scholarly journals Clinical and inflammatory features based machine learning model for fatal risk prediction of hospitalized COVID-19 patients: results from a retrospective cohort study

2021 ◽  
Vol 53 (1) ◽  
pp. 257-266
Author(s):  
Xin Guan ◽  
Bo Zhang ◽  
Ming Fu ◽  
Mengying Li ◽  
Xu Yuan ◽  
...  
Keyword(s):  
Machine Learning ◽  
Cohort Study ◽  
Risk Prediction ◽  
Retrospective Cohort Study ◽  
Retrospective Cohort ◽  
Learning Model ◽  
Machine Learning Model

A risk prediction model for xerostomia: a retrospective cohort study

Gerodontology ◽  
2015 ◽  
Vol 33 (4) ◽  
pp. 562-568 ◽  
Author(s):  
Alessandro Villa ◽  
Francesco Nordio ◽  
Anita Gohel
Keyword(s):  
Cohort Study ◽  
Prediction Model ◽  
Risk Prediction ◽  
Retrospective Cohort Study ◽  
Retrospective Cohort ◽  
Risk Prediction Model

scholarly journals Risk Identification, Assessments, and Prediction for Mega Construction Projects: A Risk Prediction Paradigm Based on Cross Analytical-Machine Learning Model

Buildings ◽  
2021 ◽  
Vol 11 (4) ◽  
pp. 172
Author(s):  
Debalina Banerjee Chattapadhyay ◽  
Jagadeesh Putta ◽  
Rama Mohan Rao P
Keyword(s):  
Machine Learning ◽  
Risk Factors ◽  
Risk Management ◽  
High Risk ◽  
Risk Prediction ◽  
Learning Model ◽  
Risk Identification ◽  
Large Set ◽  
High Risk Factors ◽  
Machine Learning Model

Risk identification and management are the two most important parts of construction project management. Better risk management can help in determining the future consequences, but identifying possible risk factors has a direct and indirect impact on the risk management process. In this paper, a risk prediction system based on a cross analytical-machine learning model was developed for construction megaprojects. A total of 63 risk factors pertaining to the cost, time, quality, and scope of the megaproject and primary data were collected from industry experts on a five-point Likert scale. The obtained sample was further processed statistically to generate a significantly large set of features to perform K-means clustering based on high-risk factor and allied sub-risk component identification. Descriptive analysis, followed by the synthetic minority over-sampling technique (SMOTE) and the Wilcoxon rank-sum test was performed to retain the most significant features pertaining to cost, time, quality, and scope. Eventually, unlike classical K-means clustering, a genetic-algorithm-based K-means clustering algorithm (GA–K-means) was applied with dual-objective functions to segment high-risk factors and allied sub-risk components. The proposed model identified different high-risk factors and sub-risk factors, which cumulatively can impact overall performance. Thus, identifying these high-risk factors and corresponding sub-risk components can help stakeholders in achieving project success.

scholarly journals Machine learning-based prediction models for accidental hypothermia patients

2021 ◽  
Vol 9 (1) ◽  
Author(s):  
Yohei Okada ◽  
Tasuku Matsuyama ◽  
Sachiko Morita ◽  
Naoki Ehara ◽  
Nobuhiro Miyamae ◽  
...  
Keyword(s):  
Machine Learning ◽  
Cohort Study ◽  
Random Forest ◽  
Hospital Mortality ◽  
Retrospective Cohort Study ◽  
Retrospective Cohort ◽  
Prediction Models ◽  
Validation Cohort ◽  
Accidental Hypothermia ◽  
Gradient Boosting

Abstract Background Accidental hypothermia is a critical condition with high risks of fatal arrhythmia, multiple organ failure, and mortality; however, there is no established model to predict the mortality. The present study aimed to develop and validate machine learning-based models for predicting in-hospital mortality using easily available data at hospital admission among the patients with accidental hypothermia. Method This study was secondary analysis of multi-center retrospective cohort study (J-point registry) including patients with accidental hypothermia. Adult patients with body temperature 35.0 °C or less at emergency department were included. Prediction models for in-hospital mortality using machine learning (lasso, random forest, and gradient boosting tree) were made in development cohort from six hospitals, and the predictive performance were assessed in validation cohort from other six hospitals. As a reference, we compared the SOFA score and 5A score. Results We included total 532 patients in the development cohort [N = 288, six hospitals, in-hospital mortality: 22.0% (64/288)], and the validation cohort [N = 244, six hospitals, in-hospital mortality 27.0% (66/244)]. The C-statistics [95% CI] of the models in validation cohorts were as follows: lasso 0.784 [0.717–0.851] , random forest 0.794[0.735–0.853], gradient boosting tree 0.780 [0.714–0.847], SOFA 0.787 [0.722–0.851], and 5A score 0.750[0.681–0.820]. The calibration plot showed that these models were well calibrated to observed in-hospital mortality. Decision curve analysis indicated that these models obtained clinical net-benefit. Conclusion This multi-center retrospective cohort study indicated that machine learning-based prediction models could accurately predict in-hospital mortality in validation cohort among the accidental hypothermia patients. These models might be able to support physicians and patient’s decision-making. However, the applicability to clinical settings, and the actual clinical utility is still unclear; thus, further prospective study is warranted to evaluate the clinical usefulness.

Sign in / Sign up

Export Citation Format

Share Document