Machine learning in predicting early remission in patients after surgical treatment of acromegaly: a multicenter study

Qiao, Na; Shen, Ming; He, Wenqiang; He, Min; Zhang, Zhaoyun; Ye, Hongying; Li, Yiming; Shou, Xuefei; Li, Shiqi; Jiang, Changzhen; Wang, Yongfei; Zhao, Yao

doi:10.1007/s11102-020-01086-4

Cited by 22 publications

(33 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To date, few ML-based models have been proposed for predicting off-medication remission with high performance. AUC of the best full model was 0.888 in a training, retrospective cohort of 833 patients (0.871 in the external cohort) [25]; similarly, AUC of the best full model was 0.855 in a training, retrospective cohort of 534 patients (0.817 in the validation cohort) [26].…”

Section: Discussionmentioning

confidence: 88%

First but not second postoperative day growth hormone assessments as early predictive tests for long-term acromegaly persistence

Cambria

Beccuti

Prencipe

et al. 2021

J Endocrinol Invest

View full text Add to dashboard Cite

Purpose Postoperative assessment of acromegaly activity is typically performed at least 3 months after neurosurgery (NS). Few studies have evaluated the use of early postoperative growth hormone (GH) levels as a test to predict short- and long-term remission of acromegaly. Our objective was to evaluate the diagnostic performance of serum random GH on a postoperative day one (D1-rGH) and two (D2-rGH), particularly in predicting long-term disease persistence. Materials and methods Forty-one subjects with acromegaly who were undergoing NS were enrolled (mean age ± SD 47.4 ± 13.1 years at diagnosis; women 54%; macroadenomas 71%). The final assessment of disease activity was performed one year after NS. ROC curves were used to evaluate the diagnostic performance of D1-rGH and D2-rGH. Results After a 1-year follow-up, the overall remission rate was 55%. ROC analysis identified an optimal D1-rGH cut-off value of 2.1 ng/mL for diagnosing long-term disease persistence (55.6% SE; 90.9% SP). The cut-off point became 2.5 ng/mL after maximizing specificity for disease persistence (yielding a 100% positive predictive value) and 0.3 ng/mL after maximizing sensitivity for disease remission. The optimal D2-rGH cut-off value was 0.6 ng/mL (81.8% SE; 50% SP); the cut-off point became 2.9 ng/mL after maximizing specificity and 0.1 ng/mL after maximizing sensitivity, with no clinical utility. Conclusions D1-rGH could be a highly specific test for the early diagnosis of long-term acromegaly persistence, which is predicted by a value > 2.5 ng/mL with a great degree of certainty. The diagnostic performance of D2-rGH was insufficient. Further research is required to validate these preliminary results prior to modifying the postoperative management of acromegaly.

show abstract

Section: Discussionmentioning

confidence: 88%

First but not second postoperative day growth hormone assessments as early predictive tests for long-term acromegaly persistence

Cambria

Beccuti

Prencipe

et al. 2021

J Endocrinol Invest

View full text Add to dashboard Cite

show abstract

“…Recent studies have identified similar characteristics as predictors of hormonal remission in patients with acromegaly. Predictive models took into account patient age (26), cavernous sinus invasion (26)(27)(28)(29), preoperative GH levels (26,29), EOR (28), and POD1 GH (28) in various combinations to anticipate postoperative remission. Our conclusions are primarily in line with the findings from these studies.…”

Section: Discussionmentioning

confidence: 99%

Postoperative GH and Degree of Reduction in IGF-1 Predicts Postoperative Hormonal Remission in Acromegaly

et al. 2021

View full text Add to dashboard Cite

PurposeDetermine predictive factors for long-term remission of acromegaly after transsphenoidal resection of growth hormone (GH)-secreting pituitary adenomas.MethodsWe identified 94 patients who had undergone transsphenoidal resection of GH-secreting pituitary adenomas for treatment of acromegaly at the USC Pituitary Center from 1999-2019 to determine the predictive value of postoperative endocrine lab values.ResultsPatients underwent direct endoscopic endonasal (60%), microscopic transsphenoidal (38%), and extended endoscopic approaches (2%). The cohort was 63% female and 37% male, with average age of 48.9 years. Patients presented with acral enlargement (72, 77%), macroglossia (40, 43%), excessive sweating (39, 42%), prognathism (38, 40%) and frontal bossing (35, 37%). Seventy-five (80%) were macroadenomas and 19 (20%) were microadenomas. Cavernous sinus invasion was present in 45%. Available immunohistochemical data demonstrated GH staining in 88 (94%) and prolactin in 44 (47%). Available postoperative MRI demonstrated gross total resection in 63% of patients and subtotal resection in 37%. Most patients (66%) exhibited hormonal remission at 12 weeks postoperatively. Receiver operating characteristic (ROC) curves demonstrated postoperative day 1 (POD1) GH levels ≥1.55ng/mL predicted failure to remit from surgical resection alone (59% specificity, 75% sensitivity). A second ROC curve showed decrease in corrected insulin-like growth factor-1 (IGF-1) levels of at least 37% prognosticated biochemical control (90% sensitivity, 80% specificity).ConclusionPOD1 GH and short-term postoperative IGF-1 levels can be used to successfully predict immediate and long-term hormonal remission respectively. A POD1 GH cutoff can identify patients likely to require adjuvant therapy to emphasize clinical follow-up.

show abstract

“…By comparing the six models, the GBDT model has the best predictive performance, can obtain quantitative predictive value, has a higher accuracy rate than clinicians, and can better assist the preoperative clinical diagnosis and treatment decision-making of patients with acromegaly. Qiao ( 17 ) included 833 patients with GH-secreting PAs as a training cohort and trained a partial model (using only preoperative variables) and a full model (using all variables) to predict off-medication endocrine remission at the 6-month follow-up after TSS using multiple ML algorithms. These models have been validated to accurately predict early endocrine remission after TSS in patients with GH-secreting PAs.…”

Section: Magnetic Resonance Imaging-based Radiomics and ML In Pasmentioning

confidence: 99%

The Application of Artificial Intelligence and Machine Learning in Pituitary Adenomas

et al. 2021

View full text Add to dashboard Cite

Pituitary adenomas (PAs) are a group of tumors with complex and heterogeneous clinical manifestations. Early accurate diagnosis, individualized management, and precise prediction of the treatment response and prognosis of patients with PA are urgently needed. Artificial intelligence (AI) and machine learning (ML) have garnered increasing attention to quantitatively analyze complex medical data to improve individualized care for patients with PAs. Therefore, we critically examined the current use of AI and ML in the management of patients with PAs, and we propose improvements for future uses of AI and ML in patients with PAs. AI and ML can automatically extract many quantitative features based on massive medical data; moreover, related diagnosis and prediction models can be developed through quantitative analysis. Previous studies have suggested that AI and ML have wide applications in early accurate diagnosis; individualized treatment; predicting the response to treatments, including surgery, medications, and radiotherapy; and predicting the outcomes of patients with PAs. In addition, facial imaging-based AI and ML, pathological picture-based AI and ML, and surgical microscopic video-based AI and ML have also been reported to be useful in assisting the management of patients with PAs. In conclusion, the current use of AI and ML models has the potential to assist doctors and patients in making crucial surgical decisions by providing an accurate diagnosis, response to treatment, and prognosis of PAs. These AI and ML models can improve the quality and safety of medical services for patients with PAs and reduce the complication rates of neurosurgery. Further work is needed to obtain more reliable algorithms with high accuracy, sensitivity, and specificity for the management of PA patients.

show abstract

Machine learning in predicting early remission in patients after surgical treatment of acromegaly: a multicenter study

Cited by 22 publications

References 17 publications

First but not second postoperative day growth hormone assessments as early predictive tests for long-term acromegaly persistence

First but not second postoperative day growth hormone assessments as early predictive tests for long-term acromegaly persistence

Postoperative GH and Degree of Reduction in IGF-1 Predicts Postoperative Hormonal Remission in Acromegaly

The Application of Artificial Intelligence and Machine Learning in Pituitary Adenomas

Contact Info

Product

Resources

About