Characterizing Design Patterns of EHR-Driven Phenotype Extraction Algorithms

Yizhen Zhong, Luke Rasmussen, Yu Deng, Jennifer Pacheco, Maureen E Smith, Justin B Starren, Wei Qi Wei, Peter Speltz, Joshua Denny, Nephi Walton, George Hripcsak, Christopher G. Chute, Yuan Luo*

*Corresponding author for this work

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

Abstract

The automatic development of phenotype algorithms from Electronic Health Record data with machine learning (ML) techniques is of great interest given the current practice is very time-consuming and resource intensive. The extraction of design patterns from phenotype algorithms is essential to understand their rationale and standard, with great potential to automate the development process. In this pilot study, we perform network visualization on the design patterns and their associations with phenotypes and sites. We classify design patterns using the fragments from previously annotated phenotype algorithms as the ground truth. The classification performance is used as a proxy for coherence at the attribution level. The bag-of-words representation with knowledge-based features generated a good performance in the classification task (0.79 macro-f1 scores). Good classification accuracy with simple features demonstrated the attribution coherence and the feasibility of automatic identification of design patterns. Our results point to both the feasibility and challenges of automatic identification of phenotyping design patterns, which would power the automatic development of phenotype algorithms.

Original languageEnglish (US)
Title of host publicationProceedings - 2018 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2018
EditorsHarald Schmidt, David Griol, Haiying Wang, Jan Baumbach, Huiru Zheng, Zoraida Callejas, Xiaohua Hu, Julie Dickerson, Le Zhang
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages1143-1146
Number of pages4
ISBN (Electronic)9781538654880
DOIs
StatePublished - Jan 21 2019
Event2018 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2018 - Madrid, Spain
Duration: Dec 3 2018Dec 6 2018

Publication series

NameProceedings - 2018 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2018

Conference

Conference2018 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2018
CountrySpain
CityMadrid
Period12/3/1812/6/18

Fingerprint

Phenotype
Electronic Health Records
Proxy
Macros
Learning systems
Visualization
Health

Keywords

  • Design pattern
  • Machine learning
  • Network visualization
  • Phenotype algorithm

ASJC Scopus subject areas

  • Biomedical Engineering
  • Health Informatics

Cite this

Zhong, Y., Rasmussen, L., Deng, Y., Pacheco, J., Smith, M. E., Starren, J. B., ... Luo, Y. (2019). Characterizing Design Patterns of EHR-Driven Phenotype Extraction Algorithms. In H. Schmidt, D. Griol, H. Wang, J. Baumbach, H. Zheng, Z. Callejas, X. Hu, J. Dickerson, ... L. Zhang (Eds.), Proceedings - 2018 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2018 (pp. 1143-1146). [8621240] (Proceedings - 2018 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2018). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/BIBM.2018.8621240
Zhong, Yizhen ; Rasmussen, Luke ; Deng, Yu ; Pacheco, Jennifer ; Smith, Maureen E ; Starren, Justin B ; Wei, Wei Qi ; Speltz, Peter ; Denny, Joshua ; Walton, Nephi ; Hripcsak, George ; Chute, Christopher G. ; Luo, Yuan. / Characterizing Design Patterns of EHR-Driven Phenotype Extraction Algorithms. Proceedings - 2018 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2018. editor / Harald Schmidt ; David Griol ; Haiying Wang ; Jan Baumbach ; Huiru Zheng ; Zoraida Callejas ; Xiaohua Hu ; Julie Dickerson ; Le Zhang. Institute of Electrical and Electronics Engineers Inc., 2019. pp. 1143-1146 (Proceedings - 2018 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2018).
@inproceedings{556e14ec8d8a46c38fa51d109272e843,
title = "Characterizing Design Patterns of EHR-Driven Phenotype Extraction Algorithms",
abstract = "The automatic development of phenotype algorithms from Electronic Health Record data with machine learning (ML) techniques is of great interest given the current practice is very time-consuming and resource intensive. The extraction of design patterns from phenotype algorithms is essential to understand their rationale and standard, with great potential to automate the development process. In this pilot study, we perform network visualization on the design patterns and their associations with phenotypes and sites. We classify design patterns using the fragments from previously annotated phenotype algorithms as the ground truth. The classification performance is used as a proxy for coherence at the attribution level. The bag-of-words representation with knowledge-based features generated a good performance in the classification task (0.79 macro-f1 scores). Good classification accuracy with simple features demonstrated the attribution coherence and the feasibility of automatic identification of design patterns. Our results point to both the feasibility and challenges of automatic identification of phenotyping design patterns, which would power the automatic development of phenotype algorithms.",
keywords = "Design pattern, Machine learning, Network visualization, Phenotype algorithm",
author = "Yizhen Zhong and Luke Rasmussen and Yu Deng and Jennifer Pacheco and Smith, {Maureen E} and Starren, {Justin B} and Wei, {Wei Qi} and Peter Speltz and Joshua Denny and Nephi Walton and George Hripcsak and Chute, {Christopher G.} and Yuan Luo",
year = "2019",
month = "1",
day = "21",
doi = "10.1109/BIBM.2018.8621240",
language = "English (US)",
series = "Proceedings - 2018 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2018",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "1143--1146",
editor = "Harald Schmidt and David Griol and Haiying Wang and Jan Baumbach and Huiru Zheng and Zoraida Callejas and Xiaohua Hu and Julie Dickerson and Le Zhang",
booktitle = "Proceedings - 2018 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2018",
address = "United States",

}

Zhong, Y, Rasmussen, L, Deng, Y, Pacheco, J, Smith, ME, Starren, JB, Wei, WQ, Speltz, P, Denny, J, Walton, N, Hripcsak, G, Chute, CG & Luo, Y 2019, Characterizing Design Patterns of EHR-Driven Phenotype Extraction Algorithms. in H Schmidt, D Griol, H Wang, J Baumbach, H Zheng, Z Callejas, X Hu, J Dickerson & L Zhang (eds), Proceedings - 2018 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2018., 8621240, Proceedings - 2018 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2018, Institute of Electrical and Electronics Engineers Inc., pp. 1143-1146, 2018 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2018, Madrid, Spain, 12/3/18. https://doi.org/10.1109/BIBM.2018.8621240

Characterizing Design Patterns of EHR-Driven Phenotype Extraction Algorithms. / Zhong, Yizhen; Rasmussen, Luke; Deng, Yu; Pacheco, Jennifer; Smith, Maureen E; Starren, Justin B; Wei, Wei Qi; Speltz, Peter; Denny, Joshua; Walton, Nephi; Hripcsak, George; Chute, Christopher G.; Luo, Yuan.

Proceedings - 2018 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2018. ed. / Harald Schmidt; David Griol; Haiying Wang; Jan Baumbach; Huiru Zheng; Zoraida Callejas; Xiaohua Hu; Julie Dickerson; Le Zhang. Institute of Electrical and Electronics Engineers Inc., 2019. p. 1143-1146 8621240 (Proceedings - 2018 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2018).

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

TY - GEN

T1 - Characterizing Design Patterns of EHR-Driven Phenotype Extraction Algorithms

AU - Zhong, Yizhen

AU - Rasmussen, Luke

AU - Deng, Yu

AU - Pacheco, Jennifer

AU - Smith, Maureen E

AU - Starren, Justin B

AU - Wei, Wei Qi

AU - Speltz, Peter

AU - Denny, Joshua

AU - Walton, Nephi

AU - Hripcsak, George

AU - Chute, Christopher G.

AU - Luo, Yuan

PY - 2019/1/21

Y1 - 2019/1/21

N2 - The automatic development of phenotype algorithms from Electronic Health Record data with machine learning (ML) techniques is of great interest given the current practice is very time-consuming and resource intensive. The extraction of design patterns from phenotype algorithms is essential to understand their rationale and standard, with great potential to automate the development process. In this pilot study, we perform network visualization on the design patterns and their associations with phenotypes and sites. We classify design patterns using the fragments from previously annotated phenotype algorithms as the ground truth. The classification performance is used as a proxy for coherence at the attribution level. The bag-of-words representation with knowledge-based features generated a good performance in the classification task (0.79 macro-f1 scores). Good classification accuracy with simple features demonstrated the attribution coherence and the feasibility of automatic identification of design patterns. Our results point to both the feasibility and challenges of automatic identification of phenotyping design patterns, which would power the automatic development of phenotype algorithms.

AB - The automatic development of phenotype algorithms from Electronic Health Record data with machine learning (ML) techniques is of great interest given the current practice is very time-consuming and resource intensive. The extraction of design patterns from phenotype algorithms is essential to understand their rationale and standard, with great potential to automate the development process. In this pilot study, we perform network visualization on the design patterns and their associations with phenotypes and sites. We classify design patterns using the fragments from previously annotated phenotype algorithms as the ground truth. The classification performance is used as a proxy for coherence at the attribution level. The bag-of-words representation with knowledge-based features generated a good performance in the classification task (0.79 macro-f1 scores). Good classification accuracy with simple features demonstrated the attribution coherence and the feasibility of automatic identification of design patterns. Our results point to both the feasibility and challenges of automatic identification of phenotyping design patterns, which would power the automatic development of phenotype algorithms.

KW - Design pattern

KW - Machine learning

KW - Network visualization

KW - Phenotype algorithm

UR - http://www.scopus.com/inward/record.url?scp=85062568899&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85062568899&partnerID=8YFLogxK

U2 - 10.1109/BIBM.2018.8621240

DO - 10.1109/BIBM.2018.8621240

M3 - Conference contribution

T3 - Proceedings - 2018 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2018

SP - 1143

EP - 1146

BT - Proceedings - 2018 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2018

A2 - Schmidt, Harald

A2 - Griol, David

A2 - Wang, Haiying

A2 - Baumbach, Jan

A2 - Zheng, Huiru

A2 - Callejas, Zoraida

A2 - Hu, Xiaohua

A2 - Dickerson, Julie

A2 - Zhang, Le

PB - Institute of Electrical and Electronics Engineers Inc.

ER -

Zhong Y, Rasmussen L, Deng Y, Pacheco J, Smith ME, Starren JB et al. Characterizing Design Patterns of EHR-Driven Phenotype Extraction Algorithms. In Schmidt H, Griol D, Wang H, Baumbach J, Zheng H, Callejas Z, Hu X, Dickerson J, Zhang L, editors, Proceedings - 2018 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2018. Institute of Electrical and Electronics Engineers Inc. 2019. p. 1143-1146. 8621240. (Proceedings - 2018 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2018). https://doi.org/10.1109/BIBM.2018.8621240