Dynamical phenotyping: Using temporal analysis of clinically collected physiologic data to stratify populations

D. J. Albers, Noémie Elhadad, E. Tabak, A. Perotte, George Hripcsak

Research output: Contribution to journalArticle

Abstract

Using glucose time series data from a well measured population drawn from an electronic health record (EHR) repository, the variation in predictability of glucose values quantified by the time-delayed mutual information (TDMI) was explained using a mechanistic endocrine model and manual and automated review of written patient records. The results suggest that predictability of glucose varies with health state where the relationship (e.g., linear or inverse) depends on the source of the acuity. It was found that on a fine scale in parameter variation, the less insulin required to process glucose, a condition that correlates with good health, the more predictable glucose values were. Nevertheless, the most powerful effect on predictability in the EHR subpopulation was the presence or absence of variation in health state, specifically, in- and out-of-control glucose versus in-control glucose. Both of these results are clinically and scientifically relevant because the magnitude of glucose is the most commonly used indicator of health as opposed to glucose dynamics, thus providing for a connection between a mechanistic endocrine model and direct insight to human health via clinically collected data.

Original languageEnglish (US)
Article numbere96443
JournalPLoS One
Volume9
Issue number6
DOIs
StatePublished - Jun 16 2014

Fingerprint

phenotype
Glucose
glucose
Health
Population
Electronic Health Records
electronics
human health
Time series
time series analysis
insulin
Insulin

ASJC Scopus subject areas

  • Agricultural and Biological Sciences(all)
  • Biochemistry, Genetics and Molecular Biology(all)
  • Medicine(all)

Cite this

Dynamical phenotyping : Using temporal analysis of clinically collected physiologic data to stratify populations. / Albers, D. J.; Elhadad, Noémie; Tabak, E.; Perotte, A.; Hripcsak, George.

In: PLoS One, Vol. 9, No. 6, e96443, 16.06.2014.

Research output: Contribution to journalArticle

Albers, D. J. ; Elhadad, Noémie ; Tabak, E. ; Perotte, A. ; Hripcsak, George. / Dynamical phenotyping : Using temporal analysis of clinically collected physiologic data to stratify populations. In: PLoS One. 2014 ; Vol. 9, No. 6.
@article{e034db135aa1448b92706b997442ce39,
title = "Dynamical phenotyping: Using temporal analysis of clinically collected physiologic data to stratify populations",
abstract = "Using glucose time series data from a well measured population drawn from an electronic health record (EHR) repository, the variation in predictability of glucose values quantified by the time-delayed mutual information (TDMI) was explained using a mechanistic endocrine model and manual and automated review of written patient records. The results suggest that predictability of glucose varies with health state where the relationship (e.g., linear or inverse) depends on the source of the acuity. It was found that on a fine scale in parameter variation, the less insulin required to process glucose, a condition that correlates with good health, the more predictable glucose values were. Nevertheless, the most powerful effect on predictability in the EHR subpopulation was the presence or absence of variation in health state, specifically, in- and out-of-control glucose versus in-control glucose. Both of these results are clinically and scientifically relevant because the magnitude of glucose is the most commonly used indicator of health as opposed to glucose dynamics, thus providing for a connection between a mechanistic endocrine model and direct insight to human health via clinically collected data.",
author = "Albers, {D. J.} and No{\'e}mie Elhadad and E. Tabak and A. Perotte and George Hripcsak",
year = "2014",
month = "6",
day = "16",
doi = "10.1371/journal.pone.0096443",
language = "English (US)",
volume = "9",
journal = "PLoS One",
issn = "1932-6203",
publisher = "Public Library of Science",
number = "6",

}

TY - JOUR

T1 - Dynamical phenotyping

T2 - Using temporal analysis of clinically collected physiologic data to stratify populations

AU - Albers, D. J.

AU - Elhadad, Noémie

AU - Tabak, E.

AU - Perotte, A.

AU - Hripcsak, George

PY - 2014/6/16

Y1 - 2014/6/16

N2 - Using glucose time series data from a well measured population drawn from an electronic health record (EHR) repository, the variation in predictability of glucose values quantified by the time-delayed mutual information (TDMI) was explained using a mechanistic endocrine model and manual and automated review of written patient records. The results suggest that predictability of glucose varies with health state where the relationship (e.g., linear or inverse) depends on the source of the acuity. It was found that on a fine scale in parameter variation, the less insulin required to process glucose, a condition that correlates with good health, the more predictable glucose values were. Nevertheless, the most powerful effect on predictability in the EHR subpopulation was the presence or absence of variation in health state, specifically, in- and out-of-control glucose versus in-control glucose. Both of these results are clinically and scientifically relevant because the magnitude of glucose is the most commonly used indicator of health as opposed to glucose dynamics, thus providing for a connection between a mechanistic endocrine model and direct insight to human health via clinically collected data.

AB - Using glucose time series data from a well measured population drawn from an electronic health record (EHR) repository, the variation in predictability of glucose values quantified by the time-delayed mutual information (TDMI) was explained using a mechanistic endocrine model and manual and automated review of written patient records. The results suggest that predictability of glucose varies with health state where the relationship (e.g., linear or inverse) depends on the source of the acuity. It was found that on a fine scale in parameter variation, the less insulin required to process glucose, a condition that correlates with good health, the more predictable glucose values were. Nevertheless, the most powerful effect on predictability in the EHR subpopulation was the presence or absence of variation in health state, specifically, in- and out-of-control glucose versus in-control glucose. Both of these results are clinically and scientifically relevant because the magnitude of glucose is the most commonly used indicator of health as opposed to glucose dynamics, thus providing for a connection between a mechanistic endocrine model and direct insight to human health via clinically collected data.

UR - http://www.scopus.com/inward/record.url?scp=84903172946&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84903172946&partnerID=8YFLogxK

U2 - 10.1371/journal.pone.0096443

DO - 10.1371/journal.pone.0096443

M3 - Article

C2 - 24933368

AN - SCOPUS:84903172946

VL - 9

JO - PLoS One

JF - PLoS One

SN - 1932-6203

IS - 6

M1 - e96443

ER -