MediBoost: a Patient Stratification Tool for Interpretable Decision Making in the Era of Precision Medicine

By Gilmer Valdes, José-Marcio Luna, Eric Eaton, Charles B. Simone II, Lyle Ungar, Timothy D. Solberg. 2016

111 citations recorded by the source corpus.

Machine learning algorithms that are both interpretable and accurate are essential in applications such as medicine where errors can have a dire consequence. Unfortunately, there is currently a tradeoff between accuracy and interpretability among state-of-the-art methods. Decision trees are interpretable and are therefore used extensively throughout medicine for stratifying patients. Current decision tree algorithms, however, are consistently outperformed in accuracy by other, less-interpretable machine learning models, such as ensemble methods. We present MediBoost, a novel framework for constructing decision trees that retain interpretability while having accuracy similar to ensemble methods, and compare MediBoost’s performance to that of conventional decision trees and ensemble methods on 13 medical classification problems. MediBoost significantly outperformed current decision tree algorithms in 11 out of 13 problems, giving accuracy comparable to ensemble methods. The resulting trees are of the same type as decision trees used throughout clinical practice but have the advantage of improved accuracy. Our algorithm thus gives the best of both worlds: it grows a single, highly interpretable tree that has the high accuracy of ensemble methods.

Subfields: Artificial Intelligence, Health Informatics

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 Informatics

Citations in the corpus

Interpretability via Model Extraction (2017, background): “Recent advances in machine learning have revolutionized our ability to use data to inform critical decisions, such as medical diagnosis [8, 19, 27], bail decisions for defendants [16, 17], and aircra collision avoidance systems [25].”
Learning Optimal and Fair Decision Trees for Non-Discriminative Decision-Making (2019, methodology): “1984) which have been used to generate interpretable models in many settings (Valdes et al. 2016; Huang, Gromiha, and Ho 2007; Che et al. 2016).”
Interpreting Blackbox Models via Model Extraction (2017, neutral): “Introduction Machine learning has revolutionized our ability to use data to inform critical decisions, such as medical diagnosis (Kononenko, 2001; Caruana et al., 2015; Valdes et al., 2016), bail decisions for defendants (Kleinberg et al.”
Artificial intelligence with multi-functional machine learning platform development for better healthcare and precision medicine (2020, background): “A few real-time examples include supporting clinical decisions (147), strategies for alternating therapies in oncology patients (148), collaborative clinical decisionmaking in mental health care (149), identifying predictors of health outcomes (150), finding factors related to hypertension (151), di”
Machine Learning in Radiation Oncology: Opportunities, Requirements, and Needs (2018, background): “If the goal is to assist physicians and patients reach the best decision, then a balance between interpretability of the results and accurate predictions is needed (23, 24).”
Designing Fair, Efficient, and Interpretable Policies for Prioritizing Homeless Youth for Housing Resources (2018, methodology): “Kidney Allocation System, we build on decision trees, which have been used to create interpretable models in many contexts [28, 10, 6].”
Unbox the black-box for the medical explainable AI via multi-modal and multi-centre data fusion: A mini-review, two showcases and beyond (2021, methodology): “5 shows, decision tree based methods are normally interpretable, research studies have been done using automated pruning of decision trees for various classifications of illnesses [132] and accurate decision trees focused on boosting patient stratification [133].”
Artificial intelligence and machine learning for medical imaging: A technology review. (2021, unknown): “…many other works in the medical field have also compared the accuracy of RFs against more complex or simpler ML classifiers, and it is well known that their performance may vary for different applications [103,113,132,134 – 139] and even for different datasets within the same application [131,132].”