Computer-Assisted Levothyroxine Dose Selection for the Treatment of Postoperative Hypothyroidism
Authors' conclusion
The standard-of-care LT4 dosing does not achieve the target TSH in most thyroidectomy patients. Computer-assisted LT4 dose calculation performs better by considering multiple relevant patient characteristics and providing personalized and equitable care to patients with postoperative hypothyroidism.
Study context
- Population
- Patients with postoperative hypothyroidism after thyroidectomy
- Participants
- 951 patients
- Exposure
- Computer-assisted levothyroxine (LT4) dose calculator vs standard-of-care weight-based dosing
- Outcome
- Postoperative TSH goal met (standard-of-care) and prescribed LT4 dose predicted (calculator)
Methodological detailsmachine learning model development, fivefold cross-validation, out-of-sample testing
- Machine learning model development
- Fivefold cross-validation
- Out-of-sample testing
Main finding
As reported in the abstract
Standard-of-care
30%
285 events
- OLS regression predicted prescribed LT4 dose, all patients
- 43.5%
- OLS regression predicted prescribed LT4 dose, patients with normal postoperative TSH (0.45-4.5 mIU/L)
- 45.3%
Observational data: associations, not effects.
Further findings
Other machine learning methods
- Ordinal logistic regression, artificial neural networks and random forest achieved comparable performance
Obese patients
- Obese patients were overtreated with LT4; calculator recommended lower LT4 doses to obese patients
Original publication
Computer-Assisted Levothyroxine Dose Selection for the Treatment of Postoperative Hypothyroidism. Thyroid. Published 20 April 2023. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →