Using methods from the data mining and machine learning literature for disease classification and prediction: A case study examining classification of heart failure sub-types

By Peter C. Austin, J. Tu, J. Ho, Daniel Levy, Douglas S. Lee. Journal of Clinical Epidemiology, 2013

320 citations recorded by the source corpus.

Objective Physicians classify patients into those with or without a specific disease. Furthermore, there is often interest in classifying patients according to disease etiology or subtype. Classification trees are frequently used to classify patients according to the presence or absence of a disease. However, classification trees can suffer from limited accuracy. In the data-mining and machine learning literature, alternate classification schemes have been developed. These include bootstrap aggregation (bagging), boosting, random forests, and support vector machines. Study design and Setting We compared the performance of these classification methods with those of conventional classification trees to classify patients with heart failure according to the following sub-types: heart failure with preserved ejection fraction (HFPEF) vs. heart failure with reduced ejection fraction (HFREF). We also compared the ability of these methods to predict the probability of the presence of HFPEF with that of conventional logistic regression. Results We found that modern, flexible tree-based methods from the data mining literature offer substantial improvement in prediction and classification of heart failure sub-type compared to conventional classification and regression trees. However, conventional logistic regression had superior performance for predicting the probability of the presence of HFPEF compared to the methods proposed in the data mining literature. Conclusion The use of tree-based methods offers superior performance over conventional classification and regression trees for predicting and classifying heart failure subtypes in a population-based sample of patients from Ontario. However, these methods do not offer substantial improvements over logistic regression for predicting the presence of HFPEF.

Subfields: Artificial Intelligence, Health Information Management

View Paper: https://www.semanticscholar.org/paper/7d8a77ac29c7c26643fe41feb01e66766c75e633

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Health Information Management

Citations in the corpus

Using EHRs and Machine Learning for Heart Failure Survival Analysis (2015, methodology): “Similarly, Austin et al. [7] used regression tree, bagging, Random Forest, boosting, SVM and logistic regression to classify HF patients with preserved Ejection Fraction (EF) from those patients with reduced EF.”
Machine‐Learning‐Based Electronic Triage More Accurately Differentiates Patients With Respect to Clinical Outcomes Compared With the Emergency Severity Index (2017, background): “…selection as part of the model building process, 29 are ﬂ exible in handling predictor data favorable for electronic health record applications, 29,30 and are adept at identifying interactions in patient information, enabling them to de ﬁ ne patient subgroups with respect to predicted outcomes.”
Prediction and Sensitivity Analysis of Bubble Dissolution Time in 3D Selective Laser Sintering Using Ensemble Decision Trees (2019, methodology): “Out of these methods, bagging method uses the bootstrap sampling to optimize the input training data for learning the decision trees [45].”
Machine-Learning-Based Disease Diagnosis: A Comprehensive Review (2021, methodology): “(2013) [32] Using methods from the data-mining and Machine-Learning literature for disease classification and prediction: a case study examining classification of Heart failure subtypes 139”
Development, Implementation, and Evaluation of an In-Hospital Optimized Early Warning Score for Patient Deterioration (2020, methodology): “While there are a variety of machine learning methods that we could have used to model these data, previous work has shown that regularized models often perform quite well in comparison.(19) Another modeling constraint was how to handle the longitudinal information.”
Heart disease prediction using supervised machine learning algorithms: Performance analysis and comparison (2021, background): “Data mining techniques can do the job efficiently at a very low cost using a classification algorithm, which plays a key role in clinical research [6].”
Moving beyond regression techniques in cardiovascular risk prediction: applying machine learning to address analytic challenges (2016, background): “48 More-over, extra considerations are needed when observations are correlated.”
Human-in-the-loop Artificial Intelligence (2017, background): “Intelligent risk predictors may replace doctors [2, 18, 10].”