It is unclear whether the proportions of remission and the recurrence rates differ between endoscopic transsphenoidal surgery (TS) and microscopic TS in Cushing’s disease (CD); thus, we conducted a systematic review and meta-analysis to evaluate studies of endoscopic TS and microscopic TS.
We conducted a comprehensive search of PubMed to identify relevant studies. Remission and recurrence were used as outcome measures following surgical treatment of CD.
A total of 24 cohort studies involving 1670 adult patients were included in the comparison. Among these studies, 702 patients across 9 studies underwent endoscopic TS, and 968 patients across 15 studies underwent microscopic TS. Similar baseline characteristics were observed in both groups. There was no significant difference in remission between the two groups: 79.7% (95% CI: 73.1–85.0%) in the endoscopic group and 76.9% (95% CI: 71.3–81.6%) in the microscopic group (P = 0.485). It appears that patients who underwent endoscopic surgery experience recurrence less often than patients who underwent microscopic surgery, with recurrence proportions of 11.0% and 15.9%, respectively (P = 0.134). However, if follow-up time is taken into account, both groups had a recurrence rate of approximately 4% per person per year (95% CI: 3.1–5.4% and 3.6–5.1%, P = 0.651).
We found that remission proportion and recurrence rate were the same in patients who underwent endoscopic TS as in patients who underwent microscopic TS. The definition of diagnosis, remission and recurrence should always be considered in the studies assessing therapeutic efficacy in CD.
Machine learning methods in sellar region diseases present a particular challenge because of the complexity and the necessity for reproducibility. This systematic review aims to compile the current literature on sellar region diseases that utilized machine learning methods and to propose a quality assessment tool and reporting checklist for future studies.
PubMed and Web of Science were searched to identify relevant studies. The quality assessment included five categories: unmet needs, reproducibility, robustness, generalizability and clinical significance.
Seventeen studies were included with the diagnosis of general pituitary neoplasms, acromegaly, Cushing’s disease, craniopharyngioma and growth hormone deficiency. 87.5% of the studies arbitrarily chose one or two machine learning models. One study chose ensemble models, and one study compared several models. 43.8% of studies did not provide the platform for model training, and roughly half did not offer parameters or hyperparameters. 62.5% of the studies provided a valid method to avoid over-fitting, but only five reported variations in the validation statistics. Only one study validated the algorithm in a different external database. Four studies reported how to interpret the predictors, and most studies (68.8%) suggested possible clinical applications of the developed algorithm. The workflow of a machine-learning study and the recommended reporting items were also provided based on the results.
Machine learning methods were used to predict diagnosis and posttreatment outcomes in sellar region diseases. Though most studies had substantial unmet need and proposed possible clinical application, replicability, robustness and generalizability were major limits in current studies.