Using hidden Markov models to determine changes in subject data over time, studying the immunoregulatory effect of mesenchymal stem cells

Edgar F. Black, Luigi Marini, Ashwini Vaidya, Dora Berman-Weinberg, Melissa Willman, Dan Salomon, Amelia Bartholomew, Norma S Kenyon, Kenton McHenry

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

3 Citations (Scopus)

Abstract

A novel application of Hidden Markov Models is used to help research intended to test the immunuregulatory effects of mesenchymal stem cells in a cynomolgus monkey model of islet transplantation. The Hidden Markov Model, an unsupervised learning data mining technique, is used to automatically determine the postoperative day (POD) corresponding to a decrease of graft function, a possible sign of transplant rejection, on nonhuman primates after isolated islet cell transplant. Currently, decrease of graft function is being determined solely on experts' judgment. Further, information gathered from the evaluation of constructed Hidden Markov Models is used as part of a clustering method to aggregate the nonhuman subjects into groups or clusters with the objective of finding similarities that could potentially help predict the health outcome of subjects undergoing postoperative care. Results on expert labelled data show the HMM to be accurate 60% of the time. Clusters based on the HMMs further suggest a possible correspondence between donor haplotypes matching and loss of function outcomes.

Original languageEnglish (US)
Title of host publicationProceedings - 2014 IEEE 10th International Conference on eScience, eScience 2014
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages83-91
Number of pages9
Volume1
ISBN (Print)9781479942886
DOIs
StatePublished - Dec 2 2014
Externally publishedYes
Event10th IEEE International Conference on eScience, eScience 2014 - Guaruja, Brazil
Duration: Oct 20 2014Oct 24 2014

Other

Other10th IEEE International Conference on eScience, eScience 2014
CountryBrazil
CityGuaruja
Period10/20/1410/24/14

Fingerprint

Hidden Markov models
Stem cells
Transplants
Grafts
Unsupervised learning
Data mining
Health

Keywords

  • data mining
  • Hidden Markov Models
  • unsupervised learning

ASJC Scopus subject areas

  • Computer Science(all)

Cite this

Black, E. F., Marini, L., Vaidya, A., Berman-Weinberg, D., Willman, M., Salomon, D., ... McHenry, K. (2014). Using hidden Markov models to determine changes in subject data over time, studying the immunoregulatory effect of mesenchymal stem cells. In Proceedings - 2014 IEEE 10th International Conference on eScience, eScience 2014 (Vol. 1, pp. 83-91). [6972252] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/eScience.2014.29

Using hidden Markov models to determine changes in subject data over time, studying the immunoregulatory effect of mesenchymal stem cells. / Black, Edgar F.; Marini, Luigi; Vaidya, Ashwini; Berman-Weinberg, Dora; Willman, Melissa; Salomon, Dan; Bartholomew, Amelia; Kenyon, Norma S; McHenry, Kenton.

Proceedings - 2014 IEEE 10th International Conference on eScience, eScience 2014. Vol. 1 Institute of Electrical and Electronics Engineers Inc., 2014. p. 83-91 6972252.

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

Black, EF, Marini, L, Vaidya, A, Berman-Weinberg, D, Willman, M, Salomon, D, Bartholomew, A, Kenyon, NS & McHenry, K 2014, Using hidden Markov models to determine changes in subject data over time, studying the immunoregulatory effect of mesenchymal stem cells. in Proceedings - 2014 IEEE 10th International Conference on eScience, eScience 2014. vol. 1, 6972252, Institute of Electrical and Electronics Engineers Inc., pp. 83-91, 10th IEEE International Conference on eScience, eScience 2014, Guaruja, Brazil, 10/20/14. https://doi.org/10.1109/eScience.2014.29
Black EF, Marini L, Vaidya A, Berman-Weinberg D, Willman M, Salomon D et al. Using hidden Markov models to determine changes in subject data over time, studying the immunoregulatory effect of mesenchymal stem cells. In Proceedings - 2014 IEEE 10th International Conference on eScience, eScience 2014. Vol. 1. Institute of Electrical and Electronics Engineers Inc. 2014. p. 83-91. 6972252 https://doi.org/10.1109/eScience.2014.29
Black, Edgar F. ; Marini, Luigi ; Vaidya, Ashwini ; Berman-Weinberg, Dora ; Willman, Melissa ; Salomon, Dan ; Bartholomew, Amelia ; Kenyon, Norma S ; McHenry, Kenton. / Using hidden Markov models to determine changes in subject data over time, studying the immunoregulatory effect of mesenchymal stem cells. Proceedings - 2014 IEEE 10th International Conference on eScience, eScience 2014. Vol. 1 Institute of Electrical and Electronics Engineers Inc., 2014. pp. 83-91
@inproceedings{b6e395def1204c48909c23817aa43aae,
title = "Using hidden Markov models to determine changes in subject data over time, studying the immunoregulatory effect of mesenchymal stem cells",
abstract = "A novel application of Hidden Markov Models is used to help research intended to test the immunuregulatory effects of mesenchymal stem cells in a cynomolgus monkey model of islet transplantation. The Hidden Markov Model, an unsupervised learning data mining technique, is used to automatically determine the postoperative day (POD) corresponding to a decrease of graft function, a possible sign of transplant rejection, on nonhuman primates after isolated islet cell transplant. Currently, decrease of graft function is being determined solely on experts' judgment. Further, information gathered from the evaluation of constructed Hidden Markov Models is used as part of a clustering method to aggregate the nonhuman subjects into groups or clusters with the objective of finding similarities that could potentially help predict the health outcome of subjects undergoing postoperative care. Results on expert labelled data show the HMM to be accurate 60{\%} of the time. Clusters based on the HMMs further suggest a possible correspondence between donor haplotypes matching and loss of function outcomes.",
keywords = "data mining, Hidden Markov Models, unsupervised learning",
author = "Black, {Edgar F.} and Luigi Marini and Ashwini Vaidya and Dora Berman-Weinberg and Melissa Willman and Dan Salomon and Amelia Bartholomew and Kenyon, {Norma S} and Kenton McHenry",
year = "2014",
month = "12",
day = "2",
doi = "10.1109/eScience.2014.29",
language = "English (US)",
isbn = "9781479942886",
volume = "1",
pages = "83--91",
booktitle = "Proceedings - 2014 IEEE 10th International Conference on eScience, eScience 2014",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - Using hidden Markov models to determine changes in subject data over time, studying the immunoregulatory effect of mesenchymal stem cells

AU - Black, Edgar F.

AU - Marini, Luigi

AU - Vaidya, Ashwini

AU - Berman-Weinberg, Dora

AU - Willman, Melissa

AU - Salomon, Dan

AU - Bartholomew, Amelia

AU - Kenyon, Norma S

AU - McHenry, Kenton

PY - 2014/12/2

Y1 - 2014/12/2

N2 - A novel application of Hidden Markov Models is used to help research intended to test the immunuregulatory effects of mesenchymal stem cells in a cynomolgus monkey model of islet transplantation. The Hidden Markov Model, an unsupervised learning data mining technique, is used to automatically determine the postoperative day (POD) corresponding to a decrease of graft function, a possible sign of transplant rejection, on nonhuman primates after isolated islet cell transplant. Currently, decrease of graft function is being determined solely on experts' judgment. Further, information gathered from the evaluation of constructed Hidden Markov Models is used as part of a clustering method to aggregate the nonhuman subjects into groups or clusters with the objective of finding similarities that could potentially help predict the health outcome of subjects undergoing postoperative care. Results on expert labelled data show the HMM to be accurate 60% of the time. Clusters based on the HMMs further suggest a possible correspondence between donor haplotypes matching and loss of function outcomes.

AB - A novel application of Hidden Markov Models is used to help research intended to test the immunuregulatory effects of mesenchymal stem cells in a cynomolgus monkey model of islet transplantation. The Hidden Markov Model, an unsupervised learning data mining technique, is used to automatically determine the postoperative day (POD) corresponding to a decrease of graft function, a possible sign of transplant rejection, on nonhuman primates after isolated islet cell transplant. Currently, decrease of graft function is being determined solely on experts' judgment. Further, information gathered from the evaluation of constructed Hidden Markov Models is used as part of a clustering method to aggregate the nonhuman subjects into groups or clusters with the objective of finding similarities that could potentially help predict the health outcome of subjects undergoing postoperative care. Results on expert labelled data show the HMM to be accurate 60% of the time. Clusters based on the HMMs further suggest a possible correspondence between donor haplotypes matching and loss of function outcomes.

KW - data mining

KW - Hidden Markov Models

KW - unsupervised learning

UR - http://www.scopus.com/inward/record.url?scp=84919482451&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84919482451&partnerID=8YFLogxK

U2 - 10.1109/eScience.2014.29

DO - 10.1109/eScience.2014.29

M3 - Conference contribution

AN - SCOPUS:84919482451

SN - 9781479942886

VL - 1

SP - 83

EP - 91

BT - Proceedings - 2014 IEEE 10th International Conference on eScience, eScience 2014

PB - Institute of Electrical and Electronics Engineers Inc.

ER -