Optimizing Levothyroxine Dose Adjustment After Thyroidectomy With a Decision Tree
| Autor: | Rebecca S. Sippel, Kristin L. Long, Amanda R. Doubleday, Susan C. Pitt, Sarah Schaefer, David F. Schneider, Stephen S. Chen, Nick Zaborek |
|---|---|
| Rok vydání: | 2019 |
| Předmět: |
Adult
Male Pediatrics medicine.medical_specialty endocrine system Hormone Replacement Therapy medicine.medical_treatment Decision tree Levothyroxine Mean absolute error Patient characteristics Thyrotropin Article Machine Learning 03 medical and health sciences 0302 clinical medicine Hypothyroidism Dose adjustment Medicine Humans Drug Dosage Calculations Aged Retrospective Studies Completion thyroidectomy Postoperative Care business.industry Decision Trees Thyroidectomy Retrospective cohort study Middle Aged Hyperthyroxinemia Thyroxine 030220 oncology & carcinogenesis 030211 gastroenterology & hepatology Surgery Female business medicine.drug |
| Zdroj: | J Surg Res |
| ISSN: | 1095-8673 |
| Popis: | Background After thyroidectomy, patients require Levothyroxine (LT4). It may take years of dose adjustments to achieve euthyroidism. During this time, patients encounter undesirable symptoms associated with hypo- or hyper-thyroidism. Currently, providers adjust LT4 dose by clinical estimation, and no algorithm exists. The objective of this study was to build a decision tree that could estimate LT4 dose adjustments and reduce the time to euthyroidism. Methods We performed a retrospective cohort analysis on 320 patients who underwent total or completion thyroidectomy at our institution. All patients required one or more LT4 dose adjustments from their initial postoperative dose before attaining euthyroidism. Using the Classification and Regression Tree algorithm, we built various decision trees from patient characteristics, estimating the dose adjustment to reach euthyroidism. Results The most accurate decision tree used thyroid-stimulating hormone values at first dose adjustment (mean absolute error = 13.0 μg). In comparison, the expert provider and naive system had a mean absolute error of 11.7 μg and 17.2 μg, respectively. In the evaluation dataset, the decision tree correctly predicted the dose adjustment within the smallest LT4 dose increment (12.5 μg) 79 of 106 times (75%, confidence interval = 65%-82%). In comparison, expert provider estimation correctly predicted the dose adjustment 76 of 106 times (72%, confidence interval = 62%-80%). Conclusions A decision tree predicts the correct LT4 dose adjustment with an accuracy exceeding that of a completely naive system and comparable to that of an expert provider. It can assist providers inexperienced with LT4 dose adjustment. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Full Text from ScienceDirect