The utility of artificial neural networks and classification and regression trees for the prediction of endometrial cancer in postmenopausal women

Pergialiotis, Vasilios; Pouliakis, Abraham; Parthenis, Christos; Damaskou, Vasileia; Chrelias, Charalampos; Παπαντωνίου, Ν.; Panayiotides, Ioannis G.

doi:10.1016/j.puhe.2018.07.012

Cited by 56 publications

(33 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Many studies have demonstrated that ANN outperformed logistic regression in predicting survival, morbidity and mortality post-surgery and cancer diagnosis accuracy (Hanai et al, 2003;Pergialiotis et al, 2018;Wise et al, 2019). However, in the field of prostate cancer, the predictive accuracy of logistic regression is better than that of ANN (Chun et al, 2007;Kawakami et al, 2008).…”

Section: Discussionmentioning

confidence: 99%

Development, Validation and Comparison of Artificial Neural Network Models and Logistic Regression Models Predicting Survival of Unresectable Pancreatic Cancer

Tong

Liu

et al. 2020

Front. Bioeng. Biotechnol.

View full text Add to dashboard Cite

Background: Prediction models for the overall survival of pancreatic cancer remain unsatisfactory. We aimed to explore artificial neural networks (ANNs) modeling to predict the survival of unresectable pancreatic cancer patients. Methods: Thirty-two clinical parameters were collected from 221 unresectable pancreatic cancer patients, and their prognostic ability was evaluated using univariate and multivariate logistic regression. ANN and logistic regression (LR) models were developed on a training group (168 patients), and the area under the ROC curve (AUC) was used for comparison of the ANN and LR models. The models were further tested on the testing group (53 patients), and k-statistics were used for accuracy comparison. Results: We built three ANN models, based on 3, 7, and 32 basic features, to predict 8 month survival. All 3 ANN models showed better performance, with AUCs significantly higher than those from the respective LR models (0.811 vs. 0.680, 0.844 vs. 0.722, 0.921 vs. 0.849, all p < 0.05). The ability of the ANN models to discriminate 8 month survival with higher accuracy than the respective LR models was further confirmed in 53 consecutive patients. Conclusion: We developed ANN models predicting the 8 month survival of unresectable pancreatic cancer patients. These models may help to optimize personalized patient management.

show abstract

Section: Discussionmentioning

confidence: 99%

Development, Validation and Comparison of Artificial Neural Network Models and Logistic Regression Models Predicting Survival of Unresectable Pancreatic Cancer

Tong

Liu

et al. 2020

Front. Bioeng. Biotechnol.

View full text Add to dashboard Cite

show abstract

“…Among the four decision tree methods available in SPSS, Chi-squared Automatic Interaction Detection (CHAID) and Classification and Regression Tree (CRT) stood out for highest accuracy and epidemiological plausibility of the structure. A reasonable strategy to construct the tree was adopted to get the optimal tree model [21][22][23][24][25][26][27]. Firstly, potential variables related to dependent variable in terms of temporal sequence, logic, and profession were selected out, all of which were set as independent variables to generate the tree as large as possible.…”

Section: Statistical Analysis and Model Parametermentioning

confidence: 99%

Management of imported malaria cases and healthcare institutions in central China, 2012–2017: application of decision tree analysis

Wang

Cao

et al. 2019

Malar J

View full text Add to dashboard Cite

Background: Imported malaria has been an important challenge for China. Fatality rates from malaria increased in China, particularly in Henan Province, primarily due to malpractice and misdiagnoses in healthcare institutions, and the level of imported malaria. This study aims to investigate the relationship between the state of diagnosis and subsequent complications among imported malaria cases at healthcare institutions, based on malaria surveillance data in Henan Province from 2012 to 2017. Methods: A retrospective descriptive analysis was performed using data from the Centre for Disease Control and Prevention, Zhengzhou City, the capital of Henan Province. A decision tree method was exploited to provide valuable insight into the correlation between imported malaria cases and healthcare institutions. Results: From 2012 to 2017, there were 371 imported malaria cases, mostly in males aged between 20 and 50 years, including 319 Plasmodium falciparum cases. First visits of 32.3%, 19.9% and 15.9% malaria cases for treatment were to provincial, municipal and county healthcare institutions, respectively. The time interval between onset and initial diagnosis of 284 cases (76.5%) and the time interval between initial diagnosis and final diagnosis of 197 cases (53.1%) was no more than 72 h. An apparent trend was found that there were notably fewer patients misdiagnosed at first visit to healthcare institutions of a higher administrative level; 12.5% of cases were misdiagnosed in provincial healthcare institutions compared to 98.2% in private clinics, leading to fewer complications at healthcare institutions of higher administrative level due to correct initial diagnosis. In the tree model, the rank of healthcare facilities for initial diagnosis, and number of days between onset and initial diagnosis, made a major contribution to the classification of initial diagnosis, which subsequently became the most significant factor influencing complications developed in the second tree model. The classification accuracy were 82.2 and 74.1%, respectively for the tree models of initial diagnosis and complications developed. Conclusion: Inadequate seeking medical care by imported malaria patients, and insufficient capacity to diagnose malaria by healthcare institutions of lower administrative level were identified as major factors influencing complications of imported malaria cases in Henan Province. The lack of connection between uncommon imported malaria

show abstract

“…Artificial neural networks (ANNs) are among the main tools used for data mining. They have a complex computational structure that is inspired by the human brain and nervous system [ 2 ]. The structure consists of input and output layers and a hidden layer of units that transform the inputs into something that the output layer can use [ 3 ].…”

Section: Introductionmentioning

confidence: 99%

Validation of the usefulness of artificial neural networks for risk prediction of adverse drug reactions used for individual patients in clinical practice

et al. 2020

View full text Add to dashboard Cite

Artificial neural networks are the main tools for data mining and were inspired by the human brain and nervous system. Studies have demonstrated their usefulness in medicine. However, no studies have used artificial neural networks for the prediction of adverse drug reactions. We aimed to validate the usefulness of artificial neural networks for the prediction of adverse drug reactions and focused on vancomycin -induced nephrotoxicity. For constructing an artificial neural network, a multilayer perceptron algorithm was employed. A 10-fold cross validation method was adopted for evaluating the resultant artificial neural network. In total, 1141 patients who received vancomycin at Hokkaido University Hospital from November 2011 to February 2019 were enrolled. Among these patients, 179 (15.7%) developed vancomycin -induced nephrotoxicity. The top three risk factors of vancomycin -induced nephrotoxicity which are relatively important in the artificial neural networks were average vancomycin trough concentration ≥ 13.0 mg/L and concomitant use of piperacillin–tazobactam and vasopressor drugs. The predictive accuracy of the artificial neural network was 86.3% and that of the multiple logistic regression model (conventional statistical method) was 85.1%. Moreover, area under the receiver operating characteristic curve (AUROC) of the artificial neural network was 0.83. In the 10-fold cross-validation, the accuracy obtained was 86.0% and AUROC was 0.82. The artificial neural network model predicting the vancomycin -induced nephrotoxicity showed good predictive performance. This appears to be the first report of the usefulness of artificial neural networks for an adverse drug reactions risk prediction model.

show abstract

The utility of artificial neural networks and classification and regression trees for the prediction of endometrial cancer in postmenopausal women

Cited by 56 publications

References 15 publications

Development, Validation and Comparison of Artificial Neural Network Models and Logistic Regression Models Predicting Survival of Unresectable Pancreatic Cancer

Development, Validation and Comparison of Artificial Neural Network Models and Logistic Regression Models Predicting Survival of Unresectable Pancreatic Cancer

Management of imported malaria cases and healthcare institutions in central China, 2012–2017: application of decision tree analysis

Validation of the usefulness of artificial neural networks for risk prediction of adverse drug reactions used for individual patients in clinical practice

Contact Info

Product

Resources

About