Metric learning on healthcare data with incomplete modalities

Qiuling Suo, Weida Zhong, Fenglong Ma, Ye Yuan, Jing Gao, Aidong Zhang

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Utilizing multiple modalities to learn a good distance metric is of vital importance for various clinical applications. However, it is common that modalities are incomplete for some patients due to various technical and practical reasons in healthcare datasets. Existing metric learning methods cannot directly learn the distance metric on such data with missing modalities. Nevertheless, the incomplete data contains valuable information to characterize patient similarity and modality relationships, and they should not be ignored during the learning process. To tackle the aforementioned challenges, we propose a metric learning framework to perform missing modality completion and multi-modal metric learning simultaneously. Employing the generative adversarial networks, we incorporate both complete and incomplete data to learn the mapping relationship between modalities. After completing the missing modalities, we use the nonlinear representations extracted by the discriminator to learn the distance metric among patients. Through jointly training the adversarial generation part and metric learning, the similarity among patients can be learned on data with missing modalities. Experimental results show that the proposed framework learns more accurate distance metric on real-world healthcare datasets with incomplete modalities, comparing with the state-of-the-art approaches. Meanwhile, the quality of the generated modalities can be preserved.

Original languageEnglish (US)
Title of host publicationProceedings of the 28th International Joint Conference on Artificial Intelligence, IJCAI 2019
EditorsSarit Kraus
PublisherInternational Joint Conferences on Artificial Intelligence
Pages3534-3540
Number of pages7
ISBN (Electronic)9780999241141
StatePublished - Jan 1 2019
Event28th International Joint Conference on Artificial Intelligence, IJCAI 2019 - Macao, China
Duration: Aug 10 2019Aug 16 2019

Publication series

NameIJCAI International Joint Conference on Artificial Intelligence
Volume2019-August
ISSN (Print)1045-0823

Conference

Conference28th International Joint Conference on Artificial Intelligence, IJCAI 2019
CountryChina
CityMacao
Period8/10/198/16/19

Fingerprint

Discriminators

All Science Journal Classification (ASJC) codes

  • Artificial Intelligence

Cite this

Suo, Q., Zhong, W., Ma, F., Yuan, Y., Gao, J., & Zhang, A. (2019). Metric learning on healthcare data with incomplete modalities. In S. Kraus (Ed.), Proceedings of the 28th International Joint Conference on Artificial Intelligence, IJCAI 2019 (pp. 3534-3540). (IJCAI International Joint Conference on Artificial Intelligence; Vol. 2019-August). International Joint Conferences on Artificial Intelligence.
Suo, Qiuling ; Zhong, Weida ; Ma, Fenglong ; Yuan, Ye ; Gao, Jing ; Zhang, Aidong. / Metric learning on healthcare data with incomplete modalities. Proceedings of the 28th International Joint Conference on Artificial Intelligence, IJCAI 2019. editor / Sarit Kraus. International Joint Conferences on Artificial Intelligence, 2019. pp. 3534-3540 (IJCAI International Joint Conference on Artificial Intelligence).
@inproceedings{17dccb2c9fe74162a5c67dc840df327f,
title = "Metric learning on healthcare data with incomplete modalities",
abstract = "Utilizing multiple modalities to learn a good distance metric is of vital importance for various clinical applications. However, it is common that modalities are incomplete for some patients due to various technical and practical reasons in healthcare datasets. Existing metric learning methods cannot directly learn the distance metric on such data with missing modalities. Nevertheless, the incomplete data contains valuable information to characterize patient similarity and modality relationships, and they should not be ignored during the learning process. To tackle the aforementioned challenges, we propose a metric learning framework to perform missing modality completion and multi-modal metric learning simultaneously. Employing the generative adversarial networks, we incorporate both complete and incomplete data to learn the mapping relationship between modalities. After completing the missing modalities, we use the nonlinear representations extracted by the discriminator to learn the distance metric among patients. Through jointly training the adversarial generation part and metric learning, the similarity among patients can be learned on data with missing modalities. Experimental results show that the proposed framework learns more accurate distance metric on real-world healthcare datasets with incomplete modalities, comparing with the state-of-the-art approaches. Meanwhile, the quality of the generated modalities can be preserved.",
author = "Qiuling Suo and Weida Zhong and Fenglong Ma and Ye Yuan and Jing Gao and Aidong Zhang",
year = "2019",
month = "1",
day = "1",
language = "English (US)",
series = "IJCAI International Joint Conference on Artificial Intelligence",
publisher = "International Joint Conferences on Artificial Intelligence",
pages = "3534--3540",
editor = "Sarit Kraus",
booktitle = "Proceedings of the 28th International Joint Conference on Artificial Intelligence, IJCAI 2019",

}

Suo, Q, Zhong, W, Ma, F, Yuan, Y, Gao, J & Zhang, A 2019, Metric learning on healthcare data with incomplete modalities. in S Kraus (ed.), Proceedings of the 28th International Joint Conference on Artificial Intelligence, IJCAI 2019. IJCAI International Joint Conference on Artificial Intelligence, vol. 2019-August, International Joint Conferences on Artificial Intelligence, pp. 3534-3540, 28th International Joint Conference on Artificial Intelligence, IJCAI 2019, Macao, China, 8/10/19.

Metric learning on healthcare data with incomplete modalities. / Suo, Qiuling; Zhong, Weida; Ma, Fenglong; Yuan, Ye; Gao, Jing; Zhang, Aidong.

Proceedings of the 28th International Joint Conference on Artificial Intelligence, IJCAI 2019. ed. / Sarit Kraus. International Joint Conferences on Artificial Intelligence, 2019. p. 3534-3540 (IJCAI International Joint Conference on Artificial Intelligence; Vol. 2019-August).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Metric learning on healthcare data with incomplete modalities

AU - Suo, Qiuling

AU - Zhong, Weida

AU - Ma, Fenglong

AU - Yuan, Ye

AU - Gao, Jing

AU - Zhang, Aidong

PY - 2019/1/1

Y1 - 2019/1/1

N2 - Utilizing multiple modalities to learn a good distance metric is of vital importance for various clinical applications. However, it is common that modalities are incomplete for some patients due to various technical and practical reasons in healthcare datasets. Existing metric learning methods cannot directly learn the distance metric on such data with missing modalities. Nevertheless, the incomplete data contains valuable information to characterize patient similarity and modality relationships, and they should not be ignored during the learning process. To tackle the aforementioned challenges, we propose a metric learning framework to perform missing modality completion and multi-modal metric learning simultaneously. Employing the generative adversarial networks, we incorporate both complete and incomplete data to learn the mapping relationship between modalities. After completing the missing modalities, we use the nonlinear representations extracted by the discriminator to learn the distance metric among patients. Through jointly training the adversarial generation part and metric learning, the similarity among patients can be learned on data with missing modalities. Experimental results show that the proposed framework learns more accurate distance metric on real-world healthcare datasets with incomplete modalities, comparing with the state-of-the-art approaches. Meanwhile, the quality of the generated modalities can be preserved.

AB - Utilizing multiple modalities to learn a good distance metric is of vital importance for various clinical applications. However, it is common that modalities are incomplete for some patients due to various technical and practical reasons in healthcare datasets. Existing metric learning methods cannot directly learn the distance metric on such data with missing modalities. Nevertheless, the incomplete data contains valuable information to characterize patient similarity and modality relationships, and they should not be ignored during the learning process. To tackle the aforementioned challenges, we propose a metric learning framework to perform missing modality completion and multi-modal metric learning simultaneously. Employing the generative adversarial networks, we incorporate both complete and incomplete data to learn the mapping relationship between modalities. After completing the missing modalities, we use the nonlinear representations extracted by the discriminator to learn the distance metric among patients. Through jointly training the adversarial generation part and metric learning, the similarity among patients can be learned on data with missing modalities. Experimental results show that the proposed framework learns more accurate distance metric on real-world healthcare datasets with incomplete modalities, comparing with the state-of-the-art approaches. Meanwhile, the quality of the generated modalities can be preserved.

UR - http://www.scopus.com/inward/record.url?scp=85074919681&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85074919681&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:85074919681

T3 - IJCAI International Joint Conference on Artificial Intelligence

SP - 3534

EP - 3540

BT - Proceedings of the 28th International Joint Conference on Artificial Intelligence, IJCAI 2019

A2 - Kraus, Sarit

PB - International Joint Conferences on Artificial Intelligence

ER -

Suo Q, Zhong W, Ma F, Yuan Y, Gao J, Zhang A. Metric learning on healthcare data with incomplete modalities. In Kraus S, editor, Proceedings of the 28th International Joint Conference on Artificial Intelligence, IJCAI 2019. International Joint Conferences on Artificial Intelligence. 2019. p. 3534-3540. (IJCAI International Joint Conference on Artificial Intelligence).