Trung tâm Thông tin - Thư viện Trường Đại học Y Dược Hải Phòng

NLM	B13
Tác giả CN	Nguyễn Thị Thu Phương - Cb.
Tác giả TT
Nhan đề	Developing a machine learning-based predictive model for levothyroxine dosage estimation in hypothyroid patients: a retrospective study
Tóm tắt	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).
Từ khóa tự do	Hypothyroid patients; Levothyroxine; Pharmacy; Pharmacy
Tác giả(bs) CN	Ngô Thị Quỳnh Mai
Tác giả(bs) CN	Trần Thị Ngân
Địa chỉ	100Bài báo quốc tế(1): BQT00002
Tệp tin điện tử	https://pmc.ncbi.nlm.nih.gov/articles/PMC11949781/
Tệp tin điện tử	https://lib.hpmu.edu.vn/kiposdata2/tapchi2026/anhbiatc/biabbqt_thumbimage.jpg

MARC

Hiển thị đầy đủ trường & trường con

Tag	Giá trị
000	00000nab#a2200000ui#4500
001	33880
002	13
004	F9749848-5292-4EA3-8B5A-8B557B7FF618
005	202605111531
008	081223s vm\| vie
009	1 0
039	[ ] \|a 20260511153129 \|b phuongntt \|c 20260506193059 \|d phuongntt \|y 20260504022217 \|z phuongntt
084	[ ] \|a B13
100	[ ] \|a Nguyễn Thị Thu Phương \|e Cb.
110	[ ] \|b Frontiers in Endocrinology
245	[ ] \|a Developing a machine learning-based predictive model for levothyroxine dosage estimation in hypothyroid patients: a retrospective study
520	[ ] \|a 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).
653	[ ] \|a Hypothyroid patients
653	[ ] \|a Levothyroxine
653	[ ] \|a Pharmacy
653	[ ] \|a Pharmacy
700	[ ] \|a Ngô Thị Quỳnh Mai
700	[ ] \|a Trần Thị Ngân
773	[ ] \|t Frontiers in Endocrinology \|d Frontiers Media
852	[ ] \|a 100 \|b Bài báo quốc tế \|j (1): BQT00002
856	[ ] \|u https://pmc.ncbi.nlm.nih.gov/articles/PMC11949781/
856	[1 ] \|u https://lib.hpmu.edu.vn/kiposdata2/tapchi2026/anhbiatc/biabbqt_thumbimage.jpg
890	[ ] \|a 1 \|b 0 \|c 0 \|d 0

Dòng	Mã vạch	Bản sao	Nơi lưu	Tình trạng	Cho phép yêu cầu
1	BQT00002	1	Kho Bài báo quốc tế
#1 BQT00002 Nơi lưu Kho Bài báo quốc tế Tình trạng

Bình luận