Analysis of epidemiological association patterns of serum thyrotropin by combining random forests and Bayesian networks.
<h4>Background</h4>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 interpretabili...
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Public Library of Science (PLoS)
2022-01-01
|
| Series: | PLoS ONE |
| Online Access: | https://doi.org/10.1371/journal.pone.0271610 |
| _version_ | 1829099012344512512 |
|---|---|
| author | Ann-Kristin Becker Till Ittermann Markus Dörr Stephan B Felix Matthias Nauck Alexander Teumer Uwe Völker Henry Völzke Lars Kaderali Neetika Nath |
| author_facet | Ann-Kristin Becker Till Ittermann Markus Dörr Stephan B Felix Matthias Nauck Alexander Teumer Uwe Völker Henry Völzke Lars Kaderali Neetika Nath |
| author_sort | Ann-Kristin Becker |
| collection | DOAJ |
| description | <h4>Background</h4>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.<h4>Method</h4>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.<h4>Results</h4>Evaluations using simulated data show that feature associations can be correctly recovered by combining random forests and Bayesian networks. The presented model achieves predictive accuracy that is similar to state-of-the-art models (root mean square error of 0.66, mean absolute error of 0.55, coefficient of determination of R2 = 0.15). We identify 62 relevant features from the final random forest model, ranging from general health variables over dietary and genetic factors to physiological, hematological and hemostasis parameters. The Bayesian network model is used to put these features into context and make the black-box random forest model more understandable.<h4>Conclusion</h4>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. |
| first_indexed | 2024-12-10T21:17:36Z |
| format | Article |
| id | doaj.art-14f023515ef44921a368174a33428a13 |
| institution | Directory Open Access Journal |
| issn | 1932-6203 |
| language | English |
| last_indexed | 2024-12-10T21:17:36Z |
| publishDate | 2022-01-01 |
| publisher | Public Library of Science (PLoS) |
| record_format | Article |
| series | PLoS ONE |
| spelling | doaj.art-14f023515ef44921a368174a33428a132022-12-22T01:33:14ZengPublic Library of Science (PLoS)PLoS ONE1932-62032022-01-01177e027161010.1371/journal.pone.0271610Analysis of epidemiological association patterns of serum thyrotropin by combining random forests and Bayesian networks.Ann-Kristin BeckerTill IttermannMarkus DörrStephan B FelixMatthias NauckAlexander TeumerUwe VölkerHenry VölzkeLars KaderaliNeetika Nath<h4>Background</h4>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.<h4>Method</h4>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.<h4>Results</h4>Evaluations using simulated data show that feature associations can be correctly recovered by combining random forests and Bayesian networks. The presented model achieves predictive accuracy that is similar to state-of-the-art models (root mean square error of 0.66, mean absolute error of 0.55, coefficient of determination of R2 = 0.15). We identify 62 relevant features from the final random forest model, ranging from general health variables over dietary and genetic factors to physiological, hematological and hemostasis parameters. The Bayesian network model is used to put these features into context and make the black-box random forest model more understandable.<h4>Conclusion</h4>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.https://doi.org/10.1371/journal.pone.0271610 |
| spellingShingle | Ann-Kristin Becker Till Ittermann Markus Dörr Stephan B Felix Matthias Nauck Alexander Teumer Uwe Völker Henry Völzke Lars Kaderali Neetika Nath Analysis of epidemiological association patterns of serum thyrotropin by combining random forests and Bayesian networks. PLoS ONE |
| title | Analysis of epidemiological association patterns of serum thyrotropin by combining random forests and Bayesian networks. |
| title_full | Analysis of epidemiological association patterns of serum thyrotropin by combining random forests and Bayesian networks. |
| title_fullStr | Analysis of epidemiological association patterns of serum thyrotropin by combining random forests and Bayesian networks. |
| title_full_unstemmed | Analysis of epidemiological association patterns of serum thyrotropin by combining random forests and Bayesian networks. |
| title_short | Analysis of epidemiological association patterns of serum thyrotropin by combining random forests and Bayesian networks. |
| title_sort | analysis of epidemiological association patterns of serum thyrotropin by combining random forests and bayesian networks |
| url | https://doi.org/10.1371/journal.pone.0271610 |
| work_keys_str_mv | AT annkristinbecker analysisofepidemiologicalassociationpatternsofserumthyrotropinbycombiningrandomforestsandbayesiannetworks AT tillittermann analysisofepidemiologicalassociationpatternsofserumthyrotropinbycombiningrandomforestsandbayesiannetworks AT markusdorr analysisofepidemiologicalassociationpatternsofserumthyrotropinbycombiningrandomforestsandbayesiannetworks AT stephanbfelix analysisofepidemiologicalassociationpatternsofserumthyrotropinbycombiningrandomforestsandbayesiannetworks AT matthiasnauck analysisofepidemiologicalassociationpatternsofserumthyrotropinbycombiningrandomforestsandbayesiannetworks AT alexanderteumer analysisofepidemiologicalassociationpatternsofserumthyrotropinbycombiningrandomforestsandbayesiannetworks AT uwevolker analysisofepidemiologicalassociationpatternsofserumthyrotropinbycombiningrandomforestsandbayesiannetworks AT henryvolzke analysisofepidemiologicalassociationpatternsofserumthyrotropinbycombiningrandomforestsandbayesiannetworks AT larskaderali analysisofepidemiologicalassociationpatternsofserumthyrotropinbycombiningrandomforestsandbayesiannetworks AT neetikanath analysisofepidemiologicalassociationpatternsofserumthyrotropinbycombiningrandomforestsandbayesiannetworks |