Temporal Comorbidity-Adjusted Risk of Emergency Readmission (T-CARER): A tool for comorbidity risk assessment

Mesgarpour, Mohsen; Chaussalet, Thierry J.; Chahed, Salma

doi:10.1016/j.asoc.2019.03.015

Cited by 4 publications

(6 citation statements)

References 45 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Predictive model is created from data trained using machine learning algorithms. The main objectives of risk modelling using predictive analytics are to identify risk level and critical causal factors that directly related to the risks [20]. Several learning algorithms have been proposed in previous research including decision tree, nearest neighbor, regression, neural network, support vector machines, Bayesian, classification rules, and several variants of them.…”

Section: Predictive Modelling Techniques For Identifying At-risk Studentmentioning

confidence: 99%

“…BN has some properties that make determining the strengths of variables in influencing outcomes an ideal choice. According to Mesgarpour et al [20], accuracy and efficiency of BN models depend on four main design choices; the frameworks of causal tree, the framework of the system state, inference approximation algorithm and finally the assignment and update method of prior probabilities. BN have applied have applied many different areas successfully [27].…”

Section: Bayesian Networkmentioning

confidence: 99%

“…Table 1 shows comparison of major machine learning techniques for predicting at-risk students. Agnihotri and Ott [14] Marquez-Vera et al [21] Marbouti et al [23] Oliverra et al [33] Abbott [34] Nandeswar et al [42] Baker et al [ Mesgarspour et al [20] Wolff et al [24] Abbott [34] Subbiah et al [36] Howard et al [38] Kuzilek et al [44] Logistic Regression  More robust: the independent variables don't have to be normally distributed  Does not assume a linear relationship between the independent and dependent variable  May handle nonlinear effects  Does not require that the independents be interval and unbounded…”

Section: Ensemblementioning

confidence: 99%

“…Agnihotri and Ott [14] Mesgarspour et al [20] Abbott [34] Howard et al [38] Norrish et al [39] Huang and Fang [40] Tran et al [41] Baker et al [43] Kuzilek et al [44] Linear Regression  Assume linear relationship  Suitable for simple application  Space complexity is very low  It's a high latency algorithm.  Its very simple to understand  Good interpretability  Feature importance is generated at the time model building.…”

Section: Lakkaraju Et Al [2]mentioning

confidence: 99%

“…Predictive modelling using BN have been studied for healthcare risk modelling Mesgarpour et al [20], for prediction of future event of large scale complex event from IOT network [29], computer security analytics [30] and life sciences [50]. BN has also been studied for course selection of high school environment [31].…”

Section: Bayesian Network Technique For Predicting At-risk Studentsmentioning

confidence: 99%

See 4 more Smart Citations

Review on Predictive Modelling Techniques for Identifying Students at Risk in University Environment

et al. 2019

View full text Add to dashboard Cite

Predictive analytics including statistical techniques, predictive modelling, machine learning, and data mining that analyse current and historical facts to make predictions about future or otherwise unknown events. Higher education institutions nowadays are under increasing pressure to respond to national and global economic, political and social changes such as the growing need to increase the proportion of students in certain disciplines, embedding workplace graduate attributes and ensuring that the quality of learning programs are both nationally and globally relevant. However, in higher education institution, there are significant numbers of students that stop their studies before graduation, especially for undergraduate students. Problem related to stopping out student and late or not graduating student can be improved by applying analytics. Using analytics, administrators, instructors and student can predict what will happen in future. Administrator and instructors can decide suitable intervention programs for at-risk students and before students decide to leave their study. Many different machine learning techniques have been implemented for predictive modelling in the past including decision tree, k-nearest neighbour, random forest, neural network, support vector machine, naïve Bayesian and a few others. A few attempts have been made to use Bayesian network and dynamic Bayesian network as modelling techniques for predicting at- risk student but a few challenges need to be resolved. The motivation for using dynamic Bayesian network is that it is robust to incomplete data and it provides opportunities for handling changing and dynamic environment. The trends and directions of research on prediction and identifying at-risk student are developing prediction model that can provide as early as possible alert to administrators, predictive model that handle dynamic and changing environment and the model that provide real-time prediction.

show abstract

Section: Predictive Modelling Techniques For Identifying At-risk Studentmentioning

confidence: 99%

Section: Bayesian Networkmentioning

confidence: 99%