Showing papers on "Decision tree model published in 2022"

Ontology-based decision tree model for prediction of cardiovascular disease

Abstract: Nowadays, cardiovascular diseases (CVD) are one of the most critical reasons for death. Thus, CVD prediction is a crucial challenge in the field of clinical data analysis. Researchers are using a variety of statistical and machine learning methods to assess immense amounts of complex medical data, to help doctors predict heart disease. In this paper, we proposed a new approach to predict CVD using ML techniques and Ontology to build an efficient ontology-based model able to predict accurately the presence of cardiac disease and establish an early diagnosis. the approach consists of extracting rules from the Decision Tree algorithm that differentiate the patients with or without cardiovascular disease then implementing these rules in the ontology reasoner using Semantic Web Rule Language (SWRL). The ontology model result reach high classification accuracy of 75% compared to the decision tree model. The approach can be employed in the medical field for the prediction of cardiovascular diseases.

Predicting Disease-Specific Survival for Patients With Primary Cholangiocarcinoma Undergoing Curative Resection by Using a Decision Tree Model

Abstract: Background The aim of this study was to derive and validate a decision tree model to predict disease-specific survival after curative resection for primary cholangiocarcinoma (CCA). Method Twenty-one clinical characteristics were collected from 482 patients after curative resection for primary CCA. A total of 289 patients were randomly allocated into a training cohort and 193 were randomly allocated into a validation cohort. We built three decision tree models based on 5, 12, and 21 variables, respectively. Area under curve (AUC), sensitivity, and specificity were used for comparison of the 0.5-, 1-, and 3-year decision tree models and regression models. AUC and decision curve analysis (DCA) were used to determine the predictive performances of the 0.5-, 1-, and 3-year decision tree models and AJCC TNM stage models. Results According to the fitting degree and the computational cost, the decision tree model derived from 12 variables displayed superior predictive efficacy to the other two models, with an accuracy of 0.938 in the training cohort and 0.751 in the validation cohort. Maximum tumor size, resection margin, lymph node status, histological differentiation, TB level, ALBI, AKP, AAPR, ALT, γ-GT, CA19-9, and Child-Pugh grade were involved in the model. The performances of 0.5-, 1-, and 3-year decision tree models were better than those of conventional models and AJCC TNM stage models. Conclusion We developed a decision tree model to predict outcomes for CCA undergoing curative resection. The present decision tree model outperformed other clinical models, facilitating individual decision-making of adjuvant therapy after curative resection.

Deriving a tree growth model from any existing stand growth model

Abstract: In this study, a new method was developed to derive a tree survival and diameter growth model from any existing stand-level model, without the need for individual-tree growth data. Predictions from the derived tree model are constrained to match the number of trees and the basal area per hectare as outputted by the stand model. The tree models derived from three different stand models were evaluated against a tree model, in both unadjusted and disaggregated forms. For the same stand-level model, the derived tree model outperformed its counterpart, the disaggregated tree model. Furthermore, except for one stand model with poor performance, the tree models derived from the remaining two stand models delivered results comparable to those obtained from the unadjusted tree model. The tree model derived from one stand model even performed slightly better than the unadjusted tree model. This result is significant because the coefficients of the unadjusted and disaggregated tree models had to be estimated from tree-level growth data, whereas the derived tree model required no tree growth data at all. The methodology presented in this study should be applicable when there is no ingrowth or recruitment of new trees.

Identification Method of Influencing Factors of Hospital Catering Service Satisfaction Based on Decision Tree Algorithm

Abstract: Entering the 21st century, material abundance has been greatly enriched, and living standards have been continuously improved. Now society is gradually moving towards the era of experience economy. From the perspective of experience economy, patients' demands for hospitals are not only the satisfaction of medical technology, but their catering consumption also has begun to change to the pursuit of higher requirements. Decision tree algorithm is a kind of data mining algorithm. Data mining technology is a young technology for data analysis. It can simulate mathematical models or algorithms through data analysis, which greatly improves the prediction accuracy. This paper aims to study how to identify the influencing factors of hospital catering service satisfaction, and proposes the application of decision tree algorithm to the hospital catering service satisfaction research, and proposes decision tree-related algorithms, such as ID3, C4.5, and C5.0. Based on the analysis of patients' satisfaction with the hospital catering service in a certain hospital, the results of the model study based on the decision tree algorithm show that the risk estimation value of the training set is 0.064, and the total correct percentage is 93.6%. The risk estimate for the test set was 0.065, for a total correct percentage of 93.5%. It can be seen that the effect of the model is good and can be effectively predicted.

Decision tree model predicts live birth after surgery for moderate-to-severe intrauterine adhesions

Abstract: After treatment of intrauterine adhesions, the rate of re-adhesion is high and the pregnancy outcome unpredictable and unsatisfactory. This study established and verified a decision tree predictive model of live birth in patients after surgery for moderate-to-severe intrauterine adhesions (IUAs).A retrospective observational study initially comprised 394 patients with moderate-to-severe IUAs diagnosed via hysteroscopy. The patients underwent hysteroscopic adhesiolysis from January 2013 to January 2017, in a university-affiliated hospital. Follow-ups to determine the rate of live birth were conducted by telephone for at least the first postoperative year. A classification and regression tree algorithm was applied to establish a decision tree model of live birth after surgery.Within the final population of 374 patients, the total live birth rate after treatment was 29.7%. The accuracy of the model was 83.8%, and the area under the receiver operating characteristic curve (AUC) was 0.870 (95% CI 7.699-0.989). The root node variable was postoperative menstrual pattern. The predictive accuracy of the multivariate logistic regression model was 70.3%, and the AUC was 0.835 (95% CI 0.667-0.962).The decision tree predictive model is useful for predicting live birth after surgery for IUAs; postoperative menstrual pattern is a key factor in the model. This model will help clinicians make appropriate clinical decisions during patient consultations.

Air Combat Decision Based on Genetic Fuzzy Tree

Abstract: To solve the issue that the accurate model of complex air combat process is difficult to establish and air combat is high real-time, an air combat decision-making based on genetic fuzzy tree is proposed. Taking a dual cooperative silent attack scenario as an example, the corresponding cascade fuzzy tree model is established, the parameter coding method of the fuzzy tree model is studied, and simulation verification is performed in the set air combat environment. The simulation results show that the method of genetic fuzzy tree is effective for air combat decision-making.

A decision support system for diagnosis of hepatitis disease using an integrated rough set and fish swarm algorithm

Abstract: Healthcare data analysis is a primary concern. It leads to multiple levels of knowledge extraction for decision support systems because of the presence of uncertainties. Therefore, this paper integrates the rough set and artificial fish swarm optimization to develop a decision support system that handles uncertainties present in an information system. In the initial stage, the artificial fish swarm—the rough set procedure is implemented in finding vital features. Further, in the second phase, the rough set uses these vital features to develop a decision support system. The above model is analyzed over hepatitis B disease. The proposed model attains an accuracy of 92.4%. Further, the proposed model is compared with the classical rough set, decision tree, and artificial fish swarm‐decision tree model. The accuracy obtained is 88.9%, 83.3%, and 90.8%, respectively. The proposed model has a greater accuracy of 3.5% than the rough set model and has a greater accuracy of 9.1% than the decision tree model. Simultaneously, the proposed model has 1.6% greater accuracy than the artificial fish swarm‐decision tree model. Therefore, it is believed that the projected decision support system may be used to prevent and detect hepatitis B diseases.

Long-Term Mechanism and Fitness Impact of Rural Sports Precision Poverty Alleviation Based on Improved Decision Tree

Abstract: In the process of the development of sports resources, the first step is to strengthen mechanism construction, including the government and the market “- poor areas” tripartite coordination mechanism, the development of sports resource development policy supervision mechanism, sports resource development precision poverty alleviation mechanism, legal protection mechanism, and accountability mechanism. The establishment of the fitness model recommendation model is realized. The fitness pattern recommendation model itself is a multibranch decision tree model. Therefore, as long as it is a variety of fitness methods, according to different classification, in the fitness database to add the corresponding classification, this is helpful to build a multibranch decision tree model.

COVID-19 Detection Using CNN and Decision Tree

Abstract: Currently, the outbreak of COVID-19 is a global challenge to be addressed. To address this issue, this paper presents a novel method to determine pneumonia and COVID-19 infection in lungs caused by the virus. This method is assisted by a decision tree algorithm based on the data collected during the initial breakout in china. The database of patient symptoms is used primarily to detect pneumonia infection and uses a sequential convolutional neural network to further identify COVID-19 infection. The proposed system is implemented using open-source resources and is optimal for use. Due to this, the execution of the proposed work can be achieved with much ease and high speed. The proposed convolutional neural network model, initiated after the decision tree model offered detection accuracy of 92.81%.

An Analysis of Global House Price using Decision Tree Model

Abstract: 본 연구는 머신러닝(Machine Learning)의 일종인 의사결정트리(Decision Tree) 모형을 이용하여 글로벌 부동산 가격하락과 관련성이 높은 변수를 분석하였다. 분석기간은 1976년부터 2018년까지이며, 58개국 불균형 국가패널자료(연도별)를 사용하여 3단계 분석을 수행하였다. 분석결과 글로벌 부동산 가격하락 이벤트와 연관성이 높은 중요도 순서 상위 15개 설명변수를 도출하였다. 주요 15개 변수에 대한 글로벌 부동산 가격하락 이벤트 기간 평균과 2016년 주요국의 해당 지표들을 비교한 결과, 한국은 2016년 전후 부동산 가격의 급격한 조정 가능성이 다른 국가와 비교해 상대적으로 낮았던 것을 확인할 수 있었다. 본 연구가 국제비교를 통한 단기부동산 가격 전망에 유용한 참고자료가 될 수 있을 것으로 기대한다.

Trustable Decision Tree Model using Else-Tree Classifier

Abstract: Abstract With advances in machine learning and artificial intelligence, learning models have been used in many decision-making and classification applications. The nature of critical applications, which require a high level of trust in the prediction results, has motivated researchers to study classification algorithms that would minimize misclassification errors. In our study, we have developed the {\em trustable machine learning methodology} that allows the classification model to learn its limitations by rejecting the decision on cases likely yield to misclassificationsand hence produce highly confident outputs. This paper presents our trustable decision tree model through the development of the {\em Else-Tree} classifier algorithm. In contrast to the traditional decision tree models, which use a measurement of impurity to build the tree and decide class labels based on the majority of data samples at the leaf nodes, Else-Tree analyzes homogeneous regions of training data with similar attribute values and the same class label. After identifying the longest or most populated contiguous range per class, a decision node is created for that class, and the rest of the ranges are fed into the else branch to continue building the tree model. The Else-Tree model does not necessarily assign a class for conflicting or doubtful samples. Instead, it has an else-leaf node, led by the last else branch, to determine rejected or undecided data. The Else-Tree classifier has been evaluated and compared with other models through multiple datasets. The results show that Else-Tree can minimize the rate of misclassification.

Comparative Analysis of Decision Support Models for Faculty Performance Evaluation

Abstract: The faculty is an important asset to guarantee that an academic institution operates as expected. Performance evaluation is an important tool used to assess faculty efficiency in the workplace. The study focuses on the comparison of three different decision support models identifying the suited model to be used in the proposed faculty performance evaluation framework. A local community college provided the historical data and documents to the researchers. The researcher selected three suitable decision support models and used Weka for data analysis. The results of preliminary data analysis examined shows that the identified faculty performance evaluation criterion includes 75% of the National Budget Circular (NBC) criteria; 15% IPCR and 10% College Involvement and Participation (CIP). The comparative analysis criteria used in analyzing the decision tree would be utilized as the model in the knowledge-based decision support system. With regards to build time, both Random Tree and REP Tree resulted in 0 seconds while M5P has 0.23 seconds. Build time would affect the model efficiency in terms of resources needed for execution. REP Tree has the highest size of tree produced in the model. Since all the decision tree models have positive coefficients, it indicates that when the value of one variable increases, the value of the other variable also tends to increase. The results of comparing the decision support models in this study had identified potential suitability of a model in faculty performance evaluation. Furthermore, policies in the locale could be based on the logical decision trees presented in this study.

Selecting of Pet Adopters using C4.5 Decision Tree Model Algorithm

Abstract: This study aims to select pet adopters based from the model created from the C4.5 decision tree algorithm to address the proper way for adoption of a pet through online examination. This study uses the method of the C4.5 algorithm by finding the highest gain value to create a decision tree model and generate a decision rules that will apply to a website for decision support if the adopter is qualified or not qualified to adopt. A confusion matrix is used to calculate the accuracy of the C4.5 decision tree algorithm. The information in the confusion matrix is needed to calculate the classification model's performance. This can be done by using performance metrics for the C4.5 algorithm that is based on accuracy, sensitivity, and specificity. The total number of datasets is 1800 which consists of 15 attributes, 1500 for training which consists of 100 instances, and 300 for testing the accuracy is consist of 20 instances. The results on testing the accuracy of the C4.5 decision tree algorithm using confusion matrix is 85%, sensitivity is 84.6% and specificity is 100%. Based on the result of testing the accuracy of the algorithm using the 20 dataset that results with the accuracy value of 85%, sensitivity is 84.6% and specificity is 100%. These results prove that generated model using C4.5 decision tree algorithm is efficient in selecting of pet adopters.

A Prediction Model of Hospitalized Medical Service Behavior Using Decision Tree Analysis: Using Korea Medical Service Patient Experience Survey

Abstract: 코로나19는 우리 사회 전반에 큰 변화를 가져왔으며 특히 보건의료 분야의 의료이용에 영향을 가져왔다. 본 연구는 2020 의료서비스 경험조사 원시자료를 이용하여 치료를 목적으로 입원 의료서비스 경험이 있는 497명을 대상으로 입원 의료서비스 경험 실태를 파악하고 행동예측 모형을 개발하고자 한다. 연구 결과 입원 의료서비스 행동의도 중 치료 결과 만족도는 신체노출보호와 시설의 안락함에 의해 결정되었으며, 전반적인 만족도와 의료기관 추천의향은 담당 의사의 필요시 응대에 의해 결정되는 것으로 조사되었다. 이러한 결과를 종합적으로 정리해보면, 의료기관에서는 고객의 치료 결과 만족 향상을 위하여 진료나 검사 시 신체 노출을 최소화 할 수 있는 방안과 함께 의료진의 배려가 필요하며, 입원 의료서비스 이용 고객이 의료기관 시설환경에 안락함과 편안함을 느낄 수 있도록 하는 노력이 요구된다. 또한 입원 의료서비스 이용 시 행정부서 및 담당 의사와의 소통과 상호작용이 중요한 결정요인라 할 수 있다. 본 연구는 입원 의료서비스 이용자를 대상으로 행동의도를 예측함으로써 정부의 보건의료 정책방향과 의료기관의 효율적인 관리방안에 대하여 시사점을 제공하고자 한다.

Research on an improved prediction model based on decision tree algorithm

Abstract: In this research, we collect and complete a data set of freshmen registration, and use the machine learning algorithm of decision tree to predict it. Our goal is to use this algorithm to verify whether the enrollment of freshmen can be predicted. Then we adopt the pruning scheme to optimize the decision tree. One is to prune the number of layers of the tree, and the other is to prune the number of samples on the leaf nodes. Then, we present the confusion matrix and F1 score to assess the impact of machine learning. The exploratory comes about to appear that the pruning scheme has greatly improved our prediction model.

Performance Analysis of Air Pollution Classification Prediction Map with Decision Tree and ANN

Abstract: Jakarta is a city in Indonesia that has a high population density that must pay attention to its health condition. Good air quality provides positive benefits to support public health so that they can be more productive at work and create fresh and healthy air. This study uses Machine Learning to classify air based on certain attributes. Then, the development of a prediction model based on time data is designed to produce a predictive map of air pollution in Jakarta area for the next 3 years. The methods applied are Decision Tree and Artificial Neural Networks. As a result, the Decision Tree and Artificial Neural Network models show very good accuracy for predictions from 2024 to 2026. The Decision Tree and Artificial Neural Network models get an accuracy of 98% and 94%. In 2025 the Decision Tree and Artificial Neural Network models get 99% and 93% accuracy. In 2026 the Decision Tree and Artificial Neural Network models get an accuracy of 94% and 93% which can be seen from the Decision Tree model which is superior to the Artificial Neural Network with a difference of 1 - 6%.

Trustable Decision Tree Model using Else-Tree Classifier

Abstract: Abstract With advances in machine learning and artificial intelligence, learning models have been used in many decision-making and classification applications. The nature of critical applications, which require a high level of trust in the prediction results, has motivated researchers to study classification algorithms that would minimize misclassification errors. In our study, we have developed the {\em trustable machine learning methodology} that allows the classification model to learn its limitations by rejecting the decision on cases likely yield to misclassificationsand hence produce highly confident outputs. This paper presents our trustable decision tree model through the development of the {\em Else-Tree} classifier algorithm. In contrast to the traditional decision tree models, which use a measurement of impurity to build the tree and decide class labels based on the majority of data samples at the leaf nodes, Else-Tree analyzes homogeneous regions of training data with similar attribute values and the same class label. After identifying the longest or most populated contiguous range per class, a decision node is created for that class, and the rest of the ranges are fed into the else branch to continue building the tree model. The Else-Tree model does not necessarily assign a class for conflicting or doubtful samples. Instead, it has an else-leaf node, led by the last else branch, to determine rejected or undecided data. The Else-Tree classifier has been evaluated and compared with other models through multiple datasets. The results show that Else-Tree can minimize the rate of misclassification.

Development of Classification Model for the Prediction of Churn among Customers using Decision tree Algorithm

Abstract: No Abstract.