Portable Phenotyping System

A Portable Machine-Learning Approach to i2b2 Obesity Challenge

Himanshu Sharma, Chengsheng Mao, Yizhen Zhang, Haleh Vatani, Liang Yao, Yizhen Zhong, Luke Rasmussen, Guoqian Jiang, Jyotishman Pathak, Yuan Luo*

*Corresponding author for this work

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

Abstract

This paper presents a portable phenotyping system that is capable of integrating both rule-based and statistical machine learning based approaches. Our system utilizes UMLS to extract clinically relevant features from the unstructured text and then facilitates portability across different institutions and data systems by incorporating ODHSI's OMOP Common Data Model (CDM) to standardize necessary data elements. Our system can also store the key components of rule-based systems (e.g., regular expression matches) in the format of OMOP CDM, thus enabling the reuse, adaptation and extension of many existing rule-based clinical NLP systems. We experimented our system on the corpus from i2b2's Obesity Challenge as a pilot study. Our system facilitates portable phenotyping of obesity and its 15 comorbidities based on the unstructured patient discharge summaries, while achieving a performance that often ranked among the top 10 of the challenge participants. This standardization enables a consistent application of numerous rule-based and machine learning based classification techniques downstream.

Original languageEnglish (US)
Title of host publicationProceedings - 2018 IEEE International Conference on Healthcare Informatics Workshops, ICHI-W 2018
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages86-87
Number of pages2
ISBN (Electronic)9781538667774
DOIs
StatePublished - Jul 16 2018
Event6th IEEE International Conference on Healthcare Informatics Workshops, ICHI-W 2018 - New York, United States
Duration: Jun 4 2018Jun 7 2018

Publication series

NameProceedings - 2018 IEEE International Conference on Healthcare Informatics Workshops, ICHI-W 2018

Other

Other6th IEEE International Conference on Healthcare Informatics Workshops, ICHI-W 2018
CountryUnited States
CityNew York
Period6/4/186/7/18

Fingerprint

Patient Discharge Summaries
Obesity
Unified Medical Language System
Information Systems
Comorbidity
Machine Learning
Machine learning
Rule-based

Keywords

  • Machine Learning
  • NLP
  • OMOP CDM
  • Obesity
  • Portability
  • i2b2

ASJC Scopus subject areas

  • Information Systems and Management
  • Health Informatics

Cite this

Sharma, H., Mao, C., Zhang, Y., Vatani, H., Yao, L., Zhong, Y., ... Luo, Y. (2018). Portable Phenotyping System: A Portable Machine-Learning Approach to i2b2 Obesity Challenge. In Proceedings - 2018 IEEE International Conference on Healthcare Informatics Workshops, ICHI-W 2018 (pp. 86-87). [8411818] (Proceedings - 2018 IEEE International Conference on Healthcare Informatics Workshops, ICHI-W 2018). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICHI-W.2018.00032
Sharma, Himanshu ; Mao, Chengsheng ; Zhang, Yizhen ; Vatani, Haleh ; Yao, Liang ; Zhong, Yizhen ; Rasmussen, Luke ; Jiang, Guoqian ; Pathak, Jyotishman ; Luo, Yuan. / Portable Phenotyping System : A Portable Machine-Learning Approach to i2b2 Obesity Challenge. Proceedings - 2018 IEEE International Conference on Healthcare Informatics Workshops, ICHI-W 2018. Institute of Electrical and Electronics Engineers Inc., 2018. pp. 86-87 (Proceedings - 2018 IEEE International Conference on Healthcare Informatics Workshops, ICHI-W 2018).
@inproceedings{1433bb0d9bdb45e981765bbb82f164e6,
title = "Portable Phenotyping System: A Portable Machine-Learning Approach to i2b2 Obesity Challenge",
abstract = "This paper presents a portable phenotyping system that is capable of integrating both rule-based and statistical machine learning based approaches. Our system utilizes UMLS to extract clinically relevant features from the unstructured text and then facilitates portability across different institutions and data systems by incorporating ODHSI's OMOP Common Data Model (CDM) to standardize necessary data elements. Our system can also store the key components of rule-based systems (e.g., regular expression matches) in the format of OMOP CDM, thus enabling the reuse, adaptation and extension of many existing rule-based clinical NLP systems. We experimented our system on the corpus from i2b2's Obesity Challenge as a pilot study. Our system facilitates portable phenotyping of obesity and its 15 comorbidities based on the unstructured patient discharge summaries, while achieving a performance that often ranked among the top 10 of the challenge participants. This standardization enables a consistent application of numerous rule-based and machine learning based classification techniques downstream.",
keywords = "Machine Learning, NLP, OMOP CDM, Obesity, Portability, i2b2",
author = "Himanshu Sharma and Chengsheng Mao and Yizhen Zhang and Haleh Vatani and Liang Yao and Yizhen Zhong and Luke Rasmussen and Guoqian Jiang and Jyotishman Pathak and Yuan Luo",
year = "2018",
month = "7",
day = "16",
doi = "10.1109/ICHI-W.2018.00032",
language = "English (US)",
series = "Proceedings - 2018 IEEE International Conference on Healthcare Informatics Workshops, ICHI-W 2018",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "86--87",
booktitle = "Proceedings - 2018 IEEE International Conference on Healthcare Informatics Workshops, ICHI-W 2018",
address = "United States",

}

Sharma, H, Mao, C, Zhang, Y, Vatani, H, Yao, L, Zhong, Y, Rasmussen, L, Jiang, G, Pathak, J & Luo, Y 2018, Portable Phenotyping System: A Portable Machine-Learning Approach to i2b2 Obesity Challenge. in Proceedings - 2018 IEEE International Conference on Healthcare Informatics Workshops, ICHI-W 2018., 8411818, Proceedings - 2018 IEEE International Conference on Healthcare Informatics Workshops, ICHI-W 2018, Institute of Electrical and Electronics Engineers Inc., pp. 86-87, 6th IEEE International Conference on Healthcare Informatics Workshops, ICHI-W 2018, New York, United States, 6/4/18. https://doi.org/10.1109/ICHI-W.2018.00032

Portable Phenotyping System : A Portable Machine-Learning Approach to i2b2 Obesity Challenge. / Sharma, Himanshu; Mao, Chengsheng; Zhang, Yizhen; Vatani, Haleh; Yao, Liang; Zhong, Yizhen; Rasmussen, Luke; Jiang, Guoqian; Pathak, Jyotishman; Luo, Yuan.

Proceedings - 2018 IEEE International Conference on Healthcare Informatics Workshops, ICHI-W 2018. Institute of Electrical and Electronics Engineers Inc., 2018. p. 86-87 8411818 (Proceedings - 2018 IEEE International Conference on Healthcare Informatics Workshops, ICHI-W 2018).

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

TY - GEN

T1 - Portable Phenotyping System

T2 - A Portable Machine-Learning Approach to i2b2 Obesity Challenge

AU - Sharma, Himanshu

AU - Mao, Chengsheng

AU - Zhang, Yizhen

AU - Vatani, Haleh

AU - Yao, Liang

AU - Zhong, Yizhen

AU - Rasmussen, Luke

AU - Jiang, Guoqian

AU - Pathak, Jyotishman

AU - Luo, Yuan

PY - 2018/7/16

Y1 - 2018/7/16

N2 - This paper presents a portable phenotyping system that is capable of integrating both rule-based and statistical machine learning based approaches. Our system utilizes UMLS to extract clinically relevant features from the unstructured text and then facilitates portability across different institutions and data systems by incorporating ODHSI's OMOP Common Data Model (CDM) to standardize necessary data elements. Our system can also store the key components of rule-based systems (e.g., regular expression matches) in the format of OMOP CDM, thus enabling the reuse, adaptation and extension of many existing rule-based clinical NLP systems. We experimented our system on the corpus from i2b2's Obesity Challenge as a pilot study. Our system facilitates portable phenotyping of obesity and its 15 comorbidities based on the unstructured patient discharge summaries, while achieving a performance that often ranked among the top 10 of the challenge participants. This standardization enables a consistent application of numerous rule-based and machine learning based classification techniques downstream.

AB - This paper presents a portable phenotyping system that is capable of integrating both rule-based and statistical machine learning based approaches. Our system utilizes UMLS to extract clinically relevant features from the unstructured text and then facilitates portability across different institutions and data systems by incorporating ODHSI's OMOP Common Data Model (CDM) to standardize necessary data elements. Our system can also store the key components of rule-based systems (e.g., regular expression matches) in the format of OMOP CDM, thus enabling the reuse, adaptation and extension of many existing rule-based clinical NLP systems. We experimented our system on the corpus from i2b2's Obesity Challenge as a pilot study. Our system facilitates portable phenotyping of obesity and its 15 comorbidities based on the unstructured patient discharge summaries, while achieving a performance that often ranked among the top 10 of the challenge participants. This standardization enables a consistent application of numerous rule-based and machine learning based classification techniques downstream.

KW - Machine Learning

KW - NLP

KW - OMOP CDM

KW - Obesity

KW - Portability

KW - i2b2

UR - http://www.scopus.com/inward/record.url?scp=85051027298&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85051027298&partnerID=8YFLogxK

U2 - 10.1109/ICHI-W.2018.00032

DO - 10.1109/ICHI-W.2018.00032

M3 - Conference contribution

T3 - Proceedings - 2018 IEEE International Conference on Healthcare Informatics Workshops, ICHI-W 2018

SP - 86

EP - 87

BT - Proceedings - 2018 IEEE International Conference on Healthcare Informatics Workshops, ICHI-W 2018

PB - Institute of Electrical and Electronics Engineers Inc.

ER -

Sharma H, Mao C, Zhang Y, Vatani H, Yao L, Zhong Y et al. Portable Phenotyping System: A Portable Machine-Learning Approach to i2b2 Obesity Challenge. In Proceedings - 2018 IEEE International Conference on Healthcare Informatics Workshops, ICHI-W 2018. Institute of Electrical and Electronics Engineers Inc. 2018. p. 86-87. 8411818. (Proceedings - 2018 IEEE International Conference on Healthcare Informatics Workshops, ICHI-W 2018). https://doi.org/10.1109/ICHI-W.2018.00032