Developing a machine learning-based predictive model for levothyroxine dosage estimation in hypothyroid patients: a retrospective study

Hypothyroidism, a common endocrine disorder, has a high incidence in women and increases with age. Levothyroxine (LT4) is the standard therapy; however, achieving clinical and biochemical euthyroidism is challenging. Therefore, developing an accurate model for predicting LT4 dosage is crucial. This...

Full description

Saved in:
Bibliographic Details
Main Authors: Tran Thi Ngan, Dang Huong Tra, Ngo Thi Quynh Mai, Hoang Van Dung, Nguyen Van Khai, Pham Van Linh, Nguyen Thi Thu Phuong
Format: Article
Language:English
Published: Frontiers Media S.A. 2025-03-01
Series:Frontiers in Endocrinology
Subjects:
Online Access:https://www.frontiersin.org/articles/10.3389/fendo.2025.1415206/full
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850053630485331968
author Tran Thi Ngan
Tran Thi Ngan
Dang Huong Tra
Ngo Thi Quynh Mai
Hoang Van Dung
Nguyen Van Khai
Pham Van Linh
Nguyen Thi Thu Phuong
Nguyen Thi Thu Phuong
author_facet Tran Thi Ngan
Tran Thi Ngan
Dang Huong Tra
Ngo Thi Quynh Mai
Hoang Van Dung
Nguyen Van Khai
Pham Van Linh
Nguyen Thi Thu Phuong
Nguyen Thi Thu Phuong
author_sort Tran Thi Ngan
collection DOAJ
description Hypothyroidism, a common endocrine disorder, has a high incidence in women and increases with age. Levothyroxine (LT4) is the standard therapy; however, achieving clinical and biochemical euthyroidism is challenging. Therefore, developing an accurate model for predicting LT4 dosage is crucial. This retrospective study aimed to identify factors affecting the daily dose of LT4 and develop a model to estimate the dose of LT4 in hypothyroidism from a cohort of 1,864 patients through a comprehensive analysis of electronic medical records. Univariate analysis was conducted to explore the relationships between clinical and non-clinical variables, including weight, sex, age, body mass index, diastolic blood pressure, comorbidities, food effects, drug-drug interactions, liver function, serum albumin and TSH levels. Among the models tested, the Extra Trees Regressor (ETR) demonstrated the highest predictive accuracy, achieving an R² of 87.37% and the lowest mean absolute error of 9.4 mcg (95% CI: 7.7–11.2) in the test set. Other ensemble models, including Random Forest and Gradient Boosting, also showed strong performance (R² > 80%). Feature importance analysis highlighted BMI (0.516 ± 0.015) as the most influential predictor, followed by comorbidities (0.120 ± 0.010) and age (0.080 ± 0.005). The findings underscore the potential of machine learning in refining LT4 dose estimation by incorporating diverse clinical factors beyond traditional weight-based approaches. The model provides a solid foundation for personalized LT4 dosing, which can enhance treatment precision and reduce the risk of under- or over-medication. Further validation in external cohorts is essential to confirm its clinical applicability.
format Article
id doaj-art-bf232a5ffbcd4603a3ce309f20133d56
institution DOAJ
issn 1664-2392
language English
publishDate 2025-03-01
publisher Frontiers Media S.A.
record_format Article
series Frontiers in Endocrinology
spelling doaj-art-bf232a5ffbcd4603a3ce309f20133d562025-08-20T02:52:28ZengFrontiers Media S.A.Frontiers in Endocrinology1664-23922025-03-011610.3389/fendo.2025.14152061415206Developing a machine learning-based predictive model for levothyroxine dosage estimation in hypothyroid patients: a retrospective studyTran Thi Ngan0Tran Thi Ngan1Dang Huong Tra2Ngo Thi Quynh Mai3Hoang Van Dung4Nguyen Van Khai5Pham Van Linh6Nguyen Thi Thu Phuong7Nguyen Thi Thu Phuong8Faculty of Pharmacy & Biomedical-Pharmaceutical Sciences Research Group, Hai Phong University of Medicine and Pharmacy, Hai Phong, VietnamPharmacy Department, Hai Phong International Hospital, Hai Phong, VietnamFaculty of Pharmacy & Biomedical-Pharmaceutical Sciences Research Group, Hai Phong University of Medicine and Pharmacy, Hai Phong, VietnamFaculty of Pharmacy & Biomedical-Pharmaceutical Sciences Research Group, Hai Phong University of Medicine and Pharmacy, Hai Phong, VietnamDepartment of Rheumatology-Nephrology-Allergy and Immunology, Hai Phong International Hospital, Hai Phong, VietnamFaculty of Public Health, Hai Phong University of Medicine and Pharmacy, Hai Phong, VietnamFaculty of Medicine, Hai Phong University of Medicine and Pharmacy, Hai Phong, VietnamFaculty of Pharmacy & Biomedical-Pharmaceutical Sciences Research Group, Hai Phong University of Medicine and Pharmacy, Hai Phong, VietnamPharmacy Department, Hai Phong International Hospital, Hai Phong, VietnamHypothyroidism, a common endocrine disorder, has a high incidence in women and increases with age. Levothyroxine (LT4) is the standard therapy; however, achieving clinical and biochemical euthyroidism is challenging. Therefore, developing an accurate model for predicting LT4 dosage is crucial. This retrospective study aimed to identify factors affecting the daily dose of LT4 and develop a model to estimate the dose of LT4 in hypothyroidism from a cohort of 1,864 patients through a comprehensive analysis of electronic medical records. Univariate analysis was conducted to explore the relationships between clinical and non-clinical variables, including weight, sex, age, body mass index, diastolic blood pressure, comorbidities, food effects, drug-drug interactions, liver function, serum albumin and TSH levels. Among the models tested, the Extra Trees Regressor (ETR) demonstrated the highest predictive accuracy, achieving an R² of 87.37% and the lowest mean absolute error of 9.4 mcg (95% CI: 7.7–11.2) in the test set. Other ensemble models, including Random Forest and Gradient Boosting, also showed strong performance (R² > 80%). Feature importance analysis highlighted BMI (0.516 ± 0.015) as the most influential predictor, followed by comorbidities (0.120 ± 0.010) and age (0.080 ± 0.005). The findings underscore the potential of machine learning in refining LT4 dose estimation by incorporating diverse clinical factors beyond traditional weight-based approaches. The model provides a solid foundation for personalized LT4 dosing, which can enhance treatment precision and reduce the risk of under- or over-medication. Further validation in external cohorts is essential to confirm its clinical applicability.https://www.frontiersin.org/articles/10.3389/fendo.2025.1415206/fulllevothyroxinehypothyroidismmodel estimationendocrineretrospective study
spellingShingle Tran Thi Ngan
Tran Thi Ngan
Dang Huong Tra
Ngo Thi Quynh Mai
Hoang Van Dung
Nguyen Van Khai
Pham Van Linh
Nguyen Thi Thu Phuong
Nguyen Thi Thu Phuong
Developing a machine learning-based predictive model for levothyroxine dosage estimation in hypothyroid patients: a retrospective study
Frontiers in Endocrinology
levothyroxine
hypothyroidism
model estimation
endocrine
retrospective study
title Developing a machine learning-based predictive model for levothyroxine dosage estimation in hypothyroid patients: a retrospective study
title_full Developing a machine learning-based predictive model for levothyroxine dosage estimation in hypothyroid patients: a retrospective study
title_fullStr Developing a machine learning-based predictive model for levothyroxine dosage estimation in hypothyroid patients: a retrospective study
title_full_unstemmed Developing a machine learning-based predictive model for levothyroxine dosage estimation in hypothyroid patients: a retrospective study
title_short Developing a machine learning-based predictive model for levothyroxine dosage estimation in hypothyroid patients: a retrospective study
title_sort developing a machine learning based predictive model for levothyroxine dosage estimation in hypothyroid patients a retrospective study
topic levothyroxine
hypothyroidism
model estimation
endocrine
retrospective study
url https://www.frontiersin.org/articles/10.3389/fendo.2025.1415206/full
work_keys_str_mv AT tranthingan developingamachinelearningbasedpredictivemodelforlevothyroxinedosageestimationinhypothyroidpatientsaretrospectivestudy
AT tranthingan developingamachinelearningbasedpredictivemodelforlevothyroxinedosageestimationinhypothyroidpatientsaretrospectivestudy
AT danghuongtra developingamachinelearningbasedpredictivemodelforlevothyroxinedosageestimationinhypothyroidpatientsaretrospectivestudy
AT ngothiquynhmai developingamachinelearningbasedpredictivemodelforlevothyroxinedosageestimationinhypothyroidpatientsaretrospectivestudy
AT hoangvandung developingamachinelearningbasedpredictivemodelforlevothyroxinedosageestimationinhypothyroidpatientsaretrospectivestudy
AT nguyenvankhai developingamachinelearningbasedpredictivemodelforlevothyroxinedosageestimationinhypothyroidpatientsaretrospectivestudy
AT phamvanlinh developingamachinelearningbasedpredictivemodelforlevothyroxinedosageestimationinhypothyroidpatientsaretrospectivestudy
AT nguyenthithuphuong developingamachinelearningbasedpredictivemodelforlevothyroxinedosageestimationinhypothyroidpatientsaretrospectivestudy
AT nguyenthithuphuong developingamachinelearningbasedpredictivemodelforlevothyroxinedosageestimationinhypothyroidpatientsaretrospectivestudy