Concept-based model explanations for electronic health records

Diana Mincu, Eric Loreaux, Shaobo Hou, Sebastien Baur, Ivan Protsyuk, Martin Seneviratne, Anne Mottram, Nenad Tomašev, Alan Karthikesalingam, Jessica Schrouff

Type: Preprint

Publication Date: 2021-03-23

Citations: 14

DOI: https://doi.org/10.1145/3450439.3451858

Locations

arXiv (Cornell University) - View - PDF
DataCite API - View

Similar Works

Action	Title	Year	Authors
+	Interpretable Additive Recurrent Neural Networks For Multivariate Clinical Time Series	2021	Asif Rahman Yale Chang Jonathan Rubin
+	Self-explaining Neural Network with Plausible Explanations.	2021	Sayantan Kumar Sean Yu Andrew P. Michelson Philip Payne
+	Adaptive Prediction Timing for Electronic Health Records	2020	J. Deasy Ari Ercole Píetro Lió
+	RETAIN: An Interpretable Predictive Model for Healthcare using Reverse Time Attention Mechanism	2016	Edward Choi Mohammad Taha Bahadori Joshua A. Kulas Andy Schuetz Walter F. Stewart Jimeng Sun
+	RETAIN: An Interpretable Predictive Model for Healthcare using Reverse Time Attention Mechanism	2016	Edward Choi Mohammad Taha Bahadori Jimeng Sun Joshua A. Kulas Andy Schuetz Walter F. Stewart
+	Adaptive Prediction Timing for Electronic Health Records.	2020	J. Deasy Ari Ercole Píetro Lió
+	Improving Clinical Predictions through Unsupervised Time Series Representation Learning	2018	Xinrui Lyu Matthias Hüser Stephanie L. Hyland George Zerveas Gunnar Rätsch
+	Visual Summary of Value-level Feature Attribution in Prediction Classes with Recurrent Neural Networks	2020	Chuan Wang Xumeng Wang Kwan‐Liu Ma
+ PDF Chat	Uncertainty-Aware Deep Ensembles for Reliable and Explainable Predictions of Clinical Time Series	2020	Kristoffer Wickstrøm Karl Øyvind Mikalsen Michael Kampffmeyer Arthur Revhaug Robert Jenssen
+	Simple Recurrent Neural Networks is all we need for clinical events predictions using EHR data	2021	Laila Rasmy Jie Zhu Zhiheng Li Xin Hao Hong Thoai Nga Tran Yujia Zhou Firat Tiryaki Yang Xiang Hua Xu Degui Zhi
+	Deep EHR Spotlight: a Framework and Mechanism to Highlight Events in Electronic Health Records for Explainable Predictions	2021	Thanh Nguyen-Duc Natasha Mulligan Gurdeep Mannu Joao H. Bettencourt‐Silva
+	Deep EHR Spotlight: a Framework and Mechanism to Highlight Events in Electronic Health Records for Explainable Predictions	2021	Thanh Nguyen-Duc Natasha Mulligan Gurdeep Mannu Joao H. Bettencourt‐Silva
+	Deep EHR Spotlight: a Framework and Mechanism to Highlight Events in Electronic Health Records for Explainable Predictions.	2021	Thanh Nguyen-Duc Natasha Mulligan Gurdeep Mannu Joao H. Bettencourt‐Silva
+	Self-explaining neural network with concept-based explanations for ICU mortality prediction	2022	Sayantan Kumar Sean Yu Thomas Kannampallil Zachary B. Abrams Andrew P. Michelson Philip Payne
+	Self-explaining Neural Network with Concept-based Explanations for ICU Mortality Prediction	2021	Sayantan Kumar Sean Yu Thomas Kannampallil Zachary B. Abrams Andrew P. Michelson Philip Payne
+ PDF Chat	Attend and Diagnose: Clinical Time Series Analysis Using Attention Models	2018	Huan Song Deepta Rajan Jayaraman J. Thiagarajan Andreas Spanias
+	Benchmarking Deep Learning Architectures for Predicting Readmission to the ICU and Describing Patients-at-Risk	2019	Sebastiano Barbieri J. F. Kemp Oscar Perez‐Concha Sradha Kotwal M. W. Gallagher Angus Ritchie Louisa Jorm
+	Benchmarking Deep Learning Architectures for Predicting Readmission to the ICU and Describing Patients-at-Risk	2019	Sebastiano Barbieri James Kemp Oscar Perez‐Concha Sradha Kotwal Martin Gallagher Angus Ritchie Louisa Jorm
+	Learning to Adapt Clinical Sequences with Residual Mixture of Experts	2022	Jeong Min Lee Miloš Hauskrecht
+ PDF Chat	Self-explaining Hierarchical Model for Intraoperative Time Series	2022	Dingwen Li Bing Xue Christopher R. King Bradley A. Fritz Michael S. Avidan Joanna Abraham Chenyang Lu

Works That Cite This (4)

Action	Title	Year	Authors
+ PDF Chat	Making Corgis Important for Honeycomb Classification: Adversarial Attacks on Concept-based Explainability Tools	2023	Davis Brown Henry Kvinge
+	Acquisition of chess knowledge in AlphaZero	2022	Thomas McGrath Andrei Kapishnikov Nenad Tomašev Adam Pearce Martin Wattenberg Demis Hassabis Been Kim Ulrich Paquet Vladimir Kramnik
+	Self-explaining neural network with concept-based explanations for ICU mortality prediction	2022	Sayantan Kumar Sean Yu Thomas Kannampallil Zachary B. Abrams Andrew P. Michelson Philip Payne
+ PDF Chat	Explaining Deep Neural Networks for Bearing Fault Detection with Vibration Concepts	2023	Thomas Decker Michael Lebacher Volker Tresp

Works Cited by This (26)

Action	Title	Year	Authors
+	Learning to Diagnose with LSTM Recurrent Neural Networks	2015	Zachary C. Lipton David C. Kale Charles Elkan Randall C. Wetzel
+	RETAIN: An Interpretable Predictive Model for Healthcare using Reverse Time Attention Mechanism	2016	Edward Choi Mohammad Taha Bahadori Joshua A. Kulas Andy Schuetz Walter F. Stewart Jimeng Sun
+	Axiomatic Attribution for Deep Networks	2017	Mukund Sundararajan Ankur Taly Qiqi Yan
+	An Improved Multi-Output Gaussian Process RNN with Real-Time Validation for Early Sepsis Detection	2017	Joseph Futoma Sanjay Hariharan Mark Sendak Nathan Brajer Meredith E. Clement Armando Bedoya Cara O’Brien Katherine Heller
+	Attend and Diagnose: Clinical Time Series Analysis using Attention Models	2017	Huan Song Deepta Rajan Jayaraman J. Thiagarajan Andreas Spanias
+	A unified view of gradient-based attribution methods for Deep Neural Networks	2017	Marco Ancona Enea Ceolini Cengiz Öztireli Markus Groß
+	What Clinicians Want: Contextualizing Explainable Machine Learning for Clinical End Use	2019	Sana Tonekaboni Shalmali Joshi Melissa D. McCradden Anna Goldenberg
+	Axiomatic Attribution for Deep Networks	2017	Mukund Sundararajan Ankur Taly Qiqi Yan
+	Counterfactual Reasoning for Fair Clinical Risk Prediction.	2019	Stephen Pfohl Tony Duan Daisy Yi Ding Nigam H. Shah
+	Explaining Classifiers with Causal Concept Effect (CaCE)	2019	Yash Goyal Amir Feder Uri Shalit Been Kim