Machine learning-based clinical outcome prediction in surgery for acromegaly

Abstract

Purpose Biochemical remission (BR), gross total resection (GTR), and intraoperative cerebrospinal fluid (CSF) leaks are important metrics in transsphenoidal surgery for acromegaly, and prediction of their likelihood using machine learning would be clinically advantageous. We aim to develop and externally validate clinical prediction models for outcomes after transsphenoidal surgery for acromegaly. Methods Using data from two registries, we develop and externally validate machine learning models for GTR, BR, and CSF leaks after endoscopic transsphenoidal surgery in acromegalic patients. For the model development a registry from Bologna, Italy was used. External validation was then performed using data from Zurich, Switzerland. Gender, age, prior surgery, as well as Hardy and Knosp classification were used as input features. Discrimination and calibration metrics were assessed. Results The derivation cohort consisted of 307 patients (43.3% male; mean [SD] age, 47.2 [12.7] years). GTR was achieved in 226 (73.6%) and BR in 245 (79.8%) patients. In the external validation cohort with 46 patients, 31 (75.6%) achieved GTR and 31 (77.5%) achieved BR. Area under the curve (AUC) at external validation was 0.75 (95% confidence interval: 0.59–0.88) for GTR, 0.63 (0.40–0.82) for BR, as well as 0.77 (0.62–0.91) for intraoperative CSF leaks. While prior surgery was the most important variable for prediction of GTR, age, and Hardy grading contributed most to the predictions of BR and CSF leaks, respectively. Conclusions Gross total resection, biochemical remission, and CSF leaks remain hard to predict, but machine learning offers potential in helping to tailor surgical therapy. We demonstrate the feasibility of developing and externally validating clinical prediction models for these outcomes after surgery for acromegaly and lay the groundwork for development of a multicenter model with more robust generalization.

Machine Learning Models to Forecast Outcomes of Pituitary Surgery: A Systematic Review in Quality of Reporting and Current Evidence

“…The most common population studied were general samples of patients with PAs, without distinction (8 studies) [ 27 , 28 , 29 , 30 , 31 , 32 , 33 , 34 ]. Acromegaly patients were the main population in five studies [ 18 , 35 , 36 , 37 , 38 ]. Furthermore, Cushing disease (CD) patients were the focus in four additional studies [ 39 , 40 , 41 , 42 ].…”

“…Furthermore, Cushing disease (CD) patients were the focus in four additional studies [ 39 , 40 , 41 , 42 ]. Only two studies reported a multicenter setting for external validation [ 18 , 38 ]. Only Qiao et al reported the use of a prospective sample for internal validation [ 18 ].…”

“…Data extracted from the reviewed papers regarding the studies’ characteristics and ML algorithms aspects are presented in Table 3 and Table 4 , respectively. Three studies had their main ML model predicting pituitary surgery outcomes regarding tumor management aspects or recurrence [ 27 , 32 , 44 ], while ten focused on the endocrine outcomes after pituitary surgery [ 18 , 35 , 36 , 39 , 40 , 41 , 42 , 43 , 45 ], and seven studies presented ML models predicting complications from pituitary surgery [ 28 , 29 , 30 , 33 , 34 , 38 , 46 ].…”

“…Moreover, calibration methods were not reported in 15 studies. When reported, the calibration methods used were the Hosmer–Lemeshow test (three studies) [ 36 , 45 ], calibration plot (one study) [ 36 ], calibration slope (two studies) [ 18 , 38 ], calibration intercept (two studies) [ 18 , 38 ], and the Brier Score (one study) [ 39 ].…”

“…All studies reported internal validation. The most common approach was based on k-fold cross-validation (k-CV) (11 studies) [ 18 , 27 , 28 , 32 , 33 , 37 , 38 , 40 , 42 , 43 , 44 ]. In terms of algorithm’s type, ML models derived from support vector machines (SVMs) were the most reported (five studies) [ 32 , 33 , 35 , 39 , 43 ].…”