Temporal Pattern and Association Discovery of Diagnosis Codes Using Deep Learning

Saaed Mehrabi, Sunghwan Sohn, Dingheng Li, Joshua J. Pankratz, Terry M Therneau, Jennifer St. Sauver, Hongfang D Liu, Mathew Palakal

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

15 Citations (Scopus)

Abstract

Longitudinal health records contain data on patients' visits, condition, treatment, and test results representing progression of their health status over time. In poorly understood patient populations, such data are particularly helpful in characterizing disease progression and early detection. In this work we developed a deep learning algorithm for temporal pattern discovery over Rochester Epidemiology Project data. We modeled each patient's records as a matrix of temporal clinical events with ICD9 and HCUP CSS diagnosis codes as rows and years of diagnosis as columns. Patients aged 18 or younger at the time of diagnosis were selected. A deep Boltzmann machine network with three hidden layers was constructed with each patient's diagnosis matrix values as visible nodes. The final weights of the network model were analyzed as the common features among patients' records.

Original languageEnglish (US)
Title of host publicationProceedings - 2015 IEEE International Conference on Healthcare Informatics, ICHI 2015
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages408-416
Number of pages9
ISBN (Print)9781467395489
DOIs
StatePublished - Dec 8 2015
Event3rd IEEE International Conference on Healthcare Informatics, ICHI 2015 - Dallas, United States
Duration: Oct 21 2015Oct 23 2015

Other

Other3rd IEEE International Conference on Healthcare Informatics, ICHI 2015
CountryUnited States
CityDallas
Period10/21/1510/23/15

Fingerprint

Learning
Health Status
Disease Progression
Epidemiology
Weights and Measures
Health
Population
Therapeutics

Keywords

  • Deep Learning
  • Rochester Epidemiology Project
  • Temporal Pattern Discovery

ASJC Scopus subject areas

  • Health Informatics

Cite this

Mehrabi, S., Sohn, S., Li, D., Pankratz, J. J., Therneau, T. M., St. Sauver, J., ... Palakal, M. (2015). Temporal Pattern and Association Discovery of Diagnosis Codes Using Deep Learning. In Proceedings - 2015 IEEE International Conference on Healthcare Informatics, ICHI 2015 (pp. 408-416). [7349719] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICHI.2015.58

Temporal Pattern and Association Discovery of Diagnosis Codes Using Deep Learning. / Mehrabi, Saaed; Sohn, Sunghwan; Li, Dingheng; Pankratz, Joshua J.; Therneau, Terry M; St. Sauver, Jennifer; Liu, Hongfang D; Palakal, Mathew.

Proceedings - 2015 IEEE International Conference on Healthcare Informatics, ICHI 2015. Institute of Electrical and Electronics Engineers Inc., 2015. p. 408-416 7349719.

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

Mehrabi, S, Sohn, S, Li, D, Pankratz, JJ, Therneau, TM, St. Sauver, J, Liu, HD & Palakal, M 2015, Temporal Pattern and Association Discovery of Diagnosis Codes Using Deep Learning. in Proceedings - 2015 IEEE International Conference on Healthcare Informatics, ICHI 2015., 7349719, Institute of Electrical and Electronics Engineers Inc., pp. 408-416, 3rd IEEE International Conference on Healthcare Informatics, ICHI 2015, Dallas, United States, 10/21/15. https://doi.org/10.1109/ICHI.2015.58
Mehrabi S, Sohn S, Li D, Pankratz JJ, Therneau TM, St. Sauver J et al. Temporal Pattern and Association Discovery of Diagnosis Codes Using Deep Learning. In Proceedings - 2015 IEEE International Conference on Healthcare Informatics, ICHI 2015. Institute of Electrical and Electronics Engineers Inc. 2015. p. 408-416. 7349719 https://doi.org/10.1109/ICHI.2015.58
Mehrabi, Saaed ; Sohn, Sunghwan ; Li, Dingheng ; Pankratz, Joshua J. ; Therneau, Terry M ; St. Sauver, Jennifer ; Liu, Hongfang D ; Palakal, Mathew. / Temporal Pattern and Association Discovery of Diagnosis Codes Using Deep Learning. Proceedings - 2015 IEEE International Conference on Healthcare Informatics, ICHI 2015. Institute of Electrical and Electronics Engineers Inc., 2015. pp. 408-416
@inproceedings{de94f649f9134e4c90225346d5aa6714,
title = "Temporal Pattern and Association Discovery of Diagnosis Codes Using Deep Learning",
abstract = "Longitudinal health records contain data on patients' visits, condition, treatment, and test results representing progression of their health status over time. In poorly understood patient populations, such data are particularly helpful in characterizing disease progression and early detection. In this work we developed a deep learning algorithm for temporal pattern discovery over Rochester Epidemiology Project data. We modeled each patient's records as a matrix of temporal clinical events with ICD9 and HCUP CSS diagnosis codes as rows and years of diagnosis as columns. Patients aged 18 or younger at the time of diagnosis were selected. A deep Boltzmann machine network with three hidden layers was constructed with each patient's diagnosis matrix values as visible nodes. The final weights of the network model were analyzed as the common features among patients' records.",
keywords = "Deep Learning, Rochester Epidemiology Project, Temporal Pattern Discovery",
author = "Saaed Mehrabi and Sunghwan Sohn and Dingheng Li and Pankratz, {Joshua J.} and Therneau, {Terry M} and {St. Sauver}, Jennifer and Liu, {Hongfang D} and Mathew Palakal",
year = "2015",
month = "12",
day = "8",
doi = "10.1109/ICHI.2015.58",
language = "English (US)",
isbn = "9781467395489",
pages = "408--416",
booktitle = "Proceedings - 2015 IEEE International Conference on Healthcare Informatics, ICHI 2015",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - Temporal Pattern and Association Discovery of Diagnosis Codes Using Deep Learning

AU - Mehrabi, Saaed

AU - Sohn, Sunghwan

AU - Li, Dingheng

AU - Pankratz, Joshua J.

AU - Therneau, Terry M

AU - St. Sauver, Jennifer

AU - Liu, Hongfang D

AU - Palakal, Mathew

PY - 2015/12/8

Y1 - 2015/12/8

N2 - Longitudinal health records contain data on patients' visits, condition, treatment, and test results representing progression of their health status over time. In poorly understood patient populations, such data are particularly helpful in characterizing disease progression and early detection. In this work we developed a deep learning algorithm for temporal pattern discovery over Rochester Epidemiology Project data. We modeled each patient's records as a matrix of temporal clinical events with ICD9 and HCUP CSS diagnosis codes as rows and years of diagnosis as columns. Patients aged 18 or younger at the time of diagnosis were selected. A deep Boltzmann machine network with three hidden layers was constructed with each patient's diagnosis matrix values as visible nodes. The final weights of the network model were analyzed as the common features among patients' records.

AB - Longitudinal health records contain data on patients' visits, condition, treatment, and test results representing progression of their health status over time. In poorly understood patient populations, such data are particularly helpful in characterizing disease progression and early detection. In this work we developed a deep learning algorithm for temporal pattern discovery over Rochester Epidemiology Project data. We modeled each patient's records as a matrix of temporal clinical events with ICD9 and HCUP CSS diagnosis codes as rows and years of diagnosis as columns. Patients aged 18 or younger at the time of diagnosis were selected. A deep Boltzmann machine network with three hidden layers was constructed with each patient's diagnosis matrix values as visible nodes. The final weights of the network model were analyzed as the common features among patients' records.

KW - Deep Learning

KW - Rochester Epidemiology Project

KW - Temporal Pattern Discovery

UR - http://www.scopus.com/inward/record.url?scp=84966421136&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84966421136&partnerID=8YFLogxK

U2 - 10.1109/ICHI.2015.58

DO - 10.1109/ICHI.2015.58

M3 - Conference contribution

SN - 9781467395489

SP - 408

EP - 416

BT - Proceedings - 2015 IEEE International Conference on Healthcare Informatics, ICHI 2015

PB - Institute of Electrical and Electronics Engineers Inc.

ER -