Interpretable Machine Learning Techniques for Causal Inference Using Balancing Scores as Meta-features

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

Abstract

Estimating individual causal effect is important for decision making in many fields especially for medical interventions. We propose an interpretable and accurate algorithm for estimating causal effects from observational data. The proposed scheme is combining multiple predictors' outputs by an interpretable predictor such as linear predictor and if then rules. We secure interpretability using the interpretable predictor and balancing scores in causal inference studies as meta-features. For securing accuracy, we adapt machine learning algorithms for calculating balancing scores. We analyze the effect of t-PA therapy for stroke patients using real-world data, which has 64,609 records with 362 variables and interpret results. The results show that cross validation AUC of the proposed scheme is little less than original machine learning scheme; however, the proposed scheme provides interpretability that t-PA therapy is effective for severe patients.

Original languageEnglish
Title of host publication40th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2018
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages4042-4045
Number of pages4
ISBN (Electronic)9781538636466
DOIs
Publication statusPublished - Oct 26 2018
Event40th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2018 - Honolulu, United States
Duration: Jul 18 2018Jul 21 2018

Publication series

NameProceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS
Volume2018-July
ISSN (Print)1557-170X

Other

Other40th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2018
CountryUnited States
CityHonolulu
Period7/18/187/21/18

Fingerprint

Learning systems
Learning algorithms
Area Under Curve
Decision Making
Decision making
Stroke
Therapeutics
Machine Learning

All Science Journal Classification (ASJC) codes

  • Signal Processing
  • Biomedical Engineering
  • Computer Vision and Pattern Recognition
  • Health Informatics

Cite this

Nohara, Y., Iihara, K., & Nakashima, N. (2018). Interpretable Machine Learning Techniques for Causal Inference Using Balancing Scores as Meta-features. In 40th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2018 (pp. 4042-4045). [8513026] (Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS; Vol. 2018-July). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/EMBC.2018.8513026

Interpretable Machine Learning Techniques for Causal Inference Using Balancing Scores as Meta-features. / Nohara, Yasunobu; Iihara, Koji; Nakashima, Naoki.

40th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2018. Institute of Electrical and Electronics Engineers Inc., 2018. p. 4042-4045 8513026 (Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS; Vol. 2018-July).

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

Nohara, Y, Iihara, K & Nakashima, N 2018, Interpretable Machine Learning Techniques for Causal Inference Using Balancing Scores as Meta-features. in 40th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2018., 8513026, Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS, vol. 2018-July, Institute of Electrical and Electronics Engineers Inc., pp. 4042-4045, 40th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2018, Honolulu, United States, 7/18/18. https://doi.org/10.1109/EMBC.2018.8513026
Nohara Y, Iihara K, Nakashima N. Interpretable Machine Learning Techniques for Causal Inference Using Balancing Scores as Meta-features. In 40th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2018. Institute of Electrical and Electronics Engineers Inc. 2018. p. 4042-4045. 8513026. (Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS). https://doi.org/10.1109/EMBC.2018.8513026
Nohara, Yasunobu ; Iihara, Koji ; Nakashima, Naoki. / Interpretable Machine Learning Techniques for Causal Inference Using Balancing Scores as Meta-features. 40th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2018. Institute of Electrical and Electronics Engineers Inc., 2018. pp. 4042-4045 (Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS).
@inproceedings{08725b5227ce44328c543de15db2a15f,
title = "Interpretable Machine Learning Techniques for Causal Inference Using Balancing Scores as Meta-features",
abstract = "Estimating individual causal effect is important for decision making in many fields especially for medical interventions. We propose an interpretable and accurate algorithm for estimating causal effects from observational data. The proposed scheme is combining multiple predictors' outputs by an interpretable predictor such as linear predictor and if then rules. We secure interpretability using the interpretable predictor and balancing scores in causal inference studies as meta-features. For securing accuracy, we adapt machine learning algorithms for calculating balancing scores. We analyze the effect of t-PA therapy for stroke patients using real-world data, which has 64,609 records with 362 variables and interpret results. The results show that cross validation AUC of the proposed scheme is little less than original machine learning scheme; however, the proposed scheme provides interpretability that t-PA therapy is effective for severe patients.",
author = "Yasunobu Nohara and Koji Iihara and Naoki Nakashima",
year = "2018",
month = "10",
day = "26",
doi = "10.1109/EMBC.2018.8513026",
language = "English",
series = "Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "4042--4045",
booktitle = "40th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2018",
address = "United States",

}

TY - GEN

T1 - Interpretable Machine Learning Techniques for Causal Inference Using Balancing Scores as Meta-features

AU - Nohara, Yasunobu

AU - Iihara, Koji

AU - Nakashima, Naoki

PY - 2018/10/26

Y1 - 2018/10/26

N2 - Estimating individual causal effect is important for decision making in many fields especially for medical interventions. We propose an interpretable and accurate algorithm for estimating causal effects from observational data. The proposed scheme is combining multiple predictors' outputs by an interpretable predictor such as linear predictor and if then rules. We secure interpretability using the interpretable predictor and balancing scores in causal inference studies as meta-features. For securing accuracy, we adapt machine learning algorithms for calculating balancing scores. We analyze the effect of t-PA therapy for stroke patients using real-world data, which has 64,609 records with 362 variables and interpret results. The results show that cross validation AUC of the proposed scheme is little less than original machine learning scheme; however, the proposed scheme provides interpretability that t-PA therapy is effective for severe patients.

AB - Estimating individual causal effect is important for decision making in many fields especially for medical interventions. We propose an interpretable and accurate algorithm for estimating causal effects from observational data. The proposed scheme is combining multiple predictors' outputs by an interpretable predictor such as linear predictor and if then rules. We secure interpretability using the interpretable predictor and balancing scores in causal inference studies as meta-features. For securing accuracy, we adapt machine learning algorithms for calculating balancing scores. We analyze the effect of t-PA therapy for stroke patients using real-world data, which has 64,609 records with 362 variables and interpret results. The results show that cross validation AUC of the proposed scheme is little less than original machine learning scheme; however, the proposed scheme provides interpretability that t-PA therapy is effective for severe patients.

UR - http://www.scopus.com/inward/record.url?scp=85056635136&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85056635136&partnerID=8YFLogxK

U2 - 10.1109/EMBC.2018.8513026

DO - 10.1109/EMBC.2018.8513026

M3 - Conference contribution

T3 - Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS

SP - 4042

EP - 4045

BT - 40th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2018

PB - Institute of Electrical and Electronics Engineers Inc.

ER -