1
|
Zanier O, Zoli M, Staartjes VE, Alalfi MO, Guaraldi F, Asioli S, Rustici A, Pasquini E, Faustini-Fustini M, Erlic Z, Hugelshofer M, Voglis S, Regli L, Mazzatenta D, Serra C. Development and external validation of clinical prediction models for pituitary surgery. BRAIN & SPINE 2023; 3:102668. [PMID: 38020983 PMCID: PMC10668061 DOI: 10.1016/j.bas.2023.102668] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Received: 05/12/2023] [Revised: 08/14/2023] [Accepted: 08/25/2023] [Indexed: 12/01/2023]
Abstract
Introduction Gross total resection (GTR), Biochemical Remission (BR) and restitution of a priorly disrupted hypothalamus pituitary axis (new improvement, IMP) are important factors in pituitary adenoma (PA) resection surgery. Prediction of these metrics using simple and preoperatively available data might help improve patient care and contribute to a more personalized medicine. Research question This study aims to develop machine learning models predicting GTR, BR, and IMP in PA resection surgery, using preoperatively available data. Material and methods With data from patients undergoing endoscopic transsphenoidal surgery for PAs machine learning models for prediction of GTR, BR and IMP were developed and externally validated. Development was carried out on a registry from Bologna, Italy while external validation was conducted using patient data from Zurich, Switzerland. Results The model development cohort consisted of 1203 patients. GTR was achieved in 207 (17.2%, 945 (78.6%) missing), BR in 173 (14.4%, 992 (82.5%) missing) and IMP in 208 (17.3%, 167 (13.9%) missing) cases. In the external validation cohort 206 patients were included and GTR was achieved in 121 (58.7%, 32 (15.5%) missing), BR in 46 (22.3%, 145 (70.4%) missing) and IMP in 42 (20.4%, 7 (3.4%) missing) cases. The AUC at external validation amounted to 0.72 (95% CI: 0.63-0.80) for GTR, 0.69 (0.52-0.83) for BR, as well as 0.82 (0.76-0.89) for IMP. Discussion and conclusion All models showed adequate generalizability, performing similarly in training and external validation, confirming the possible potentials of machine learning in helping to adapt surgical therapy to the individual patient.
Collapse
Affiliation(s)
- Olivier Zanier
- Machine Intelligence in Clinical Neuroscience (MICN) Laboratory, Department of Neurosurgery, Clinical Neuroscience Center, University Hospital Zurich, University of Zurich, Zurich, Switzerland
| | - Matteo Zoli
- IRCCS Istituto Delle Scienze Neurologiche di Bologna. Programma Neurochirurgia Ipofisi - Pituitary Unit, Bologna, Italy
- Department of Biomedical and Neuromotor Sciences (DIBINEM), University of Bologna, Italy
| | - Victor E. Staartjes
- Machine Intelligence in Clinical Neuroscience (MICN) Laboratory, Department of Neurosurgery, Clinical Neuroscience Center, University Hospital Zurich, University of Zurich, Zurich, Switzerland
| | | | - Federica Guaraldi
- IRCCS Istituto Delle Scienze Neurologiche di Bologna. Programma Neurochirurgia Ipofisi - Pituitary Unit, Bologna, Italy
| | - Sofia Asioli
- Department of Biomedical and Neuromotor Sciences (DIBINEM), University of Bologna, Italy
- Azienda USL di Bologna, Anatomic Pathology Unit, Bologna, Italy
| | - Arianna Rustici
- Department of Experimental, Diagnostic and Specialty Medicine (DIMES), University of Bologna, Italy
| | - Ernesto Pasquini
- Azienda USL di Bologna, Bellaria Hospital, ENT Unit, Bologna, Italy
| | - Marco Faustini-Fustini
- IRCCS Istituto Delle Scienze Neurologiche di Bologna. Programma Neurochirurgia Ipofisi - Pituitary Unit, Bologna, Italy
| | - Zoran Erlic
- Department of Endocrinology, Diabetology and Clinical Nutrition, University Hospital Zurich (USZ) and University of Zurich (UZH), Zurich, Switzerland
| | - Michael Hugelshofer
- Machine Intelligence in Clinical Neuroscience (MICN) Laboratory, Department of Neurosurgery, Clinical Neuroscience Center, University Hospital Zurich, University of Zurich, Zurich, Switzerland
| | - Stefanos Voglis
- Machine Intelligence in Clinical Neuroscience (MICN) Laboratory, Department of Neurosurgery, Clinical Neuroscience Center, University Hospital Zurich, University of Zurich, Zurich, Switzerland
| | - Luca Regli
- Machine Intelligence in Clinical Neuroscience (MICN) Laboratory, Department of Neurosurgery, Clinical Neuroscience Center, University Hospital Zurich, University of Zurich, Zurich, Switzerland
| | - Diego Mazzatenta
- IRCCS Istituto Delle Scienze Neurologiche di Bologna. Programma Neurochirurgia Ipofisi - Pituitary Unit, Bologna, Italy
- Department of Biomedical and Neuromotor Sciences (DIBINEM), University of Bologna, Italy
| | - Carlo Serra
- Machine Intelligence in Clinical Neuroscience (MICN) Laboratory, Department of Neurosurgery, Clinical Neuroscience Center, University Hospital Zurich, University of Zurich, Zurich, Switzerland
| |
Collapse
|
2
|
Lin K, Feng T, Mu S, Wang S. Understanding of the interaction between pituitary adenoma growth and the diaphragma sellae. Asian J Surg 2022; 45:1638-1639. [PMID: 35367094 DOI: 10.1016/j.asjsur.2022.03.066] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/07/2022] [Accepted: 03/17/2022] [Indexed: 11/24/2022] Open
Affiliation(s)
- Kunzhe Lin
- Department of Neurosurgery, Affiliated Fuzhou First Hospital of Fujian Medical University, Fuzhou, 350009, China
| | - Tianshun Feng
- Department of Neurosurgery, Dongfang Affiliated Hospital of Xiamen University, School of Medicine, Xiamen University, Xiamen, 361000, China
| | - Shuwen Mu
- Fuzong Clinical Medical College of Fujian Medical University, Fuzhou, 350025, China
| | - Shousen Wang
- Department of Neurosurgery, 900th Hospital, Fuzong Clinical Medical College of Fujian Medical University, Fuzhou, 350025, China.
| |
Collapse
|
3
|
Zanier O, Zoli M, Staartjes VE, Guaraldi F, Asioli S, Rustici A, Picciola VM, Pasquini E, Faustini-Fustini M, Erlic Z, Regli L, Mazzatenta D, Serra C. Machine learning-based clinical outcome prediction in surgery for acromegaly. Endocrine 2022; 75:508-515. [PMID: 34642894 PMCID: PMC8816764 DOI: 10.1007/s12020-021-02890-z] [Citation(s) in RCA: 6] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 05/23/2021] [Accepted: 09/08/2021] [Indexed: 11/13/2022]
Abstract
PURPOSE Biochemical remission (BR), gross total resection (GTR), and intraoperative cerebrospinal fluid (CSF) leaks are important metrics in transsphenoidal surgery for acromegaly, and prediction of their likelihood using machine learning would be clinically advantageous. We aim to develop and externally validate clinical prediction models for outcomes after transsphenoidal surgery for acromegaly. METHODS Using data from two registries, we develop and externally validate machine learning models for GTR, BR, and CSF leaks after endoscopic transsphenoidal surgery in acromegalic patients. For the model development a registry from Bologna, Italy was used. External validation was then performed using data from Zurich, Switzerland. Gender, age, prior surgery, as well as Hardy and Knosp classification were used as input features. Discrimination and calibration metrics were assessed. RESULTS The derivation cohort consisted of 307 patients (43.3% male; mean [SD] age, 47.2 [12.7] years). GTR was achieved in 226 (73.6%) and BR in 245 (79.8%) patients. In the external validation cohort with 46 patients, 31 (75.6%) achieved GTR and 31 (77.5%) achieved BR. Area under the curve (AUC) at external validation was 0.75 (95% confidence interval: 0.59-0.88) for GTR, 0.63 (0.40-0.82) for BR, as well as 0.77 (0.62-0.91) for intraoperative CSF leaks. While prior surgery was the most important variable for prediction of GTR, age, and Hardy grading contributed most to the predictions of BR and CSF leaks, respectively. CONCLUSIONS Gross total resection, biochemical remission, and CSF leaks remain hard to predict, but machine learning offers potential in helping to tailor surgical therapy. We demonstrate the feasibility of developing and externally validating clinical prediction models for these outcomes after surgery for acromegaly and lay the groundwork for development of a multicenter model with more robust generalization.
Collapse
Affiliation(s)
- Olivier Zanier
- Machine Intelligence in Clinical Neuroscience (MICN) Laboratory, Department of Neurosurgery, Clinical Neuroscience Center, University Hospital Zurich, University of Zurich, Zurich, Switzerland
| | - Matteo Zoli
- IRCCS Istituto delle Scienze Neurologiche di Bologna, Programma Neurochirurgia Ipofisi-Pituitary Unit, Bologna, Italy
- Department of Biomedical and Neuromotor Sciences (DIBINEM), University of Bologna, Bologna, Italy
| | - Victor E Staartjes
- Machine Intelligence in Clinical Neuroscience (MICN) Laboratory, Department of Neurosurgery, Clinical Neuroscience Center, University Hospital Zurich, University of Zurich, Zurich, Switzerland
| | - Federica Guaraldi
- IRCCS Istituto delle Scienze Neurologiche di Bologna, Programma Neurochirurgia Ipofisi-Pituitary Unit, Bologna, Italy
| | - Sofia Asioli
- Department of Biomedical and Neuromotor Sciences (DIBINEM), University of Bologna, Bologna, Italy
- Azienda USL di Bologna, Anatomic Pathology Unit, Bologna, Italy
| | - Arianna Rustici
- Department of Experimental, Diagnostic and Specialty Medicine (DIMES), University of Bologna, Bologna, Italy
| | | | - Ernesto Pasquini
- Azienda USL di Bologna, Bellaria Hospital, ENT Unit, Bologna, Italy
| | - Marco Faustini-Fustini
- IRCCS Istituto delle Scienze Neurologiche di Bologna, Programma Neurochirurgia Ipofisi-Pituitary Unit, Bologna, Italy
| | - Zoran Erlic
- Department of Endocrinology, Diabetology and Clinical Nutrition, University Hospital Zurich (USZ) and University of Zurich (UZH), Zurich, Switzerland
| | - Luca Regli
- Machine Intelligence in Clinical Neuroscience (MICN) Laboratory, Department of Neurosurgery, Clinical Neuroscience Center, University Hospital Zurich, University of Zurich, Zurich, Switzerland
| | - Diego Mazzatenta
- IRCCS Istituto delle Scienze Neurologiche di Bologna, Programma Neurochirurgia Ipofisi-Pituitary Unit, Bologna, Italy
- Department of Biomedical and Neuromotor Sciences (DIBINEM), University of Bologna, Bologna, Italy
| | - Carlo Serra
- Machine Intelligence in Clinical Neuroscience (MICN) Laboratory, Department of Neurosurgery, Clinical Neuroscience Center, University Hospital Zurich, University of Zurich, Zurich, Switzerland.
| |
Collapse
|
4
|
Jaursch-Hancke C, Deutschbein T, Knappe UJ, Saeger W, Flitsch J, Fassnacht M. The Interdisciplinary Management of Newly Diagnosed Pituitary Tumors. DEUTSCHES ARZTEBLATT INTERNATIONAL 2021; 118:237-243. [PMID: 34114552 DOI: 10.3238/arztebl.m2021.0015] [Citation(s) in RCA: 4] [Impact Index Per Article: 1.3] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Received: 03/31/2020] [Revised: 03/31/2020] [Accepted: 09/21/2020] [Indexed: 11/27/2022]
Abstract
BACKGROUND The increasing use of cranial tomographic imaging has led to the more frequent discovery of pituitary tumors. In this review, we discuss the clinical symptoms that point toward a pituitary tumor, the required diagnostic studies, the potential need for follow-up studies, and the indications for neurosurgical treatment. METHODS This review is based on pertinent publications from the years 2005-2020 that were retrieved by a selective search in PubMed, as well as on the current German S2k guideline, which was created with the present authors playing a coordinating role, and on further guidelines from abroad. Relevant information from older reviews was also considered. RESULTS The reported prevalence of pituitary tumors varies depending on the method of data acquisition. Autopsy studies yield a figure of 10.7%, while population-based studies reported 77.6-115.6 cases per 100 000 inhabitants. These lesions are nearly always benign, and 85% of them are pituitary adenomas. Pituitary adenomas measuring less than 1 cm in diameter are called microadenomas, while those measuring 1 cm or more are called macroadenomas. According to magnetic resonance imaging (MRI) studies, the prevalence of microadenomas in the general population is in the range of 10-38%, while that of macroadenomas is 0.16-0.3%. Pituitary adenomas can be either hormonally inactive or hormonally active. Half of all patients with hormonally inactive microadenomas display no endocrine abnormality, while 37-85% of patients with hormonally inactive macroadenomas manifest at least partial pituitary insufficiency. The clinical spectrum of pituitary tumors ranges from a fully asymptomatic state to visual disturbances, neurologic deficits, severe hormone excess (e.g., in Cushing disease), and life-threatening pituitary insufficiency. Pituitary adenomas are often diagnosed only after a latency of many years, even when they are symptomatic. If an imaging study shows the tumor to be in contact with the visual pathway, an ophthalmological evaluation should be performed. There are clear indications for surgery, e.g., imminent loss of vision, but most asymptomatic pituitary tumors can be observed only. CONCLUSION The manifestations of pituitary tumors are first recognized by primary care physicians. The further diagnostic evaluation of these patients should be carried out in standardized and interdisciplinary fashion.
Collapse
Affiliation(s)
- Cornelia Jaursch-Hancke
- Department of Internal Medicine/Endocrinology, DKD Helios Klinik Wiesbaden Medicover Oldenburg MVZ; Department of Internal Medicine I, Division of Endocrinology and Diabetes, University Hospital, University of; Würzburg, Würzburg, Germany; Department of Neurosurgery, Johannes Wesling Klinikum Minden; Institute of Neuropathology, UKE Hamburg; Department of Neurosurgery, UKE Hamburg
| | | | | | | | | | | |
Collapse
|
5
|
Voglis S, van Niftrik CHB, Staartjes VE, Brandi G, Tschopp O, Regli L, Serra C. Feasibility of machine learning based predictive modelling of postoperative hyponatremia after pituitary surgery. Pituitary 2020; 23:543-551. [PMID: 32488759 DOI: 10.1007/s11102-020-01056-w] [Citation(s) in RCA: 20] [Impact Index Per Article: 5.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Indexed: 12/16/2022]
Abstract
PURPOSE Hyponatremia after pituitary surgery is a frequent finding with potential severe complications and the most common cause for readmission. Several studies have found parameters associated with postoperative hyponatremia, but no reliable specific predictor was described yet. This pilot study evaluates the feasibility of machine learning (ML) algorithms to predict postoperative hyponatremia after resection of pituitary lesions. METHODS Retrospective screening of a prospective registry of patients who underwent transsphenoidal surgery for pituitary lesions. Hyponatremia within 30 days after surgery was the primary outcome. Several pre- and intraoperative clinical, procedural and laboratory features were selected to train different ML algorithms. Trained models were compared using common performance metrics. Final model was internally validated on the testing dataset. RESULTS From 207 patients included in the study, 44 (22%) showed a hyponatremia within 30 days postoperatively. Hyponatremic measurements peaked directly postoperatively (day 0-1) and around day 7. Bootstrapped performance metrics of different trained ML-models showed largest area under the receiver operating characteristic curve (AUROC) for the boosted generalized linear model (67.1%), followed by the Naïve Bayes classifier (64.6%). The discriminative capability of the final model was assessed by predicting on unseen dataset. Large AUROC (84.3%; 67.0-96.4), sensitivity (81.8%) and specificity (77.5%) with an overall accuracy of 78.4% (66.7-88.2) was reached. CONCLUSION Our trained ML-model was able to learn the complex risk factor interactions and showed a high discriminative capability on unseen patient data. In conclusion, ML-methods can predict postoperative hyponatremia and thus potentially reduce morbidity and improve patient safety.
Collapse
Affiliation(s)
- Stefanos Voglis
- Department of Neurosurgery and Clinical Neuroscience Center, University Hospital and University of Zurich, Frauenklinkstrasse 10, 8091, Zurich, Switzerland.
| | - Christiaan H B van Niftrik
- Department of Neurosurgery and Clinical Neuroscience Center, University Hospital and University of Zurich, Frauenklinkstrasse 10, 8091, Zurich, Switzerland
| | - Victor E Staartjes
- Department of Neurosurgery and Clinical Neuroscience Center, University Hospital and University of Zurich, Frauenklinkstrasse 10, 8091, Zurich, Switzerland
| | - Giovanna Brandi
- Neurosurgical Intensive Care Unit, Institute for Intensive Care Medicine, University Hospital and University of Zurich, Zurich, Switzerland
| | - Oliver Tschopp
- Department of Endocrinology, Diabetes, and Clinical Nutrition, University Hospital and University of Zurich, Zurich, Switzerland
| | - Luca Regli
- Department of Neurosurgery and Clinical Neuroscience Center, University Hospital and University of Zurich, Frauenklinkstrasse 10, 8091, Zurich, Switzerland
| | - Carlo Serra
- Department of Neurosurgery and Clinical Neuroscience Center, University Hospital and University of Zurich, Frauenklinkstrasse 10, 8091, Zurich, Switzerland
| |
Collapse
|
6
|
Qian S, Zhan X, Lu M, Li N, Long Y, Li X, Desiderio DM, Zhan X. Quantitative Analysis of Ubiquitinated Proteins in Human Pituitary and Pituitary Adenoma Tissues. Front Endocrinol (Lausanne) 2019; 10:328. [PMID: 31191455 PMCID: PMC6540463 DOI: 10.3389/fendo.2019.00328] [Citation(s) in RCA: 19] [Impact Index Per Article: 3.8] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 01/08/2019] [Accepted: 05/07/2019] [Indexed: 12/30/2022] Open
Abstract
Protein ubiquitination is an important post-translational modification that is associated with multiple diseases, including pituitary adenomas (PAs). Protein ubiquitination profiling in human pituitary and PAs remains unknown. Here, we performed the first ubiquitination analysis with an anti-ubiquitin antibody (specific to K-ε-GG)-based label-free quantitative proteomics method and bioinformatics to investigate protein ubiquitination profiling between PA and control tissues. A total of 158 ubiquitinated sites and 142 ubiquitinated peptides in 108 proteins were identified, and five ubiquitination motifs were found. KEGG pathway network analysis of 108 ubiquitinated proteins identified four statistically significant signaling pathways, including PI3K-AKT signaling pathway, hippo signaling pathway, ribosome, and nucleotide excision repair. R software Gene Ontology (GO) analysis of 108 ubiquitinated proteins revealed that protein ubiquitination was involved in multiple biological processes, cellular components, and molecule functions. The randomly selected ubiquitinated 14-3-3 zeta/delta protein was further analyzed with Western blot, and it was found that upregulated 14-3-3 zeta/delta protein in nonfunctional PAs might be derived from the significantly decreased level of its ubiquitination compared to control pituitaries, which indicated a contribution of 14-3-3 zeta/delta protein to pituitary tumorigenesis. These findings provided the first ubiquitinated proteomic profiling and ubiquitination-involved signaling pathway networks in human PAs. This study offers new scientific evidence and basic data to elucidate the biological functions of ubiquitination in PAs, insights into its novel molecular mechanisms of pituitary tumorigenesis, and discovery of novel biomarkers and therapeutic targets for effective treatment of PAs.
Collapse
Affiliation(s)
- Shehua Qian
- Key Laboratory of Cancer Proteomics of Chinese Ministry of Health, Xiangya Hospital, Central South University, Changsha, China
- Hunan Engineering Laboratory for Structural Biology and Drug Design, Xiangya Hospital, Central South University, Changsha, China
- State Local Joint Engineering Laboratory for Anticancer Drugs, Xiangya Hospital, Central South University, Changsha, China
| | - Xiaohan Zhan
- Key Laboratory of Cancer Proteomics of Chinese Ministry of Health, Xiangya Hospital, Central South University, Changsha, China
- Hunan Engineering Laboratory for Structural Biology and Drug Design, Xiangya Hospital, Central South University, Changsha, China
- State Local Joint Engineering Laboratory for Anticancer Drugs, Xiangya Hospital, Central South University, Changsha, China
| | - Miaolong Lu
- Key Laboratory of Cancer Proteomics of Chinese Ministry of Health, Xiangya Hospital, Central South University, Changsha, China
- Hunan Engineering Laboratory for Structural Biology and Drug Design, Xiangya Hospital, Central South University, Changsha, China
- State Local Joint Engineering Laboratory for Anticancer Drugs, Xiangya Hospital, Central South University, Changsha, China
| | - Na Li
- Key Laboratory of Cancer Proteomics of Chinese Ministry of Health, Xiangya Hospital, Central South University, Changsha, China
- Hunan Engineering Laboratory for Structural Biology and Drug Design, Xiangya Hospital, Central South University, Changsha, China
- State Local Joint Engineering Laboratory for Anticancer Drugs, Xiangya Hospital, Central South University, Changsha, China
| | - Ying Long
- Key Laboratory of Cancer Proteomics of Chinese Ministry of Health, Xiangya Hospital, Central South University, Changsha, China
- Hunan Engineering Laboratory for Structural Biology and Drug Design, Xiangya Hospital, Central South University, Changsha, China
- State Local Joint Engineering Laboratory for Anticancer Drugs, Xiangya Hospital, Central South University, Changsha, China
| | - Xuejun Li
- Department of Neurosurgery, Xiangya Hospital, Central South University, Changsha, China
| | - Dominic M. Desiderio
- The Charles B. Stout Neuroscience Mass Spectrometry Laboratory, Department of Neurology, College of Medicine, University of Tennessee Health Science Center, Memphis, TN, United States
| | - Xianquan Zhan
- Key Laboratory of Cancer Proteomics of Chinese Ministry of Health, Xiangya Hospital, Central South University, Changsha, China
- Hunan Engineering Laboratory for Structural Biology and Drug Design, Xiangya Hospital, Central South University, Changsha, China
- State Local Joint Engineering Laboratory for Anticancer Drugs, Xiangya Hospital, Central South University, Changsha, China
- National Clinical Research Center for Geriatric Disorders, Xiangya Hospital, Central South University, Changsha, China
| |
Collapse
|