Quantum Kernel Advantage over Classical Collapse in Medical Foundation Model Embeddings
Organizations: 1MIT Critical Data, Massachusetts Institute of Technology, Cambridge, MA, USA · 2Clinical Research Center, Artificial Intelligence Unit, Fundaci´on Valle del Lili, Cali, Valle del Cauca, Colombia · 3Quantum Innovation Centre (Q.InC), Agency for Science, Technology and Research (A*STAR), 2 Fusionopolis Way, Innovis #08-03, Singapore 138634, Republic of Singapore · Institute of High Performance Computing (IHPC), Agency for Science, Technology and Research (A*STAR), 1 Fusionopolis Way, #16-16 Connexis, Singapore 138632, Republic of Singapore · 5Science, Mathematics and Technology Cluster, Singapore University of Technology and Design, 8 Somapah Road, Singapore 487372, Republic of Singapore · Department of Electronics, Information and Bioengineering, Politecnico di Milano, Milan, Italy · 7Bordeaux Population Health Research Center, Inserm U1219,2026 Universit´e de Bordeaux, F-33000, Bordeaux, France · 8Inria Bordeaux, Universit´e de Bordeaux, F-33000 Bordeaux, France · 9Universidad del Cauca, Popay´an, Colombia · 10Singapore Management University, 81 Victoria St, Singapore 188065 · 11National Taiwan University Hospital · School of Medicine, Johns Hopkins University, Baltimore, MD, USA27 · Department of Biomedical Engineering, Johns Hopkins University, Baltimore, MD, USA · 14AI for Responsible, Generalizable, and Open Surgical (ARGOS) Research Group, Baltimore, MD, USA · School of Information Engineering, Shanghai Maritime University, Shanghai, 201306, China · 16Research Center of Intelligent Information Processing and Quantum Intelligent Computing, Shanghai, 201306, China · Laboratory for Computational Physiology, MIT, Cambridge, MA, USA · Department of Medicine, Beth Israel Deaconess Medical Center, Boston, MA, USA
Abstract
We provide evidence of quantum kernel advantage under noiseless simulation in binary insurance classification on MIMIC-CXR chest radiographs using quantum support vector machines (QSVM) with frozen embeddings from three medical foundation models (MedSigLIP-448, RAD-DINO, ViT-patch32). We propose a two-tier fair comparison framework in which both classifiers receive identical PCA-q features. At Tier 1 (untuned QSVM vs. untuned linear SVM, C = 1 both sides), QSVM wins minority-class F1 in all 18 tested configurations (17 at p < 0.001, 1 at p < 0.01). The classical linear kernel collapses to majority-class prediction on 90-100% of seeds at every qubit count, while QSVM maintains non-trivial recall. At q = 11 (MedSigLIP-448 plateau center), QSVM achieves mean F1 = 0.343 vs. classical F1 = 0.050 (F1 gain = +0.293, p < 0.001) without hyperparameter tuning. Under Tier 2 (untuned QSVM vs. C-tuned RBF SVM), QSVM wins all seven tested configurations (mean gain +0.068, max +0.112). Eigenspectrum analysis reveals quantum kernel effective rank reaches 69.80 at q = 11, far exceeding linear kernel rank, while classical collapse remains C-invariant. A full qubit sweep reveals architecture-dependent concentration onset across models. Code: https://github.com/sebasmos/qml-medimage