Narrow Results

This study aims to develop a safe and effective multi-parameter MRI-based molecular subtype prediction model for breast cancer, emphasizing the advantages of this multi-parameter approach over single-parameter models. This study retrospectively collected and organized MRI data from 318 breast cancer patients at Liaoning Provincial Cancer Hospital, including dynamic contrast-enhanced MRI (DCE-MRI, abbreviated as DCE), diffusion weighted MRI (DWI-MRI, abbreviated as DWI), T1-weighted MRI (T1WI-MRI, abbreviated as T1WI), and T2-weighted MRI (T2WI-MRI, abbreviated as T2WI). The dataset includes 57 cases of Luminal A type, 162 cases of Luminal B type, 46 cases of human epidermal growth factor receptor-2 (HER-2) overexpression type, and 53 cases of triple-negative type. Predictive models were established using four single-parameter MRI methods and seven multi-parametric MRI methods, employing quantitative feature extraction. Model performance was evaluated through the area under the curve (AUC) and balanced accuracy (BA). In the single-parameter MRI models, the T2WI-MRI model demonstrated the best predictive performance for four-class classification, with average AUC and BA values of 0.794 and 0.518, respectively. In contrast, the multi-parameter model combining DWI+T2WI exhibited even better performance, with these metrics reaching 0.823 and 0.565, respectively. The multi-parameter feature fusion model for breast cancer molecular subtypes prediction, utilizing DWI+T2WI, exhibited superior BA and AUC values compared to models based solely on single-parameter MRI. It showed enhanced predictive capabilities for Luminal A, Luminal B, HER-2 overexpression, and triple-negative subtypes. Therefore, the multi-parameter MRI-based model offers improved predictive performance over single-parameter models.

Head-mounted tablets (HMTs), a type of augmented reality (AR) wearable device that is worn on the head like glasses, have gained vast attention in the manufacturing industry as they enable workers to receive hands-free support. For emerging technologies, it could be useful to predict their acceptance among potential users. Hence, various researchers have utilized the technology acceptance model (TAM) to forecast such acceptance, in the past decade also including HMTs and other AR smart glasses. In this research, an exploratory model is developed to investigate which factors allow to predict a future acceptance of HMTs for training new employees on the shop floor. After collecting 46 survey responses and applying a partial least squares structural equation modeling (PLS-SEM) approach, the findings indicate that the protection of personal data and satisfaction with the technology significantly influence the usage of HMTs among new employees. Furthermore, a significant effect was found for experience and ease of use.

Earnings management poses a critical challenge in corporate finance, as firms often manipulate financial statements to achieve specific targets, potentially misleading stakeholders. Traditional detection techniques, such as discretionary accrual models, face limitations in identifying the complex, nonlinear patterns of earnings manipulation. This research utilizes tree-based machine learning models — Decision Trees, Random Forests, and Gradient Boosting Machines (GBM) — to forecast earnings management in firms listed on Vietnamese stock exchanges, including the Ho Chi Minh City Stock Exchange (HOSE), Hanoi Stock Exchange (HNX), and Unlisted Public Company Market (UPCoM). The study analyzes data from 1,652 firms, covering the period from 2008 to 2023, resulting in 17,215 observations. Following rigorous data preprocessing to remove errors and outliers, the performance of the models was assessed based on their ability to predict earnings management, as indicated by discretionary accruals. The findings demonstrate that GBM surpasses the other models in key performance metrics, such as accuracy, precision, recall, and F1 score, establishing it as the most effective tool for detecting earnings manipulation. Furthermore, the study identifies Operating Cash Flow (OCF) as the most significant predictor, with Return on Assets (ROA) and firm size also playing vital roles. These results contribute to the expanding body of research on machine learning in financial analysis and provide valuable insights for financial analysts, auditors, corporate governance professionals, and regulators in improving the detection and prevention of earnings management.

This paper presents general approaches for addressing some of the most important issues in predictive computational oncology concerned with developing classes of predictive models of tumor growth. First, the process of developing mathematical models of vascular tumors evolving in the complex, heterogeneous, macroenvironment of living tissue; second, the selection of the most plausible models among these classes, given relevant observational data; third, the statistical calibration and validation of models in these classes, and finally, the prediction of key Quantities of Interest (QOIs) relevant to patient survival and the effect of various therapies. The most challenging aspects of this endeavor is that all of these issues often involve confounding uncertainties: in observational data, in model parameters, in model selection, and in the features targeted in the prediction. Our approach can be referred to as “model agnostic” in that no single model is advocated; rather, a general approach that explores powerful mixture-theory representations of tissue behavior while accounting for a range of relevant biological factors is presented, which leads to many potentially predictive models. Then representative classes are identified which provide a starting point for the implementation of OPAL, the Occam Plausibility Algorithm (OPAL) which enables the modeler to select the most plausible models (for given data) and to determine if the model is a valid tool for predicting tumor growth and morphology (in vivo). All of these approaches account for uncertainties in the model, the observational data, the model parameters, and the target QOI. We demonstrate these processes by comparing a list of models for tumor growth, including reaction–diffusion models, phase-fields models, and models with and without mechanical deformation effects, for glioma growth measured in murine experiments. Examples are provided that exhibit quite acceptable predictions of tumor growth in laboratory animals while demonstrating successful implementations of OPAL.

Background and objective: Chronic kidney disease (CKD) is one of the deadly diseases that can affect a lot of vital organs in the human body such as heart, liver, and lungs. Many individuals might be at early stage of kidney disease and not have any signs, which might lead to a sudden death. Previous research showed that early prediction of CKD is very important in the medical field for physicians’ decision-making and patients’ health and life. To this end, constructing an efficient prediction system for CKD, which is the goal of this paper, often reduces medical errors and overall healthcare cost. Methods: Classification and association rule mining techniques were integrated and utilised to construct an efficient system for predicting and diagnosing CKD and its causes using weka and SPSS as platform environments. In particular, five classification algorithms, namely, naive Bayes, decision tree, support vector machine, K-nearest neighbour, and JRip were used to achieve the research goal. In addition, Apriori algorithm was used to discover strong relationship rules between attributes. The experiments were conducted on real medical dataset collected from hospitals and patient monitoring systems. Results: The experiments achieved high accuracy of 98.50% for K-nearest neighbour (KNN) classifier and achieved 96.00% when using classier based on association rule (JRip). Conclusions: We conclude by showing that applying integrative approach by combining classification algorithms and association rule mining can significantly improve the classification accuracy and be more useful for CKD prediction. This research has also several theoretical and practical implications for the medical field and healthcare industry.

Countries have traditionally relied on various innovation measures to plan national-wise strategies and analysis, which hinders their ability to take proactive actions beforehand. This study introduces an advanced model for predicting national innovativeness using machine learning techniques. Utilizing a comprehensive dataset that includes 1,410 observation points and 20 variables from 141 countries spanning from 2011 to 2020, the data were sourced from the World Bank Open Data, Global Entrepreneurship Monitor (GEM) and Global Innovation Index (GII). The proposed model employs machine learning algorithms such as regression tree, random forest, support vector machine and extreme gradient boosting (XGBoost), and benchmarks their performance against the traditional linear regression analysis method. The findings reveal that all five machine learning models significantly outperform the traditional linear regression model in terms of correlation, root mean square error (RMSE) and mean absolute error (MAE), with XGBoost demonstrating superior performance. The XGBoost analysis highlights university and industry research collaboration, knowledge workers and logistics performance as the most critical variables influencing national innovativeness. This research not only presents a robust predictive model leveraging machine learning but also contributes to theoretical advancements by uncovering previously overlooked variables, offering new insights and practical implications for enhancing national innovation strategies.

In this study, the ultra-low cycle fatigue (ULCF) behavior of a high-strength-ductile steel AerMet100 exposed to repeated high strain rate impact loadings is investigated. Three types of coupon-level experiments were performed, in which a three-point bending (TPB) specimen with a through-thickness notch was employed for multi-impact test. A special ratchet effect associated with complex stress state, dynamic impact loading and other physical mechanisms was observed through measured principal strain variations with a specific decay rate at the notch root surface. An improved ULCF predictive model based on the continuum damage mechanics was developed to quantify the relationship between the fatigue damage and the input of localized impact energy to the notch root. The model expressed in terms of damage growth rate introduces a new exponential term for better predictive accuracy and reduced number of nonlinear dynamic response analysis. As a computational efficient tool, the proposed model can predict impact fatigue life in acceptable timeframe for multiple critical locations in a complex engineering component.

This chapter is on the Decision Tree (DT) algorithm. Decision trees are predictive models that make use of a set of bipartite rules that lead to a desired output being obtained. It can be used for categorical or continuous output values. Random forests are an ensemble learning method for classification and regression, among others, that operates by constructing multiple decision trees at training time and outputting the class that is the mode of the classes or mean prediction. We apply the algorithms to the missing date estimation problem.

Human glycaemia regulation is a complex phenomenon in which factors of different nature occur, for instance: glucose level and its variation, physical activity, morphology, time and composition of the meals, etc. In case of pancreas deficiency, diabetics have to control their glucose level thanks to injections of insulin, using empirical rules to determine the infusion rate. We propose a predictive fuzzy model of glycaemic variations, as a part of an automatic control system for diabetics. An associated learning procedure makes it possible to deal with interpersonal variations. This work about the treatment of diabetes is achieved in cooperation with the University Hospital Center of Rennes.