Exploiting Domain Knowledge as Causal Independencies in Modeling Gestational Diabetes

We consider the problem of modeling gestational diabetes in a clinical study and develop a domain expert-guided probabilistic model that is both interpretable and explainable. Specifically, we construct a probabilistic model based on causal independence (Noisy-Or) from a carefully chosen set of feat...

Descripción completa

Detalles Bibliográficos
Autores principales: Mathur, Saurabh, Karanam, Athresh, Radivojac, Predrag, Haas, David M., Kersting, Kristian, Natarajan, Sriraam
Formato: Online Artículo Texto
Lenguaje:English
Publicado: 2023
Materias:
Article
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9782711/
https://www.ncbi.nlm.nih.gov/pubmed/36540991
_version_ 1784857408061833216
author Mathur, Saurabh
Karanam, Athresh
Radivojac, Predrag
Haas, David M.
Kersting, Kristian
Natarajan, Sriraam
author_facet Mathur, Saurabh
Karanam, Athresh
Radivojac, Predrag
Haas, David M.
Kersting, Kristian
Natarajan, Sriraam
author_sort Mathur, Saurabh
collection PubMed
description We consider the problem of modeling gestational diabetes in a clinical study and develop a domain expert-guided probabilistic model that is both interpretable and explainable. Specifically, we construct a probabilistic model based on causal independence (Noisy-Or) from a carefully chosen set of features. We validate the efficacy of the model on the clinical study and demonstrate the importance of the features and the causal independence model.
format Online
Article
Text
id pubmed-9782711
institution National Center for Biotechnology Information
language English
publishDate 2023
record_format MEDLINE/PubMed
spelling pubmed-97827112023-01-01 Exploiting Domain Knowledge as Causal Independencies in Modeling Gestational Diabetes Mathur, Saurabh Karanam, Athresh Radivojac, Predrag Haas, David M. Kersting, Kristian Natarajan, Sriraam Pac Symp Biocomput Article We consider the problem of modeling gestational diabetes in a clinical study and develop a domain expert-guided probabilistic model that is both interpretable and explainable. Specifically, we construct a probabilistic model based on causal independence (Noisy-Or) from a carefully chosen set of features. We validate the efficacy of the model on the clinical study and demonstrate the importance of the features and the causal independence model. 2023 /pmc/articles/PMC9782711/ /pubmed/36540991 Text en https://creativecommons.org/licenses/by-nc/4.0/Open Access chapter published by World Scientific Publishing Company and distributed under the terms of the Creative Commons Attribution Non-Commercial (CC BY-NC) 4.0 License.
spellingShingle Article
Mathur, Saurabh
Karanam, Athresh
Radivojac, Predrag
Haas, David M.
Kersting, Kristian
Natarajan, Sriraam
Exploiting Domain Knowledge as Causal Independencies in Modeling Gestational Diabetes
title Exploiting Domain Knowledge as Causal Independencies in Modeling Gestational Diabetes
title_full Exploiting Domain Knowledge as Causal Independencies in Modeling Gestational Diabetes
title_fullStr Exploiting Domain Knowledge as Causal Independencies in Modeling Gestational Diabetes
title_full_unstemmed Exploiting Domain Knowledge as Causal Independencies in Modeling Gestational Diabetes
title_short Exploiting Domain Knowledge as Causal Independencies in Modeling Gestational Diabetes
title_sort exploiting domain knowledge as causal independencies in modeling gestational diabetes
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9782711/
https://www.ncbi.nlm.nih.gov/pubmed/36540991
work_keys_str_mv AT mathursaurabh exploitingdomainknowledgeascausalindependenciesinmodelinggestationaldiabetes
AT karanamathresh exploitingdomainknowledgeascausalindependenciesinmodelinggestationaldiabetes
AT radivojacpredrag exploitingdomainknowledgeascausalindependenciesinmodelinggestationaldiabetes
AT haasdavidm exploitingdomainknowledgeascausalindependenciesinmodelinggestationaldiabetes
AT kerstingkristian exploitingdomainknowledgeascausalindependenciesinmodelinggestationaldiabetes
AT natarajansriraam exploitingdomainknowledgeascausalindependenciesinmodelinggestationaldiabetes

Ejemplares similares