Predictive Model For Early Detection Research Articles

RADIANTYOU: Personalized PCOS Prediction Partner

The abstract outlines a study aimed at addressing the challenge of detecting polycystic ovary syndrome (PCOS) in women, particularly in Asia where a significant portion of cases go undetected. PCOS is a complex hormonal disorder affecting reproductive health, characterized by irregular menstrual cycles, excessive androgen levels, and the presence of multiple cysts on the ovaries. The researchers employed machine learning techniques to develop a predictive model for early detection of PCOS. This approach leverages data on various physiological markers such as prolactin levels, blood pressure, thyroid-stimulating hormone (TSH), and pregnancy status. These factors are known to be associated with PCOS and can potentially serve as indicators for its presence. The abstract highlights the effectiveness of Random Forest, a machine learning algorithm, in accurately predicting PCOS with minimal computational time. This implies that the model developed by the researchers can reliably identify individuals at risk of PCOS, allowing for early intervention and management

Using Artificial Intelligence Algorithms to Predict Self-Reported Problem Gambling Among Online Casino Gamblers from Different Countries Using Account-Based Player Data

AbstractThe prevalence of online gambling and the potential for related harm necessitate predictive models for early detection of problem gambling. The present study expands upon prior research by incorporating a cross-country approach to predict self-reported problem gambling using player-tracking data in an online casino setting. Utilizing a secondary dataset comprising 1743 British, Canadian, and Spanish online casino gamblers (39% female; mean age = 42.4 years; 27.4% scoring 8 + on the Problem Gambling Severity Index), the present study examined the association between demographic, behavioral, and monetary intensity variables with self-reported problem gambling, employing a hierarchical logistic regression model. The study also tested the efficacy of five different machine learning models to predict self-reported problem gambling among online casino gamblers from different countries. The findings indicated that behavioral variables, such as taking self-exclusions, frequent in-session monetary depositing, and account depletion, were paramount in predicting self-reported problem gambling over monetary intensity variables. The study also demonstrated that while machine learning models can effectively predict problem gambling across different countries without country-specific training data, incorporating such data improved the overall model performance. This suggests that specific behavioral patterns are universal, yet nuanced differences across countries exist that can improve prediction models.

Multiple Disease Prediction Using Machine Learning

In various regions worldwide, the incidence of life-threatening diseases such as brain tumors, cataracts, pneumonia, and malaria remain alarmingly high, posing significant challenges to public health systems. Multiple factors contribute to the onset of these conditions, including genetic predispositions, environmental exposures, and lifestyle choices. This research endeavors to develop and evaluate a data-driven predictive model for early detection of brain tumors, cataracts, pneumonia, and malaria utilizing convolutional neural network (CNN) algorithms trained on medical imaging data. The proposed method integrates diverse patient parameters, including demographic information, medical history, and imaging features, to forecast the risk of developing these diseases. CNN architecture is chosen as the preferred model due to its ability to effectively analyze complex image data. Ethical considerations and privacy concerns regarding the handling of sensitive medical information are thoroughly examined, emphasizing the importance of responsible model development. Furthermore, the interpretability of CNN models is addressed to facilitate understanding among healthcare professionals and patients. The developed predictive system demonstrates promising accuracy and reliability, with CNN achieving notable performance metrics across all disease categories. A web-based platform is implemented to facilitate easy input and disease prediction based on medical images. The dataset utilized in this study is sourced from reputable medical institutions and research organizations, ensuring data quality and integrity. The findings of this research contribute valuable insights into the application of CNN-based predictive models in healthcare, offering a pathway for integrating such systems into clinical practice for early disease diagnosis and intervention

Predictive model for early detection of type 2 diabetes using patients' clinical symptoms, demographic features, and knowledge of diabetes.

With the global rise in type 2 diabetes, predictive modeling has become crucial for early detection, particularly in populations with low routine medical checkup profiles. This study aimed to develop a predictive model for type 2 diabetes using health check-up data focusing on clinical details, demographic features, biochemical markers, and diabetes knowledge. Data from 444 Nigerian patients were collected and analysed. We used 80% of this data set for training, and the remaining 20% for testing. Multivariable penalized logistic regression was employed to predict the disease onset, incorporating waist-hip ratio (WHR), triglycerides (TG), catalase, and atherogenic indices of plasma (AIP). The predictive model demonstrated high accuracy, with an area under the curve of 99% (95% CI = 97%-100%) for the training set and 94% (95% CI = 89%-99%) for the test set. Notably, an increase in WHR (adjusted odds ratio [AOR] = 70.35; 95% CI = 10.04-493.1, p-value < 0.001) and elevated AIP (AOR = 4.55; 95% CI = 1.48-13.95, p-value = 0.008) levels were significantly associated with a higher risk of type 2 diabetes, while higher catalase levels (AOR = 0.33; 95% CI = 0.22-0.49, p < 0.001) correlated with a decreased risk. In contrast, TG levels (AOR = 1.04; 95% CI = 0.40-2.71, p-value = 0.94) were not associated with the disease. This study emphasizes the importance of using distinct clinical and biochemical markers for early type 2 diabetes detection in Nigeria, reflecting global trends in diabetes modeling, and highlighting the need for context-specific methods. The development of a web application based on these results aims to facilitate the early identification of individuals at risk, potentially reducing health complications, and improving diabetes management strategies in diverse settings.

Deep Learning-Based Prediction of Alzheimer's Disease Using Microarray Gene Expression Data.

Alzheimer's disease is a genetically complex disorder, and microarray technology provides valuable insights into it. However, the high dimensionality of microarray datasets and small sample sizes pose challenges. Gene selection techniques have emerged as a promising solution to this challenge, potentially revolutionizing AD diagnosis. The study aims to investigate deep learning techniques, specifically neural networks, in predicting Alzheimer's disease using microarray gene expression data. The goal is to develop a reliable predictive model for early detection and diagnosis, potentially improving patient care and intervention strategies. This study employed gene selection techniques, including Singular Value Decomposition (SVD) and Principal Component Analysis (PCA), to pinpoint pertinent genes within microarray datasets. Leveraging deep learning principles, we harnessed a Convolutional Neural Network (CNN) as our classifier for Alzheimer's disease (AD) prediction. Our approach involved the utilization of a seven-layer CNN with diverse configurations to process the dataset. Empirical outcomes on the AD dataset underscored the effectiveness of the PCA-CNN model, yielding an accuracy of 96.60% and a loss of 0.3503. Likewise, the SVD-CNN model showcased remarkable accuracy, attaining 97.08% and a loss of 0.2466. These results accentuate the potential of our method for gene dimension reduction and classification accuracy enhancement by selecting a subset of pertinent genes. Integrating gene selection methodologies with deep learning architectures presents a promising framework for elevating AD prediction and promoting precision medicine in neurodegenerative disorders. Ongoing research endeavors aim to generalize this approach for diverse applications, explore alternative gene selection techniques, and investigate a variety of deep learning architectures.

Machine Learning-Based Diabetic Risk Prediction Model for Early Detection

Diabetes is a chronic disease that affects millions of people worldwide. Early detection and effective management of diabetes can significantly reduce the risk of complications and improve the quality of life of individuals with diabetes. In recent years, machine learning techniques have been applied to predict the risk of diabetes and to develop personalized treatment plans. In this study, we propose a machine learning-based diabetic risk prediction model for early detection and management. The proposed model uses various clinical and demographic variables such as age, gender, BMI, blood pressure, and fasting blood glucose levels to predict the risk of developing diabetes. We evaluated the performance of the proposed models using a dataset of patients with diabetes and non-diabetic individuals. Machine learning techniques including Logistic Regression, Support Vector Machine, K-Nearest Neighbors, and Random Forest are evaluated using the confusion matrices. The experimental results show that the Random Forest classifier achieved an accuracy of 80%, sensitivity of 82%, specificity of 80% in predicting the risk of diabetes. However, Increasing the accuracy rates of machine learning algorithms to 90% to 100% will be the challenging part of this study.

A Predictive Model for Early Detection of Oral Cancer via Adaboost Classification Technique

Oral cancer is a serious and potentially life-threatening disease that affects millions of people around the world. Early detection is critical for improving treatment outcomes and reducing mortality rates. This study aims to develop a predictive model for early detection of oral cancer using the AdaBoost classification technique. A dataset containing various risk factors associated with oral cancer was used to train and test the model. The results show that the AdaBoost algorithm was able to accurately classify oral cancer patients and non-cancer patients with high precision and recall rates. The developed predictive model could be used as a tool for early detection of oral cancer, thus improving patient outcomes and reducing mortality rates. The significance of oral cancer prediction and classification by improvised AdaBoost proposed technique produce potential to improve patient outcomes, facilitate early detection and treatment of oral cancer, and increase the efficiency and accuracy of the diagnostic process.

Study on the prediction model of atherosclerotic cardiovascular disease in the rural Xinjiang population based on survival analysis

PurposeWith the increase in aging and cardiovascular risk factors, the morbidity and mortality of atherosclerotic cardiovascular disease (ASCVD), represented by ischemic heart disease and stroke, continue to rise in China. For better prevention and intervention, relevant guidelines recommend using predictive models for early detection of ASCVD high-risk groups. Therefore, this study aims to establish a population ASCVD prediction model in rural areas of Xinjiang using survival analysis.MethodsBaseline cohort data were collected from September to December 2016 and followed up till June 2022. A total of 7975 residents (4054 males and 3920 females) aged 30–74 years were included in the analysis. The data set was divided according to different genders, and the training and test sets ratio was 7:3 for different genders. A Cox regression, Lasso-Cox regression, and random survival forest (RSF) model were established in the training set. The model parameters were determined by cross-validation and parameter tuning and then verified in the training set. Traditional ASCVD prediction models (Framingham and China-PAR models) were constructed in the test set. Different models' discrimination and calibration degrees were compared to find the optimal prediction model for this population according to different genders and further analyze the risk factors of ASCVD.ResultsAfter 5.79 years of follow-up, 873 ASCVD events with a cumulative incidence of 10.19% were found (7.57% in men and 14.44% in women). By comparing the discrimination and calibration degrees of each model, the RSF showed the best prediction performance in males and females (male: Area Under Curve (AUC) 0.791 (95%CI 0.767,0.813), C statistic 0.780 (95%CI 0.730,0.829), Brier Score (BS):0.060, female: AUC 0.759 (95%CI 0.734,0.783) C statistic was 0.737 (95%CI 0.702,0.771), BS:0.110). Age, systolic blood pressure (SBP), apolipoprotein B (APOB), Visceral Adiposity Index (VAI), hip circumference (HC), and plasma arteriosclerosis index (AIP) are important predictors of ASCVD in the rural population of Xinjiang.ConclusionThe performance of the ASCVD prediction model based on the RSF algorithm is better than that based on Cox regression, Lasso-Cox, and the traditional ASCVD prediction model in the rural population of Xinjiang.

Abstract 3024: Development of a plasma metabolomics prediction model for early detection of ovarian cancer using prospectively collected blood samples in two independent cohorts

Abstract Background: Ovarian cancer has poor survival due to more than 60% of patients being diagnosed at advanced stage. Therefore, discovery of novel, non-invasive early detection biomarkers has high potential to improve outcomes. Here, using prospectively collected blood samples, we developed a model using plasma metabolite levels to discriminate ovarian cancer cases from controls and applied it to an independent dataset. Method: We examined 251 lipid and lipid-related metabolites measured using a liquid chromatography tandem mass spectrometry method (Broad Institute, Cambridge, MA) in plasma collected up to three years prior to ovarian cancer diagnosis and controls matched on age, blood collection characteristics, and menopausal status at blood draw and diagnosis in the Prostate, Lung, Colorectal and Ovarian Cancer Screening Trial (PLCO; n=100, testing dataset) and the Nurses’ Health Studies (NHS; n=98, replication dataset). We used a paired t-test to identify metabolites with a significant difference (p&amp;lt;0.05) between ovarian cancer cases and controls. Then we used LASSO to identify metabolites that best discriminated ovarian cancer cases from controls in PLCO. We estimated the area under the receiver operating characteristic curve (AUC) and 95% confidence interval (CI) to assess model performance in discriminating ovarian cancer cases from controls when adding the selected metabolite score to a model based on CA125 using the clinical cutoff of 35U/mL, in PLCO and NHS. Results: Ten metabolites were significantly different between ovarian cancer cases and controls (p&amp;lt;0.05) in PLCO. LASSO selected 9 of the 10 metabolites into a prediction model including CA125 [i.e., C16:0 cholesteryl ester (CE), C22:6 CE, C30:0 phosphatidyl choline (PC), C32:1 PC, C40:10 PC, C38:2 phosphatidylethanolamine, C45:0 triglyceride, acetaminophen, 4-hydroxyhippurate]. In PLCO, adding a metabolite score derived from the 9 LASSO selected metabolites to a model with CA125 alone resulted in a significant (p&amp;lt;0.01) increase in AUC (95%CI) from 0.66(0.59-0.72) to 0.87(0.80-0.94). In NHS, adding the metabolite score to a model with CA125 alone also resulted in a significant (p=0.05) increase in AUC from 0.63(0.56-0.71) to 0.72(0.61-0.83). Conclusion: Using prospectively collected blood samples, we created a metabolite score which significantly increased the AUC compared to a model with CA125 alone and discriminated ovarian cancer cases from controls in the training dataset (PLCO). We replicated our findings in an independent test dataset (NHS). Further investigations assessing the performance of other statistical methods for replication (e.g., bootstrapping) and model building (e.g., random forest) are ongoing. These results suggest plasma metabolites represent promising novel early detection biomarkers for ovarian cancer. Citation Format: Oana A. Zeleznik, Julian Avila-Pacheco, Daniel W. Cramer, Britton Trabert, Clary B. Clish, Shelley Tworoger, Kathryn L. Terry, Naoko Sasamoto. Development of a plasma metabolomics prediction model for early detection of ovarian cancer using prospectively collected blood samples in two independent cohorts [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2023; Part 1 (Regular and Invited Abstracts); 2023 Apr 14-19; Orlando, FL. Philadelphia (PA): AACR; Cancer Res 2023;83(7_Suppl):Abstract nr 3024.

156P Development of a predictive model for early detection of lung cancer: SREAL-eLUNG study

156P Development of a predictive model for early detection of lung cancer: SREAL-eLUNG study

P168 Development of predictive model for early detection of Inflammatory Bowel Disease in Korea

Abstract Background Diagnostic delay in inflammatory bowel disease (IBD) was frequent and may be associated with poor outcomes. The aim of this study was to develop a predictive model for early diagnosis of IBD. Methods From March 2020 to January 2022, a 15-item Red Flags questionnaire was administered to all patients who visited outpatient clinic with gastrointestinal symptoms suspected of IBD. All patients underwent additional diagnostic tests to confirm IBD. We estimated a model that could predict the early diagnosis of IBD using questionnaire and laboratory test results. Results A total of 186 patients were enrolled in this study and 114 (61.2%) patients were finally confirmed with IBD. The logistic regression identified 4-item independently associated with a diagnosis of IBD. 1) Perianal fistula/abscess or perianal lesions (apart from hemorrhoids) (OR, 2.6; p=0.044). 2) Chronic abdominal pain/discomfort (&amp;gt;3 months) (OR, 0.3; p=0.013). 3) Rectal bleeding (OR, 7.4; p&amp;lt;0.001). 4) First-degree relative with confirmed IBD (OR, 12.0; p=0.033). A receiver operating characteristic curve was used to evaluate predictability of the model for diagnosis of IBD and each area under the curve was as follows. 1) Questionnaire only : AUC 0.831 (95% confidence interval; 0.766-0.896), 2) Questionnaire and serum laboratory tests including blood cell counts, erythrocyte sedimentation rate and C-reactive protein : AUC 0.885 (95% C.I.; 0.834-0.936), 3) Questionnaire, serum laboratory tests and fecal calprotectin : AUC 0.895 (95% C.I.; 0.845-0.944). This model confirmed that the predictive value was particularly excellent for early diagnosis of Crohn's disease. 1) Questionnaire only : AUC 0.891 (95% C.I.; 0.818-0.964), 2) Questionnaire and serum laboratory tests : AUC 0.960 (95% C.I.; 0.914-1.000), 3) Questionnaire, serum laboratory tests and fecal calprotectin : AUC 0.975 (95% C.I.; 0.944-1.000). Conclusion The predictive model for early diagnosis of IBD has a high predictive value. The model allows for early detection of IBD from non-IBD patients.

A narrative review of progress in the application of artificial intelligence in acute respiratory distress syndrome: subtypes and predictive models.

Acute respiratory distress syndrome (ARDS) occurs in different populations, and it is very challenging to manage heterogeneous patient groups. Artificial intelligence (AI) aids in interpreting complex data of patients with ARDS and can be used to detect adverse events as it can automatically capture complex relationships. This review aimed to explore the application and progress of AI in ARDS (e.g., subgroup classification of patients with ARDS via unsupervised clustering and supervised predictive models for early detection) and identify the current ARDS-related problems that can be solved using AI. This comprehensive and narrative review was performed to obtain information about the application of AI in ARDS and summarize its subtypes and predictive models. The current applications of AI and machine learning in ARDS include ARDS subgroup classification, diagnosis, and survival prediction. In this review, the current problems that should be addressed by AI in ARDS were identified, and our findings may serve as a useful reference for its translational use in the ARDS field. Owing to the discovery of hyper- and hypoinflammatory subtypes, individualized treatment of ARDS is possible, and diagnosis and survival prediction are essential in disease management and planning. However, prospective studies should clarify the reliability and generalizability of the results using AI and machine learning and performing bedside testing in larger populations to establish a more stable and time-resilient model. Therefore, a consensus on conducting and reporting machine learning studies in medicine should be urgently established.

Identification of early predictors for infected necrosis in acute pancreatitis

BackgroundIn acute pancreatitis, secondary infection of pancreatic necrosis is a complication that mostly necessitates interventional therapy. A reliable prediction of infected necrotizing pancreatitis would enable an early identification of patients at risk, which however, is not possible yet.MethodsThis study aims to identify parameters that are useful for the prediction of infected necrosis and to develop a prediction model for early detection. We conducted a retrospective analysis from the hospital information and reimbursement data system and screened 705 patients hospitalized with diagnosis of acute pancreatitis who underwent contrast-enhanced computed tomography and additional diagnostic puncture or drainage of necrotic collections. Both clinical and laboratory parameters were analyzed for an association with a microbiologically confirmed infected pancreatic necrosis. A prediction model was developed using a logistic regression analysis with stepwise inclusion of significant variables. The model quality was tested by receiver operating characteristics analysis and compared to single parameters and APACHE II score.ResultsWe identified a total of 89 patients with necrotizing pancreatitis, diagnosed by computed tomography, who additionally received biopsy or drainage. Out of these, 59 individuals had an infected necrosis. Eleven parameters showed a significant association with an infection including C-reactive protein, albumin, creatinine, and alcoholic etiology, which were independent variables in a predictive model. This model showed an area under the curve of 0.819, a sensitivity of 0.692 (95%-CI [0.547–0.809]), and a specificity of 0.840 (95%-CI [0.631–0.947]), outperforming single laboratory markers and APACHE II score. Even in cases of missing values predictability was reliable.ConclusionA model consisting of a few single blood parameters and etiology of pancreatitis might help for differentiation between infected and non-infected pancreatic necrosis and assist medical therapy in acute necrotizing pancreatitis.

Epidemiology of Antibiotic Resistant Pathogens in Pediatric Urinary Tract Infections as a Tool to Develop a Prediction Model for Early Detection of Drug-Specific Resistance.

Antibiotic resistance is an increasing problem, especially in children with urinary tract infections. Rates of drug-specific resistant pathogens were reported, and an easy prediction model to guide the clinical decision-making process for antibiotic treatment was proposed. Data on microbiological isolation from urinoculture, between January 2007–December 2018 at Istituto Gaslini, Italy, in patients aged <19 years were extracted. Logistic regression-based prediction scores were calculated. Discrimination was determined by the area under the receiver operating characteristic curve; calibration was assessed by the Hosmer and Lemeshow test and the Spiegelhalterz test. A total of 9449 bacterial strains were isolated in 6207 patients; 27.2% were <6 months old at the first episode. Enterobacteriales (Escherichia coli and other Enterobacteriales) accounted for 80.4% of all isolates. Amoxicillin-clavulanate (AMC) and cefixime (CFI) Enterobacteriales resistance was 32.8% and 13.7%, respectively, and remained quite stable among the different age groups. On the contrary, resistance to ciprofloxacin (CIP) (overall 9.6%) and cotrimoxazole (SXT) (overall 28%) increased with age. After multivariable analysis, resistance to AMC/CFI could be predicted by the following: sex; age at sampling; department of admission; previous number of bacterial pathogens isolated. Resistance to CIP/SXT could be predicted by the same factors, excluding sex. The models achieved very good calibration but moderate discrimination performance. Specific antibiotic resistance among Enterobacteriales could be predicted using the proposed scoring system to guide empirical antibiotic choice. Further studies are needed to validate this tool.

Developing predictive models for early detection of intervertebral disc degeneration risk

Intervertebral disc degeneration (IVDD) has been associated with causing chronic back pain. Lower back pain is a common cause of doctor’s visits and disability and affects 11.9% of the worldwide population. To the best of our knowledge, this work is the first to develop a tool for predicting the risk of IVDD using machine learning algorithms (MLAs) to aid in the earlier detection of the disease. MLAs utilized in this study include logistic regression, decision tree, artificial neural network, boosting, bagging, and random forest. The Synthetic Minority Oversampling Technique (SMOTE) method was performed on the unbalanced data set to up sample the minority class (patients with disc degeneration). The cluster-then-predict technique was also utilized to determine clusters in the data to be used as another risk factor or input variable into the classification algorithms. Results showed that the bagging algorithm developed the best-performing model. Results also demonstrated that the performance of the models improved after using the cluster-then-predict technique, which supports previous literature. Moreover, an improvement in the prediction of the minority class was also observed when the SMOTE method was applied. The finding from this study can be utilized to develop a predictive tool for the early detection of disc degeneration. This predictive tool can be used by doctors and physicians in the office with patients to closely monitor and assess disc degeneration risk.

A data mining approach using machine learning algorithms for early detection of low-performing students

PurposeThe purpose of the study is to build predictive models for early detection of low-performing students and examine the factors that influence massive open online courses students' performance.Design/methodology/approachFor the first step, the author performed exploratory data analysis to analyze the dataset. The process was then followed by data pre-processing and feature engineering (Step 2). Next, the author conducted data modelling and prediction (Step 3). Finally, the performance of the developed models was evaluated (Step 4).FindingsThe paper found that the decision trees algorithm outperformed other machine learning algorithms. The study also confirms the significant effect of the academic background and virtual learning environment (VLE) interactions feature categories to academic performance. The accuracy enhancement is 17.66% for decision trees classifier, 3.49% for logistic regression classifier and 4.89% for neural networks classifier. Based on the results of CorrelationAttributeEval technique with the use of a ranker search method, the author found that the assessment_score and sum_click features are more important among academic background and VLE interactions feature categories for the classification analysis in predicting students' academic performance.Originality/valueThe work meets the originality requirement.

Predictive model of stunting in the Central Andean region of Peru based on socioeconomic and agri-food determinants

ObjectivesA limitation in the design and monitoring of public health policies is the lack of conceptual models to explain their results. The objective of this study was to develop a predictive model of stunting in children under 5 years of age in the central Andean region of Peru, using socioeconomic and agro-productive predictors. Study designCross-sectional data of 380 families in 15 districts of the central region of Peru. WHO criteria were used to define stunting prediction model. MethodsAn explanatory and predictive study of stunting in children was carried out considering causality criteria through Chi-square tests and bivariate logistic regression. Family food production, maternal education, breastfeeding practices and others determinant related to rural zone conditions were considered as explanatory variables in stunting of children under 5 years old. Three exhaustive models for predicted the presence of stunting was developed. ResultsStunting percentage was 40.3. To Hosmer and Lemeshow test, the best fit was the model that considered the level of maternal education, timely consumption of colostrum, birth weight and guinea pig rearing, having high reliability (P ​< ​0.05). ConclusionsA predictive model for early detection of stunting risk in rural areas of the Andean region was developed based on simple and easily applied indicators. Effective policies are required to improve the feeding practices of pregnant women, increase breastfeeding and promote guinea pig raising for self-consumption and improve the nutritional status of children.

A new hybrid model to foretell thermal power efficiency from energy performance certificates at residential dwellings applying a Gaussian process regression

An energy performance certificate (EPC) provides information on the energy performance of an energy system. The objective of this research aimed at obtaining a predictive model for early detection of thermal power efficiency (TPE) for energy conversion and preservation in buildings. This article expounds a sound and solid nonparametric Bayesian technique known as Gaussian process regression (GPR) approach, based on a set of data collected from different dwellings in an oceanic climate. Firstly, this model introduces the relevance of each predictive variable on energy performance in residential buildings. The second result refers to the statement that we can predict successfully the TPE by using this model. A coefficient of determination equal to 0.9687 was thus established in order to predict the TPE from the observed data, using the GPR approach in combination with the differential evolution (DE) optimiser. The concordance between experimental observed data and the predicted data from the best-proposed novel hybrid DE/GPR-relied model demonstrated here the adequate efficiency of this innovative approach.

On the Splitting Dynamics of Meetup Social Groups

Groups in online social networks witness continuous evolution by loss of existing members and gain of new members. In this paper, we present a study of group split in Meetup, where a major fraction of members leave the existing group together and join a newly formed group. We identify pivotal group members, called splitters, playing key roles in group split by influencing the existing members to leave the group. We provide an in-depth analysis of the empirical data to reveal key motivating factors leading to a group split and its subsequent impact. Finally, we develop a prediction model for early detection of splitters, as well as the group members likely to be influenced by the splitter to leave the group.

Scale up predictive models for early detection of at-risk students: a feasibility study

PurposeThis study aims to investigate the feasibility of developing general predictive models for using the learning management system (LMS) data to predict student performances in various courses. The authors focused on examining three practical but important questions: are there a common set of student activity variables that predict student performance in different courses? Which machine-learning classifiers tend to perform consistently well across different courses? Can the authors develop a general model for use in multiple courses to predict student performance based on LMS data?Design/methodology/approachThree mandatory undergraduate courses with large class sizes were selected from three different faculties at a large Western Canadian University, namely, faculties of science, engineering and education. Course-specific models for these three courses were built and compared using data from two semesters, one for model building and the other for generalizability testing.FindingsThe investigation has led the authors to conclude that it is not desirable to develop a general model in predicting course failure across variable courses. However, for the science course, the predictive model, which was built on data from one semester, was able to identify about 70% of students who failed the course and 70% of students who passed the course in another semester with only LMS data extracted from the first four weeks.Originality/valueThe results of this study are promising as they show the usability of LMS for early prediction of student course failure, which has the potential to provide students with timely feedback and support in higher education institutions.