Medical decision support systems for diagnosing diseases based on ensemble learning algorithms

The easiness of reaching information through the internet and social media and the expansiveness of opportunities for searching, copying, and spreading data have caused some problems in identifying an author for a specific text. A text carries the characteristic features of the person who wrote it, and these features can be used to identify its author. For this study, we are offering a method that is based on an approach using ensemble learning algorithm (ELA) and genetic algorithm (GA) for author identification in Tur-kish texts. The raw data set, which includes 40 authors and 3269 texts, was created from Turkish news websites and analyzed in pre-processing step. After, syntactic and structural analyses were done on the data and, in total, 6 different data sets were created. Each of the data sets was subjected to the feature selection process by using GA and ELA approach together. Each of the obtained data sets from the previous step was classified by using the ELA's bagging method which contains 5 different classifiers, namely, Naive Bayes, K-Nearest Neighbor, Artificial Neural Networks, Support Vector Machine, and Decision Tree. After applying the aforementioned processes to the raw data, the author identification approach reached 89% accuracy. The combination of ELA and GA has a strong potential to identify the author of a text.

Accurate estimation of forest aboveground biomass is essential for the assessment of regional carbon cycle and the climate change in the terrestrial ecosystem. Currently, ensemble learning algorithms and cross-validation methods have been widely applied to estimate regional forest Above Ground Biomass (AGB). However, the effects of ensemble learning algorithms, validation methods, and their interactions on forest AGB estimation were rarely investigated. Based on Landsat 8 Operational Land Imager (OLI) imagery, Airborne Laser Scanning (ALS) data and China’s National Forest Continuous Inventory data, this study explored the effects of five ensemble learning algorithms, including Simple Averaging (SA), Weighted Averaging (WA), Stacked Generalization (SG), Random Forest (RF) and Extreme Gradient Boosting (XGBoost), and two validation approaches (i.e. 10-fold and leave-one-out cross-validation) on the AGB estimation of the Natural Secondary Forests (NSFs) in northeast China. The results revealed that the ensemble learning algorithms that combine heterogenous-based models (i.e. SA, WA, SG) generally produced higher accuracy than the base models (i.e. Decision Tree (DT), K-Nearest Neighbor (KNN), Support Vector Regression (SVR), Convolutional Neural Network (CNN)). Among all ensemble learning algorithms, the SG algorithm has the highest accuracy whereas the XGBoost algorithm has the lowest accuracy. Although prediction models considerably impact the accuracy of AGB estimation, the validation approach also plays a non-negligible role in AGB estimation. The leave-one-out cross-validation produced much higher accuracy than the 10-fold cross-validation using the same prediction model and tends to generate over-optimistic AGB estimates compared to 10-fold cross-validation, especially for the averaging and stacking ensemble learning algorithms (i.e. SA, WA, SG). This study highlights the potential challenges of applying a leave-one-out cross-validation approach and provides a scientific foundation for the feasibility of different ensemble learning algorithms and cross-validation approaches for accurate AGB estimation.

There has been a sharp increase in liver disease globally, and many people are dying without even knowing that they have it. As a result of its limited symptoms, it is extremely difficult to detect liver disease until the very last stage. In the event of early detection, patients can begin treatment earlier, thereby saving their lives. It has become increasingly popular to use ensemble learning algorithms since they perform better than traditional machine learning algorithms. In this context, this paper proposes a novel architecture based on ensemble learning and enhanced preprocessing to predict liver disease using the Indian Liver Patient Dataset (ILPD). Six ensemble learning algorithms are applied to the ILPD, and their results are compared to those obtained with existing studies. The proposed model uses several data preprocessing methods, such as data balancing, feature scaling, and feature selection, to improve the accuracy with appropriate imputations. Multivariate imputation is applied to fill in missing values. On skewed columns, log1p transformation was applied, along with standardization, min–max scaling, maximum absolute scaling, and robust scaling techniques. The selection of features is carried out based on several methods including univariate selection, feature importance, and correlation matrix. These enhanced preprocessed data are trained on Gradient boosting, XGBoost, Bagging, Random Forest, Extra Tree, and Stacking ensemble learning algorithms. The results of the six models were compared with each other, as well as with the models used in other research works. The proposed model using extra tree classifier and random forest, outperformed the other methods with the highest testing accuracy of 91.82% and 86.06%, respectively, portraying our method as a real-world solution for detecting liver disease.

BackgroundThe use of speech based data in the classification of Parkinson disease (PD) has been shown to provide an effect, non-invasive mode of classification in recent years. Thus, there has been an increased interest in speech pattern analysis methods applicable to Parkinsonism for building predictive tele-diagnosis and tele-monitoring models. One of the obstacles in optimizing classifications is to reduce noise within the collected speech samples, thus ensuring better classification accuracy and stability. While the currently used methods are effect, the ability to invoke instance selection has been seldomly examined.MethodsIn this study, a PD classification algorithm was proposed and examined that combines a multi-edit-nearest-neighbor (MENN) algorithm and an ensemble learning algorithm. First, the MENN algorithm is applied for selecting optimal training speech samples iteratively, thereby obtaining samples with high separability. Next, an ensemble learning algorithm, random forest (RF) or decorrelated neural network ensembles (DNNE), is used to generate trained samples from the collected training samples. Lastly, the trained ensemble learning algorithms are applied to the test samples for PD classification. This proposed method was examined using a more recently deposited public datasets and compared against other currently used algorithms for validation.ResultsExperimental results showed that the proposed algorithm obtained the highest degree of improved classification accuracy (29.44%) compared with the other algorithm that was examined. Furthermore, the MENN algorithm alone was found to improve classification accuracy by as much as 45.72%. Moreover, the proposed algorithm was found to exhibit a higher stability, particularly when combining the MENN and RF algorithms.ConclusionsThis study showed that the proposed method could improve PD classification when using speech data and can be applied to future studies seeking to improve PD classification methods.

With the continuous development of industry, accidental or unauthorized discharges of wastewater from manufacturing enterprises have increasingly severe impacts on the environment. Rapid and accurate identification of industrial wastewater sources is of great significance for enhancing regulatory oversight and environmental protection. In this study, we propose a novel approach for discriminating the sources of industrial wastewater by integrating data standardization with ensemble learning. High-performance liquid chromatography (HPLC) is employed to collect wastewater samples. To ensure data consistency and accuracy, a local stretching alignment method combined with Gaussian fitting is introduced for precise peak alignment in chromatographic data. We compare the modeling performance of two ensemble learning algorithms: Random Forest (RF) and Extreme Gradient Boosting (XGBoost). To further improve model accuracy, hyperparameter optimization is conducted using the Optuna framework. The models are systematically evaluated through five-fold cross-validation. Experimental results show that the optimized RF model achieves an average cross-validation accuracy of 97.87%, a test set accuracy of 98.28%, and an F1 score of 0.9799, the accuracy on the newly collected samples reached 95.08%, demonstrating excellent overall performance and a well-balanced trade-off between precision and recall. This approach provides an efficient and reliable analytical tool for tracing the sources of industrial wastewater.

The method of disturbing training data randomly to train individual classifiers has been widely applied in some ensemble learning methods such as Bagging and Boosting to achieve strong generalization ability, however, it seems something blind. In this paper, a new ensemble learning algorithm named GAVPEL is proposed. By using the hierarchy nature of the data set, GAVPEL leverages the generalized attribute value partitioning method to form an ensemble tree, called a generalized classifier hierarchy tree. While classifying, GAVPEL selects part of the individual classifiers based on attribute value and ensembles them with majority voting. Experiment results show that GAVPEL can efficiently improve generalization performance when compared with some popular ensemble learning algorithms.

During daily subway operation, station closure has large impact on subway system organization and has received increasing attention. This article proposes an anomaly detection method based on ensemble algorithms to determine the range of station closure influence on passenger flow. Firstly, Ensemble Algorithm I is developed to identify the stations with passenger flow volume anomaly and origin-destination (OD) pairs with volume anomaly. Secondly, Ensemble Algorithm II is proposed to identify the OD pairs with travel time anomaly. Then, the spatial variation in passenger flow caused by station closure, i.e. shift of passenger flow to neighboring stations and shift of path flow, is analyzed, and the spatial-temporal influence range of station closure is determined. A case study of the Beijing subway system is performed to illustrate the validity of the proposed method.Compared with sub algorithm of ensemble learning and KNN algorithm, Ensemble Algorithm I and II are more robust and have less misjudgment.

This study employs the framework of Web services in conjunction with Bayesian theorem and decision trees to construct a Web-services-based decision support system for medical diagnosis and treatment. The purpose is to help users (physicians) with issues pertinent to medical diagnosis and treatment decisions. Users through the system key in available prior probability and through computation based on Bayesian theorem obtain the diagnosis. The process helps users enhance the quality and efficiency of medical decisions, and the diagnosis can be transmitted to a decision-tree-based treatment decision support service component via XML to generate recommendation and analysis for treatment decisions. On the other hand, features of web services enable this medical decision support system to offer more service platforms than conventional one. Users will have access to the system whether they use Windows, Macintosh, Linux or any other platforms that connect with the Internet via HTTP. More important is the fact that after the system is completed all Internet service providers will be able to access the system as a software unit freely and quickly. This way, the goal of this study to provide medical decision support tools and speedily integrate heterogeneous medical decision support systems can be effectively attained.

Current simulation models considerably underestimate local-scale, short-duration extreme precipitation induced by tropical cyclones (TCs). This problem needs to be addressed to establish active response policies for TC-induced disasters. Taking Shanghai, a coastal megacity, as a study area and based on the observations from 192 meteorological stations in the city during 2005–2018, this study optimized the parameterized Tropical Cyclone Precipitation Model (TCPM) initially designed for TCs at the national scale (China) to the local or regional scales by using machine learning (ML) methods, including the random forest (RF), extreme gradient boosting (XGBoost), and ensemble learning (EL) algorithms. The TCPM-ML was applied for multiple temporal scale hazard assessment. The results show that: (1) The TCPM-ML not only improved TCPM performance for simulating hourly extreme precipitations, but also preserved the physical meaning of the results, contrary to ML methods; (2) Machine learning algorithms enhanced the TCPM ability to reproduce observations, although the hourly extreme precipitations remained slightly underestimated; (3) Best performance was obtained with the XGBoost or EL algorithms. Combining the strengths of both XGBoost and RF, the EL algorithm yielded the best overall performance. This study provides essential model support for TC disaster risk assessment and response at the local and regional scales in China.

With the rapid development of deep learning technology, more and more researchers apply it to gravitational wave (GW) data analysis. Previous studies focused on a single deep learning model. In this paper we design an ensemble algorithm combining a set of convolutional neural networks for GW signal recognition. The whole ensemble model consists of two subensemble models. Each subensemble model is also an ensemble model of deep learning. The two subensemble models treat data of Hanford and Livinston detectors, respectively. Proper voting scheme is adopted to combine the two subensemble models to form the whole ensemble model. We apply this ensemble model to all reported GW events in the first observation and second observation runs (O1/O2) by LIGO-VIRGO Scientific Collaboration. We find that the ensemble algorithm can clearly identify all binary black hole merger events except GW170818. We also apply the ensemble model to one month (August 2017) data of O2. No false trigger happens, although only O1 data are used for training. Our test results indicate that the ensemble learning algorithms can be used in real-time GW data analysis.

Effectively managing network congestion in 5G systems is crucial for ensuring seamless connectivity and optimal resource utilization. In this study, an operational scheme based on hotspot prediction for Virtual Small Cell (VSC) is presented, which aims to improve coverage, reduce delay and improve energy efficiency in 5G networks for congested locations. For this purpose, at first, using the location map of users, the location of hotspots is predicted by an Ensemble deep learning algorithm. Ensemble deep learning algorithm in this research combines the advantages of GRU and GRN networks and creates an efficient and accurate deep model that is more accurate than previous approaches that used single networks. Then, the information of hotspots is used to form VSCs and finally the adaptive beamforming operation is performed. To optimally allocate resources, genetic algorithm has been used so that the answer of the problem is not trapped in the local optimum. Simulation on the Telecom Italia dataset demonstrates a 10.13% RMSE, showing superior hotspot prediction accuracy compared to existing methods. Also, the numerical results of this study show that by using the hotspots prediction results, the energy efficiency of the system based on VSC operation and adaptive beamforming can be significantly improved.

Acute kidney injury (AKI) is a common postoperative complication among patients in the neurological intensive care unit (NICU), often resulting in poor prognosis and high mortality. In this retrospective cohort study, we established a model for predicting AKI following brain surgery based on an ensemble machine learning algorithm using data from 582 postoperative patients admitted to the NICU at the Dongyang People's Hospital from March 1, 2017, to January 31, 2020. Demographic, clinical, and intraoperative data were collected. Four machine learning algorithms (C5.0, support vector machine, Bayes, and XGBoost) were used to develop the ensemble algorithm. The AKI incidence in critically ill patients after brain surgery was 20.8%. Intraoperative blood pressure; postoperative oxygenation index; oxygen saturation; and creatinine, albumin, urea, and calcium levels were associated with the postoperative AKI occurrence. The area under the curve value for the ensembled model was 0.85. The accuracy, precision, specificity, recall, and balanced accuracy values were 0.81, 0.86, 0.44, 0.91, and 0.68, respectively, indicating good predictive ability. Ultimately, the models using perioperative variables exhibited good discriminatory ability for early prediction of postoperative AKI risk in patients admitted to the NICU. Thus, the ensemble machine learning algorithm may be a valuable tool for forecasting AKI.

To address the impact of critical-scale lunar soil particles on the drilling process, a parameter identification model for critical-scale lunar soil particles based on ensemble learning algorithms was proposed. Simulation analysis was conducted using Discrete element method (DEM) simulation software, and a central composite design was used to conduct experiments under various operating conditions to obtain the load characteristics of lunar drilling tools under different conditions. Taking model took critical-scale lunar soil particle size and offset position as main variables, torque data from the lunar drilling process were collected. By extracting the features of the experimental data were extracted. Based on this, the ensemble learning algorithm was introduced for the first time for parameter identification of critical-scale lunar soil particles, and a bivariate model was developed to simultaneously identify particle size and offset position. Experimental results show that the ensemble learning algorithm achieved high accuracy in predicting particle positions, with a mean squared error (MSE) of 0, and it also demonstrated good performance in particle size identification, with an MSE of 1.61. This model effectively solves the parameter identification challenge under the condition that particle size and location cannot be directly observed. These findings can provide a reference for developing identification model technologies for autonomous drilling and sampling.

The spread of the COVID-19 disease has prompted a need for immediate reaction by governments to curb the pandemic. Many countries have adopted different policies and studies are performed to understand the effect of each of the policies on the growth rate of the infected cases. In this article, the data about the policies taken by all countries at each date, and the effect of the policies on the growth rate of the pandemic are used to build a model of the pandemic’s behavior. The model takes as input a set of policies and predicts the growth rate of the pandemic. Then, a population-based multiobjective optimization algorithm is developed, which uses the model to search through the policy space and finds a set of policies that minimize the cost induced to the society due to the policies and the growth rate of the pandemic. Because of the complexity of the modeling problem and the uncertainty in measuring the growth rate of the pandemic via the models, an ensemble learning algorithm is proposed in this article to improve the performance of individual learning algorithms. The ensemble consists of ten learning algorithms and a metamodel algorithm that is built to predict the accuracy of each learning algorithm for a given data record. The metamodel is a set of support vector machine (SVM) algorithms that is used in the aggregation phase of the ensemble algorithm. Because there is uncertainty in measuring the growth rate via the models, a landscape smoothing operator is proposed in the optimization process, which aims at reducing uncertainty. The algorithm is tested on open access data online and experiments on the ensemble learning and the policy optimization algorithms are performed.

This volume is a result of the fruitful and vivid discussions during the MedDecSup'2012 International Workshop bringing together a relevant body of knowledge, and new developments in the increasingly important field of medical informatics. This carefully edited book presents new ideas aimed at the development of intelligent processing of various kinds of medical information and the perfection of the contemporary computer systems for medical decision support. The book presents advances of the medical information systems for intelligent archiving, processing, analysis and search-by-content which will improve the quality of the medical services for every patient and of the global healthcare system. The book combines in a synergistic way theoretical developments with the practicability of the approaches developed and presents the last developments and achievements in medical informatics to a broad range of readers: engineers, mathematicians, physicians, and PhD students.