Cargando…

Predicting Serum Levels of Lithium-Treated Patients: A Supervised Machine Learning Approach

Routine monitoring of lithium levels is common clinical practice. This is because the lithium prediction strategies available developed by previous studies are still limited due to insufficient prediction performance. Thus, we used machine learning approaches to predict lithium concentration in a la...

Descripción completa

Detalles Bibliográficos
Autores principales: Hsu, Chih-Wei, Tsai, Shang-Ying, Wang, Liang-Jen, Liang, Chih-Sung, Carvalho, Andre F., Solmi, Marco, Vieta, Eduard, Lin, Pao-Yen, Hu, Chien-An, Kao, Hung-Yu
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2021
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8615637/
https://www.ncbi.nlm.nih.gov/pubmed/34829787
http://dx.doi.org/10.3390/biomedicines9111558
_version_ 1784604152428494848
author Hsu, Chih-Wei
Tsai, Shang-Ying
Wang, Liang-Jen
Liang, Chih-Sung
Carvalho, Andre F.
Solmi, Marco
Vieta, Eduard
Lin, Pao-Yen
Hu, Chien-An
Kao, Hung-Yu
author_facet Hsu, Chih-Wei
Tsai, Shang-Ying
Wang, Liang-Jen
Liang, Chih-Sung
Carvalho, Andre F.
Solmi, Marco
Vieta, Eduard
Lin, Pao-Yen
Hu, Chien-An
Kao, Hung-Yu
author_sort Hsu, Chih-Wei
collection PubMed
description Routine monitoring of lithium levels is common clinical practice. This is because the lithium prediction strategies available developed by previous studies are still limited due to insufficient prediction performance. Thus, we used machine learning approaches to predict lithium concentration in a large real-world dataset. Real-world data from multicenter electronic medical records were used in different machine learning algorithms to predict: (1) whether the serum level was 0.6–1.2 mmol/L or 0.0–0.6 mmol/L (binary prediction), and (2) its concentration value (continuous prediction). We developed models from 1505 samples through 5-fold cross-validation and used 204 independent samples to test their performance by evaluating their accuracy. Moreover, we ranked the most important clinical features in different models and reconstructed three reduced models with fewer clinical features. For binary and continuous predictions, the average accuracy of these models was 0.70–0.73 and 0.68–0.75, respectively. Seven features were listed as important features related to serum lithium levels of 0.6–1.2 mmol/L or higher lithium concentration, namely older age, lower systolic blood pressure, higher daily and last doses of lithium prescription, concomitant psychotropic drugs with valproic acid and -pine drugs, and comorbid substance-related disorders. After reducing the features in the three new predictive models, the binary or continuous models still had an average accuracy of 0.67–0.74. Machine learning processes complex clinical data and provides a potential tool for predicting lithium concentration. This may help in clinical decision-making and reduce the frequency of serum level monitoring.
format Online
Article
Text
id pubmed-8615637
institution National Center for Biotechnology Information
language English
publishDate 2021
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-86156372021-11-26 Predicting Serum Levels of Lithium-Treated Patients: A Supervised Machine Learning Approach Hsu, Chih-Wei Tsai, Shang-Ying Wang, Liang-Jen Liang, Chih-Sung Carvalho, Andre F. Solmi, Marco Vieta, Eduard Lin, Pao-Yen Hu, Chien-An Kao, Hung-Yu Biomedicines Article Routine monitoring of lithium levels is common clinical practice. This is because the lithium prediction strategies available developed by previous studies are still limited due to insufficient prediction performance. Thus, we used machine learning approaches to predict lithium concentration in a large real-world dataset. Real-world data from multicenter electronic medical records were used in different machine learning algorithms to predict: (1) whether the serum level was 0.6–1.2 mmol/L or 0.0–0.6 mmol/L (binary prediction), and (2) its concentration value (continuous prediction). We developed models from 1505 samples through 5-fold cross-validation and used 204 independent samples to test their performance by evaluating their accuracy. Moreover, we ranked the most important clinical features in different models and reconstructed three reduced models with fewer clinical features. For binary and continuous predictions, the average accuracy of these models was 0.70–0.73 and 0.68–0.75, respectively. Seven features were listed as important features related to serum lithium levels of 0.6–1.2 mmol/L or higher lithium concentration, namely older age, lower systolic blood pressure, higher daily and last doses of lithium prescription, concomitant psychotropic drugs with valproic acid and -pine drugs, and comorbid substance-related disorders. After reducing the features in the three new predictive models, the binary or continuous models still had an average accuracy of 0.67–0.74. Machine learning processes complex clinical data and provides a potential tool for predicting lithium concentration. This may help in clinical decision-making and reduce the frequency of serum level monitoring. MDPI 2021-10-28 /pmc/articles/PMC8615637/ /pubmed/34829787 http://dx.doi.org/10.3390/biomedicines9111558 Text en © 2021 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
Hsu, Chih-Wei
Tsai, Shang-Ying
Wang, Liang-Jen
Liang, Chih-Sung
Carvalho, Andre F.
Solmi, Marco
Vieta, Eduard
Lin, Pao-Yen
Hu, Chien-An
Kao, Hung-Yu
Predicting Serum Levels of Lithium-Treated Patients: A Supervised Machine Learning Approach
title Predicting Serum Levels of Lithium-Treated Patients: A Supervised Machine Learning Approach
title_full Predicting Serum Levels of Lithium-Treated Patients: A Supervised Machine Learning Approach
title_fullStr Predicting Serum Levels of Lithium-Treated Patients: A Supervised Machine Learning Approach
title_full_unstemmed Predicting Serum Levels of Lithium-Treated Patients: A Supervised Machine Learning Approach
title_short Predicting Serum Levels of Lithium-Treated Patients: A Supervised Machine Learning Approach
title_sort predicting serum levels of lithium-treated patients: a supervised machine learning approach
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8615637/
https://www.ncbi.nlm.nih.gov/pubmed/34829787
http://dx.doi.org/10.3390/biomedicines9111558
work_keys_str_mv AT hsuchihwei predictingserumlevelsoflithiumtreatedpatientsasupervisedmachinelearningapproach
AT tsaishangying predictingserumlevelsoflithiumtreatedpatientsasupervisedmachinelearningapproach
AT wangliangjen predictingserumlevelsoflithiumtreatedpatientsasupervisedmachinelearningapproach
AT liangchihsung predictingserumlevelsoflithiumtreatedpatientsasupervisedmachinelearningapproach
AT carvalhoandref predictingserumlevelsoflithiumtreatedpatientsasupervisedmachinelearningapproach
AT solmimarco predictingserumlevelsoflithiumtreatedpatientsasupervisedmachinelearningapproach
AT vietaeduard predictingserumlevelsoflithiumtreatedpatientsasupervisedmachinelearningapproach
AT linpaoyen predictingserumlevelsoflithiumtreatedpatientsasupervisedmachinelearningapproach
AT huchienan predictingserumlevelsoflithiumtreatedpatientsasupervisedmachinelearningapproach
AT kaohungyu predictingserumlevelsoflithiumtreatedpatientsasupervisedmachinelearningapproach