Advertisement

Efficacy of machine learning to identify clinical factors influencing levothyroxine dosage after total thyroidectomy

Published:November 20, 2022DOI:https://doi.org/10.1016/j.amjsurg.2022.11.025

      Highlights

      • Retrospective study on patients who underwent total or completion thyroidectomy.
      • Machine learning utilized to find predictors of levothyroxine dosing.
      • Algorithms found race and ethnicity significantly associated with dosing.
      • Alcohol use and osteoarthritis were also associated with dosing.
      • Confirmed previously known factors: weight, BMI, age, and sex.

      Abstract

      Background

      We employed Machine Learning (ML) to evaluate potential additional clinical factors influencing replacement dosage requirements of levothyroxine.

      Method

      This was a retrospective study of patients who underwent total or completion thyroidectomy with benign pathology. Patients who achieved an euthyroid state were included in three different ML models.

      Results

      Of the 487 patients included, mean age was 54.1 ± 14.1 years, 86.0% were females, 39.0% were White, 53.0% Black, 2.7% Hispanic, 1.4% Asian, and 3.9% Other. The Extreme Gradient Boosting (XGBoost) model achieved the highest accuracy at 61.0% in predicting adequate dosage compared to 47.0% based on 1.6mcg/kg/day (p < 0.05). The Poisson regression indicated non-Caucasian race (p < 0.05), routine alcohol use (estimate = 0.03, p = 0.02), and osteoarthritis (estimate = −0.10, p < 0.001) in addition to known factors such as age (estimate = −0.003, p < 0.001), sex (female, estimate = −0.06, p < 0.001), and weight (estimate = 0.01, p < 0.001) were associated with the dosing of levothyroxine.

      Conclusions

      Along with weight, sex, age, and BMI, ML algorithms indicated that race, ethnicity, lifestyle and comorbidity factors also may impact levothyroxine dosing in post-thyroidectomy patients with benign conditions.
      To read this article in full you will need to make a payment

      Purchase one-time access:

      Academic & Personal: 24 hour online accessCorporate R&D Professionals: 24 hour online access
      One-time access price info
      • For academic or personal research use, select 'Academic and Personal'
      • For corporate R&D use, select 'Corporate R&D Professionals'

      Subscribe:

      Subscribe to The American Journal of Surgery
      Already a print subscriber? Claim online access
      Already an online subscriber? Sign in
      Institutional Access: Sign in to ScienceDirect

      References

        • Olubowale O.
        • Chadwick D.R.
        Optimization of thyroxine replacement therapy after total or near-total thyroidectomy for benign thyroid disease.
        Br J Surg. 2005; 93: 57-60https://doi.org/10.1002/bjs.5157
        • Chen S.S.
        • Zaborek N.A.
        • Doubleday A.R.
        • et al.
        Optimizing levothyroxine dose adjustment after thyroidectomy with a decision tree.
        J Surg Res. 2019; 244: 102-106https://doi.org/10.1016/j.jss.2019.06.025
        • Mistry D.
        • Atkin S.
        • Atkinson H.
        • et al.
        Predicting thyroxine requirements following total thyroidectomy.
        Clin Endocrinol. 2011; 74: 384-387https://doi.org/10.1111/j.1365-2265.2010.03940.x
        • Elfenbein D.M.
        Prospective intervention of a novel levothyroxine dosing protocol based on body mass index after thyroidectomy.
        J Am Coll Surg. 2016; 222: 6
        • Zaborek N.A.
        • Cheng A.
        • Imbus J.R.
        • et al.
        The optimal levothyroxine dosing scheme After thyroidectomy: a comprehensive comparison and evaluation.
        Surgery. 2019; 165: 92-98https://doi.org/10.1016/j.surg.2018.04.097
        • Biondi B.
        • Cooper D.S.
        Thyroid hormone suppression therapy.
        Endocrinol Metab Clin N Am. 2019; 48: 227-237https://doi.org/10.1016/j.ecl.2018.10.008
        • Uzzan B.
        • Campos J.
        • Cucherat M.
        • Nony P.
        • Boissel J.P.
        • Perret G.Y.
        Effects on bone mass of long term treatment with thyroid hormones: a meta-analysis.
        J Clin Endocrinol Metab. 1996; 81: 4278-4289https://doi.org/10.1210/jcem.81.12.8954028
        • Fazio S.
        • Palmieri E.
        • Lombardi G.
        • Biondi B.
        Effects of thyroid hormone on the cardiovascular system.
      1. Sawin CT, Geller A, Wolf PA, et al. Low Serum Thyrotropin Concentrations as a Risk Factor for Atrial Fibrillation in Older Persons. https://doi.org/10.1056/NEJM199411103311901. doi:10.1056/NEJM199411103311901.

        • Bauer D.C.
        • Ettinger B.
        • Nevitt M.C.
        • Stone K.L.
        Risk for fracture in women with low serum levels of thyroid-stimulating hormone.
        Ann Intern Med. 2001; 134: 561-568https://doi.org/10.7326/0003-4819-134-7-200104030-00009
        • Ernst F.R.
        • Barr P.
        • Elmor R.
        • et al.
        The economic impact of levothyroxine dose adjustments: the CONTROL HE study.
        Clin Drug Invest. 2017; 37: 71-83https://doi.org/10.1007/s40261-016-0462-3
        • Papoian V.
        • Ylli D.
        • Felger E.A.
        • Wartofsky L.
        • Rosen J.E.
        Evaluation of thyroid hormone replacement dosing in overweight and obese patients after a thyroidectomy.
        Thyroid. 2019; 29: 1558-1562https://doi.org/10.1089/thy.2019.0251
        • Ojomo K.
        • Schneider D.
        • Reicher A.
        • et al.
        Using body mass index to predict optimal thyroid dosing after thyroidectomy.
        J Am Coll Surg. 2013; 216: 7
        • Di Donna V.
        • Santoro M.G.
        • de Waure C.
        • et al.
        A new strategy to estimate levothyroxine requirement after total thyroidectomy for benign thyroid disease.
        Thyroid. 2014; 24: 1759-1764https://doi.org/10.1089/thy.2014.0111
        • Cunningham J.J.
        • Barzel U.S.
        Lean body mass is a predictor of the daily requirement for thyroid hormone in older men and women.
        J Am Geriatr Soc. 1984; 32: 204-207https://doi.org/10.1111/j.1532-5415.1984.tb02003.x
        • McAninch E.A.
        • Bianco A.C.
        Thyroid hormone signaling in energy homeostasis and energy metabolism.
        Ann N Y Acad Sci. 2014; 1311: 77-87https://doi.org/10.1111/nyas.12374
        • Berman D.M.
        • Rodrigues L.M.
        • Nicklas B.J.
        • Ryan A.S.
        • Dennis K.E.
        • Goldberg A.P.
        Racial disparities in metabolism, central obesity, and sex hormone-binding globulin in postmenopausal Women 1.
        J Clin Endocrinol Metab. 2001; 86: 97-103https://doi.org/10.1210/jcem.86.1.7147
        • Sharp T.A.
        • Bell M.L.
        • Grunwald G.K.
        • et al.
        Differences in resting metabolic rate between white and African-American young adults.
        Obes Res. 2002; 10: 726-732https://doi.org/10.1038/oby.2002.99
        • Burnside E.S.
        • Rubin D.L.
        • Fine J.P.
        • Shachter R.D.
        • Sisney G.A.
        • Leung W.K.
        Bayesian network to predict breast cancer risk of mammographic microcalcifications and reduce number of benign biopsy results: initial experience.
        Radiology. 2006; 240: 666-673https://doi.org/10.1148/radiol.2403051096
        • Falconer N.
        • Abdel-Hafez A.
        • Scott I.A.
        • Marxen S.
        • Canaris S.
        • Barras M.
        Systematic review of machine learning models for personalised dosing of heparin.
        Br J Clin Pharmacol. 2021; 87: 4124-4139https://doi.org/10.1111/bcp.14852
        • Jonklaas J.
        • Bianco A.C.
        • Bauer A.J.
        • et al.
        Guidelines for the treatment of hypothyroidism: prepared by the American thyroid association task force on thyroid hormone replacement.
        Thyroid. 2014; 24: 1670-1751https://doi.org/10.1089/thy.2014.0028
        • Gruppen E.G.
        • Kootstra-Ros J.
        • Kobold A.M.
        • et al.
        Cigarette smoking is associated with higher thyroid hormone and lower TSH levels: the PREVEND study.
        Endocrine. 2020; 67: 613-622https://doi.org/10.1007/s12020-019-02125-2
        • Deere B.P.
        • Ferdinand K.C.
        Hypertension and race/ethnicity.
        Curr Opin Cardiol. 2020; 35: 342-350https://doi.org/10.1097/HCO.0000000000000742
        • Pi-Sunyer F.X.
        Obesity and diabetes in blacks.
        Diabetes Care. 1990; 13: 1144-1149https://doi.org/10.2337/diacare.13.11.1144
        • Nikolian V.C.
        • Williams A.M.
        • Jacobs B.N.
        • et al.
        Pilot study to evaluate the safety, feasibility, and financial implications of a postoperative telemedicine program.
        Ann Surg. 2018; 268: 700-707https://doi.org/10.1097/SLA.0000000000002931
        • Choy G.
        • Khalilzadeh O.
        • Michalski M.
        • et al.
        Current applications and future impact of machine learning in radiology.
        Radiology. 2018; 288: 318-328https://doi.org/10.1148/radiol.2018171820
        • Geras K.J.
        • Mann R.M.
        • Moy L.
        Artificial intelligence for mammography and digital breast tomosynthesis: current concepts and future perspectives.
        Radiology. 2019; 293: 246-259https://doi.org/10.1148/radiol.2019182627
        • Jin J.
        • Allemang M.T.
        • McHenry C.R.
        Levothyroxine replacement dosage determination after thyroidectomy.
        Am J Surg. 2013; 205 (; discussion 363-364): 360-363https://doi.org/10.1016/j.amjsurg.2012.10.015
        • Hills A.P.
        • Mokhtar N.
        • Byrne N.M.
        Assessment of physical activity and energy expenditure: an overview of objective measures.
        Front Nutr. 2014; 1: 5https://doi.org/10.3389/fnut.2014.00005
        • Valenzuela F.
        • Berrios L.
        • Robledo C.A.
        • et al.
        Comparison of dosing schemes for thyroid hormone replacement therapy after thyroidectomy.
        J Surg Res. 2021; 264: 316-320https://doi.org/10.1016/j.jss.2021.03.016
        • Autzen B.
        Is the replication crisis a base-rate fallacy?.
        Theor Med Bioeth. 2021; 42: 233-243https://doi.org/10.1007/s11017-022-09561-8
        • An G.
        The crisis of reproducibility, the denominator problem and the scientific role of multi-scale modeling.
        Bull Math Biol. 2018; 80: 3071-3080https://doi.org/10.1007/s11538-018-0497-0