A medical data driven-based hypothyroid individualized dose prediction method, system, device and storage medium

By constructing a gradient boosting decision tree model based on medical data and utilizing standardized feature vectors and TSH dynamic trajectory features, the dosage adjustment for children with hypothyroidism is optimized, which solves the shortcomings of individualized dosage adjustment in existing technologies and improves treatment efficacy.

CN122245605APending Publication Date: 2026-06-19SHENZHEN MATERNITY & CHILD HEALTHCARE HOSPITAL
View PDF 0 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
SHENZHEN MATERNITY & CHILD HEALTHCARE HOSPITAL
Filing Date
2026-04-28
Publication Date
2026-06-19

AI Technical Summary

Technical Problem

In existing technologies, clinicians cannot effectively utilize the TSH time-series data from each follow-up visit of children with hypothyroidism, resulting in a lack of individualized dosage adjustments for children with hypothyroidism. This makes it impossible to distinguish the differences in response of different children to the same dosage adjustment range, and ignores the influence of feeding methods, seasonal physiological rhythms, and comorbidities, leading to poor treatment outcomes.

Method used

A gradient boosting decision tree model based on medical data is constructed. By standardizing feature vectors and TSH dynamic trajectory features, combined with feeding methods, seasonal sinusoidal cycles and comorbidity correction coefficients, the dosage adjustment pattern is optimized so that the model learns the optimal clinical decision level.

Benefits of technology

It improves the accuracy of dose prediction for children with hypothyroidism, takes into account multiple clinical confounding factors, and increases the TSH control target achievement rate, especially the adjustment effect for different feeding methods and seasonal fluctuations.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN122245605A_ABST
    Figure CN122245605A_ABST
Patent Text Reader

Abstract

This invention relates to the field of medical data-driven dose prediction technology, and discloses a method, system, device, and storage medium for individualized dose prediction of hypothyroidism based on medical data. The method includes: constructing a standardized feature vector based on the child's weight, age in days, corrected age in months, current L-T4 dose, TSH value, FT4 value, previous TSH value, TSH rate of change, feeding method, month of consultation, etiology of hypothyroidism, comorbidity status, previous dose adjustment magnitude, and age at which TSH first reached target levels; extracting TSH dynamic trajectory features from the child's TSH time-series data from previous follow-ups; obtaining a basic recommended dose using a gradient boosting decision tree model constructed with counterfactual filtering training data; and correcting the basic recommended dose to obtain an individualized recommended dose. This method improves the prediction accuracy of the gradient boosting decision tree model and allows the individualized recommended dose to simultaneously take into account multiple clinical confounding factors.
Need to check novelty before this filing date? Find Prior Art