Enhancing decision-making in glioblastoma surgery through an explainable human-AI collaboration: an international multicenter model development and external validation study

Surgical resection improves survival in glioblastoma, yet predicting the extent of resection (EOR) remains highly challenging. We developed and externally validated an explainable AI model to generate personalized EOR estimates in 811 glioblastoma patients undergoing microsurgical resection. EOR was categorized into gross-total (GTR), near-total (NTR), and subtotal resections (STR). An interpretable framework provided model explanations and sensitivity analyses to assess the model's strengths and limitations. To demonstrate clinical impact, we compared the performance of the human expert (gold standard) with our AI model and a combined human-AI approach. External validation confirmed generalizability (AUC 0.78, CI 0.73-0.82). Class-specific AUCs were 0.75 (0.67-0.82) for GTR, 0.59 (0.50-0.69) for NTR, and 0.69 (0.53-0.85) for STR. Key predictors included KPS and NANO scores, age, tumor volume, and unfavorable anatomical locations. A combined human-AI collaboration outperformed human experts, with higher overall accuracies (0.53 to 0.94), F1 scores (0.30 to 0.92), and Cohen's κ (0.41 to 0.84). Enhancing predictive performance through the clinician-AI collaboration, our explainable model supports preoperative planning and highlights the value of integrating machine intelligence into surgical decision-making.

Authors

Institutions

Publication Details

Journal
npj Precision Oncology
Published
2025-11-27
DOI
https://doi.org/10.1038/s41698-025-01183-2
Primary Topic
Glioma Diagnosis and Treatment
Type
article
Field-Weighted Citation Impact
0.00

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Enhancing decision-making in glioblastoma surgery through an explainable human-AI collaboration: an international multicenter model development and external validation study

Kevin Akeret, Jonas Ort, David Ryan Ormond, Stefan Josef Grau et al.
npj Precision Oncology
Glioma Diagnosis and Treatment
article

Enhancing decision-making in glioblastoma surgery through an explainable human-AI collaboration: an international multicenter model development and external validation study

Kevin Akeret, Jonas Ort, David Ryan Ormond, Stefan Josef Grau, Martin Bendszus, Martin Wiesmann, Moira Vieli, Julius M. Kernbach, Matthias Simon, Victor E. Staartjes, Charlotte S. Weyland, Hagen Meredig, Alexander Grote, Ulrik Schroeder, Oliver Schnell, Daniel Delev, Marianne Schell, Carlo Serra, Yasin Temel, Luca Regli, Karlijn Hakvoort, Pieter Kubben, Franz Ricklefs, Lasse Dührsen, Georg Neuloh, Hans Clusmann, Hussam Aldin Hamou, Dieter-Henrik Heiland, Danilo Bzdok
article en

Abstract

Surgical resection improves survival in glioblastoma, yet predicting the extent of resection (EOR) remains highly challenging. We developed and externally validated an explainable AI model to generate personalized EOR estimates in 811 glioblastoma patients undergoing microsurgical resection. EOR was categorized into gross-total (GTR), near-total (NTR), and subtotal resections (STR). An interpretable framework provided model explanations and sensitivity analyses to assess the model's strengths and limitations. To demonstrate clinical impact, we compared the performance of the human expert (gold standard) with our AI model and a combined human-AI approach. External validation confirmed generalizability (AUC 0.78, CI 0.73-0.82). Class-specific AUCs were 0.75 (0.67-0.82) for GTR, 0.59 (0.50-0.69) for NTR, and 0.69 (0.53-0.85) for STR. Key predictors included KPS and NANO scores, age, tumor volume, and unfavorable anatomical locations. A combined human-AI collaboration outperformed human experts, with higher overall accuracies (0.53 to 0.94), F1 scores (0.30 to 0.92), and Cohen's κ (0.41 to 0.84). Enhancing predictive performance through the clinician-AI collaboration, our explainable model supports preoperative planning and highlights the value of integrating machine intelligence into surgical decision-making.

npj Precision OncologyVol. 9(1)
Montreal Neurological Institute and Hospital (CA), Universität Hamburg (DE), Philipps University of Marburg (DE), University of Cologne (DE), Friedrich-Alexander-Universität Erlangen-Nürnberg (DE), Fulda University of Applied Sciences (DE), University of Zurich (CH), Heidelberg University (DE), Maastricht University Medical Centre (NL), Maastricht University (NL), University Hospital of Zurich (CH), Evangelisches Krankenhaus Bielefeld (DE), University Medical Center Hamburg-Eppendorf (DE), Universitätsklinikum Aachen (DE), Klinikum Bremerhaven-Reinkenheide (DE), Mila - Quebec Artificial Intelligence Institute (CA), University of Colorado Anschutz Medical Campus (US), RWTH Aachen University (DE)
Bundesministerium für Bildung und Forschung, Ministerul Educaţiei Naţionale
Openalex Percentile: Top 46%
Glioma Diagnosis and Treatment
DOIOpen Access PDFOpenAlex
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.