Victor E Staartjes1,2, Morgan Broggi3, Costanza Maria Zattra3, Flavio Vasella1, Julia Velz1, Silvia Schiavolin4, Carlo Serra1, Jiri Bartek5,6,7, Alexander Fletcher-Sandersjöö5,6, Petter Förander5,6, Darius Kalasauskas8, Mirjam Renovanz8, Florian Ringel8, Konstantin R Brawanski9, Johannes Kerschbaumer9, Christian F Freyschlag9, Asgeir S Jakola10,11, Kristin Sjåvik12, Ole Solheim13, Bawarjan Schatlo14, Alexandra Sachkova14, Hans Christoph Bock14, Abdelhalim Hussein14, Veit Rohde14, Marike L D Broekman15,16, Claudine O Nogarede15,16, Cynthia M C Lemmens17, Julius M Kernbach18, Georg Neuloh18, Oliver Bozinov1, Niklaus Krayenbühl1, Johannes Sarnthein1, Paolo Ferroli3, Luca Regli1, Martin N Stienen. 1. 1Department of Neurosurgery and Machine Intelligence in Clinical Neuroscience (MICN) Laboratory, Clinical Neuroscience Center, University Hospital Zurich, University of Zurich, Switzerland. 2. 2Amsterdam UMC, Vrije Universiteit Amsterdam, Neurosurgery, Amsterdam Movement Sciences, Amsterdam, The Netherlands. 3. 3Department of Neurosurgery, Fondazione IRCCS Istituto Neurologico Carlo Besta, Milan. 4. 4Neurology, Public Health and Disability Unit, Fondazione IRCCS Istituto Neurologico Carlo Besta, Milan, Italy. 5. 5Department of Neurosurgery, Karolinska University Hospital, Stockholm. 6. 6Department of Clinical Neuroscience and Medicine, Karolinska Institutet, Stockholm, Sweden. 7. 7Department of Neurosurgery, Rigshospitalet, Copenhagen, Denmark. 8. 8Department of Neurosurgery, University Medical Center, Johannes Gutenberg University Mainz, Germany. 9. 9Department of Neurosurgery, Medical University of Innsbruck, Austria. 10. 10Department of Neurosurgery, Sahlgrenska University Hospital, Gothenburg. 11. 11Institute of Neuroscience and Physiology, Sahlgrenska Academy, Gothenburg, Sweden. 12. 12Department of Neurosurgery, University Hospital of North Norway, Tromsö. 13. 13Department of Neurosurgery, St. Olav's University Hospital, Trondheim, Norway. 14. 14Department of Neurosurgery, Georg August University, University Medical Center, Göttingen, Germany. 15. 15Department of Neurosurgery, Haaglanden Medical Center, The Hague. 16. 16Department of Neurosurgery, Leiden University Medical Center, Leiden. 17. 17Department of Neurology, Haaglanden Medical Center, The Hague, The Netherlands; and. 18. 18Department of Neurosurgery, Faculty of Medicine, RWTH Aachen University, Aachen, Germany.
Abstract
OBJECTIVE: Decision-making for intracranial tumor surgery requires balancing the oncological benefit against the risk for resection-related impairment. Risk estimates are commonly based on subjective experience and generalized numbers from the literature, but even experienced surgeons overestimate functional outcome after surgery. Today, there is no reliable and objective way to preoperatively predict an individual patient's risk of experiencing any functional impairment. METHODS: The authors developed a prediction model for functional impairment at 3 to 6 months after microsurgical resection, defined as a decrease in Karnofsky Performance Status of ≥ 10 points. Two prospective registries in Switzerland and Italy were used for development. External validation was performed in 7 cohorts from Sweden, Norway, Germany, Austria, and the Netherlands. Age, sex, prior surgery, tumor histology and maximum diameter, expected major brain vessel or cranial nerve manipulation, resection in eloquent areas and the posterior fossa, and surgical approach were recorded. Discrimination and calibration metrics were evaluated. RESULTS: In the development (2437 patients, 48.2% male; mean age ± SD: 55 ± 15 years) and external validation (2427 patients, 42.4% male; mean age ± SD: 58 ± 13 years) cohorts, functional impairment rates were 21.5% and 28.5%, respectively. In the development cohort, area under the curve (AUC) values of 0.72 (95% CI 0.69-0.74) were observed. In the pooled external validation cohort, the AUC was 0.72 (95% CI 0.69-0.74), confirming generalizability. Calibration plots indicated fair calibration in both cohorts. The tool has been incorporated into a web-based application available at https://neurosurgery.shinyapps.io/impairment/. CONCLUSIONS: Functional impairment after intracranial tumor surgery remains extraordinarily difficult to predict, although machine learning can help quantify risk. This externally validated prediction tool can serve as the basis for case-by-case discussions and risk-to-benefit estimation of surgical treatment in the individual patient.
OBJECTIVE: Decision-making for intracranial tumor surgery requires balancing the oncological benefit against the risk for resection-related impairment. Risk estimates are commonly based on subjective experience and generalized numbers from the literature, but even experienced surgeons overestimate functional outcome after surgery. Today, there is no reliable and objective way to preoperatively predict an individual patient's risk of experiencing any functional impairment. METHODS: The authors developed a prediction model for functional impairment at 3 to 6 months after microsurgical resection, defined as a decrease in Karnofsky Performance Status of ≥ 10 points. Two prospective registries in Switzerland and Italy were used for development. External validation was performed in 7 cohorts from Sweden, Norway, Germany, Austria, and the Netherlands. Age, sex, prior surgery, tumor histology and maximum diameter, expected major brain vessel or cranial nerve manipulation, resection in eloquent areas and the posterior fossa, and surgical approach were recorded. Discrimination and calibration metrics were evaluated. RESULTS: In the development (2437 patients, 48.2% male; mean age ± SD: 55 ± 15 years) and external validation (2427 patients, 42.4% male; mean age ± SD: 58 ± 13 years) cohorts, functional impairment rates were 21.5% and 28.5%, respectively. In the development cohort, area under the curve (AUC) values of 0.72 (95% CI 0.69-0.74) were observed. In the pooled external validation cohort, the AUC was 0.72 (95% CI 0.69-0.74), confirming generalizability. Calibration plots indicated fair calibration in both cohorts. The tool has been incorporated into a web-based application available at https://neurosurgery.shinyapps.io/impairment/. CONCLUSIONS:Functional impairment after intracranial tumor surgery remains extraordinarily difficult to predict, although machine learning can help quantify risk. This externally validated prediction tool can serve as the basis for case-by-case discussions and risk-to-benefit estimation of surgical treatment in the individual patient.
Entities:
Keywords:
AUC = area under the curve; EOR = extent of resection; KPS = Karnofsky Performance Status; ML = machine learning; PROM = patient-reported outcome measure; functional impairment; machine learning; neurosurgery; oncology; outcome prediction; predictive analytics
Authors: Julia Klingenschmid; Aleksandrs Krigers; Daniel Pinggera; Johannes Kerschbaumer; Claudius Thomé; Christian F Freyschlag Journal: J Neurooncol Date: 2022-04-25 Impact factor: 4.506
Authors: Yang Yang; Anna M Zeitlberger; Marian C Neidert; Victor E Staartjes; Morgan Broggi; Costanza Maria Zattra; Flavio Vasella; Julia Velz; Jiri Bartek; Alexander Fletcher-Sandersjöö; Petter Förander; Darius Kalasauskas; Mirjam Renovanz; Florian Ringel; Konstantin R Brawanski; Johannes Kerschbaumer; Christian F Freyschlag; Asgeir S Jakola; Kristin Sjåvik; Ole Solheim; Bawarjan Schatlo; Alexandra Sachkova; Hans Christoph Bock; Abdelhalim Hussein; Veit Rohde; Marike L D Broekman; Claudine O Nogarede; Cynthia M C Lemmens; Julius M Kernbach; Georg Neuloh; Niklaus Krayenbühl; Paolo Ferroli; Luca Regli; Oliver Bozinov; Martin N Stienen Journal: Brain Spine Date: 2021-10-21