Critical Predictors Research Articles

How online reviews of sports tourism affect tourists’ value co-creation behavior: Findings from PLS-SEM, NCA, and fsQCA

Online reviews generated by digital technology play a significant role in promoting value co-creation among sports tourists. However, the existing literature on this relationship needs further research on the underlying influence processes. Based on the C-A-C framework, this study found that the characteristics of online reviews and reviewers significantly affect sports tourists' perceived value, shaping their destination identity and flow experience, thereby fostering value co-creation behavior. Sports tourists should not be completely unsatisfied with the perceived objectivity of online reviews. Instead, combining various antecedents is necessary for high levels of tourists' value co-creation behavior. Perceived aesthetics and professionalism were critical predictors across most configurations, with perceived value being a core condition. We identified five different configurations and further categorized them into three types, revealing the complex relationship between online reviews and sports tourists’ value co-creation behavior. The results provide valuable practical and theoretical insights for stakeholders in the sports tourism industry and highlight the pivotal role that online reviews play in enriching the value co-creation of sports tourism.

Integrating ECM, TAM, and SDT in Studying Accounting Lecturers' Continuance Intention for ODL: A Review

Lecturers are increasingly expected to use technology to prepare their students for 21st century skills (Ahmad et al., 2019). As a result, online learning will become a common trend in university education in the near future, particularly in accounting (Sarea et al., 2021), especially since the COVID-19 pandemic has brought enormous changes to the educational landscape. Thus, given that the ultimate success of Open and Distance Learning (ODL) hinges on the continuance of intention to use it, it is important to discuss this intention. This review paper aims to explore the factors that could influence accounting lecturers' continuance intention to use ODL by integrating three prominent theoretical models: the Expectation-Confirmation Model (ECM), the Technology Acceptance Model (TAM), and the Self-Determination Theory (SDT). This paper included 23 articles that covered studies from 2008 to 2024. The key ECM, TAM, and SDT constructs that have been used in the literature to predict continuance intention are identified in this paper. The findings suggest that perceived usefulness, perceived ease of use, satisfaction, and intrinsic motivation are potentially critical predictors. It is posited that the integration of the ECM, TAM, and SDT frameworks provide a comprehensive understanding of both extrinsic and intrinsic factors that drive the continued use of ODL among accounting lecturers, offering insights for designing effective online learning environments.

Optimizing Electric Vehicle (EV) Charging with Integrated Renewable Energy Sources: A Cloud-Based Forecasting Approach for Eco-Sustainability

As electric vehicles (EVs) are becoming more common and the need for sustainable energy practices is growing, better management of EV charging station loads is a necessity. The simple act of folding renewable power from solar or wind in an EV charging system presents a huge opportunity to make them even greener as well as improve grid resiliency. This paper proposes an innovative EV charging station energy consumption forecasting approach by incorporating integrated renewable energy data. The optimization is achieved through the application of SARLDNet, which enhances predictive accuracy and reduces forecast errors, thereby allowing for more efficient energy allocation and load management in EV charging stations. The technique leverages comprehensive solar and wind energy statistics alongside detailed EV charging station utilization data collected over 3.5 years from various locations across California. To ensure data integrity, missing data were meticulously addressed, and data quality was enhanced. The Boruta approach was employed for feature selection, identifying critical predictors, and improving the dataset through feature engineering to elucidate energy consumption trends. Empirical mode decomposition (EMD) signal decomposition extracts intrinsic mode functions, revealing temporal patterns and significantly boosting forecasting accuracy. This study introduces a novel stem-auxiliary-reduction-LSTM-dense network (SARLDNet) architecture tailored for robust regression analysis. This architecture combines regularization, dense output layers, LSTM-based temporal context learning, dimensionality reduction, and early feature extraction to mitigate overfitting. The performance of SARLDNet is benchmarked against established models including LSTM, XGBoost, and ARIMA, demonstrating superior accuracy with a mean absolute percentage error (MAPE) of 7.2%, Root Mean Square Error (RMSE) of 22.3 kWh, and R2 Score of 0.87. This validation of SARLDNet’s potential for real-world applications, with its enhanced predictive accuracy and reduced error rates across various EV charging stations, is a reason for optimism in the field of renewable energy and EV infrastructure planning. This study also emphasizes the role of cloud infrastructure in enabling real-time forecasting and decision support. By facilitating scalable and efficient data processing, the insights generated support informed energy management and infrastructure planning decisions under dynamic conditions, empowering the audience to adopt sustainable energy practices.

Assessment of habitat features modulated carbon sequestration strategies for drought management in tropical dry forest fragments

Habitat features, such as species diversity, functional diversity, tree size, disturbances and fragment sizes have differential impacts on carbon (C) storage and C-sequestration in forest ecosystems. Present study attempted to understand the tree strategies for modulating C-sequestration capacity across tropical dry forest fragments with variable edge distances. We evaluated the differences between drought strategies (i.e., drought avoiding and drought tolerant) for variations in stem density, relative growth rate (RGR), C-storage and C-sequestration, species diversity, functional diversity, tree size and disturbance indicators along edge distance gradient, besides analyzed the differences between drought strategies for responses of C-storage and C-sequestration to variations in species diversity, functional diversity, tree size and disturbance indicators. Various traits and functional indices were analyzed using standard statistical techniques. For total trees and for the two drought strategies, generalized linear modeling results showed a significant decline in stem density, RGR, C-stock, C-sequestration, species diversity, functional diversity and tree size indicators, while a considerable increase in disturbance indicators, along decreasing edge distance across the fragments. The drought strategies exhibited a high degree of variation in the slope of associations for above variables with edge distance across fragments. For predicting C-sequestration, structural equation modeling results showed highly significant influence of functional diversity indicators for drought avoiding strategy, while species diversity indicators were strongly significant for drought tolerant strategy. Moreover, fire index and drought index were critical predictors for C-sequestration for drought avoiding and drought tolerant strategies, respectively. This study provide inputs to understand the largely ignored processes of C-storage and C-sequestration in fragmented forests, which are currently prevalent due to heavy anthropogenic pressures. Our findings are useful for forest managers to understand vegetation responses to interactions of species diversity, functional diversity, tree size and disturbance indicators, for predicting the stability of larger fragments and for planning restoration of smaller fragments.

Homicidality risk prediction based on ecological systems theory in an early adolescent cohort using machine learning

PurposeIdentifying high-risk adolescents prone to homicidality, linked to serious criminal activities and homicide, offers vital avenues for homicide prevention. MethodsThis study analyzed data from 1596, 1596, and 1526 students at baseline, one-year, and two-year follow-ups, respectively, drawn from the Chinese Early Adolescent Cohort study. Based on Bronfenbrenner's ecological systems theory, predictors of adolescent homicidality were categorized into individual, family, and school and peer levels. Five machine learning methods were utilized to construct prediction models for homicidality risk and to pinpoint predictive factors. ResultsLogistic regression models using only significant features effectively predicted adolescent homicidality and new onsets in the short term, as well as homicidal trajectories throughout early adolescence. Key factors identified included suicidal ideation, emotional abuse, life satisfaction, physical violence, and verbal violence, with suicidal ideation and emotional abuse emerging as the most critical predictors. ConclusionsThis study successfully developed risk-predictive models for adolescent homicidality using machine learning, emphasizing suicidal ideation and emotional abuse as primary predictors. These findings highlight the importance of targeted interventions focused on these key variables for the early prevention of adolescent homicide.

Canonical Correlations on Positive and Negative Attitudes of Computer-Based Statistics among Business Students

This study aims to investigate the canonical relationship between positive and negative attitudes of economics and business students when using computer-based analytical tools. The subjects of this study were students of the Faculty of Economics and Business in Medan. Samples were taken from two universities, including state universities and private universities. Using a random sampling technique, this study collected 247 responses, consisting of 47 male and 200 female respondents. The data in this study were collected using a questionnaire with a 5-Likert scale and analyzed by canonical correlation. The results of the canonical correlation analysis in this study revealed that Perceived Usefulness (PU) and Perceive Enjoyment (PE) were critical predictors of the construct set of positive attitudes. At the same time, Strain (ST) and Negative Affectivity (NA) were essential predictors of the formation of negative attitudes among users when using computer-based statistical tools. This study produces a new insight related to attitude toward Information Technology (IT) in a specific task, namely statistical analysis. This study also has practical recommendations for universities and lecturers to invest in and use statistical software that is easy and convenient for teaching statistics.

Novel machine-learning prediction tools for overall survival of patients with chondrosarcoma: Based on recursive partitioning analysis.

Chondrosarcoma (CHS), a bone malignancy, poses a significant challenge due to its heterogeneous nature and resistance to conventional treatments. There is a clear need for advanced prognostic instruments that can integrate multiple prognostic factors to deliver personalized survival predictions for individual patients. This study aimed to develop a novel prediction tool based on recursive partitioning analysis (RPA) to improve the estimation of overall survival for patients with CHS. Data from the Surveillance, Epidemiology, and End Results (SEER) database were analyzed, including demographic, clinical, and treatment details of patients diagnosed between 2000 and 2018. Using C5.0 algorithm, decision trees were created to predict survival probabilities at 12, 24, 60, and 120 months. The performance of the models was assessed through confusion scatter plot, accuracy rate, receiver operator characteristic (ROC) curve, and area under ROC curve (AUC). The study identified tumor histology, surgery, age, visceral (brain/liver/lung) metastasis, chemotherapy, tumor grade, and sex as critical predictors. Decision trees revealed distinct patterns for survival prediction at each time point. The models showed high accuracy (82.40%-89.09% in training group, and 82.16%-88.74% in test group) and discriminatory power (AUC: 0.806-0.894 in training group, and 0.808-0.882 in test group) in both training and testing datasets. An interactive web-based shiny APP (URL: https://yangxg1209.shinyapps.io/chondrosarcoma_survival_prediction/) was developed, simplifying the survival prediction process for clinicians. This study successfully employed RPA to develop a user-friendly tool for personalized survival predictions in CHS. The decision tree models demonstrated robust predictive capabilities, with the interactive application facilitating clinical decision-making. Future prospective studies are recommended to validate these findings and further refine the predictive model.

High salt intake and HIV infection on endothelial glycocalyx shedding in salt-sensitive hypertension.

The endothelial glycocalyx is closely associated with various physiological and pathophysiological events. Significant modification of the endothelial glycocalyx is an early process in the pathogenesis of cardiovascular disease. High dietary salt and HIV infection damages the endothelial glycocalyx causing endothelial dysfunction and increasing the risk for salt-sensitive hypertension and cardiovascular disease. The two factors, HIV infection and dietary salt are critical independent predictors of hypertension and cardiovascular disease and often synergize to exacerbate and accelerate disease pathogenesis. Salt-sensitive hypertension is more common among people living with HIV and is associated with risk for cardiovascular disease, stroke, heart attack and even death. However, the underlying mechanisms linking endothelial glycocalyx damage to dietary salt and HIV infection are lacking. Yet, both HIV infection/treatment and dietary salt are closely linked to endothelial glycocalyx damage and development of salt-sensitive hypertension. Moreover, the majority of individuals globally, consume more salt than is recommended and the burden of HIV especially in sub-Sahara Africa is disproportionately high. In this review, we have discussed the missing link between high salt and endothelial glycocalyx shedding in the pathogenesis of salt-sensitive hypertension. We have further elaborated the role played by HIV infection and treatment in modifying endothelial glycocalyx integrity to contribute to the development of hypertension and cardiovascular disease.

Distribution, relationship, and environmental driving factors of chlorophyll-a and algal cell density: A national view of China

Chlorophyll-a (Chl-a) and algal cell density (ACD) are vital for assessing algal proliferation and eutrophication in aquatic ecosystems. Although Chl-a is often used as a proxy for ACD, its accuracy requires validation, and studies on their linear correlation are scarce. Additionally, Chl-a and ACD are influenced by various factors, including nutritional, economic, biochemical, physicochemical, and meteorological factors. However, the relative importance of these factors on Chl-a and ACD remains insufficiently studied. This study analyzed data from 57 lakes and reservoirs across China from March 2021 to February 2023, investigating the distribution patterns of Chl-a and ACD across different regions and seasons. The study employed a linear regression model to explore the correlation between Chl-a and ACD in various regions and seasons throughout China. Furthermore, Mantel test and generalized linear model were used to evaluated the relative importance of nutritional factors (total nitrogen (TN), total phosphorus (TP), TN/TP ratio (TN/TP), and ammonia nitrogen (NH3-N)), economic factors (gross domestic product), meteorological factors (surface pressure, net solar radiation, air temperature, wind speed (WS), and rainfall (RF)), as well as biochemical and physicochemical factors (turbidity (TUR), pH value, water temperature (WT), permanganate index, and dissolved oxygen) on Chl-a and ACD. Results showed that the average concentrations of Chl-a and ACD in South China were highest, at 12 μg/L and 19.5 × 106 cells/L, respectively. Seasonally, Chl-a peaked in spring and was lowest in winter, while ACD peaked in summer and was lowest in winter. Significant seasonal and regional variations in the Chl-a and ACD correlation were observed, with spring showing the strongest relationship. In Central China, Chl-a and ACD were significantly correlated throughout the four seasons, whereas correlations were less distinct in Eastern and Western regions. Therefore, Chl-a as a proxy for ACD requires caution. Nutrient factors (TN, TP, TN/TP, NH3-N) were identified as the primary drivers of Chl-a and ACD. Meteorological factors (WS, RF), along with biochemical and physicochemical factors (WT, TUR) also emerged as critical predictors of Chl-a and ACD, with spatial variations. This study validates Chl-a as a proxy for ACD, analyzes their spatiotemporal distribution, and assesses the influence of various factors on Chl-a and ACD, enhancing our understanding of algal dynamics in Chinese lakes and reservoirs.

Deep learning for predicting fibrotic progression risk in diabetic individuals with metabolic dysfunction-associated steatotic liver disease initially free of hepatic fibrosis

ObjectiveMetabolic dysfunction-associated steatotic liver disease (MASLD) significantly impacts patients with type 2 diabetes mellitus (T2DM), where current non-invasive assessment methods show limited predictive power for future fibrotic progression. This study aims to develop an enhanced deep learning (DL) model that integrates ultrasound elastography images with clinical data, refining the prediction of fibrotic progression in T2DM patients with MASLD who initially exhibit no signs of hepatic fibrosis. MethodsWe enrolled 946 diabetic MASLD patients without advanced fibrosis, confirmed by initial liver stiffness measurements (LSM) below 6.5 kPa. Patients were divided into a training dataset of 671 and a testing dataset of 275. Hepatic shear wave elastography (SWE) images measured liver stiffness, classifying participants based on progression. A DL integrated model (DI-model) combining SWE images and clinical data was trained and its predictive performance compared with individual Image and Tabular models, as well as a logistic regression model on the testing dataset. ResultsFibrotic progression was observed in 18.1 % of patients over three years. During the training phase, the DI-model outperformed other models, achieving the lowest validation loss of 0.161 and highest accuracy of 0.933 through cross-validation. In the testing phase, it demonstrated robust discrimination with AUCs of 0.884 and 0.903 for the receiver operating characteristic and precision-recall curves, respectively, clearly outperforming other models. Shapley analysis identified BMI, LSM, and glycated hemoglobin as critical predictors. ConclusionThe DI-model significantly enhances the prediction of future fibrotic progression in diabetic MASLD patients, demonstrating the benefit of combining clinical and imaging data for early diagnosis and intervention.

Unveiling End-users' Satisfaction and Actual Use of Blockchain in e-Health: Empirical Evidence from Bangladesh

Data safety and security have become threatening issues in the health industry. Against this backdrop, blockchain technology has opened up a new window for healthcare stakeholders. This research aims to enhance the understanding of the factors that influence user satisfaction and actual use behavior of blockchain technology in the electronic health sector in Bangladesh. A convenience sampling collected primary data (270 responses) from nurses, doctors, emergency staff, and laboratory technicians. AMOS and SPSS were used for analysis. The data were analyzed using descriptive statistics, assessing normality, common method bias, validity, reliability test and regression weight analysis. The findings of this study reveal that the task characteristics, performance expectancy, information quality, and service quality of blockchain are significantly related to end-user satisfaction. Performance expectancy had the greatest weighted influence on satisfaction. End-user satisfaction reflects strong usage behavior towards blockchain technology in Bangladesh. Surprisingly, system quality does not substantially affect user satisfaction derived from blockchain technology. This study analyzes the most critical predictors of satisfaction evoked by using blockchain, particularly relevant to the context of Least Developed Countries (LDCs), such as Bangladesh. To our knowledge, limited studies have yet examined user satisfaction and actual use behavior through the lens of IS success, Task Technology Fit (TTF), and UTAUT models in Bangladesh's e-health sector. This study is anticipated to provide an opportunity for additional investigation into the potential uses of blockchain in the medical field and other commercial sectors.

Towards Enhanced Autonomous Driving Takeovers: Fuzzy Logic Perspective for Predicting Situational Awareness

This paper investigates the application of fuzzy logic to enhance situational awareness in Advanced Driver Assistance Systems (ADAS). Situational awareness is critical for drivers to respond appropriately to dynamic driving scenarios. As car automation increases, monitoring situational awareness ensures that drivers can effectively take control of the vehicle when needed. Our study explores whether fuzzy logic can accurately assess situational awareness using a set of 14 critical predictors categorized into time decision, criticality, eye-related metrics, and driver experience. We based our work on prior research that used machine learning (ML) models to achieve high accuracy. Our proposed fuzzy logic system aims to match the predictive accuracy of ML models while providing additional benefits in terms of interpretability and robustness. This approach emphasizes a fresh perspective on situational awareness within ADAS, potentially improving safety and efficiency in real-world driving scenarios.

Predictive scores for critically ill obstetric patients in a resource‐limited setting: A retrospective validation of the Obstetric Early Warning Score.

Background. In South Africa (SA), an unacceptably high institutional maternal mortality rate persists due to failure to recognise critically ill patients. Early warning systems could assist in identifying these patients sooner. Objectives. We evaluated the Obstetric Early Warning Score (OEWS) as a predictor of maternal outcomes in an intensive care unit (ICU) and compared its prognostic validity with the Acute Physiology and Chronic Health Evaluation (APACHE) II and the quick Sequential Organ Failure Assessment score (qSOFA). Methods. Data were extracted on pregnant and post-partum ICU-admitted patients at a tertiary and regional centre in SA between October 2015 and April 2020. Clinical characteristics and outcomes were used to compare the three scoring systems. Results. Among 251 eligible patients, the mortality rate was 8.5%. The OEWS score failed to differentiate between survivors and non-survivors (odds ratio 1.13, 95% confidence intervals (CI) 0.972 - 1.311, p=0.113). APACHE II outperformed the OEWS (area under the receiver operating characteristics curve (AUROC) 0.69, 95% CI 0.540 - 0.846 v. 0.55, 95% CI 0.430 - 0.674). The OEWS (AUROC 0.55, 95% CI 0.430 - 0.674) and qSOFA (AUROC 0.60, 95% CI 0.500 - 0.703) showed no differences. Further analysis revealed that positive scoring for diastolic blood pressure and high systolic blood pressure weakened OEWS performance. Removing these variables improved OEWS prediction (AUROC 0.68). Conclusion. In a SA obstetric population, OEWS did not predict mortality in ICU-admitted patients and offered no advantages over APACHE II or qSOFA scores. Further research should identify critical outcome predictors for low-resource populations.

Machine learning is an effective method to predict the 3-month prognosis of patients with acute ischemic stroke

Background and objectivesUpwards of 50% of acute ischemic stroke (AIS) survivors endure varying degrees of disability, with a recurrence rate of 17.7%. Thus, the prediction of outcomes in AIS may be useful for treatment decisions. This study aimed to determine the applicability of a machine learning approach for forecasting early outcomes in AIS patients.MethodsA total of 659 patients with new-onset AIS admitted to the Department of Neurology of both the First and Second Affiliated Hospitals of Bengbu Medical University from January 2020 to October 2022 included in the study. The patient’ demographic information, medical history, Trial of Org 10,172 in Acute Stroke Treatment (TOAST), National Institute of Health Stroke Scale (NIHSS) and laboratory indicators at 24 h of admission data were collected. The Modified Rankine Scale (mRS) was used to assess the 3-mouth outcome of participants’ prognosis. We constructed nine machine learning models based on 18 parameters and compared their accuracies for outcome variables.ResultsFeature selection through the Least Absolute Shrinkage and Selection Operator cross-validation (Lasso CV) method identified the most critical predictors for early prognosis in AIS patients as white blood cell (WBC), homocysteine (HCY), D-Dimer, baseline NIHSS, fibrinogen degradation product (FDP), and glucose (GLU). Among the nine machine learning models evaluated, the Random Forest model exhibited superior performance in the test set, achieving an Area Under the Curve (AUC) of 0.852, an accuracy rate of 0.818, a sensitivity of 0.654, a specificity of 0.945, and a recall rate of 0.900.ConclusionThese findings indicate that RF models utilizing general clinical and laboratory data from the initial 24 h of admission can effectively predict the early prognosis of AIS patients.

Predictors of Mortality and the Development of a Risk Score for Gallbladder Adenocarcinoma: A Population-Based Analysis Using Healthcare Cost and Utilization Project National Inpatient Database (HCUP-NIS) Data.

Objective This study aims to identify factors predictive of mortality in patients with gallbladder adenocarcinoma and to develop a risk score to predict poor outcomes using data from the Using Healthcare Cost and Utilization Project National Inpatient Database (HCUP-NIS) database between 2016 and 2020. Methods We conducted a retrospective cohort study analyzing 8596 patients diagnosed with gallbladder adenocarcinoma. Data were extracted using the International Classification of Diseases (ICD) 10th Edition Clinical Modification(CM) code C23. Variables analyzed included age, gender, hospital division, race, income quartile, and APRDRG mortality risk. Logistic regression was utilized to determine the predictors of mortality and develop a risk-scoring system. Descriptive statistics and Chi-squared tests assessed the relationship between variables and mortality, with p-values indicating significance. Results The study population had a mean age of 68.3 years, with 66.6% female patients. The overall mortality rate was 7.2%. Key predictors of mortality included higher All Patients Refined Diagnosis Related Groups (APR DRG) risk of mortality (p<0.001), age (p=0.04), and female gender (p=0.033). Race and hospital division were significantly associated with mortality (p<0.001 and p=0.015, respectively). A logistic regression model incorporating these variables yielded an area under the receiver operating characteristics curve of 0.82, indicating good discriminative ability. The developed risk score categorized patients into low, medium, and high-risk groups, with corresponding mortality rates of 0.88%, 5.28%, and 17.78%. Conclusion This study identified critical predictors of mortality in gallbladder adenocarcinoma patients, with APR DRG risk of mortality and age being the most significant. The developed risk score effectively stratifies patients by risk, potentially guiding clinical decision-making and improving patient outcomes.

Clinical characteristics and hearing loss etiology of cochlear implantees undergoing surgery in their teens, 20s, and 30s

PurposeThis study aimed to investigate the etiology of hearing loss, including genetic variants, in individuals who underwent cochlear implantation (CI) in their teens to thirties. It also sought to analyze post-CI speech performance and identify prognostic factors affecting CI outcomes in this age group.MethodsWe conducted a retrospective review of 421 cochlear implant patients at Seoul National University Bundang Hospital, focusing on 63 subjects aged 10–39 years who underwent their first CI by a single surgeon between July 2018 and June 2022. The study included audiologic evaluation, molecular genetic testing, and analysis of speech performance post-CI. Statistical analyses were performed using SPSS 25 and GraphPad Prism 7.ResultsAmong 63 participants (M:F, 24:39), nine underwent CI in their teens, 24 in their 20 s, and 30 in their 30 s. Most of them (40, 63.5%) had postlingual deafness. The study found that 65.2% (40/63) of subjects received a genetic diagnosis, with DFNB4 being the most common etiology (37.5%, 15/40). Post-CI speech evaluation showed an average sentence score of 80% across all subjects. Factors such as the onset of hearing loss, duration of deafness (DoD), and preoperative Speech Intelligibility Rating (SIR) significantly influenced CI outcomes. Notably, longer DoD was associated with poorer CI outcomes, but this did not affect individuals with postlingual hearing loss as much.ConclusionThe study concludes that in individuals aged 10–39 undergoing CI, the onset of hearing loss and preoperative SIR are critical predictors of postoperative outcomes. CI is recommended for those with postlingual hearing loss in this age group, irrespective of the DoD. The study highlights the importance of genetic factors especially DFNB4 in hearing loss etiology and underscores the value of the relatively easy-to-evaluate factor, preoperative SIR in predicting CI outcomes.

#1665 Mechanisms underlying long-term weight changes and their impact on all-cause mortality among chronic hemodialysis patients

Abstract Background and Aims Observational studies have demonstrated a significant association between long-term weight loss and weight gain and an increased risk of mortality among chronic hemodialysis patients. However, underlying mechanisms of these associations remain insufficiently explored. To address this knowledge gap, we conducted an in-depth analysis using a cohort of hemodialysis patients, benefiting from comprehensive baseline data, regular six-month evaluations, and an extended follow-up period. We employed advanced statistical techniques, including Lasso regression, to construct predictive models for long-term weight loss and gain. Furthermore, we conducted mediation analyses to elucidate whether weight change mediates the impact of major risk factors on all-cause mortality. Method This post-hoc analysis utilized data from participants in a previous randomized controlled trial conducted between 2006 and 2011, named as the Olmesartan clinical trial in Okinawan patients under the OKIDS (OCTOPUS) study. Subsequently, we tracked participants' mortality outcomes until July 2018. At the time of enrollment, we collected comprehensive baseline information, encompassing demographics, medical history, and laboratory data. Throughout the trial, participants' body weights were meticulously recorded every six months. Our analysis was restricted to patients who survived for at least two years post-enrollment, ensuring a minimum of five body weight measurements during the trial. Lasso regression was employed in training datasets (comprising 60% of participants) to identify crucial risk factors associated with long-term weight gain (&amp;gt;1 kg per year) or weight loss (&amp;lt;−1 kg per year) among chronic hemodialysis patients. These selected models were subsequently applied to paired validation datasets (comprising 40% of participants), and receiver operating characteristic (ROC) curves were used to calculate the area under the curve (AUC), aiding in the identification of key risk factors for long-term weight changes. Subsequently, we conducted mediation analyses to investigate whether weight change mediated the relationship between risk factors and all-cause mortality. Results Our analysis included 404 out of 461 OCTOPUS participants, with 60.9% being male, a mean age of 59.2 years (±11.7), and a mortality rate of 41.6%. The median follow-up period extended to 10.3 years. In the training datasets, Lasso models identified critical predictors for weight increase, including a history of diabetes, younger age, normal cardio-thoracic ratio (CTR) (&amp;lt;50% for males and &amp;lt;53% for females), and BMI &amp;lt;20. Conversely, predictors for weight decrease included BMI ≥20, serum sodium &amp;lt;135 mEq/L, serum albumin &amp;lt;3.5 g/dL, and older age. Weight increase demonstrated higher predictability (mean AUC of 0.59) compared to weight decrease (mean AUC of 0.55) in the validation datasets. Mediation analyses revealed that weight loss mediated 30% of the impact of older age (≥70 years old) on all-cause mortality (P = 0.068). Conclusion Our findings suggest that, among chronic hemodialysis patients, long-term weight increase is associated with a history of diabetes and younger age, while long-term weight loss is linked to BMI (≥20), hyponatremia, hypoalbuminemia, and older age. Notably, long-term weight loss appears to explain 30% of the increased risk of all-cause mortality associated with older age (≥70 years old).

Risk prediction models of depression in older adults with chronic diseases

BackgroundDetecting potential depression and identifying the critical predictors of depression among older adults with chronic diseases are essential for timely intervention and management of depression. Therefore, risk prediction models (RPMs) of depression in elderly people should be further explored. MethodsA total of 3959 respondents aged 60 years or over from the wave four survey of the China Health and Retired Longitudinal Study (CHARLS) were included in this study. We used five machine learning (ML) algorithms and three data balancing techniques to construct RPMs of depression and calculated feature importance scores to determine which features are essential to depression. ResultsThe prevalence of depression was 19.2 % among older Chinese adults with chronic diseases in the wave four survey. The random forest (RF) model was more accurate than the other models after balancing the data using the Synthetic Minority Oversampling Technique (SMOTE) algorithm, with an area under the receiver operating characteristic curve (AUROC) and area under the precision-recall curve (AUPRC) of 0.957 and 0.920, respectively, a balanced accuracy of 0.891 and a sensitivity of 0.875. Furthermore, we further identified several important predictors between male and female patients via constructed sex-stratified models. LimitationsFurther research on the clinical impact studies of our models and external validation are needed. ConclusionsAfter several techniques were used to address class imbalance issues, most RPMs achieved satisfactory accuracy in predicting depression among elderly people with chronic diseases. RPMs may thus become valuable screening tools for both older individuals and healthcare practitioners to assess the risk of depression.

Employing machine learning for enhanced abdominal fat prediction in cavitation post-treatment

This study investigates the application of cavitation in non-invasive abdominal fat reduction and body contouring, a topic of considerable interest in the medical and aesthetic fields. We explore the potential of cavitation to alter abdominal fat composition and delve into the optimization of fat prediction models using advanced hyperparameter optimization techniques, Hyperopt and Optuna. Our objective is to enhance the predictive accuracy of abdominal fat dynamics post-cavitation treatment. Employing a robust dataset with abdominal fat measurements and cavitation treatment parameters, we evaluate the efficacy of our approach through regression analysis. The performance of Hyperopt and Optuna regression models is assessed using metrics such as mean squared error, mean absolute error, and R-squared score. Our results reveal that both models exhibit strong predictive capabilities, with R-squared scores reaching 94.12% and 94.11% for post-treatment visceral fat, and 71.15% and 70.48% for post-treatment subcutaneous fat predictions, respectively. Additionally, we investigate feature selection techniques to pinpoint critical predictors within the fat prediction models. Techniques including F-value selection, mutual information, recursive feature elimination with logistic regression and random forests, variance thresholding, and feature importance evaluation are utilized. The analysis identifies key features such as BMI, waist circumference, and pretreatment fat levels as significant predictors of post-treatment fat outcomes. Our findings underscore the effectiveness of hyperparameter optimization in refining fat prediction models and offer valuable insights for the advancement of non-invasive fat reduction methods. This research holds important implications for both the scientific community and clinical practitioners, paving the way for improved treatment strategies in the realm of body contouring.

AeroSense: Sensing Aerosol Emissions from Indoor Human Activities

The types of human activities occupants are engaged in within indoor spaces significantly contribute to the spread of airborne diseases through emitting aerosol particles. Today, ubiquitous computing technologies can inform users of common atmosphere pollutants for indoor air quality. However, they remain uninformed of the rate of aerosol generated directly from human respiratory activities, a fundamental parameter impacting the risk of airborne transmission. In this paper, we present AeroSense, a novel privacy-preserving approach using audio sensing to accurately predict the rate of aerosol generated from detecting the kinds of human respiratory activities and determining the loudness of these activities. Our system adopts a privacy-first as a key design choice; thus, it only extracts audio features that cannot be reconstructed into human audible signals using two omnidirectional microphone arrays. We employ a combination of binary classifiers using the Random Forest algorithm to detect simultaneous occurrences of activities with an average recall of 85%. It determines the level of all detected activities by estimating the distance between the microphone and the activity source. This level estimation technique yields an average of 7.74% error. Additionally, we developed a lightweight mask detection classifier to detect mask-wearing, which yields a recall score of 75%. These intermediary outputs are critical predictors needed for AeroSense to estimate the amounts of aerosol generated from an active human source. Our model to predict aerosol is a Random Forest regression model, which yields 2.34 MSE and 0.73 r2 value. We demonstrate the accuracy of AeroSense by validating our results in a cleanroom setup and using advanced microbiological technology. We present results on the efficacy of AeroSense in natural settings through controlled and in-the-wild experiments. The ability to estimate aerosol emissions from detected human activities is part of a more extensive indoor air system integration, which can capture the rate of aerosol dissipation and inform users of airborne transmission risks in real time.