Searcharxiv⌕ Search
Home/Archive/arXiv

arXiv · 2511.03769

Current validation practice undermines surgical AI development

Annika Reinke·Ziying O. Li·Minu D. Tizabi·Pascaline André·Marcel Knopp·Mika M. Rother·Ines P. Machado·Maria S. Altieri·Deepak Alapatt·Sophia Bano·Sebastian Bodenstedt·Oliver Burgert·Elvis C. S. Chen·Justin W. Collins·Olivier Colliot·Evangelia Christodoulou·Tobias Czempiel·Adrito Das·Reuben Docea·Daniel Donoho·Qi Dou·Jennifer Eckhoff·Sandy Engelhardt·Gabor Fichtinger·Philipp Fuernstahl·Pablo García Kilroy·Stamatia Giannarou·Stephen Gilbert·Ines Gockel·Patrick Godau·Jan Gödeke·Teodor P. Grantcharov·Tamas Haidegger·Alexander Hann·Makoto Hashizume·Charles Heitz·Rebecca Hisey·Hanna Hoffmann·Arnaud Huaulmé·Paul F. Jäger·Pierre Jannin·Anthony Jarc·Rohit Jena·Yueming Jin·Leo Joskowicz·Luc Joyeux·Max Kirchner·Axel Krieger·Gernot Kronreif·Kyle Lam·Shlomi Laufer·Joël L. Lavanchy·Gyusung I. Lee·Robert Lim·Peng Liu·Lucas Luttner·Hani J. Marcus·Pietro Mascagni·Leon Mayer·Ozanan R. Meireles·Beat P. Mueller·Lars Mündermann·Hirenkumar Nakawala·Nassir Navab·Abdourahmane Ndong·Juliane Neumann·Felix Nickel·Marco Nolden·Chinedu Nwoye·Namkee Oh·Nicolas Padoy·Thomas Pausch·Micha Pfeiffer·Tim Rädsch·Hongliang Ren·Nicola Rieke·Dominik Rivoir·Duygu Sarikaya·Samuel Schmidgall·Matthias Seibold·Silvia Seidlitz·Alexander Seitel·Lalith Sharan·Jeffrey H. Siewerdsen·Vinkle Srivastav·Raphael Sznitman·Russell Taylor·Thuy N. Tran·Matthias Unberath·Fons van der Sommen·Martin Wagner·Amine Yamlahi·Shaohua K. Zhou·Aneeq Zia·Amin Madani·Danail Stoyanov·Stefanie Speidel·Daniel A. Hashimoto·Fiona R. Kolbinger·Lena Maier-Hein
View original source ↗Read source document ↗Export metadata ↓

Abstract

Surgical data science (SDS) is rapidly advancing, yet clinical adoption of artificial intelligence (AI) in surgery remains limited, with inadequate validation as an important contributing factor. Existing validation practices often neglect the temporal and hierarchical structure of intraoperative videos, yielding misleading or clinically irrelevant results. We introduce a comprehensive catalogue of validation pitfalls in AI-based surgical video analysis, derived from a multi-stage Delphi process with 92 international experts. Pitfalls span three categories: (1) data, (2) metric selection/configuration, and (3) aggregation and reporting. A systematic review of surgical AI papers reveals that these pitfalls are widespread. Experiments on surgical video datasets show that ignoring temporal and hierarchical data structures can understate uncertainty, obscure critical failure modes, and alter algorithm rankings. To address these shortcomings, we provide consensus-based best practices compiled. Together, this work provides an evidence-based framework for rigorous validation of surgical video analysis algorithms, guiding benchmarking, reporting, regulatory review, and clinical translation.

Explore related subjects

q-bio.OT

Keep this discovery

BibTeXRIS

Annika Reinke, Ziying O. Li, Minu D. Tizabi, Pascaline André, Marcel Knopp, Mika M. Rother, Ines P. Machado, Maria S. Altieri, Deepak Alapatt, Sophia Bano, Sebastian Bodenstedt, Oliver Burgert, Elvis C. S. Chen, Justin W. Collins, Olivier Colliot, Evangelia Christodoulou, Tobias Czempiel, Adrito Das, Reuben Docea, Daniel Donoho, Qi Dou, Jennifer Eckhoff, Sandy Engelhardt, Gabor Fichtinger, Philipp Fuernstahl, Pablo García Kilroy, Stamatia Giannarou, Stephen Gilbert, Ines Gockel, Patrick Godau, Jan Gödeke, Teodor P. Grantcharov, Tamas Haidegger, Alexander Hann, Makoto Hashizume, Charles Heitz, Rebecca Hisey, Hanna Hoffmann, Arnaud Huaulmé, Paul F. Jäger, Pierre Jannin, Anthony Jarc, Rohit Jena, Yueming Jin, Leo Joskowicz, Luc Joyeux, Max Kirchner, Axel Krieger, Gernot Kronreif, Kyle Lam, Shlomi Laufer, Joël L. Lavanchy, Gyusung I. Lee, Robert Lim, Peng Liu, Lucas Luttner, Hani J. Marcus, Pietro Mascagni, Leon Mayer, Ozanan R. Meireles, Beat P. Mueller, Lars Mündermann, Hirenkumar Nakawala, Nassir Navab, Abdourahmane Ndong, Juliane Neumann, Felix Nickel, Marco Nolden, Chinedu Nwoye, Namkee Oh, Nicolas Padoy, Thomas Pausch, Micha Pfeiffer, Tim Rädsch, Hongliang Ren, Nicola Rieke, Dominik Rivoir, Duygu Sarikaya, Samuel Schmidgall, Matthias Seibold, Silvia Seidlitz, Alexander Seitel, Lalith Sharan, Jeffrey H. Siewerdsen, Vinkle Srivastav, Raphael Sznitman, Russell Taylor, Thuy N. Tran, Matthias Unberath, Fons van der Sommen, Martin Wagner, Amine Yamlahi, Shaohua K. Zhou, Aneeq Zia, Amin Madani, Danail Stoyanov, Stefanie Speidel, Daniel A. Hashimoto, Fiona R. Kolbinger, Lena Maier-Hein. 2025-11-05. Current validation practice undermines surgical AI development. https://arxiv.org/abs/2511.03769

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related papers

arXiv2026

MarkerScout: A Disease-Agnostic Machine Learning Framework for Biomarker Prediction from Multi-Scale Mechanistic Models

We demonstrate the framework on three infectious diseases derived from a companion mechanistic immune-simulation platform: SARS-CoV-2, Influenza A Virus, and Plasmodium falciparum. Each disease was evaluated across hospitalization and intensive care unit cohorts, yielding six cohorts in total. Best-pipeline cross-validated macro F1 ranged from 0.82 for IAV-HOSP to 0.99 for COV-ICU, and the framework produced tiered, direction-aware biomarker lists for each disease and phase. Interleukin-18 (IL-18) reached the strongest tier in both SARS-CoV-2 phases with consistent direction. When benchmarked against three separate, independently collected clinical ICU datasets, MarkerScout's top-ranked features outperformed 94.4% of randomly selected feature sets of equivalent size for SARS-CoV-2, with a weaker but directionally consistent advantage for Influenza A Virus (66.7%) and Plasmodium falciparum (60.7%).

q-bio.OT↗
arXiv2026

Enhancing Clinical Decision Support and Differential Diagnosis with Knowledge Graphs, and Retrieval Augmented Generation in Generative AI

Diagnostic error carries a burden, while unconstrained large language models (LLMs) remain vulnerable to hallucination and weak integration of quantitative laboratory dynamics. We developed a decision-support pipeline combining disease-specific biomarker correlation graphs, ordinary differential equations (ODEs), deep sequence classification, and retrieval-augmented generation (RAG). For 103 disease classes from a full blood count (FBC) repository, biomarker networks were used as coupling matrices to generate 30 trajectories per disease (3,090 total). A one-dimensional convolutional neural network (CNN) and long short-term memory (LSTM) network classified disease trajectories and six dynamical clusters. A constrained GPT-4o-mini RAG layer used a 19-pattern BMJ Best Practice/NICE corpus to generate differential diagnoses evaluated for diagnostic suitability, evidential grounding, and clinical plausibility. Across five random-seed runs, disease-level accuracy was $0.940 \pm 0.006$ for the CNN (95\% CI 0.933--0.948) and $0.852 \pm 0.019$ for the LSTM (95\% CI 0.828--0.875); the CNN advantage was 8.87 percentage points (95\% CI 6.47--11.27; $t(4)=10.26$, $p=5.1\times10^{-4}$; Hedges' $g=3.67$). Among 100 sampled RAG cases, 96 parsed successfully; evidence was cited in 97.9\%, the true diagnosis was mentioned in 71.9\%, and the composite score was 3.82/5 with a 47.9\% strict pass rate. The central finding was a decoupling between grounding and diagnostic correctness: classifier-correct versus classifier-wrong outputs differed in diagnostic suitability but not evidential grounding. Post-hoc analysis confirmed a 1.02-point diagnostic-score difference (Mann--Whitney $p=0.0024$; Hedges' $g=0.72$), whereas grounding differed by only $-0.02$ points ($p=0.839$; $g=-0.04$).

q-bio.OT↗
arXiv2026

Expanding the Human Ancestry Ontology to include under-represented populations and ethnicities for broader utility in annotations

Successful discovery, integration and reuse of data relies on the availability of rich, well-structured and machine-readable metadata to describe every aspect of the data, from sample sources to collection processes to experimental protocols. The use of standardised terminologies to express concepts in a harmonised fashion lies at the core of high-quality data annotation, increasing the FAIRness of the data, facilitating data integration and promoting reproducibility. Here, we describe the Human Ancestry Ontology (HANCESTRO), originally developed to improve standardised reporting of genetic ancestry genomic resources such as the NHGRI-EBI GWAS Catalog and the Human Cell Atlas through high-level population descriptors, and more recently expanded to include diverse and previously under-represented populations in genomics and genetics research. HANCESTRO provides a framework for population descriptors that includes both ancestry based on the analysis of genetic information and self-reported ethnicity, which is based on social and cultural factors that don't necessarily align with genetic populations. By enabling the accurate and interoperable representation of population-related data, it promotes inclusive, representative and reproducible science.

q-bio.OT↗