Explainability and Interpretability: Keys to Deep Medicine

Arash Shaban-Nejad; Martin Michalowski; David L. Buckeridge

doi:10.1007/978-3-030-53352-6_1

Explainability and Interpretability: Keys to Deep Medicine

Arash Shaban-Nejad, Martin Michalowski, David L. Buckeridge

Academics (Nursing)

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

18 Scopus citations

Abstract

Deep medicine, which aims to push the boundaries of artificial intelligence to reshape the health and medical intelligence and decision making, is a promising concept that is gaining attention over traditional EMR-based medical information management systems. The success of intelligent solutions in health and medicine depends on the degree to which they support interoperability, to allow consistent integration of different systems and data sources, and explainability, to make their decisions understandable, interpretable, and justifiable by humans.

Original language	English (US)
Title of host publication	Explainable AI in Healthcare and Medicine - Building a Culture of Transparency and Accountability
Editors	Arash Shaban-Nejad, Martin Michalowski, David L. Buckeridge
Publisher	Springer Science and Business Media Deutschland GmbH
Pages	1-10
Number of pages	10
ISBN (Print)	9783030533519
DOIs	https://doi.org/10.1007/978-3-030-53352-6_1
State	Published - 2021
Event	AAAI International Workshop on Health Intelligence, W3PHIAI 2020 - New York City, United States Duration: Feb 7 2020 → Feb 7 2020

Publication series

Name	Studies in Computational Intelligence
Volume	914
ISSN (Print)	1860-949X
ISSN (Electronic)	1860-9503

Conference

Conference	AAAI International Workshop on Health Intelligence, W3PHIAI 2020
Country/Territory	United States
City	New York City
Period	2/7/20 → 2/7/20

Bibliographical note

Publisher Copyright:
© 2021, The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Switzerland AG.

Keywords

Deep medicine
Explainable AI
Interpretability
Precision medicine

Access

10.1007/978-3-030-53352-6_1

OpenUrl availability

Full text

Cite this

Shaban-Nejad, A., Michalowski, M., & Buckeridge, D. L. (2021). Explainability and Interpretability: Keys to Deep Medicine. In A. Shaban-Nejad, M. Michalowski, & D. L. Buckeridge (Eds.), Explainable AI in Healthcare and Medicine - Building a Culture of Transparency and Accountability (pp. 1-10). (Studies in Computational Intelligence; Vol. 914). Springer Science and Business Media Deutschland GmbH. https://doi.org/10.1007/978-3-030-53352-6_1

Explainability and Interpretability: Keys to Deep Medicine. / Shaban-Nejad, Arash; Michalowski, Martin; Buckeridge, David L.
Explainable AI in Healthcare and Medicine - Building a Culture of Transparency and Accountability. ed. / Arash Shaban-Nejad; Martin Michalowski; David L. Buckeridge. Springer Science and Business Media Deutschland GmbH, 2021. p. 1-10 (Studies in Computational Intelligence; Vol. 914).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Shaban-Nejad, A, Michalowski, M & Buckeridge, DL 2021, Explainability and Interpretability: Keys to Deep Medicine. in A Shaban-Nejad, M Michalowski & DL Buckeridge (eds), Explainable AI in Healthcare and Medicine - Building a Culture of Transparency and Accountability. Studies in Computational Intelligence, vol. 914, Springer Science and Business Media Deutschland GmbH, pp. 1-10, AAAI International Workshop on Health Intelligence, W3PHIAI 2020, New York City, United States, 2/7/20. https://doi.org/10.1007/978-3-030-53352-6_1

Shaban-Nejad A, Michalowski M, Buckeridge DL. Explainability and Interpretability: Keys to Deep Medicine. In Shaban-Nejad A, Michalowski M, Buckeridge DL, editors, Explainable AI in Healthcare and Medicine - Building a Culture of Transparency and Accountability. Springer Science and Business Media Deutschland GmbH. 2021. p. 1-10. (Studies in Computational Intelligence). doi: 10.1007/978-3-030-53352-6_1

Shaban-Nejad, Arash ; Michalowski, Martin ; Buckeridge, David L. / Explainability and Interpretability : Keys to Deep Medicine. Explainable AI in Healthcare and Medicine - Building a Culture of Transparency and Accountability. editor / Arash Shaban-Nejad ; Martin Michalowski ; David L. Buckeridge. Springer Science and Business Media Deutschland GmbH, 2021. pp. 1-10 (Studies in Computational Intelligence).

@inproceedings{415e6216767c4175836bf2e842e2d9b2,

title = "Explainability and Interpretability: Keys to Deep Medicine",

abstract = "Deep medicine, which aims to push the boundaries of artificial intelligence to reshape the health and medical intelligence and decision making, is a promising concept that is gaining attention over traditional EMR-based medical information management systems. The success of intelligent solutions in health and medicine depends on the degree to which they support interoperability, to allow consistent integration of different systems and data sources, and explainability, to make their decisions understandable, interpretable, and justifiable by humans.",

keywords = "Deep medicine, Explainable AI, Interpretability, Precision medicine",

author = "Arash Shaban-Nejad and Martin Michalowski and Buckeridge, {David L.}",

note = "Publisher Copyright: {\textcopyright} 2021, The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Switzerland AG.; AAAI International Workshop on Health Intelligence, W3PHIAI 2020 ; Conference date: 07-02-2020 Through 07-02-2020",

year = "2021",

doi = "10.1007/978-3-030-53352-6_1",

language = "English (US)",

isbn = "9783030533519",

series = "Studies in Computational Intelligence",

publisher = "Springer Science and Business Media Deutschland GmbH",

pages = "1--10",

editor = "Arash Shaban-Nejad and Martin Michalowski and Buckeridge, {David L.}",

booktitle = "Explainable AI in Healthcare and Medicine - Building a Culture of Transparency and Accountability",

address = "Germany",

}

TY - GEN

T1 - Explainability and Interpretability

T2 - AAAI International Workshop on Health Intelligence, W3PHIAI 2020

AU - Shaban-Nejad, Arash

AU - Michalowski, Martin

AU - Buckeridge, David L.

PY - 2021

Y1 - 2021

N2 - Deep medicine, which aims to push the boundaries of artificial intelligence to reshape the health and medical intelligence and decision making, is a promising concept that is gaining attention over traditional EMR-based medical information management systems. The success of intelligent solutions in health and medicine depends on the degree to which they support interoperability, to allow consistent integration of different systems and data sources, and explainability, to make their decisions understandable, interpretable, and justifiable by humans.

AB - Deep medicine, which aims to push the boundaries of artificial intelligence to reshape the health and medical intelligence and decision making, is a promising concept that is gaining attention over traditional EMR-based medical information management systems. The success of intelligent solutions in health and medicine depends on the degree to which they support interoperability, to allow consistent integration of different systems and data sources, and explainability, to make their decisions understandable, interpretable, and justifiable by humans.

KW - Deep medicine

KW - Explainable AI

KW - Interpretability

KW - Precision medicine

UR - http://www.scopus.com/inward/record.url?scp=85097061078&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85097061078&partnerID=8YFLogxK

U2 - 10.1007/978-3-030-53352-6_1

DO - 10.1007/978-3-030-53352-6_1

M3 - Conference contribution

AN - SCOPUS:85097061078

SN - 9783030533519

T3 - Studies in Computational Intelligence

SP - 1

EP - 10

BT - Explainable AI in Healthcare and Medicine - Building a Culture of Transparency and Accountability

A2 - Shaban-Nejad, Arash

A2 - Michalowski, Martin

A2 - Buckeridge, David L.

PB - Springer Science and Business Media Deutschland GmbH

Y2 - 7 February 2020 through 7 February 2020

ER -

Explainability and Interpretability: Keys to Deep Medicine

Abstract

Publication series

Conference

Bibliographical note

Keywords

Access

OpenUrl availability

Other files and links

Fingerprint

Cite this