Learning T2D Evolving Complexity from EMR and Administrative Data by Means of Continuous Time Bayesian Networks

Simone Marini, Arianna Dagliati, Lucia Sacchi, Riccardo Bellazzi

2016

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.

Paper Citation

in Harvard Style

Marini S., Dagliati A., Sacchi L. and Bellazzi R. (2016). Learning T2D Evolving Complexity from EMR and Administrative Data by Means of Continuous Time Bayesian Networks . In Proceedings of the 9th International Joint Conference on Biomedical Engineering Systems and Technologies - Volume 5: HEALTHINF, (BIOSTEC 2016) ISBN 978-989-758-170-0, pages 338-344. DOI: 10.5220/0005708103380344

in Bibtex Style

@conference{healthinf16,
author={Simone Marini and Arianna Dagliati and Lucia Sacchi and Riccardo Bellazzi},
title={Learning T2D Evolving Complexity from EMR and Administrative Data by Means of Continuous Time Bayesian Networks},
booktitle={Proceedings of the 9th International Joint Conference on Biomedical Engineering Systems and Technologies - Volume 5: HEALTHINF, (BIOSTEC 2016)},
year={2016},
pages={338-344},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0005708103380344},
isbn={978-989-758-170-0},
}

in EndNote Style

TY - CONF
JO - Proceedings of the 9th International Joint Conference on Biomedical Engineering Systems and Technologies - Volume 5: HEALTHINF, (BIOSTEC 2016)
TI - Learning T2D Evolving Complexity from EMR and Administrative Data by Means of Continuous Time Bayesian Networks
SN - 978-989-758-170-0
AU - Marini S.
AU - Dagliati A.
AU - Sacchi L.
AU - Bellazzi R.
PY - 2016
SP - 338
EP - 344
DO - 10.5220/0005708103380344