Earlier post-operative hypocortisolemia may predict durable remission from Cushing’s disease

Ironside, Natasha; Chatain, Grégoire P.; Asuzu, David T.; Benzo, Sarah; Lodish, Maya; Sharma, Susmeeta T.; Nieman, Lynnette K.; Stratakis, Constantine A.; Lonser, Russell R.; Chittiboina, Prashant

doi:10.1530/eje-17-0873

Cited by 40 publications

(39 citation statements)

References 56 publications

(126 reference statements)

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Incorporating feature selection and univariate analysis, some results corroborated the previous studies, suggesting that younger age [43, 44], higher postoperative morning serum cortisol [6, 9-13], and higher postoperative morning ACTH [11, 14, 45, 46] had a detrimental effect on recurrence.…”

Section: Discussionsupporting

confidence: 75%

“…Although the reported long-term remission rates were relatively high, ranging from 65 to 98% [1, 3-6], the recurrence rates varied widely, ranging from 15 to 66% [2, 3, 7, 8]. Exploring appropriate models to predict the recurrence after TSS for CD presented a clinical challenge.…”

Section: Discussionmentioning

confidence: 99%

“…Some studies suggested that patients with subnormal postoperative cortisol levels [6, 9-13], low postoperative UFC levels [11], or low postoperative ACTH levels [14] tended to have a lower risk of recurrence after initial TSS for CD, while others indicated that there were no reliable risk factors [41, 42]. A meta-analysis [15] also concluded that no reliable predictors of recurrence after TSS were found.…”

Section: Discussionmentioning

confidence: 99%

“…Transsphenoidal surgery (TSS) is a standard treatment for CD [2]. The reported long-term remission rate of TSS for CD ranges from 65 to 98% [3-6], while the reported recurrence rate ranges from 15 to 66% [2, 3, 7, 8] which, compared with that of other types of pituitary adenomas, is a much higher and more variable recurrence rate.…”

Section: Introductionmentioning

confidence: 99%

“…Some studies have shown that patients with subnormal postoperative cortisol levels [6, 9-13], low postoperative urinary free cortisol (UFC) levels [11], or low postoperative ACTH levels [14] tended to face a lower risk of recurrence after initial TSS for CD. However, no clear predictive models for recurrence were developed.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Prediction of Recurrence after Transsphenoidal Surgery for Cushing’s Disease: The Use of Machine Learning Algorithms

Liu

Hong

et al. 2019

Neuroendocrinology

View full text Add to dashboard Cite

Background: There are no reliable predictive models for recurrence after transsphenoidal surgery (TSS) for Cushing’s disease (CD). Objectives: This study aimed to develop machine learning (ML)-based predictive models for CD recurrence after initial TSS and to evaluate their performance. Method: A total of 354 CD patients were included in this retrospective, supervised learning, data mining study. Predictive models for recurrence were developed according to 17 variables using 7 algorithms. Models were evaluated based on the area under the receiver operating characteristic curve (AUC). Results: All patients were followed up for over 12 months (mean ± SD 43.80 ± 35.61). The recurrence rate was 13.0%. Age (p < 0.001), postoperative morning serum cortisol nadir (p = 0.002), and postoperative (p < 0.001) and preoperative (p = 0.04) morning adrenocorticotropin (ACTH) level were significantly related to recurrence. AUCs of the 7 models ranged from 0.608 to 0.781. The best performance (AUC = 0.781, 95% CI 0.706, 0.856) appeared when 8 variables were introduced to the random forest (RF) algorithm, which was much better than that of logistic regression (AUC = 0.684, p = 0.008) and that of using only postoperative morning serum cortisol (AUC = 0.635, p < 0.001). According to the feature selection algorithms, the top 3 predictors were age, postoperative serum cortisol, and postoperative ACTH. Conclusions: Using ML-based models for prediction of the recurrence after initial TSS for CD is feasible, and RF performs best. The performance of most of ML-based models was significantly better than that of some conventional models.

show abstract

Section: Discussionsupporting

confidence: 75%

Section: Discussionmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Prediction of Recurrence after Transsphenoidal Surgery for Cushing’s Disease: The Use of Machine Learning Algorithms

Liu

Hong

et al. 2019

Neuroendocrinology

View full text Add to dashboard Cite

show abstract

Machine Learning in Pituitary Surgery

Stumpo

Staartjes

Regli

et al. 2021

Acta Neurochirurgica Supplement

View full text Add to dashboard Cite

An early post-operative ACTH suppression test can safely predict short- and long-term remission after surgery of Cushing’s disease

et al. 2018

View full text Add to dashboard Cite

PurposeThe present study evaluates the usefulness of an ACTH suppression test shortly after surgery, and to determine optimal cut-off values of included laboratory analyses, in predicting short- and long-term remission after surgery of Cushing’s disease.MethodsA 48 h suppression test with betamethasone 2 mg/day applied after 45 transphenoidal adenomectomies in 28 patients was evaluated. Receiver operating characteristic (ROC)-curves were created for the included assays: plasma cortisol, plasma adrenocorticotropic hormone (ACTH) and urinary free cortisol (UFC). Plasma levels of cortisol and ACTH were measured both at 24 and 48 h. Youden’s index was used to determine cut-off with the highest sensitivity and specificity in predicting short- (3 months) and long-term (5 years or longer) remission. The area under curve (AUC) illustrated the clinical accuracy of the different assays.ResultsPlasma cortisol after 24 h with betamethasone was most accurate in predicting both short- and long-term remission. 3 months remission with cut-off 107 nmol/L: sensitivity 0.85, specificity 0.94, positive predictive value (PPV) 0.96 and AUC 0.92 (95% CI 0.85–1). 5 years remission with cut-off 49 nmol/L: sensitivity: 0.94, specificity 0.93, PPV 0.88, AUC 0.98 (95% CI 0.95–1). Analyses of ACTH or UFC did not improve diagnostic accuracy.ConclusionsA 48 h, 2 mg/day betamethasone suppression test after transphenoidal surgery of Cushing’s disease could predict short- and long-term remission with a high accuracy. Suppression of plasma cortisol after 24 h with betamethasone to values excluding Cushings disease in the diagnostic setting yielded the highest accuracy in predicting long-term remission.

show abstract

Earlier post-operative hypocortisolemia may predict durable remission from Cushing’s disease

Abstract: In our cohort, early, profound hypocortisolemia could be used as a clinical prediction tool for durable remission. Achievement of hypocortisolemia ≤2 µg/dL before 21 post-operative hours appeared to accurately predict durable remission in the intermediate term.

Cited by 40 publications

References 56 publications

Prediction of Recurrence after Transsphenoidal Surgery for Cushing’s Disease: The Use of Machine Learning Algorithms

Prediction of Recurrence after Transsphenoidal Surgery for Cushing’s Disease: The Use of Machine Learning Algorithms

Machine Learning in Pituitary Surgery

An early post-operative ACTH suppression test can safely predict short- and long-term remission after surgery of Cushing’s disease

Contact Info

Product

Resources

About