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

Simone Marini; Arianna Dagliati; Lucia Sacchi; Riccardo Bellazzi

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

Simone Marini, Arianna Dagliati, Lucia Sacchi, Riccardo Bellazzi

Division of Informatics, Imaging & Data Sciences (L5)

Universita Degli Studi di Pavia

Research output: Chapter in Book/Conference proceeding › Conference contribution › peer-review

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 language	English
Title of host publication	HEALTHINF 2016 - 9th International Conference on Health Informatics, Proceedings; Part of 9th International Joint Conference on Biomedical Engineering Systems and Technologies, BIOSTEC 2016
Editors	Haim Azhari, Hesham Ali, Ana Fred, James Gilbert, Carolina Ruiz, Jan Sliwa, Carla Quintao, Hugo Gamboa
Publisher	Science and Technology Publications Lda
Pages	338-344
Number of pages	7
ISBN (Electronic)	9789897581700
Publication status	Published - 1 Jan 2016
Event	9th International Conference on Health Informatics, HEALTHINF 2016 - Part of 9th International Joint Conference on Biomedical Engineering Systems and Technologies, BIOSTEC 2016 - Rome, Italy Duration: 21 Feb 2016 → 23 Feb 2016

Conference

Conference	9th International Conference on Health Informatics, HEALTHINF 2016 - Part of 9th International Joint Conference on Biomedical Engineering Systems and Technologies, BIOSTEC 2016
Country/Territory	Italy
City	Rome
Period	21/02/16 → 23/02/16

Keywords

Cohort modeling
Continuous time Bayesian network
Disease complexity
Type 2 diabetes

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

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 H. Azhari, H. Ali, A. Fred, J. Gilbert, C. Ruiz, J. Sliwa, C. Quintao, & H. Gamboa (Eds.), 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). Science and Technology Publications Lda.

Marini, Simone ; Dagliati, Arianna ; Sacchi, Lucia et al. / 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. editor / Haim Azhari ; Hesham Ali ; Ana Fred ; James Gilbert ; Carolina Ruiz ; Jan Sliwa ; Carla Quintao ; Hugo Gamboa. Science and Technology Publications Lda, 2016. pp. 338-344

@inproceedings{d08ac5908967403b9c2cdb58b049ac6f,

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",

month = jan,

day = "1",

language = "English",

pages = "338--344",

editor = "Haim Azhari and Hesham Ali and Ana Fred and James Gilbert and Carolina Ruiz and Jan Sliwa and Carla Quintao and Hugo Gamboa",

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 = "Science and Technology Publications Lda",

address = "Portugal",

note = "9th International Conference on Health Informatics, HEALTHINF 2016 - Part of 9th International Joint Conference on Biomedical Engineering Systems and Technologies, BIOSTEC 2016 ; Conference date: 21-02-2016 Through 23-02-2016",

}

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 H Azhari, H Ali, A Fred, J Gilbert, C Ruiz, J Sliwa, C Quintao & H Gamboa (eds), HEALTHINF 2016 - 9th International Conference on Health Informatics, Proceedings; Part of 9th International Joint Conference on Biomedical Engineering Systems and Technologies, BIOSTEC 2016. Science and Technology Publications Lda, 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, 21/02/16.

Learning T2D evolving complexity from EMR and administrative data by means of Continuous time Bayesian networks. / Marini, Simone; Dagliati, Arianna; Sacchi, Lucia et al.
HEALTHINF 2016 - 9th International Conference on Health Informatics, Proceedings; Part of 9th International Joint Conference on Biomedical Engineering Systems and Technologies, BIOSTEC 2016. ed. / Haim Azhari; Hesham Ali; Ana Fred; James Gilbert; Carolina Ruiz; Jan Sliwa; Carla Quintao; Hugo Gamboa. Science and Technology Publications Lda, 2016. p. 338-344.

Research output: Chapter in Book/Conference proceeding › Conference contribution › peer-review

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 - 2016/1/1

Y1 - 2016/1/1

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

M3 - Conference contribution

AN - SCOPUS:84969165079

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

A2 - Azhari, Haim

A2 - Ali, Hesham

A2 - Fred, Ana

A2 - Gilbert, James

A2 - Ruiz, Carolina

A2 - Sliwa, Jan

A2 - Quintao, Carla

A2 - Gamboa, Hugo

PB - Science and Technology Publications Lda

T2 - 9th International Conference on Health Informatics, HEALTHINF 2016 - Part of 9th International Joint Conference on Biomedical Engineering Systems and Technologies, BIOSTEC 2016

Y2 - 21 February 2016 through 23 February 2016

ER -

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 Azhari H, Ali H, Fred A, Gilbert J, Ruiz C, Sliwa J, Quintao C, Gamboa H, editors, HEALTHINF 2016 - 9th International Conference on Health Informatics, Proceedings; Part of 9th International Joint Conference on Biomedical Engineering Systems and Technologies, BIOSTEC 2016. Science and Technology Publications Lda. 2016. p. 338-344

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

Abstract

Conference

Keywords

UN SDGs

Other files and links

Fingerprint

Cite this