Improve the trustwortiness of medical text interpretations

Siyue Song; Tianhua Chen; Grigoris Antoniou

doi:10.1109/BHI56158.2022.9926894

Improve the trustwortiness of medical text interpretations

Siyue Song, Tianhua Chen, Grigoris Antoniou

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

Abstract

Currently, how to make a concrete and correct disease prediction is a popular research trend. Researchers made more efforts to develop various models to provide interpretations of medical area, however, there is still lack of human understandable explanations provided due to the non-transparency structure of some machine learning and deep learning models. According to this work, there is one combined model application we would like to adopt. After comparison experiments of classification and interpretation, it is found the combination model can address the issues from the latest interpretation models, and try to improve the trustworthiness of medical text interpretations.

Original language	English
Title of host publication	IEEE-EMBS International Conference on Biomedical and Health Informatics (BHI'22)
Publisher	IEEE
Number of pages	7
ISBN (Electronic)	9781665487917
ISBN (Print)	9781665487924
DOIs	https://doi.org/10.1109/BHI56158.2022.9926894
Publication status	Published - 4 Nov 2022
Event	IEEE-EMBS International Conference on Biomedical and Health Informatics (BHI'22) Jointly Organised with the 17th IEEE-EMBS International Conference on Wearable and Implantable Body Sensor Networks (BSN'22) - Ioannina, Greece Duration: 27 Sep 2022 → 30 Sep 2022 Conference number: 17 https://bhi-bsn-2022.org/

Publication series

Name	IEEE-EMBS International Conference on Biomedical and Health Informatics
Publisher	IEEE
ISSN (Print)	2641-3590
ISSN (Electronic)	2641-3604

Conference

Conference	IEEE-EMBS International Conference on Biomedical and Health Informatics (BHI'22) Jointly Organised with the 17th IEEE-EMBS International Conference on Wearable and Implantable Body Sensor Networks (BSN'22)
Abbreviated title	IEEE BHI-BSN 2022
Country/Territory	Greece
City	Ioannina
Period	27/09/22 → 30/09/22
Internet address	https://bhi-bsn-2022.org/

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1109/BHI56158.2022.9926894Licence: Unspecified

1570818255 finalAccepted author manuscript, 1.96 MBLicence: Unspecified

Cite this

@inproceedings{e083d90a5a424c80b5891d83d98931fd,

title = "Improve the trustwortiness of medical text interpretations",

abstract = "Currently, how to make a concrete and correct disease prediction is a popular research trend. Researchers made more efforts to develop various models to provide interpretations of medical area, however, there is still lack of human understandable explanations provided due to the non-transparency structure of some machine learning and deep learning models. According to this work, there is one combined model application we would like to adopt. After comparison experiments of classification and interpretation, it is found the combination model can address the issues from the latest interpretation models, and try to improve the trustworthiness of medical text interpretations.",

keywords = "interpretations, trustworthiness, explainability, transparency",

author = "Siyue Song and Tianhua Chen and Grigoris Antoniou",

note = "Publisher Copyright: {\textcopyright} 2022 IEEE.; IEEE-EMBS International Conference on Biomedical and Health Informatics (BHI'22) Jointly Organised with the 17th IEEE-EMBS International Conference on Wearable and Implantable Body Sensor Networks (BSN'22), IEEE BHI-BSN 2022 ; Conference date: 27-09-2022 Through 30-09-2022",

year = "2022",

month = nov,

day = "4",

doi = "10.1109/BHI56158.2022.9926894",

language = "English",

isbn = "9781665487924",

series = "IEEE-EMBS International Conference on Biomedical and Health Informatics",

publisher = "IEEE",

booktitle = "IEEE-EMBS International Conference on Biomedical and Health Informatics (BHI'22)",

address = "United States",

url = "https://bhi-bsn-2022.org/",

}

Song, S, Chen, T & Antoniou, G 2022, Improve the trustwortiness of medical text interpretations. in IEEE-EMBS International Conference on Biomedical and Health Informatics (BHI'22)., 9926894, IEEE-EMBS International Conference on Biomedical and Health Informatics, IEEE, IEEE-EMBS International Conference on Biomedical and Health Informatics (BHI'22) Jointly Organised with the 17th IEEE-EMBS International Conference on Wearable and Implantable Body Sensor Networks (BSN'22), Ioannina, Greece, 27/09/22. https://doi.org/10.1109/BHI56158.2022.9926894

Improve the trustwortiness of medical text interpretations. / Song, Siyue; Chen, Tianhua; Antoniou, Grigoris.

IEEE-EMBS International Conference on Biomedical and Health Informatics (BHI'22). IEEE, 2022. 9926894 (IEEE-EMBS International Conference on Biomedical and Health Informatics).

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

TY - GEN

T1 - Improve the trustwortiness of medical text interpretations

AU - Song, Siyue

AU - Chen, Tianhua

AU - Antoniou, Grigoris

N1 - Conference code: 17

PY - 2022/11/4

Y1 - 2022/11/4

N2 - Currently, how to make a concrete and correct disease prediction is a popular research trend. Researchers made more efforts to develop various models to provide interpretations of medical area, however, there is still lack of human understandable explanations provided due to the non-transparency structure of some machine learning and deep learning models. According to this work, there is one combined model application we would like to adopt. After comparison experiments of classification and interpretation, it is found the combination model can address the issues from the latest interpretation models, and try to improve the trustworthiness of medical text interpretations.

AB - Currently, how to make a concrete and correct disease prediction is a popular research trend. Researchers made more efforts to develop various models to provide interpretations of medical area, however, there is still lack of human understandable explanations provided due to the non-transparency structure of some machine learning and deep learning models. According to this work, there is one combined model application we would like to adopt. After comparison experiments of classification and interpretation, it is found the combination model can address the issues from the latest interpretation models, and try to improve the trustworthiness of medical text interpretations.

KW - interpretations

KW - trustworthiness

KW - explainability

KW - transparency

UR - http://www.scopus.com/inward/record.url?scp=85143049057&partnerID=8YFLogxK

U2 - 10.1109/BHI56158.2022.9926894

DO - 10.1109/BHI56158.2022.9926894

M3 - Conference contribution

SN - 9781665487924

T3 - IEEE-EMBS International Conference on Biomedical and Health Informatics

BT - IEEE-EMBS International Conference on Biomedical and Health Informatics (BHI'22)

PB - IEEE

T2 - IEEE-EMBS International Conference on Biomedical and Health Informatics (BHI'22) Jointly Organised with the 17th IEEE-EMBS International Conference on Wearable and Implantable Body Sensor Networks (BSN'22)

Y2 - 27 September 2022 through 30 September 2022

ER -

Improve the trustwortiness of medical text interpretations

Abstract

Publication series

Conference

UN SDGs

Access to Document

Other files and links

Fingerprint

Cite this