Usefulness of Heat Map Explanations for Deep-Learning-Based Electrocardiogram Analysis
Authors:
- Andrea M. StoråsASAndrea M. Storås
- Ole Emil AndersenOAOle Emil Andersen
- Sam LockhartSLSam Lockhart
- Roman ThielemannRTRoman Thielemann
- Filip GnesinFGFilip Gnesin
- Vajira ThambawitaVajira Thambawita
- Steven A. HicksSHSteven A. Hicks
- Jørgen K. KantersJKJørgen K. Kanters
- Inga StrümkeInga Strümke
- Pål HalvorsenPål Halvorsen
- Michael A. RieglerMichael A. Riegler
Open Access
- 11 July 2023
- journal article
- research article
- Published by MDPI AG in Diagnostics
- Vol. 13 (14) , 2345
Abstract
Deep neural networks are complex machine learning models that have shown promising results in analyzing high-dimensional data such as those collected from medical examinations. Such models have the potential to provide fast and accurate medical diagnoses. However, the high complexity makes deep neural networks and their predictions difficult to understand. Providing model explanations can be a way of increasing the understanding of “black box” models and building trust. In this work, we applied transfer learning to develop a deep neural network to predict sex from electrocardiograms. Using the visual explanation method Grad-CAM, heat maps were generated from the model in order to understand how it makes predictions. To evaluate the usefulness of the heat maps and determine if the heat maps identified electrocardiogram features that could be recognized to discriminate sex, medical doctors provided feedback. Based on the feedback, we concluded that, in our setting, this mode of explainable artificial intelligence does not provide meaningful information to medical doctors and is not useful in the clinic. Our results indicate that improved explanation techniques that are tailored to medical data should be developed before deep neural networks can be applied in the clinic for diagnostic purposes.Keywords
Funding Information
- Wellcome Trust Clinical PhD Fellowship (225479/Z/22/Z)
This publication has 30 references indexed in Scilit:
- A Deep Learning Model to Predict a Diagnosis of Alzheimer Disease by Using 18F-FDG PET of the BrainRadiology, 2019
- Hidradenitis suppurativa and electrocardiographic changes: a cross‐sectional population studyBritish Journal of Dermatology, 2017
- Grad-CAM: Visual Explanations from Deep Networks via Gradient-Based Localization2017
- A survey of transfer learningJournal of Big Data, 2016
- Rare genetic variants previously associated with congenital forms of long QT syndrome have little or no effect on the QT intervalEuropean Heart Journal, 2015
- Gender Differences in the Prevalence of Electrocardiogram Abnormalities in the Elderly: A Population Survey in India2012
- Delay From Symptom Onset to Hospital Presentation for Patients With Non–ST-Segment Elevation Myocardial InfarctionArchives of internal medicine (1960), 2010
- Gender Differences in Ventricular Repolarization:Pacing and Clinical Electrophysiology, 2003
- PhysioBank, PhysioToolkit, and PhysioNetCirculation, 2000
- Missed Diagnoses of Acute Cardiac Ischemia in the Emergency DepartmentNew England Journal of Medicine, 2000