Deep Learning for Cardiovascular Risk Stratification
Purpose of review Although deep learning represents an exciting platform for the development of risk stratification models, it is challenging to evaluate these models beyond simple statistical measures of success, which do not always provide insight into a model’s clinical utility. Here we propose...
Main Authors: | , |
---|---|
Other Authors: | |
Format: | Article |
Language: | English |
Published: |
Springer Science and Business Media LLC
2021
|
Online Access: | https://hdl.handle.net/1721.1/131714 |
_version_ | 1811078797315801088 |
---|---|
author | Schlesinger, Daphne E. Stultz, Collin M |
author2 | Massachusetts Institute of Technology. Institute for Medical Engineering & Science |
author_facet | Massachusetts Institute of Technology. Institute for Medical Engineering & Science Schlesinger, Daphne E. Stultz, Collin M |
author_sort | Schlesinger, Daphne E. |
collection | MIT |
description | Purpose of review
Although deep learning represents an exciting platform for the development of risk stratification models, it is challenging to evaluate these models beyond simple statistical measures of success, which do not always provide insight into a model’s clinical utility. Here we propose a framework for evaluating deep learning models and discuss a number of interesting applications in light of these rubrics.
Recent findings
Data scientists and clinicians alike have applied a variety of deep learning techniques to both medical images and structured electronic medical record data. In many cases, these methods have resulted in risk stratification models that have improved discriminatory ability relative to more straightforward methods. Nevertheless, in many instances, it remains unclear how useful the resulting models are to practicing clinicians.
Summary
To be useful, deep learning models for cardiovascular risk stratification must not only be accurate but they must also provide insight into when they are likely to yield inaccurate results and be explainable in the sense that health care providers can understand why the model arrives at a particular result. These additional criteria help to ensure that the model can be faithfully applied to the demographic for which it is most accurate. |
first_indexed | 2024-09-23T11:05:38Z |
format | Article |
id | mit-1721.1/131714 |
institution | Massachusetts Institute of Technology |
language | English |
last_indexed | 2024-09-23T11:05:38Z |
publishDate | 2021 |
publisher | Springer Science and Business Media LLC |
record_format | dspace |
spelling | mit-1721.1/1317142022-09-27T17:06:44Z Deep Learning for Cardiovascular Risk Stratification Schlesinger, Daphne E. Stultz, Collin M Massachusetts Institute of Technology. Institute for Medical Engineering & Science Massachusetts Institute of Technology. Research Laboratory of Electronics Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science Purpose of review Although deep learning represents an exciting platform for the development of risk stratification models, it is challenging to evaluate these models beyond simple statistical measures of success, which do not always provide insight into a model’s clinical utility. Here we propose a framework for evaluating deep learning models and discuss a number of interesting applications in light of these rubrics. Recent findings Data scientists and clinicians alike have applied a variety of deep learning techniques to both medical images and structured electronic medical record data. In many cases, these methods have resulted in risk stratification models that have improved discriminatory ability relative to more straightforward methods. Nevertheless, in many instances, it remains unclear how useful the resulting models are to practicing clinicians. Summary To be useful, deep learning models for cardiovascular risk stratification must not only be accurate but they must also provide insight into when they are likely to yield inaccurate results and be explainable in the sense that health care providers can understand why the model arrives at a particular result. These additional criteria help to ensure that the model can be faithfully applied to the demographic for which it is most accurate. 2021-09-20T17:29:52Z 2021-09-20T17:29:52Z 2020-06 2020-06-26T13:31:02Z Article http://purl.org/eprint/type/JournalArticle 1092-8464 1534-3189 https://hdl.handle.net/1721.1/131714 Schlesinger, Daphne E. and C.M. Stultz. "Deep Learning for Cardiovascular Risk Stratification." Current Treatment Options in Cardiovascular Medicine 22, 8 (June 2020): 15 © 2020 Springer Nature en http://dx.doi.org/10.1007/s11936-020-00814-0 Current Treatment Options in Cardiovascular Medicine Creative Commons Attribution The Author(s) application/pdf Springer Science and Business Media LLC Springer US |
spellingShingle | Schlesinger, Daphne E. Stultz, Collin M Deep Learning for Cardiovascular Risk Stratification |
title | Deep Learning for Cardiovascular Risk Stratification |
title_full | Deep Learning for Cardiovascular Risk Stratification |
title_fullStr | Deep Learning for Cardiovascular Risk Stratification |
title_full_unstemmed | Deep Learning for Cardiovascular Risk Stratification |
title_short | Deep Learning for Cardiovascular Risk Stratification |
title_sort | deep learning for cardiovascular risk stratification |
url | https://hdl.handle.net/1721.1/131714 |
work_keys_str_mv | AT schlesingerdaphnee deeplearningforcardiovascularriskstratification AT stultzcollinm deeplearningforcardiovascularriskstratification |