Learning T2D evolving complexity from EMR and administrative data by means of Continuous time Bayesian networks

Simone Marini, Arianna Dagliati, Lucia Sacchi, Riccardo Bellazzi

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

Abstract

Predicting the complexity level (i.e. the number of complications and their related hospitalizations) in a T2D cohort is a critical step in prevention, resource optimization and overall patient management. Our data set was obtained by monitoring a T2D diabetic cohort along up to 10 years through electronic medical records of a local healthcare agency data warehouse. In order to conveniently handle temporarily sparse data, we designed a model describing the cohort evolution with Continuous Time Bayesian Networks (CTBN). The network structure and its parameters are entirely data driven. Compared to traditional Bayesian Networks, CTBNs admit cycles. As consequence, CTBNs fit the complexity of chronic metabolic syndromes where variables show a reciprocal influence. Network nodes represent metabolic (glycated hemoglobin, lipid profile (cholesterol, triglycerides), and biometric (BMI) data. We observed how these variables directly or indirectly affect the disease level of complexity, and how the variables influence the cumulative adverse events a patient undergoes.

Original languageEnglish
Title of host publicationHEALTHINF 2016 - 9th International Conference on Health Informatics, Proceedings; Part of 9th International Joint Conference on Biomedical Engineering Systems and Technologies, BIOSTEC 2016
PublisherSciTePress
Pages338-344
Number of pages7
ISBN (Print)9789897581700
Publication statusPublished - 2016
Event9th International Conference on Health Informatics, HEALTHINF 2016 - Part of 9th International Joint Conference on Biomedical Engineering Systems and Technologies, BIOSTEC 2016 - Rome, Italy
Duration: Feb 21 2016Feb 23 2016

Other

Other9th International Conference on Health Informatics, HEALTHINF 2016 - Part of 9th International Joint Conference on Biomedical Engineering Systems and Technologies, BIOSTEC 2016
CountryItaly
CityRome
Period2/21/162/23/16

Fingerprint

Bayesian networks
Electronic medical equipment
Data warehouses
Hemoglobin
Cholesterol
Biometrics
Lipids
Monitoring
Triglycerides

Keywords

  • Cohort modeling
  • Continuous time Bayesian network
  • Disease complexity
  • Type 2 diabetes

ASJC Scopus subject areas

  • Biomedical Engineering
  • Electrical and Electronic Engineering

Cite this

Marini, S., Dagliati, A., Sacchi, L., & Bellazzi, R. (2016). Learning T2D evolving complexity from EMR and administrative data by means of Continuous time Bayesian networks. In HEALTHINF 2016 - 9th International Conference on Health Informatics, Proceedings; Part of 9th International Joint Conference on Biomedical Engineering Systems and Technologies, BIOSTEC 2016 (pp. 338-344). SciTePress.

Learning T2D evolving complexity from EMR and administrative data by means of Continuous time Bayesian networks. / Marini, Simone; Dagliati, Arianna; Sacchi, Lucia; Bellazzi, Riccardo.

HEALTHINF 2016 - 9th International Conference on Health Informatics, Proceedings; Part of 9th International Joint Conference on Biomedical Engineering Systems and Technologies, BIOSTEC 2016. SciTePress, 2016. p. 338-344.

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

Marini, S, Dagliati, A, Sacchi, L & Bellazzi, R 2016, Learning T2D evolving complexity from EMR and administrative data by means of Continuous time Bayesian networks. in HEALTHINF 2016 - 9th International Conference on Health Informatics, Proceedings; Part of 9th International Joint Conference on Biomedical Engineering Systems and Technologies, BIOSTEC 2016. SciTePress, pp. 338-344, 9th International Conference on Health Informatics, HEALTHINF 2016 - Part of 9th International Joint Conference on Biomedical Engineering Systems and Technologies, BIOSTEC 2016, Rome, Italy, 2/21/16.
Marini S, Dagliati A, Sacchi L, Bellazzi R. Learning T2D evolving complexity from EMR and administrative data by means of Continuous time Bayesian networks. In HEALTHINF 2016 - 9th International Conference on Health Informatics, Proceedings; Part of 9th International Joint Conference on Biomedical Engineering Systems and Technologies, BIOSTEC 2016. SciTePress. 2016. p. 338-344
Marini, Simone ; Dagliati, Arianna ; Sacchi, Lucia ; Bellazzi, Riccardo. / Learning T2D evolving complexity from EMR and administrative data by means of Continuous time Bayesian networks. HEALTHINF 2016 - 9th International Conference on Health Informatics, Proceedings; Part of 9th International Joint Conference on Biomedical Engineering Systems and Technologies, BIOSTEC 2016. SciTePress, 2016. pp. 338-344
@inproceedings{ccc2f64198464628b197bce167e00700,
title = "Learning T2D evolving complexity from EMR and administrative data by means of Continuous time Bayesian networks",
abstract = "Predicting the complexity level (i.e. the number of complications and their related hospitalizations) in a T2D cohort is a critical step in prevention, resource optimization and overall patient management. Our data set was obtained by monitoring a T2D diabetic cohort along up to 10 years through electronic medical records of a local healthcare agency data warehouse. In order to conveniently handle temporarily sparse data, we designed a model describing the cohort evolution with Continuous Time Bayesian Networks (CTBN). The network structure and its parameters are entirely data driven. Compared to traditional Bayesian Networks, CTBNs admit cycles. As consequence, CTBNs fit the complexity of chronic metabolic syndromes where variables show a reciprocal influence. Network nodes represent metabolic (glycated hemoglobin, lipid profile (cholesterol, triglycerides), and biometric (BMI) data. We observed how these variables directly or indirectly affect the disease level of complexity, and how the variables influence the cumulative adverse events a patient undergoes.",
keywords = "Cohort modeling, Continuous time Bayesian network, Disease complexity, Type 2 diabetes",
author = "Simone Marini and Arianna Dagliati and Lucia Sacchi and Riccardo Bellazzi",
year = "2016",
language = "English",
isbn = "9789897581700",
pages = "338--344",
booktitle = "HEALTHINF 2016 - 9th International Conference on Health Informatics, Proceedings; Part of 9th International Joint Conference on Biomedical Engineering Systems and Technologies, BIOSTEC 2016",
publisher = "SciTePress",

}

TY - GEN

T1 - Learning T2D evolving complexity from EMR and administrative data by means of Continuous time Bayesian networks

AU - Marini, Simone

AU - Dagliati, Arianna

AU - Sacchi, Lucia

AU - Bellazzi, Riccardo

PY - 2016

Y1 - 2016

N2 - Predicting the complexity level (i.e. the number of complications and their related hospitalizations) in a T2D cohort is a critical step in prevention, resource optimization and overall patient management. Our data set was obtained by monitoring a T2D diabetic cohort along up to 10 years through electronic medical records of a local healthcare agency data warehouse. In order to conveniently handle temporarily sparse data, we designed a model describing the cohort evolution with Continuous Time Bayesian Networks (CTBN). The network structure and its parameters are entirely data driven. Compared to traditional Bayesian Networks, CTBNs admit cycles. As consequence, CTBNs fit the complexity of chronic metabolic syndromes where variables show a reciprocal influence. Network nodes represent metabolic (glycated hemoglobin, lipid profile (cholesterol, triglycerides), and biometric (BMI) data. We observed how these variables directly or indirectly affect the disease level of complexity, and how the variables influence the cumulative adverse events a patient undergoes.

AB - Predicting the complexity level (i.e. the number of complications and their related hospitalizations) in a T2D cohort is a critical step in prevention, resource optimization and overall patient management. Our data set was obtained by monitoring a T2D diabetic cohort along up to 10 years through electronic medical records of a local healthcare agency data warehouse. In order to conveniently handle temporarily sparse data, we designed a model describing the cohort evolution with Continuous Time Bayesian Networks (CTBN). The network structure and its parameters are entirely data driven. Compared to traditional Bayesian Networks, CTBNs admit cycles. As consequence, CTBNs fit the complexity of chronic metabolic syndromes where variables show a reciprocal influence. Network nodes represent metabolic (glycated hemoglobin, lipid profile (cholesterol, triglycerides), and biometric (BMI) data. We observed how these variables directly or indirectly affect the disease level of complexity, and how the variables influence the cumulative adverse events a patient undergoes.

KW - Cohort modeling

KW - Continuous time Bayesian network

KW - Disease complexity

KW - Type 2 diabetes

UR - http://www.scopus.com/inward/record.url?scp=84969165079&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84969165079&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:84969165079

SN - 9789897581700

SP - 338

EP - 344

BT - HEALTHINF 2016 - 9th International Conference on Health Informatics, Proceedings; Part of 9th International Joint Conference on Biomedical Engineering Systems and Technologies, BIOSTEC 2016

PB - SciTePress

ER -