Abstract
BackgroundFirst-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.ObjectiveTo 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.MethodsBy jointly examining two independent performance metrics – the area under the receiver operating characteristic (AUROC) and the Matthews correlation coefficient (MCC) – in combination with a stacked super learner, we present a novel perspective on how to assess and compare the discrimination capacity of a set of binary classifiers.ResultsWe demonstrate that for upfront surgery in prolactinoma patients there are not a one-algorithm-fits-all 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 base learners in a so-called super learner offers great potential: the super learner exhibits very good prediction skill for the primary outcome (AUROC: mean 0.9, 95% CI: 0.92 – 1.00; MCC: 0.85, 95% CI: 0.60 – 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 – 0.83) vs. long-term follow-up (AUROC: 0.80, 95% CI: 0.58 – 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.ConclusionsThis 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.
Highlights
Dopamine agonists (DAs) are the treatment of choice for prolactinomas, given their effectiveness in controlling hyperprolactinemia and restoring gonadal function [1–3]
Accurate prediction of unfavorable outcomes after upfront surgery in prolactinoma patients is crucial to the triage of therapy and interdisciplinary decision-making
Our results highlight the benefits of employing a Machine Learning (ML) approach in addition to traditional methods such as logistic regression for outcome prediction in prolactinoma patients treated with firstline surgery, in particular in a situation of near-complete variable separation, as is the case here for the primary outcome with the predictor remission 30 days
Summary
Dopamine agonists (DAs) are the treatment of choice for prolactinomas, given their effectiveness in controlling hyperprolactinemia and restoring gonadal function [1–3]. Upfront surgery has recently been given a more dominant role in the treatment of prolactinomas [16, 17], their indication still remains controversial in selected patients [18, 19]. Accurate prediction of unfavorable outcomes after upfront surgery in prolactinoma patients is crucial to the triage of therapy and interdisciplinary decision-making. In this context of medical prognosis and prediction analysis, combining patient data with statistical methods, algorithms and tools that constitute the field of Machine Learning (ML) entails a distinct impact on medical research and clinical practice [20–25]. Accurate prediction of unfavorable outcomes after upfront surgery in prolactinoma patients is critical for the triage of therapy and for interdisciplinary decision-making
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.