White, Alexandra J.

Abstract Introduction Cushing's disease (CD) is associated with hypercoagulability which is associated with an increased risk of venous thromboembolic events (VTEs) perioperatively. This risk persists even after successful transsphenoidal surgery (TSS). However, there are no current guidelines for pharmacologic thromboprophylaxis in this patient population. Objective Characterize existing thromboprophylaxis management practices in patients undergoing TSS for CD. Methods An anonymous RedCap survey comprised of questions about perioperative thromboprophylaxis in CD patients was distributed via the American Association of Neurological Surgeons (AANS)/Congress of Neurological Surgeons (CNS) Joint Tumor Section and the North American Skull Base Society (NASBS) email lists. Results The survey was distributed to 554 members of the AANS/CNS Joint Tumor Section and 1,094 members of NASBS asking that members who surgically treat CD respond. Sixty responses (3.0% response rate) were received. Fifty-two (86.7%) respondents are involved in the postoperative management of CD patients. Thirty-six (69.2%) treat all patients with postoperative VTE chemoprophylaxis, 8 (15.4%) treat some patients, while 8 (15.4%) do not use chemoprophylaxis. Preferred chemoprophylaxis varies as 26 (59.1%) administer low molecular weight heparin, 14 (31.8%) give unfractionated heparin, 1 (2.3%) give direct oral anticoagulants, and 3 (6.8%) give aspirin. Most (28, 53.8%) of the respondents perceive the VTE risk in this patient population to be 0 to 5%, 16 (30.8%) perceive the risk to be 6 to 10%, and 8 (15.4%) perceive it to be 11 to 20%. Conclusion There is great variability in VTE detection and postoperative prevention practice patterns in CD patients. This study highlights the need for prospective studies to clarify optimal pharmacologic chemoprophylaxis strategies and duration in this patient population.

Background: The complex nature and heterogeneity involving pituitary surgery results have increased interest in machine learning (ML) applications for prediction of outcomes over the last decade. This study aims to systematically review the characteristics of ML models involving pituitary surgery outcome prediction and assess their reporting quality. Methods: We searched the PubMed, Scopus, and Web of Knowledge databases for publications on the use of ML to predict pituitary surgery outcomes. We used the Transparent Reporting of a multivariable prediction model for Individual Prognosis Or Diagnosis (TRIPOD) to assess report quality. Our search strategy was based on the terms “artificial intelligence”, “machine learning”, and “pituitary”. Results: 20 studies were included in this review. The principal models reported in each article were post-surgical endocrine outcomes (n = 10), tumor management (n = 3), and intra- and postoperative complications (n = 7). Overall, the included studies adhered to a median of 65% (IQR = 60–72%) of TRIPOD criteria, ranging from 43% to 83%. The median reported AUC was 0.84 (IQR = 0.80–0.91). The most popular algorithms were support vector machine (n = 5) and random forest (n = 5). Only two studies reported external validation and adherence to any reporting guideline. Calibration methods were not reported in 15 studies. No model achieved the phase of actual clinical applicability. Conclusion: Applications of ML in the prediction of pituitary outcomes are still nascent, as evidenced by the lack of any model validated for clinical practice. Although studies have demonstrated promising results, greater transparency in model development and reporting is needed to enable their use in clinical practice. Further adherence to reporting guidelines can help increase AI’s real-world utility and improve clinical practice.