Interpretable Deep Models for ICU Outcome Prediction

By Zhengping Che, Sanjay Purushotham, Robinder G. Khemani, Yan Liu. 2016

293 citations recorded by the source corpus.

Subfields: Safety, Robustness & Interpretability, Medical & Health AI

How researchers see this paper

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

In Safety, Robustness & Interpretability

In Medical & Health AI

Citations in the corpus

Explainable Artificial Intelligence (XAI): Concepts, Taxonomies, Opportunities and Challenges toward Responsible AI (2019, positive): “For instance, [56] presents a simple distillation method called Interpretable Mimic Learning to extract an interpretable model by means of gradient boosting trees.”
Peeking Inside the Black-Box: A Survey on Explainable Artificial Intelligence (XAI) (2018, background): “Recently, researchers have conducted preliminary work aiming to make clinical AI-based systems explainable [37], [45]–[47].”
Interpreting CNNs via Decision Trees (2018, background): “Decision trees for neural networks: Distilling knowledge from neural networks into tree structures is an emerging direction [13, 31, 5], but the trees did not explain the network knowledge at a human-interpretable semantic level.”
Learning Optimal and Fair Decision Trees for Non-Discriminative Decision-Making (2019, methodology): “In this paper, we build on decision trees (Breiman et al. 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).”
Interpretable and Steerable Sequence Learning via Prototypes (2019, methodology): “Recently, model distillation is also used to explain deep sequence models [5, 23, 26, 27].”
Toward Interpretable Deep Reinforcement Learning with Linear Model U-Trees (2018, methodology): “arameter () updates minimize the dierentiable loss function: L( i) ˇ(r t+ max a t Q(s t+1;a t+1j i) Q(s t;a tj i)) 2 (1) i+1 = i+ r L( i) (2) Mimic Learning. Recent works on mimic learning [1,5,7] have demonstrated that models like shallow feed-forward neural network or decision trees can mimic th”
The role of explainability in creating trustworthy artificial intelligence for health care: a comprehensive survey of the terminology, design choices, and evaluation strategies (2020, result): “[61] used mimic learning to transfer knowledge from deep neural networks to smaller, more interpretable models for intensive care unit outcome prediction to verify agreement with earlier findings.”
Opportunities and challenges in developing deep learning models using electronic health records data: a systematic review (2018, background): “91,115 The main idea is to use the complex model to generate more soft-labeled examples to train a simpler model.”
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, background): “Che et al. [92] introduced an interpretable mimic-learning approach, which is a straightforward knowledge-distillation method that uses gradient-boosting trees to learn interpretable structures and make the baseline model understandable.”
Explaining How Deep Neural Networks Forget by Deep Visualization (2020, unknown): “lity methods bring us advantages to understand the decision-making process of deep neural networks, ranging from visualizing saliency maps [2,13] to transforming models into human-friendly structures [1]. In [16], deconvnets allow us to recognize which features are expected by a speciﬁc part of a ne”
Deep EHR: A Survey of Recent Advances in Deep Learning Techniques for Electronic Health Record (EHR) Analysis (2017, unknown): “[40], [47], [51], [59] [19], [34], [46]”
The importance of interpretability and visualization in machine learning for applications in medicine and health care (2019, methodology): “This includes mimicking the performance of DL using simpler more interpretable models such as decision trees [51,52], visual analytics on their own or combined with attention models [53–56], motif analysis [57], or semantic representations [56, 58].”
Exploring Interpretable LSTM Neural Networks over Multi-Variable Data (2019, background): “They still fall short of aforementioned two types of interpretation (Montavon et al., 2018; Foerster et al., 2017; Che et al., 2016).”
Principles and Practice of Explainable Machine Learning (2020, background): “In [14], the authors introduce Interpretable Mimic Learning , which builds on model distillation ideas, in order to approximate the original NN with a simpler, interpretable model.”
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].”