1
|
Findlay MC, Tenhoeve S, Alt J, Rennert RC, Couldwell WT, Evans J, Collopy S, Kim W, Delery W, Pacione D, Kim A, Silverstein JM, Chicoine MR, Gardner P, Rotman L, Yuen KCJ, Barkhoudarian G, Fernandez-Miranda J, Benjamin C, Kshettry VR, Zada G, Van Gompel J, Catalino MHS, Little AS, Karsy M. Predictors of Durable Remission After Successful Surgery for Cushing Disease: Results From the Multicenter RAPID Registry. Neurosurgery 2024:00006123-990000000-01223. [PMID: 38905223 DOI: 10.1227/neu.0000000000003042] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/31/2024] [Accepted: 04/14/2024] [Indexed: 06/23/2024] Open
Abstract
BACKGROUND AND OBJECTIVE Cushing disease (CD) affects mortality and quality of life along with limited long-term remission, underscoring the need to better identify recurrence risk. The identification of surgical or imaging predictors for CD remission after transsphenoidal surgery has yielded some inconsistent results and has been limited by single-center, single-surgeon, or meta-analyses studies. We sought to evaluate the multicenter Registry of Adenomas of the Pituitary and Related Disorders (RAPID) database of academic US pituitary centers to assess whether robust nonhormonal recurrence predictors could be elucidated. METHODS Patients with treated CD from 2011 to 2023 were included. The perioperative and long-term characteristics of CD patients with and without recurrence were assessed using univariable and multivariable analyses. RESULTS Of 383 patients with CD from 26 surgeons achieving postoperative remission, 288 (75.2%) maintained remission at last follow-up while 95 (24.8%) showed recurrence (median time to recurrence 9.99 ± 1.34 years). Patients with recurrence required longer postoperative hospital stays (5 ± 3 vs 4 ± 2 days, P = .002), had larger average tumor volumes (1.76 ± 2.53 cm3 vs 0.49 ± 1.17 cm3, P = .0001), and more often previously failed prior treatment (31.1% vs 14.9%, P = .001) mostly being prior surgery. Multivariable hazard prediction models for tumor recurrence found younger age (odds ratio [OR] = 0.95, P = .002) and Knosp grade of 0 (OR = 0.09, reference Knosp grade 4, P = .03) to be protective against recurrence. Comparison of Knosp grade 0 to 2 vs 3 to 4 showed that lower grades had reduced risk of recurrence (OR = 0.27, P = .04). Other factors such as length of stay, surgeon experience, prior tumor treatment, and Knosp grades 1, 2, or 3 failed to reach levels of statistical significance in multivariable analysis. CONCLUSION This multicenter study centers suggests that the strongest predictors of recurrence include tumor size/invasion and age. This insight can help with patient counseling and prognostication. Long-term follow-up is necessary for patients, and early treatment of small tumors may improve outcomes.
Collapse
Affiliation(s)
- Matthew C Findlay
- Department of Neurosurgery, Clinical Neurosciences Center, University of Utah, Salt Lake City, Utah, USA
- School of Medicine, University of Utah, Salt Lake City, Utah, USA
| | - Sam Tenhoeve
- Department of Neurosurgery, Clinical Neurosciences Center, University of Utah, Salt Lake City, Utah, USA
- School of Medicine, University of Utah, Salt Lake City, Utah, USA
| | - Jeremiah Alt
- Department of Otolaryngology-Head and Neck Surgery, University of Utah, Salt Lake City, Utah, USA
| | - Robert C Rennert
- Department of Neurosurgery, Clinical Neurosciences Center, University of Utah, Salt Lake City, Utah, USA
| | - William T Couldwell
- Department of Neurosurgery, Clinical Neurosciences Center, University of Utah, Salt Lake City, Utah, USA
| | - James Evans
- Department of Neurosurgery, Thomas Jefferson University, Philadelphia, Pennsylvania, USA
| | - Sarah Collopy
- Department of Neurosurgery, Thomas Jefferson University, Philadelphia, Pennsylvania, USA
| | - Won Kim
- Department of Neurosurgery, University of California Los Angeles, Los Angeles, California, USA
| | - William Delery
- Department of Neurosurgery, University of California Los Angeles, Los Angeles, California, USA
| | - Donato Pacione
- Department of Neurosurgery, New York University, Lagone Medical Center, New York, New York, USA
| | - Albert Kim
- Department of Neurosurgery, Washington University School of Medicine, St. Louis, Missouri, USA
| | - Julie M Silverstein
- Department of Neurosurgery, Washington University School of Medicine, St. Louis, Missouri, USA
- Division of Endocrinology, Metabolism, & Lipid Research, Washington University School of Medicine, St. Louis, Missouri, USA
| | - Michael R Chicoine
- Department of Neurosurgery, University of Missouri, Columbia, Missouri, USA
| | - Paul Gardner
- Department of Neurosurgery, University of Pittsburgh Medical Center, Pittsburg, Pennsylvania, USA
| | - Lauren Rotman
- Department of Neurosurgery, The Children's Hospital of Philadelphia, Philadelphia, Pennsylvania, USA
| | - Kevin C J Yuen
- Department of Neurosurgery, Barrow Neurological Institute, Phoenix, Arizona, USA
| | - Garni Barkhoudarian
- Department of Neurosurgery, Providence Medical Center, Los Angeles, California, USA
| | | | - Carolina Benjamin
- Department of Neurosurgery, University of Miami Miller School of Medicine, Miami, Florida, USA
| | - Varun R Kshettry
- Department of Neurosurgery, Cleveland Clinic Foundation, Cleveland, Ohio, USA
| | - Gabriel Zada
- Department of Neurosurgery, University of Southern California, Los Angeles, California, USA
| | - Jamie Van Gompel
- Department of Neurosurgery, Mayo Clinic, Rochester, Minnesota, USA
| | - Michael H S Catalino
- Department of Neurosurgery, University of Virginia, Charlottesville, Virginia, USA
| | - Andrew S Little
- Department of Neurosurgery, Barrow Neurological Institute, Phoenix, Arizona, USA
| | - Michael Karsy
- Global Neurosciences Institute, Philadelphia, Pennsylvania, USA
- Department of Neurosurgery, Drexel University College of Medicine, Philadelphia, Pennsylvania, USA
| |
Collapse
|
2
|
Yang DB, Smith AD, Smith EJ, Naik A, Janbahan M, Thompson CM, Varshney LR, Hassaneen W. The State of Machine Learning in Outcomes Prediction of Transsphenoidal Surgery: A Systematic Review. J Neurol Surg B Skull Base 2023; 84:548-559. [PMID: 37854535 PMCID: PMC10581827 DOI: 10.1055/a-1941-3618] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/30/2021] [Accepted: 03/03/2022] [Indexed: 10/14/2022] Open
Abstract
The purpose of this analysis is to assess the use of machine learning (ML) algorithms in the prediction of postoperative outcomes, including complications, recurrence, and death in transsphenoidal surgery. Following Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines, we systematically reviewed all papers that used at least one ML algorithm to predict outcomes after transsphenoidal surgery. We searched Scopus, PubMed, and Web of Science databases for studies published prior to May 12, 2021. We identified 13 studies enrolling 5,048 patients. We extracted the general characteristics of each study; the sensitivity, specificity, area under the curve (AUC) of the ML models developed as well as the features identified as important by the ML models. We identified 12 studies with 5,048 patients that included ML algorithms for adenomas, three with 1807 patients specifically for acromegaly, and five with 2105 patients specifically for Cushing's disease. Nearly all were single-institution studies. The studies used a heterogeneous mix of ML algorithms and features to build predictive models. All papers reported an AUC greater than 0.7, which indicates clinical utility. ML algorithms have the potential to predict postoperative outcomes of transsphenoidal surgery and can improve patient care. Ensemble algorithms and neural networks were often top performers when compared with other ML algorithms. Biochemical and preoperative features were most likely to be selected as important by ML models. Inexplicability remains a challenge, but algorithms such as local interpretable model-agnostic explanation or Shapley value can increase explainability of ML algorithms. Our analysis shows that ML algorithms have the potential to greatly assist surgeons in clinical decision making.
Collapse
Affiliation(s)
- Darrion B. Yang
- Carle Illinois College of Medicine, University of Illinois Urbana Champaign, Champaign, Illinois, United States
| | - Alexander D. Smith
- Carle Illinois College of Medicine, University of Illinois Urbana Champaign, Champaign, Illinois, United States
| | - Emily J. Smith
- Carle Illinois College of Medicine, University of Illinois Urbana Champaign, Champaign, Illinois, United States
| | - Anant Naik
- Carle Illinois College of Medicine, University of Illinois Urbana Champaign, Champaign, Illinois, United States
| | - Mika Janbahan
- Carle Illinois College of Medicine, University of Illinois Urbana Champaign, Champaign, Illinois, United States
| | - Charee M. Thompson
- Department of Communication, University of Illinois Urbana Champaign, Champaign, Illinois, United States
| | - Lav R. Varshney
- Department of Electrical and Computer Engineering, University of Illinois Urbana Champaign, Urbana, Illinois, United States
| | - Wael Hassaneen
- Carle Illinois College of Medicine, University of Illinois Urbana Champaign, Champaign, Illinois, United States
- Department of Neurosurgery, Carle Foundation Hospital, Urbana, Illinois, United States
| |
Collapse
|
3
|
Yu Z, Wang K, Wan Z, Xie S, Lv Z. Popular deep learning algorithms for disease prediction: a review. CLUSTER COMPUTING 2022; 26:1231-1251. [PMID: 36120180 PMCID: PMC9469816 DOI: 10.1007/s10586-022-03707-y] [Citation(s) in RCA: 5] [Impact Index Per Article: 2.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Received: 02/02/2022] [Revised: 07/07/2022] [Accepted: 08/03/2022] [Indexed: 06/15/2023]
Abstract
Due to its automatic feature learning ability and high performance, deep learning has gradually become the mainstream of artificial intelligence in recent years, playing a role in many fields. Especially in the medical field, the accuracy rate of deep learning even exceeds that of doctors. This paper introduces several deep learning algorithms: Artificial Neural Network (NN), FM-Deep Learning, Convolutional NN and Recurrent NN, and expounds their theory, development history and applications in disease prediction; we analyze the defects in the current disease prediction field and give some current solutions; our paper expounds the two major trends in the future disease prediction and medical field-integrating Digital Twins and promoting precision medicine. This study can better inspire relevant researchers, so that they can use this article to understand related disease prediction algorithms and then make better related research.
Collapse
Affiliation(s)
- Zengchen Yu
- College of Computer Science and Technology, Qingdao University, Ningxia Road, Qingdao, 266071 China
| | - Ke Wang
- Psychiatric Department, Qingdao Municipal Hospital, Zhuhai Road, Qingdao, 266071 China
| | - Zhibo Wan
- College of Computer Science and Technology, Qingdao University, Ningxia Road, Qingdao, 266071 China
| | - Shuxuan Xie
- College of Computer Science and Technology, Qingdao University, Ningxia Road, Qingdao, 266071 China
| | - Zhihan Lv
- Department of Game Design, Faculty of Arts, Uppsala University, 75105 Uppsala, Sweden
| |
Collapse
|
5
|
Koh CH, Khan DZ, Digpal R, Layard Horsfall H, Ali AMS, Baldeweg SE, Bouloux PM, Dorward NL, Drake WM, Evanson J, Grieve J, Stoyanov D, Korbonits M, Marcus HJ. The clinical outcomes of imaging modalities for surgical management Cushing's disease - A systematic review and meta-analysis. Front Endocrinol (Lausanne) 2022; 13:1090144. [PMID: 36714581 PMCID: PMC9880448 DOI: 10.3389/fendo.2022.1090144] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 11/05/2022] [Accepted: 12/23/2022] [Indexed: 01/15/2023] Open
Abstract
INTRODUCTION Cushing's disease presents major diagnostic and management challenges. Although numerous preoperative and intraoperative imaging modalities have been deployed, it is unclear whether these investigations have improved surgical outcomes. Our objective was to investigate whether advances in imaging improved outcomes for Cushing's disease. METHODS Searches of PubMed and EMBASE were conducted. Studies reporting on imaging modalities and clinical outcomes after surgical management of Cushing's disease were included. Multilevel multivariable meta-regressions identified predictors of outcomes, adjusting for confounders and heterogeneity prior to investigating the effects of imaging. RESULTS 166 non-controlled single-arm studies were included, comprising 13181 patients over 44 years.The overall remission rate was 77.0% [CI: 74.9%-79.0%]. Cavernous sinus invasion (OR: 0.21 [CI: 0.07-0.66]; p=0.010), radiologically undetectable lesions (OR: 0.50 [CI: 0.37-0.69]; p<0.0001), previous surgery (OR=0.48 [CI: 0.28-0.81]; p=0.008), and lesions ≥10mm (OR: 0.63 [CI: 0.35-1.14]; p=0.12) were associated with lower remission. Less stringent thresholds for remission was associated with higher reported remission (OR: 1.37 [CI: 1.1-1.72]; p=0.007). After adjusting for this heterogeneity, no imaging modality showed significant differences in remission compared to standard preoperative MRI.The overall recurrence rate was 14.5% [CI: 12.1%-17.1%]. Lesion ≥10mm was associated with greater recurrence (OR: 1.83 [CI: 1.13-2.96]; p=0.015), as was greater duration of follow-up (OR: 1.53 (CI: 1.17-2.01); p=0.002). No imaging modality was associated with significant differences in recurrence.Despite significant improvements in detection rates over four decades, there were no significant changes in the reported remission or recurrence rates. CONCLUSION A lack of controlled comparative studies makes it difficult to draw definitive conclusions. Within this limitation, the results suggest that despite improvements in radiological detection rates of Cushing's disease over the last four decades, there were no changes in clinical outcomes. Advances in imaging alone may be insufficient to improve surgical outcomes. SYSTEMATIC REVIEW REGISTRATION https://www.crd.york.ac.uk/PROSPERO/, identifier CRD42020187751.
Collapse
Affiliation(s)
- Chan Hee Koh
- Victor Horsley Department of Neurosurgery, National Hospital for Neurology and Neurosurgery, London, United Kingdom
- Wellcome/EPSRC Centre for Interventional and Surgical Sciences, University College London, London, United Kingdom
- Department of Neurosurgery, Royal Stoke University Hospital, Stoke, United Kingdom
- *Correspondence: Chan Hee Koh,
| | - Danyal Z. Khan
- Victor Horsley Department of Neurosurgery, National Hospital for Neurology and Neurosurgery, London, United Kingdom
- Wellcome/EPSRC Centre for Interventional and Surgical Sciences, University College London, London, United Kingdom
| | - Ronneil Digpal
- Department of Neurosurgery, University Hospital Southampton, Southampton, United Kingdom
| | - Hugo Layard Horsfall
- Victor Horsley Department of Neurosurgery, National Hospital for Neurology and Neurosurgery, London, United Kingdom
- Wellcome/EPSRC Centre for Interventional and Surgical Sciences, University College London, London, United Kingdom
| | - Ahmad M. S. Ali
- Department of Neurosurgery, The Walton Centre, Liverpool, United Kingdom
| | - Stephanie E. Baldeweg
- Department of Diabetes and Endocrinology, University College Hospital, London, United Kingdom
- Centre for Obesity & Metabolism, Department of Experimental & Translational Medicine, Division of Medicine, University College London, London, United Kingdom
| | - Pierre-Marc Bouloux
- Centre for Neuroendocrinology University College London Medical School, London, United Kingdom
| | - Neil L. Dorward
- Victor Horsley Department of Neurosurgery, National Hospital for Neurology and Neurosurgery, London, United Kingdom
| | - William M. Drake
- Centre for Endocrinology, Barts and The London School of Medicine, Queen Mary University of London, London, United Kingdom
| | - Jane Evanson
- Department of Radiology, Barts Health NHS Trust, London, United Kingdom
| | - Joan Grieve
- Victor Horsley Department of Neurosurgery, National Hospital for Neurology and Neurosurgery, London, United Kingdom
| | - Danail Stoyanov
- Wellcome/EPSRC Centre for Interventional and Surgical Sciences, University College London, London, United Kingdom
| | - Márta Korbonits
- Centre for Endocrinology, Barts and The London School of Medicine, Queen Mary University of London, London, United Kingdom
| | - Hani J. Marcus
- Victor Horsley Department of Neurosurgery, National Hospital for Neurology and Neurosurgery, London, United Kingdom
- Wellcome/EPSRC Centre for Interventional and Surgical Sciences, University College London, London, United Kingdom
| |
Collapse
|