Analysis of epidemiological association patterns of serum thyrotropin by combining random forests and Bayesian networks

Approaching epidemiological data with flexible machine learning algorithms is of great value for understanding disease-specific association patterns. However, it can be difficult to correctly extract and understand those patterns due to the lack of model interpretability. We here propose a machine l...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:PloS one Jg. 17; H. 7; S. e0271610
Hauptverfasser: Becker, Ann-Kristin, Ittermann, Till, Dörr, Markus, Felix, Stephan B., Nauck, Matthias, Teumer, Alexander, Völker, Uwe, Völzke, Henry, Kaderali, Lars, Nath, Neetika
Format: Journal Article
Sprache:Englisch
Veröffentlicht: San Francisco Public Library of Science 21.07.2022
Public Library of Science (PLoS)
Schlagworte:
Algorithms
Analysis
Bayesian analysis
Bayesian statistical decision theory
Biology and Life Sciences
Computer and Information Sciences
Decision making
Decision trees
Diet
Epidemiology
Evaluation
Genetic factors
Hemostasis
Hemostatics
Learning algorithms
Machine learning
Mathematical models
Medicine and Health Sciences
Model accuracy
Modelling
Network analysis
Physiological effects
Pituitary gland
Population studies
Properties
Random variables
Research and Analysis Methods
Ships
Thyroid
Thyroid gland
Thyroid-stimulating hormone
Thyrotropin
Workflow
Germany
ISSN:1932-6203, 1932-6203
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Approaching epidemiological data with flexible machine learning algorithms is of great value for understanding disease-specific association patterns. However, it can be difficult to correctly extract and understand those patterns due to the lack of model interpretability. We here propose a machine learning workflow that combines random forests with Bayesian network surrogate models to allow for a deeper level of interpretation of complex association patterns. We first evaluate the proposed workflow on synthetic data. We then apply it to data from the large population-based Study of Health in Pomerania (SHIP). Based on this combination, we discover and interpret broad patterns of individual serum TSH concentrations, an important marker of thyroid functionality. We demonstrate that the combination of random forest and Bayesian network analysis is helpful to reveal and interpret broad association patterns of individual TSH concentrations. The discovered patterns are in line with state-of-the-art literature. They may be useful for future thyroid research and improved dosing of therapeutics.
Bibliographie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
Competing Interests: The authors have declared that no competing interests exist.
ISSN:1932-6203
1932-6203
DOI:10.1371/journal.pone.0271610