54 low nuclear grade, 175 positive estrogen receptor (ER+), 163 positive progesterone receptor (PR+), and 81 positive human epidermal growth factor receptor 2 (HER2+)] were collected. Radiologists extracted ultrasonographic features of DCIS lesions based on the 5th Edition of Breast Imaging Reporting and Data System (BI-RADS). Patient age and BI-RADS characteristics were used to construct clinical machine learning (CML) models. The RadImageNet pretrained network was used for extracting radiomics features and as an input for DLR modeling. For training and validation datasets, 80% and 20% of the data, respectively, were used. Logistic regression (LR), support vector machine (SVM), random forest (RF), and eXtreme Gradient Boosting (XGBoost) algorithms were performed and compared for the final classification modeling. Each task used the area under the receiver operating characteristic curve (AUC) to evaluate the effectiveness of DLR and CML models. In the training dataset, low nuclear grade, ER+, PR+, and HER2+ DCIS lesions accounted for 19.20%, 65.12%, 61.21%, and 30.19%, respectively; the validation set, they consisted of 19.30%, 62.50%, 57.14%, and 30.91%, respectively. In the DLR models we developed, the best AUC values for identifying features were 0.633 for identifying low nuclear grade, completed by the XGBoost Classifier of ResNet50; 0.618 for identifying ER, completed by the RF Classifier of InceptionV3; 0.755 for identifying PR, completed by the XGBoost Classifier of InceptionV3; and 0.713 for identifying HER2, completed by the LR Classifier of ResNet50. The CML models had better performance than DLR in predicting low nuclear grade, ER+, PR+, and HER2+ DCIS lesions. The best AUC values by classification were as follows: for low nuclear grade by RF classification, AUC: 0.719; for ER+ by XGBoost classification, AUC: 0.761; for PR+ by XGBoost classification, AUC: 0.780; and for HER2+ by RF classification, AUC: 0.723. Based on small-scale datasets, our study showed that the DLR models developed using RadImageNet pretrained network and CML models may help predict low nuclear grade, ER+, PR+, and HER2+ DCIS lesions so that patients benefit from hierarchical and personalized treatment.

Research efforts in the prediction of stroke and diabetes prioritize early detection in order to enhance patient outcomes. To achieve this, a variety of methodologies are integrated. Existing studies, on the other hand, are marred by imbalanced datasets, lack of diversity in their datasets, potential bias, and inadequate model comparisons; these flaws underscore the necessity for more comprehensive and inclusive research methodologies. This paper provides a thorough assessment of machine learning algorithms in the context of early detection and diagnosis of stroke and diabetes. The research employed widely used algorithms, including Logistic Regression, Decision Tree, Random Forest, K-Nearest Neighbors (KNN), and XGBoost Classifier, to examine medical data and derive significant findings. The XGBoost Classifier demonstrated superior performance, with an outstanding accuracy, precision, recall, and F1-score of 87.5%. The comparative examination of the algorithms indicated that the Decision Tree, Random Forest, and XGBoost classifiers consistently exhibited strong performance across all measures. The models demonstrated impressive discrimination capabilities, with the XGBoost Classifier and Random Forest reaching accuracy rates of roughly 87.5% and 86.5% respectively. The Decision Tree Classifier exhibited notable performance, with an accuracy rate of 83%. The overall accuracy of the models was evident in the F1-score, a metric that incorporates recall and precision, where the XGBoost model exhibited a marginal improvement of 2% over the Random Forest and Decision Tree models, and 4.25 percent over the last two. The aforementioned results underscore the effectiveness of the XGBoost Classifier, which will be employed as a predictive model in this study, alongside the Random Forest and Decision Tree models, for the accurate identification of stroke and diabetes. Furthermore, combining datasets improves model performance by utilizing relative features. This integrated dataset improves the model's efficiency and creates a resilient and comprehensive prediction model, improving healthcare outcomes. The findings of this research make a valuable contribution to the advancement of AI-driven diagnostic systems, hence enhancing the quality of healthcare decision-making.

The classification of IP traffic is important for many reasons, including network management and security, quality of service (QoS) monitoring and provisioning, and high hardware utilisation. Recently, many machine learning-based IP traffic classifiers have been developed. Unfortunately, most of them need to be trained on large datasets and thus require a long training time and significant computational power. In this paper, I investigate this problem and, as a solution, present a hybrid system, which I call the ISITC, that combines the random forest (RF) and XGBoost (XGB) machine learning techniques with the support vector classifier (SVC) as the final estimator, the stacking classifier. This design leads to the development of a model that performs the classification of IP traffic and internet applications efficiently and with high accuracy. I evaluate the performance of the ISITC and various IP traffic classifiers, including neural network (NN), RF, decision tree (DT), and XGB classifiers and SVCs. The experimental results show that the ISITC provides the best IP traffic classification, with an accuracy of 96.7, and outperforms the other IP traffic classifiers: the NN classifier has an accuracy of 59, the RF classifier has an accuracy of 88.5, the DT classifier has an accuracy of 90.5, the XGB classifier has an accuracy of 89.8, and the SVC has an accuracy of 64.8.

The eradication of Giant Rat Tail (GRT) grass (Sporobolus natalensis and Sporobolus pyramidalis) in southeastern and central Queensland is essential for maintaining agricultural productivity. These invasive weeds significantly deplete soil nutrients, thereby rendering the land unsuitable for crop cultivation. Moreover, their high silica, phenolic compound, and lignin content make them unpalatable to livestock, further diminishing the utility of infested pastures. This study proposes a novel methodology that integrates drone-based imaging with machine learning techniques to classify and manage GRT grass infestations. Highresolution RGB imagery of pastureland was captured using a DJI Phantom 4 Pro UAV. The collected data were subjected to square patch segmentation, resulting in over 315574 image segments categorized into GRT and non-GRT classes. For each segment, an extensive set of 37 features, encompassing texture, radiometric, runlength characteristics and color, was extracted. Subsequent data pre-processing included the removal of tiles having no data value and the partitioning of the dataset into training and testing subsets. Five tree based machine learning classifiers-Decision Tree Classifier, Random Forest Classifier, AdaBoost Classifier, XGBoost Classifier, and XGBoost Random Forest Classifier-were developed and assessed. The classification performance was optimized by retraining the XGBoost classifier using the top 21 features identified based on their importance as determined by the already trained XGBoost classifier. Among the evaluated models, the XGBoost classifier with top 21 features achieved the highest accuracy (95.5 %), along with robust performance metrics for GRT classification, including a precision of 95.3 %, recall of 94.2 %, and <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$F 1$</tex> score of 94.7 %. These findings underscore the potential of UAV-assisted remote sensing, coupled with advanced machine learning methodologies, as a scalable and costefficient solution for the precise detection of invasive weed species, thereby facilitating their effective management and enhancing agricultural sustainability.

The accurate and timely prediction of financial market crises remains a persistent challenge for economists, policymakers, and investors. Traditional early warning systems (EWS) often rely on low-frequency macroeconomic indicators and static econometric models, limiting their effectiveness in dynamic market environments. This study proposes to fill this gap by developing a novel framework for crisis prediction through constructing a Composite Early Warning Index (CEWI) that integrates daily data from financial markets, macroeconomic fundamentals, and political uncertainty indicators. Principal Component Analysis (PCA) was employed to synthesize these diverse variables into a single latent factor, capturing the underlying systemic risk. Machine learning algorithms, including Logistic Regression, Random Forest, and XGBoost classifiers, were trained on historical data spanning from 2000 to 2025 to predict crisis periods, defined by sharp equity market declines and official recession declarations. The XGBoost model achieved superior performance with an ROC-AUC of 0.953. Feature importance analysis utilizing SHAP values identified market volatility (VIX), gold prices, and oil prices as the most influential predictors. The results demonstrate that combining high-frequency financial and political indicators with advanced machine learning techniques significantly enhances crisis prediction accuracy. The proposed CEWI-based framework offers a powerful tool for early risk detection and has important implications for financial regulation, investment strategy, and economic policy design.

Introduction: Chronic Obstructive Pulmonary Disease (COPD), is a condition caused by damage to theairways or other parts of the lung that blocks airflow and makes it hard to breathe [1]. COPD is the thirdleading cause of death worldwide, and the seventh leading cause of poor health worldwide [2]. Studieshave shown that 20–86% of people with COPD worldwide may be undiagnosed [3]. As there is currentlyno cure for COPD, early detection is the best option. Current Machine Learning (ML) models focus onusing chest images (CT or X-ray scans) to detect COPD; however, the scanning process can be unsafe forpatients with COPD [4].Methods: This study utilized an open data set containing various physical tests of 100 patients withCOPD. To train this model, the Random Forest (RF) classifier was used. The accuracy was then plottedon a graph.Results: The Random Forest classifier was able to achieve an accuracy of 92.41% with a perfect recallvalue of 1.00. This recall value indicates that the Random Forest classifier was able to correctly diagnoseall of the patients with COPD in this dataset.Discussion: This study developed a novel ML model that can accurately provide a diagnosis for COPD.Further studies could use this code with a larger dataset to obtain a higher accuracy. White individualshave been reported to have a higher prevalence of COPD [5]. By developing a dataset that accounts forrace, we will be able to obtain a more accurate diagnosis.

The objective of this study was to develop a machine learning (ML) application to determine the optimal dosage of sodium hypochlorite (NaOCl) to curtail corrosion and odor by H2 S in the headworks of a water resource recovery facility (WRRF) without overly consuming volatile fatty acids (VFAs) that are essential for the enhanced biological phosphorus removal. Given the highly diverse datasets available, three subproblems were formulated, and three cascaded ML modules were developed accordingly. The final ML models, chosen based on performance, were able to predict various targeted variables. More specifically, in Module 1, a recurrent neural network (RNN) was designed to predict wastewater characteristics. In Module 2, a random forest (RF) classifier and a support vector machine (SVM) classifier were built with the information from Module 1 along with other datasets to predict the concentrations of VFAs and H2 S, respectively. Finally, in Module 3, with the information obtained from Module 2, another RF classifier was developed to predict NaOCl dosage to reduce H2 S but keeping VFAs within the target range. These efforts are relevant and informative for WRRFs that are considering developing Intelligent Water Systems to predict the wastewater characteristics to make operational improvements. PRACTITIONER POINTS: A recurrent neural network (RNN) using long short-term memory (LSTM) successfully predicted influent wastewater parameters. A support vector machine classifier predicted hydrogen sulfide (H2 S) with 97.6% accuracy. The concentration of VFAs, an important parameter in EBPR, was predicted using a random forest classifier with 93.4% accuracy. The optimal NaOCl dosage for H2 S control can be predicted with a random forest classifier using H2 S, VFAs, and flow.

Monitored natural attenuation is commonly used to manage petroleum hydrocarbon-contaminated groundwater. However, it requires periodic, costly grab sampling. We propose a cost-effective, real-time groundwater monitoring proof-of-concept machine learning (ML) framework using in-situ sensors-pH, dissolved oxygen, electrical conductivity, and redox potential-to detect benzene, ethylbenzene, and xylenes (BEX). We built upon the established correlations between hydrocarbon concentrations and in-situ water quality parameters (iWQPs). Due to limited field data, we validated the framework using datasets at virtual wells within a simulated aquifer from our previously developed reactive transport model. In this application, we detected the spreading of pollution downstream of the established pollution plume. The used framework is a binary classification system that flags contamination at virtual downstream wells. We compared five ML classifiers, i.e. Logistic Regression, Random Forest, XGBoost, Multi-layer Perceptron, and Support Vector Classifier, for early warning when BEX reached or exceeded the regulatory threshold of 5μg/L. The models were trained on virtual wells at and near the source zone and predicted contamination before BEX reached the threshold at downstream virtual wells. This reflects the spatial variability in flow and reaction dynamics that altered BEX-iWQP relationships. Scenario analyses revealed the ML models' sensitivity to aquifer properties, i.e., hydraulic conductivity, electrical conductivity, and electron acceptor availability. We also assessed the impact of sensor noise and seasonal fluctuations on iWQPs. We found that even moderate levels of noise (10-20%) can significantly affect model accuracy, particularly when the noise was introduced into the test data. Therefore, we recommended to combine hardware stabilization with adaptive smoothing techniques. With these approaches, our proposed framework remains promising for providing early warnings of plume migration toward sensitive receptors.

COVID-19, also known as the coronavirus disease 2019 is a highly contagious respiratory illness caused by SARS-COV-2 virus which spread form china globally resulting in pandemic. With advances in diagnostic tools, radiologic imaging is widely used for COVID-19 pneumonia diagnosis other than usual clinical and laboratory testing. In this paper, several deep learning and machine learning enhanced techniques are applied to X-Ray and CT-Scan medical images for the detection of covid-19 and also a clinical data for the prediction of the covid19. The images are preprocessed and trained using U-Net model, a popular architecture for image segmentation tasks. The accuracy and F1-score were found to be above 98% in the diagnosis of COVID-19 using CT-scan images. Further, transfer learning techniques were applied to overcome the insufficient data and to improve the training time. The binary and multi-class classification of X-ray images tasks were performed by utilizing enhanced CNN deep transfer learning architecture. An accuracy of 99% was achieved by enhanced CNN in the detection of X-ray images from COVID-19 and pneumonia.Further,using clinical dataset we compared the performance of supervised machine learning algorithms: logistic regression, random forest classifier, and XGBoost classifier. These algorithms were trained and evaluated on the preprocessed and feature-selected dataset to predict COVID-19 cases. The results showed that XGBoost classifier outperformed logistic regression and random forest classifier in predicting COVID-19 cases based on symptoms, age, gender, and test indications.

Cardiovascular diseases (CVD) are the leading cause of death globally. Cardiac rehabilitation (CR) programs' benefits are overall consensual; however, during exercise, progressive physiological effects have not been studied yet in cardiac patients. Our study aims to analyze physiological parameters of thermography, heart rate variability (HRV), blood pressure, central nervous system (CNS) fatigue, and cortical arousal in heart attack patients (HAP) who belong to CR programs of High-Intensity Interval Training (HIIT) and Moderate-intensity Continuous Training (MICT) compared to healthy participants. In this case control study, two HAP patients (both male, age 35 and 48, respectively) and two healthy people (both male, age 38 and 46, respectively) were randomly assigned in a 1:1:1:1 allocation ratio to one of four groups: cardiac MICT, cardiac HIIT, control MICT, and control HIIT. The HIIT at ≈85-95% of peak heart rate (HR) was followed by a one-minute recovery interval at 40% peakHR, and MICT at ≈70-75% of peakHR. Outcome measurements included thermography, HRV, blood pressure, CNS fatigue, and cortical arousal; The HAP presents more than twice the CNS fatigue in MICT than control participants, but HIIT has almost the same CNS fatigue in HAP and control. In addition, both of the HAP groups presented higher temperatures in the chest. The HIIT protocol showed better physiological responses during exercise, compared to MICT in HAP.

A stroke is a dangerous, life-threatening disease that mostly affects people over 65, but an unhealthy diet is also contributing to the development of strokes at younger ages. Strokes can be treated successfully if they are identified early enough, and suitable therapies are available. The purpose of this study is to develop a stroke prediction model that will improve stroke prediction effectiveness as well as accuracy. Predicting whether someone is suffering from a stroke or not can be accomplished with this proposed machine learning algorithm. In this research, various machine learning techniques are evaluated for predicting stroke on the healthcare stroke dataset. The feature selection algorithms used here are gradient boosting and random forest, and classifiers include the decision tree classifier, Support Vector Machine (SVM) classifier, logistic regression classifier, gradient boosting classifier, random forest classifier, K neighbors classifier, and Xtreme gradient boosting classifier. In this process, different machine-learning approaches are employed to test predictive methods on different data samples. As a result obtained from the different methods applied, and the comparison of different classification models, the random forest model offers an accuracy rate of 98%.

Parkinson’s disease (PD) is a nervous system disorder first described as a neurological condition in 1817. It is one of the more prevalent diseases in the elderly, and Alzheimer’s is the second most common neurodegenerative illness. It impacts the patient’s movement. Symptoms start gradually with tremors, stiffness in movement, and speech and voice disorders. Researches proved that 89% of patients with Parkinson’s has speech disorder including uncertain articulation, hoarse and breathy voice and monotone pitch. The cause behind this voice change is the reduction of dopamine due to damage of neurons in the substantia nigra responsible for dopamine production. In this work, Parkinson’s disease is classified with the help of human voice signals. Six different machine learning (ML) algorithms are used in the classification: Stochastic Gradient Descent (SGD) Classifier, Extreme Gradient Boosting (XGB) Classifier, Logistic Regression Classifier, Random Forest Classifier, K-Nearest Neighbour (KNN) Classifier, and Decision Tree (DT) Classifier. This research aims to classify Parkinson’s disease using human voice signals and extract essential features to reduce the complexity of the dataset. Then, human voice signals are analyzed to check the voice intensity and spectrum for PD patients. Then, machine learning classifiers are applied to classify the PD patients based on the extracted features. The results show that SGD-Classifier has 91% accuracy, XGB-Classifier has 95% accuracy, Logistic Regression has 91% accuracy, Random Forest shows 97% accuracy, KNN shows 95% accuracy, and Decision Tree has 95% accuracy. Hence, Random Forest has the highest accuracy. The disease can be studied more by looking for more characteristics of PD patients to enhance its proper use in the medical field.

Heart disease is a major cause of death worldwide. About 31% of global deaths occur due to this disease. According to the WHO report, approximately 17.9 million people worldwide die each year due to this disease. Early detection of heart disease can reduce the chance of the disease progressing to a more severe stage by providing appropriate treatment. Coronary angiography is the most precise method of detecting the disease; nevertheless, it is a painful and expensive procedure, and patients do not prefer it in the early stages. As a result, a non-invasive and reliable method that can be employed as a screening tool for disease diagnosis is required. Machine learning has influenced every element of human life in the modern era, and it has a huge impact in the health care sector also. Machine learning (ML) based decision support systems can be used to diagnose heart disease by evaluating the clinical parameters of a patient. Various ML techniques have been investigated in this paper, and a system has been designed for the diagnosis of heart disease, with an emphasis on coronary artery disease. Relevant features were selected using the Extra Tree feature selection method and classification was done by XGBoost (extreme gradient boosting), KNN (K-nearest neighbor), SVM (support vector machine), logistic regression (LR), decision tree (DT), random forest (RF) and neural network (NN) classifiers. A regularized NN model for heart disease diagnosis is also developed that has provided 84.0% accuracy and 85.0% accuracy for RF on the Kaggle dataset.