AUTHOR=Zhang Wentai , Sun Mengke , Fan Yanghua , Wang He , Feng Ming , Zhou Shaohua , Wang Renzhi 

TITLE=Machine Learning in Preoperative Prediction of Postoperative Immediate Remission of Histology-Positive Cushing’s Disease

JOURNAL=Frontiers in Endocrinology

VOLUME=Volume 12 - 2021

YEAR=2021

URL=https://www.frontiersin.org/journals/endocrinology/articles/10.3389/fendo.2021.635795

DOI=10.3389/fendo.2021.635795

ISSN=1664-2392

ABSTRACT=Background: There are no established accurate models that use machine learning (ML) methods to preoperatively predict immediate remission after transsphenoidal surgery (TSS) in patients diagnosed with Cushing’s disease (CD).
Purpose: Our current study aims to devise and assess an ML-based model to preoperatively predict immediate remission after TSS in patients with CD.
Methods: A total of 1045 participants with CD who received TSS at Peking Union Medical College Hospital in a 20-year period (February 2000 and September 2019) were enrolled in the present study, which examined their clinical characteristics and early postoperative outcomes. In total 9 ML classifiers were applied to construct models for the preoperative prediction of immediate remission. The area under the receiver operating characteristic (ROC) curve (AUC) was used to evaluate the performance of the models. The performance of each ML-based model was evaluated in terms of the AUC.
Results: The overall immediate remission rate was 73.3% (766/1045). First operation (p<0.001), cavernous sinus invasion on preoperative MRI(p<0.001), tumour size (p<0.001), morning adrenocorticotropic hormone (ACTH)(p=0.008) and disease course (p=0.010) were significantly related to immediate remission on logistic univariate analysis. The AUCs of the models ranged between 0.664 and 0.743. The highest AUC, i.e., the best performance, was 0.743, which was achieved using stacking ensemble method with 4 characteristics: first operation, cavernous sinus invasion on preoperative MRI, tumour size and preoperative ACTH.
Conclusion: We developed a readily available ML-based model that is useful for the preoperative prediction of immediate remission in patients with CD.