Routine ICU surveillance after brain tumor surgery

• Verfasst von: Neumann, Jan-Oliver [VerfasserIn]
• Verfasst von: Schmidt, Stephanie [VerfasserIn]
• Verfasst von: Nohman, Amin [VerfasserIn]
• Verfasst von: Naser, Paul [VerfasserIn]
• Verfasst von: Jakobs, Martin [VerfasserIn]
• Verfasst von: Unterberg, Andreas [VerfasserIn]
• Titel: Routine ICU surveillance after brain tumor surgery
• Titelzusatz: patient selection using machine learning
• Verf.angabe: Jan-Oliver Neumann, Stephanie Schmidt, Amin Nohman, Paul Naser, Martin Jakobs and Andreas Unterberg
• E-Jahr: 2024
• Jahr: 26 September 2024
• Umfang: 12 S.
• Illustrationen: Diagramme
• Fussnoten: Gesehen am 26.03.2025
• Weitere Titel: Titel des special issue: Neurocritical Care: New Insights and Challenges
• Titel Quelle: Enthalten in: Journal of Clinical Medicine
• Ort Quelle: Basel : MDPI, 2012
• Jahr Quelle: 2024
• Band/Heft Quelle: 13(2024), 19, special issue, Artikel-ID 5747, Seite 1-12
• ISSN Quelle: 2077-0383
• DOI: doi:10.3390/jcm13195747
• Datenträger: Online-Ressource
• Sprache: eng
• Sach-SW: complications
• Sach-SW: craniotomy
• Sach-SW: ICU
• Sach-SW: machine learning
• Sach-SW: postoperative surveillance
• K10plus-PPN: 1920611207

Abstract

Background/Objectives: Routine postoperative ICU admission following brain tumor surgery may not benefit selected patients. The objective of this study was to develop a risk prediction instrument for early (within 24 h) postoperative adverse events using machine learning techniques. Methods: Retrospective cohort of 1000 consecutive adult patients undergoing elective brain tumor resection. Nine events/interventions (CPR, reintubation, return to OR, mechanical ventilation, vasopressors, impaired consciousness, intracranial hypertension, swallowing disorders, and death) were chosen as target variables. Potential prognostic features (n = 27) from five categories were chosen and a gradient boosting algorithm (XGBoost) was trained and cross-validated in a 5 × 5 fashion. Prognostic performance, potential clinical impact, and relative feature importance were analyzed. Results: Adverse events requiring ICU intervention occurred in 9.2% of cases. Other events not requiring ICU treatment were more frequent (35% of cases). The boosted decision trees yielded a cross-validated ROC-AUC of 0.81 ± 0.02 (mean ± CI95) when using pre- and post-op data. Using only pre-op data (scheduling decisions), ROC-AUC was 0.76 ± 0.02. PR-AUC was 0.38 ± 0.04 and 0.27 ± 0.03 for pre- and post-op data, respectively, compared to a baseline value (random classifier) of 0.092. Targeting a NPV of at least 95% would require ICU admission in just 15% (pre- and post-op data) or 30% (only pre-op data) of cases when using the prediction algorithm. Conclusions: Adoption of a risk prediction instrument based on boosted trees can support decision-makers to optimize ICU resource utilization while maintaining adequate patient safety. This may lead to a relevant reduction in ICU admissions for surveillance purposes.