Cargando…

Extracting New Temporal Features to Improve the Interpretability of Undiagnosed Type 2 Diabetes Mellitus Prediction Models

Type 2 diabetes mellitus (T2DM) often results in high morbidity and mortality. In addition, T2DM presents a substantial financial burden for individuals and their families, health systems, and societies. According to studies and reports, globally, the incidence and prevalence of T2DM are increasing...

Descripción completa

Detalles Bibliográficos
Autores principales: Kocbek, Simon, Kocbek, Primož, Gosak, Lucija, Fijačko, Nino, Štiglic, Gregor
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8950921/
https://www.ncbi.nlm.nih.gov/pubmed/35330368
http://dx.doi.org/10.3390/jpm12030368
_version_ 1784675259265318912
author Kocbek, Simon
Kocbek, Primož
Gosak, Lucija
Fijačko, Nino
Štiglic, Gregor
author_facet Kocbek, Simon
Kocbek, Primož
Gosak, Lucija
Fijačko, Nino
Štiglic, Gregor
author_sort Kocbek, Simon
collection PubMed
description Type 2 diabetes mellitus (T2DM) often results in high morbidity and mortality. In addition, T2DM presents a substantial financial burden for individuals and their families, health systems, and societies. According to studies and reports, globally, the incidence and prevalence of T2DM are increasing rapidly. Several models have been built to predict T2DM onset in the future or detect undiagnosed T2DM in patients. Additional to the performance of such models, their interpretability is crucial for health experts, especially in personalized clinical prediction models. Data collected over 42 months from health check-up examinations and prescribed drugs data repositories of four primary healthcare providers were used in this study. We propose a framework consisting of LogicRegression based feature extraction and Least Absolute Shrinkage and Selection operator based prediction modeling for undiagnosed T2DM prediction. Performance of the models was measured using Area under the ROC curve (AUC) with corresponding confidence intervals. Results show that using LogicRegression based feature extraction resulted in simpler models, which are easier for healthcare experts to interpret, especially in cases with many binary features. Models developed using the proposed framework resulted in an AUC of 0.818 (95% Confidence Interval (CI): 0.812−0.823) that was comparable to more complex models (i.e., models with a larger number of features), where all features were included in prediction model development with the AUC of 0.816 (95% CI: 0.810−0.822). However, the difference in the number of used features was significant. This study proposes a framework for building interpretable models in healthcare that can contribute to higher trust in prediction models from healthcare experts.
format Online
Article
Text
id pubmed-8950921
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-89509212022-03-26 Extracting New Temporal Features to Improve the Interpretability of Undiagnosed Type 2 Diabetes Mellitus Prediction Models Kocbek, Simon Kocbek, Primož Gosak, Lucija Fijačko, Nino Štiglic, Gregor J Pers Med Article Type 2 diabetes mellitus (T2DM) often results in high morbidity and mortality. In addition, T2DM presents a substantial financial burden for individuals and their families, health systems, and societies. According to studies and reports, globally, the incidence and prevalence of T2DM are increasing rapidly. Several models have been built to predict T2DM onset in the future or detect undiagnosed T2DM in patients. Additional to the performance of such models, their interpretability is crucial for health experts, especially in personalized clinical prediction models. Data collected over 42 months from health check-up examinations and prescribed drugs data repositories of four primary healthcare providers were used in this study. We propose a framework consisting of LogicRegression based feature extraction and Least Absolute Shrinkage and Selection operator based prediction modeling for undiagnosed T2DM prediction. Performance of the models was measured using Area under the ROC curve (AUC) with corresponding confidence intervals. Results show that using LogicRegression based feature extraction resulted in simpler models, which are easier for healthcare experts to interpret, especially in cases with many binary features. Models developed using the proposed framework resulted in an AUC of 0.818 (95% Confidence Interval (CI): 0.812−0.823) that was comparable to more complex models (i.e., models with a larger number of features), where all features were included in prediction model development with the AUC of 0.816 (95% CI: 0.810−0.822). However, the difference in the number of used features was significant. This study proposes a framework for building interpretable models in healthcare that can contribute to higher trust in prediction models from healthcare experts. MDPI 2022-02-28 /pmc/articles/PMC8950921/ /pubmed/35330368 http://dx.doi.org/10.3390/jpm12030368 Text en © 2022 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Kocbek, Simon
Kocbek, Primož
Gosak, Lucija
Fijačko, Nino
Štiglic, Gregor
Extracting New Temporal Features to Improve the Interpretability of Undiagnosed Type 2 Diabetes Mellitus Prediction Models
title Extracting New Temporal Features to Improve the Interpretability of Undiagnosed Type 2 Diabetes Mellitus Prediction Models
title_full Extracting New Temporal Features to Improve the Interpretability of Undiagnosed Type 2 Diabetes Mellitus Prediction Models
title_fullStr Extracting New Temporal Features to Improve the Interpretability of Undiagnosed Type 2 Diabetes Mellitus Prediction Models
title_full_unstemmed Extracting New Temporal Features to Improve the Interpretability of Undiagnosed Type 2 Diabetes Mellitus Prediction Models
title_short Extracting New Temporal Features to Improve the Interpretability of Undiagnosed Type 2 Diabetes Mellitus Prediction Models
title_sort extracting new temporal features to improve the interpretability of undiagnosed type 2 diabetes mellitus prediction models
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8950921/
https://www.ncbi.nlm.nih.gov/pubmed/35330368
http://dx.doi.org/10.3390/jpm12030368
work_keys_str_mv AT kocbeksimon extractingnewtemporalfeaturestoimprovetheinterpretabilityofundiagnosedtype2diabetesmellituspredictionmodels
AT kocbekprimoz extractingnewtemporalfeaturestoimprovetheinterpretabilityofundiagnosedtype2diabetesmellituspredictionmodels
AT gosaklucija extractingnewtemporalfeaturestoimprovetheinterpretabilityofundiagnosedtype2diabetesmellituspredictionmodels
AT fijackonino extractingnewtemporalfeaturestoimprovetheinterpretabilityofundiagnosedtype2diabetesmellituspredictionmodels
AT stiglicgregor extractingnewtemporalfeaturestoimprovetheinterpretabilityofundiagnosedtype2diabetesmellituspredictionmodels