{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,13]],"date-time":"2026-09-13T15:02:55Z","timestamp":1789311775559,"version":"build-2803163510"},"reference-count":66,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2022,2,16]],"date-time":"2022-02-16T00:00:00Z","timestamp":1644969600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Endocrinol."],"abstract":"<jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>First-line surgery for prolactinomas has gained increasing acceptance, but the indication still remains controversial. Thus, accurate prediction of unfavorable outcomes after upfront surgery in prolactinoma patients is critical for the triage of therapy and for interdisciplinary decision-making.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Objective<\/jats:title>\n                    <jats:p>To evaluate whether contemporary machine learning (ML) methods can facilitate this crucial prediction task in a large cohort of prolactinoma patients with first-line surgery, we investigated the performance of various classes of supervised classification algorithms. The primary endpoint was ML-applied risk prediction of long-term dopamine agonist (DA) dependency. The secondary outcome was the prediction of the early and long-term control of hyperprolactinemia.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>\n                      By jointly examining two independent performance metrics \u2013 the area under the receiver operating characteristic (AUROC) and the Matthews correlation coefficient (MCC) \u2013 in combination with a stacked\n                      <jats:italic>super learner<\/jats:italic>\n                      , we present a novel perspective on how to assess and compare the discrimination capacity of a set of binary classifiers.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>\n                      We demonstrate that for upfront surgery in prolactinoma patients there are not a\n                      <jats:italic>one-algorithm-fits-all<\/jats:italic>\n                      solution in outcome prediction: different algorithms perform best for different time points and different outcomes parameters. In addition, ML classifiers outperform logistic regression in both performance metrics in our cohort when predicting the primary outcome at long-term follow-up and secondary outcome at early follow-up, thus provide an added benefit in risk prediction modeling. In such a setting, the stacking framework of combining the predictions of individual\n                      <jats:italic>base learners<\/jats:italic>\n                      in a so-called\n                      <jats:italic>super learner<\/jats:italic>\n                      offers great potential: the\n                      <jats:italic>super learner<\/jats:italic>\n                      exhibits very good prediction skill for the primary outcome (AUROC: mean 0.9, 95% CI: 0.92 \u2013 1.00; MCC: 0.85, 95% CI: 0.60 \u2013 1.00). In contrast, predicting control of hyperprolactinemia is challenging, in particular in terms of early follow-up (AUROC: 0.69, 95% CI: 0.50 \u2013 0.83) vs. long-term follow-up (AUROC: 0.80, 95% CI: 0.58 \u2013 0.97). It is of clinical importance that baseline prolactin levels are by far the most important outcome predictor at early follow-up, whereas remissions at 30 days dominate the ML prediction skill for DA-dependency over the long-term.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>This study highlights the performance benefits of combining a diverse set of classification algorithms to predict the outcome of first-line surgery in prolactinoma patients. We demonstrate the added benefit of considering two performance metrics jointly to assess the discrimination capacity of a diverse set of classifiers.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fendo.2022.810219","type":"journal-article","created":{"date-parts":[[2022,2,15]],"date-time":"2022-02-15T23:58:04Z","timestamp":1644969484000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":25,"title":["Machine Learning for Outcome Prediction in First-Line Surgery of Prolactinomas"],"prefix":"10.3389","volume":"13","author":[{"given":"Markus","family":"Huber","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Markus M.","family":"Luedi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gerrit A.","family":"Schubert","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Christian","family":"Musahl","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Angelo","family":"Tortora","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Janine","family":"Frey","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"J\u00fcrgen","family":"Beck","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Luigi","family":"Mariani","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Emanuel","family":"Christ","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lukas","family":"Andereggen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2022,2,16]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","DOI":"10.1111\/j.1365-2265.2007.02905.x","article-title":"Predictors of Remission of Hyperprolactinaemia After Long-Term Withdrawal of Cabergoline Therapy","volume":"67","author":"Colao","year":"2007","journal-title":"Clin Endocrinol"},{"key":"B2","doi-asserted-by":"publisher","DOI":"10.1210\/jc.2009-0177","article-title":"Estimated Age- and Sex-Specific Incidence and Prevalence of Dopamine Agonist-Treated Hyperprolactinemia","volume":"94","author":"Kars","year":"2009","journal-title":"J Clin Endocrinol Metab"},{"key":"B3","doi-asserted-by":"publisher","first-page":"47","DOI":"10.1136\/jnnp.2004.045740","article-title":"Pituitary Disease: Presentation, Diagnosis, and Management","volume":"75","author":"Levy","year":"2004","journal-title":"J Neurol Neurosurg Psychiatry"},{"key":"B4","doi-asserted-by":"publisher","first-page":"43","DOI":"10.1210\/jc.2009-1238","article-title":"Recurrence of Hyperprolactinemia After Withdrawal of Dopamine Agonists: Systematic Review and Meta-Analysis","volume":"95","author":"Dekkers","year":"2010","journal-title":"J Clin Endocrinol Metab"},{"key":"B5","doi-asserted-by":"publisher","DOI":"10.1111\/j.1365-2265.2008.03458.x","article-title":"Valvular Heart Disease and the Use of Cabergoline for the Treatment of Prolactinoma","volume":"70","author":"Herring","year":"2009","journal-title":"Clin Endocrinol"},{"key":"B6","doi-asserted-by":"publisher","first-page":"39","DOI":"10.1056\/NEJMoa054830","article-title":"Valvular Heart Disease and the Use of Dopamine Agonists for Parkinson\u2019s Disease","volume":"356","author":"Zanettini","year":"2007","journal-title":"New Engl J Med"},{"key":"B7","doi-asserted-by":"publisher","DOI":"10.1001\/jamainternmed.2014.5262","article-title":"Reports of Pathological Gambling, Hypersexuality, and Compulsive Shopping Associated With Dopamine Receptor Agonist Drugs","volume":"174","author":"Moore","year":"2014","journal-title":"JAMA Internal Med"},{"key":"B8","doi-asserted-by":"publisher","DOI":"10.1001\/jamainternmed.2014.4097","article-title":"Dopamine Receptor Agonist Drugs and Impulse Control Disorders","volume":"174","author":"Weiss","year":"2014","journal-title":"JAMA Internal Med"},{"key":"B9","doi-asserted-by":"publisher","DOI":"10.1111\/cen.12375","article-title":"Impulse Control Disorders in Patients With Dopamine Agonist-Treated Prolactinomas and Nonfunctioning Pituitary Adenomas: A Case\u2013Control Study","volume":"80","author":"Bancos","year":"2014","journal-title":"Clin Endocrinol"},{"key":"B10","doi-asserted-by":"publisher","DOI":"10.3389\/fendo.2020.579606","article-title":"Depression and Impulsivity Self-Assessment Tools to Identify Dopamine Agonist Side Effects in Patients With Pituitary Adenomas","volume":"11","author":"Hinojosa-Amaya","year":"2020","journal-title":"Front Endocrinol"},{"key":"B11","doi-asserted-by":"publisher","DOI":"10.1007\/s40618-021-01569-6","article-title":"First-Line Surgery in Prolactinomas: Lessons From a Long-Term Follow-Up Study in a Tertiary Referral Center","volume":"44","author":"Andereggen","year":"2021","journal-title":"J Endocrinol Invest"},{"key":"B12","doi-asserted-by":"publisher","DOI":"10.1016\/j.jcte.2021.100258","article-title":"Impact of Primary Medical or Surgical Therapy on Prolactinoma Patients\u2019 BMI and Metabolic Profile Over the Long-Term","volume":"24","author":"Andereggen","year":"2021","journal-title":"J Clin Trans Endocrinol"},{"key":"B13","doi-asserted-by":"publisher","first-page":"5122","DOI":"10.1038\/s41598-021-84606-x","article-title":"Persistent Bone Impairment Despite Long-Term Control of Hyperprolactinemia and Hypogonadism in Men and Women With Prolactinomas","volume":"11","author":"Andereggen","year":"2021","journal-title":"Sci Rep"},{"key":"B14","doi-asserted-by":"publisher","DOI":"10.1007\/s12020-020-02557-1","article-title":"Long-Term IGF-1 Monitoring in Prolactinoma Patients Treated With Cabergoline Might Not be Indicated","volume":"72","author":"Andereggen","year":"2021","journal-title":"Endocrine"},{"key":"B15","doi-asserted-by":"publisher","DOI":"10.3389\/fendo.2020.00439","article-title":"Prolactinomas: Prognostic Factors of Early Remission After Transsphenoidal Surgery","volume":"11","author":"Zielinski","year":"2020","journal-title":"Front Endocrinol"},{"key":"B16","doi-asserted-by":"publisher","first-page":"653","DOI":"10.1186\/s13063-021-05604-y","article-title":"The PRolaCT Studies \u2014 a Study Protocol for a Combined Randomised Clinical Trial and Observational Cohort Study Design in Prolactinoma","volume":"22","author":"Zandbergen","year":"2021","journal-title":"Trials"},{"key":"B17","doi-asserted-by":"publisher","DOI":"10.3390\/cancers13133252","article-title":"Reappraising the Role of Trans-Sphenoidal Surgery in Prolactin-Secreting Pituitary Tumors","volume":"13","author":"Mattogno","year":"2021","journal-title":"Cancers"},{"key":"B18","doi-asserted-by":"publisher","DOI":"10.3389\/fendo.2018.00636","article-title":"The Chance of Permanent Cure for Micro- and Macroprolactinomas, Medication or Surgery? A Systematic Review and Meta-Analysis","volume":"9","author":"Ma","year":"2018","journal-title":"Front Endocrinol"},{"key":"B19","doi-asserted-by":"publisher","DOI":"10.1210\/clinem\/dgz144","article-title":"Surgery as a Viable Alternative First-Line Treatment for Prolactinoma Patients. A Systematic Review and Meta-Analysis","volume":"105","author":"Zamanipoor Najafabadi","year":"2019","journal-title":"J Clin Endocrinol Metab"},{"key":"B20","doi-asserted-by":"publisher","DOI":"10.1056\/NEJMra1814259","article-title":"Machine Learning in Medicine","volume":"380","author":"Rajkomar","year":"2019","journal-title":"New Engl J Med"},{"key":"B21","doi-asserted-by":"publisher","DOI":"10.3389\/fnins.2021.647535","article-title":"GAMER-MRI in Multiple Sclerosis Identifies the Diffusion-Based Microstructural Measures That Are Most Sensitive to Focal Damage: A Deep-Learning-Based Analysis and Clinico-Biological Validation","volume":"15","author":"Lu","year":"2021","journal-title":"Front Neurosci"},{"key":"B22","doi-asserted-by":"publisher","DOI":"10.1001\/jamacardio.2021.0122","article-title":"Use of Machine Learning Models to Predict Death After Acute Myocardial Infarction","volume":"6","author":"Khera","year":"2021","journal-title":"JAMA Cardiol"},{"key":"B23","doi-asserted-by":"publisher","DOI":"10.3389\/fendo.2021.748725","article-title":"Machine-Learning Prediction of Postoperative Pituitary Hormonal Outcomes in Nonfunctioning Pituitary Adenomas: A Multicenter Study","volume":"2021","author":"Fang","year":"1266","journal-title":"Front Endocrinol"},{"key":"B24","doi-asserted-by":"publisher","first-page":"81","DOI":"10.1038\/s41574-021-00543-9","article-title":"Machine Intelligence in Non-Invasive Endocrine Cancer Diagnostics","volume":"18","author":"Thomasian","year":"2021","journal-title":"Nat Rev Endocrinol"},{"key":"B25","doi-asserted-by":"publisher","DOI":"10.1210\/clinem\/dgab159","article-title":"Radiomics With Ensemble Machine Learning Predicts Dopamine Agonist Response in Patients With Prolactinoma","volume":"106","author":"Park","year":"2021","journal-title":"J Clin Endocrinol Metab"},{"key":"B26","doi-asserted-by":"publisher","DOI":"10.1227\/00006123-199310000-00008","article-title":"Pituitary Adenomas With Invasion of the Cavernous Sinus Space: A Magnetic Resonance Imaging Classification Compared With Surgical Findings","volume":"33","author":"Knosp","year":"1993","journal-title":"Neurosurgery"},{"key":"B27","doi-asserted-by":"publisher","DOI":"10.3171\/2014.12.JNS141083","article-title":"Invasion of the Cavernous Sinus Space in Pituitary Adenomas: Endoscopic Verification and Its Correlation With an MRI-Based Classification","volume":"122","author":"Micko","year":"2015","journal-title":"J Neurosurg JNS"},{"key":"B28","doi-asserted-by":"publisher","DOI":"10.1016\/j.neurad.2019.05.004","article-title":"Influence of Inferior Petrosal Sinus Drainage Symmetry on Detection of Adenomas in Cushing\u2019s Syndrome","volume":"48","author":"Andereggen","year":"2021","journal-title":"J Neuroradiol"},{"key":"B29","doi-asserted-by":"publisher","DOI":"10.4414\/smw.2018.14521","article-title":"A Ten-Year Follow-Up Study of Treatment Outcome of Craniopharyngiomas","volume":"148","author":"Andereggen","year":"2018","journal-title":"Swiss Med Weekly"},{"key":"B30","doi-asserted-by":"publisher","DOI":"10.1007\/s00701-021-04830-2","article-title":"Lateral One-Third Gland Resection in Cushing Patients With Failed Adenoma Identification Leads to Low Remission Rates: Long-Term Observations From a Small, Single-Center Cohort","volume":"163","author":"Andereggen","year":"2021","journal-title":"Acta Neurochir (Wien)"},{"key":"B31","doi-asserted-by":"publisher","DOI":"10.1111\/j.1365-2265.2006.02627.x","article-title":"Do the Limits of Serum Prolactin in Disconnection Hyperprolactinaemia Need Re-Definition? A Study of 226 Patients With Histologically Verified non-Functioning Pituitary Macroadenoma","volume":"65","author":"Karavitaki","year":"2006","journal-title":"Clin Endocrinol"},{"key":"B32","article-title":"Macroprolactinaemia, the Major Unknown in the Differential Diagnosis of Hyperprolactinaemia","volume":"131","author":"Cattaneo","year":"2001","journal-title":"Swiss Med Weekly"},{"key":"B33","doi-asserted-by":"publisher","DOI":"10.1210\/jc.2010-1692","article-title":"Diagnosis and Treatment of Hyperprolactinemia: An Endocrine Society Clinical Practice Guideline","volume":"96","author":"Melmed","year":"2011","journal-title":"J Clin Endocrinol Metab"},{"key":"B34","doi-asserted-by":"publisher","DOI":"10.1007\/s00401-017-1769-8","article-title":"The 2017 World Health Organization Classification of Tumors of the Pituitary Gland: A Summary","volume":"134","author":"Lopes","year":"2017","journal-title":"Acta Neuropathol"},{"key":"B35","doi-asserted-by":"publisher","DOI":"10.1007\/s40618-014-0212-4","article-title":"Retrospective Comparison of Cabergoline and Bromocriptine Effects in Hyperprolactinemia: A Single Center Experience","volume":"38","author":"Arduc","year":"2015","journal-title":"J Endocrinol Invest"},{"key":"B36","doi-asserted-by":"publisher","DOI":"10.1038\/ncpendmet0162","article-title":"When to Discontinue Treatment of Prolactinoma","volume":"2","author":"Wass","year":"2006","journal-title":"Nat Clin Pract Endocrinol Metab"},{"key":"B37","doi-asserted-by":"publisher","DOI":"10.1056\/NEJMoa022657","article-title":"Withdrawal of Long-Term Cabergoline Therapy for Tumoral and Nontumoral Hyperprolactinemia","volume":"349","author":"Colao","year":"2003","journal-title":"New Engl J Med"},{"key":"B38","article-title":"Randomforest: Breiman and Cutler\u2019s Random Forests for Classification and Regression","author":"Breiman","year":"2018"},{"key":"B39","article-title":"Kknn: Weighted K-Nearest Neighbors","author":"Schliep","year":"2016"},{"key":"B40","article-title":"Glmnet: Lasso and Elastic-Net Regularized Generalized Linear Models","author":"Friedman","year":"2021"},{"key":"B41","article-title":"Nnet: Feed-Forward Neural Networks and Multinomial Log-Linear Models","author":"Ripley","year":"2021"},{"key":"B42","article-title":"Earth: Multivariate Adaptive Regression Splines","author":"Milborrow","year":"2021"},{"key":"B43","article-title":"Misc Functions of the Department of Statistics, Probability Theory Group (Formerly: E1071), TU Wien","author":"Meyer","year":"2021"},{"key":"B44","article-title":"Gbm: Generalized Boosted Regression Models","author":"Greenwell","year":"2020"},{"key":"B45","doi-asserted-by":"crossref","DOI":"10.1007\/978-0-387-84858-7","volume-title":"The Elements of Statistical Learning","author":"Hastie","year":"2009"},{"key":"B46","doi-asserted-by":"crossref","DOI":"10.1201\/9780367816377","volume-title":"Hands-On Machine Learning With R","author":"Boehmke","year":"2019"},{"key":"B47","doi-asserted-by":"publisher","DOI":"10.2202\/1544-6115.1309","article-title":"Super Learner","volume":"6","author":"Laan","year":"2007","journal-title":"Stat Appl Genet Mol Biol"},{"key":"B48","doi-asserted-by":"publisher","DOI":"10.1186\/s12864-019-6413-7","article-title":"The Advantages of the Matthews Correlation Coefficient (MCC) Over F1 Score and Accuracy in Binary Classification Evaluation","volume":"21","author":"Chicco","year":"2020","journal-title":"BMC Genomics"},{"key":"B49","doi-asserted-by":"publisher","first-page":"e0177678","DOI":"10.1371\/journal.pone.0177678","article-title":"Optimal Classifier for Imbalanced Data Using Matthews Correlation Coefficient Metric","volume":"12","author":"Boughorbel","year":"2017","journal-title":"PloS One"},{"key":"B50","article-title":"R: A Language and Environment for Statistical Computing","year":"2020","journal-title":"Vienna Austria"},{"key":"B51","first-page":"1","article-title":"Mlr: Machine Learning in R","volume":"17","author":"Bischl","year":"2016","journal-title":"J Mach Learn Res"},{"key":"B52","doi-asserted-by":"publisher","first-page":"12","DOI":"10.1016\/j.jclinepi.2019.02.004","article-title":"A Systematic Review Shows No Performance Benefit of Machine Learning Over Logistic Regression for Clinical Prediction Models","volume":"110","author":"Christodoulou","year":"2019","journal-title":"J Clin Epidemiol"},{"key":"B53","doi-asserted-by":"publisher","first-page":"56","DOI":"10.1016\/j.jclinepi.2020.03.002","article-title":"Logistic Regression was as Good as Machine Learning for Predicting Major Chronic Diseases","volume":"122","author":"Nusinovici","year":"2020","journal-title":"J Clin Epidemiol"},{"key":"B54","doi-asserted-by":"publisher","DOI":"10.1007\/s11102-017-0806-x","article-title":"Prolactinoma Management: Predictors of Remission and Recurrence After Dopamine Agonists Withdrawal","volume":"20","author":"Teixeira","year":"2017","journal-title":"Pituitary"},{"key":"B55","doi-asserted-by":"publisher","DOI":"10.1007\/s11102-016-0708-3","article-title":"Withdrawal of Dopamine Agonist Therapy in Prolactinomas: In Which Patients and When","volume":"19","author":"Dogansen","year":"2016","journal-title":"Pituitary"},{"key":"B56","doi-asserted-by":"publisher","DOI":"10.1210\/jc.2006-1668","article-title":"High Prevalence of Pituitary Adenomas: A Cross-Sectional Study in the Province of Lie\u0300ge, Belgium","volume":"91","author":"Daly","year":"2006","journal-title":"J Clin Endocrinol Metab"},{"key":"B57","doi-asserted-by":"publisher","first-page":"63","DOI":"10.1007\/s11102-007-0072-4","article-title":"Five Years Follow-Up of Invasive Prolactinomas With Special Reference to the Control of Cavernous Sinus Invasion","volume":"11","author":"Wu","year":"2008","journal-title":"Pituitary"},{"key":"B58","doi-asserted-by":"publisher","DOI":"10.1007\/s11102-014-0617-2","article-title":"Current Drug Withdrawal Strategy in Prolactinoma Patients Treated With Cabergoline: A Systematic Review and Meta-Analysis","volume":"18","author":"Hu","year":"2015","journal-title":"Pituitary"},{"key":"B59","doi-asserted-by":"publisher","DOI":"10.1007\/s11102-013-0525-x","article-title":"Second Attempt to Withdraw Cabergoline in Prolactinomas: A Pilot Study","volume":"17","author":"Kwancharoen","year":"2014","journal-title":"Pituitary"},{"key":"B60","doi-asserted-by":"publisher","first-page":"50","DOI":"10.1007\/s12020-017-1444-9","article-title":"Optimal Timing of Dopamine Agonist Withdrawal in Patients With Hyperprolactinemia: A Systematic Review and Meta-Analysis","volume":"59","author":"Xia","year":"2018","journal-title":"Endocrine"},{"key":"B61","doi-asserted-by":"publisher","DOI":"10.1007\/s40618-016-0483-z","article-title":"Recurrence of Hyperprolactinemia Following Dopamine Agonist Withdrawal and Possible Predictive Factors of Recurrence in Prolactinomas","volume":"39","author":"Sala","year":"2016","journal-title":"J Endocrinol Invest"},{"key":"B62","doi-asserted-by":"publisher","DOI":"10.1530\/EJE-11-1000","article-title":"Outcomes of Transsphenoidal Surgery in Prolactinomas: Improvement of Hormonal Control in Dopamine Agonist-Resistant Patients","volume":"166","author":"Primeau","year":"2012","journal-title":"Eur J Endocrinol"},{"key":"B63","doi-asserted-by":"publisher","DOI":"10.3389\/fendo.2021.695498","article-title":"Commentary: \u201cProlactinomas: Prognostic Factors of Early Remission After Transsphenoidal Surgery\u201d","volume":"12","author":"Andereggen","year":"2021","journal-title":"Front Endocrinol"},{"key":"B64","doi-asserted-by":"publisher","first-page":"37","DOI":"10.4158\/EP161446.OR","article-title":"Surgical Outcomes of Prolactinomas in Recent Era: Results of a Heterogenous Group","volume":"23","author":"Donegan","year":"2017","journal-title":"Endocrine Pract"},{"key":"B65","doi-asserted-by":"publisher","DOI":"10.1007\/s12020-016-1115-2","article-title":"10-Year Follow-Up Study Comparing Primary Medical vs. Surgical Therapy in Women With Prolactinomas","volume":"55","author":"Andereggen","year":"2017","journal-title":"Endocrine"},{"key":"B66","doi-asserted-by":"publisher","DOI":"10.1016\/j.jclinepi.2018.07.010","article-title":"Validation in Prediction Research: The Waste by Data Splitting","volume":"103","author":"Steyerberg","year":"2018","journal-title":"J Clin Epidemiol"}],"container-title":["Frontiers in Endocrinology"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fendo.2022.810219\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,2,15]],"date-time":"2022-02-15T23:58:13Z","timestamp":1644969493000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fendo.2022.810219\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,2,16]]},"references-count":66,"alternative-id":["10.3389\/fendo.2022.810219"],"URL":"https:\/\/doi.org\/10.3389\/fendo.2022.810219","relation":{},"ISSN":["1664-2392"],"issn-type":[{"value":"1664-2392","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,2,16]]},"article-number":"810219"}}