Clemente García-Hidalgo
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Clemente García-Hidalgo has a total of 39 co-authors. Here are the top co-authors by number of shared publications:
José Antonio Consentino Hernández
5 shared publications- José Vicente Cayuela Espí
Servicio de Radiología, Hospital General Universitario Morales Meseguer, Avenida Marqués de los Vélez s/n, 30008 Murcia, Spain
4 shared publications José Vicente Cayuela Espí
Radiology Department, Hospital Universitario Morales Meseguer, Murcia, Spain
3 shared publications- Carlos Carazo-Casas
Department of Otolaryngology, Hospital Universitario Ramón y Cajal, 28034 Madrid, Spain
2 shared publications Gonzalo Pagán Vicente
2 shared publications- Gonzalo Pagán Vicente
Servicio de Radiología, Hospital General Universitario Morales Meseguer, Avenida Marqués de los Vélez s/n, 30008 Murcia, Spain
2 shared publications
Latest Publications
- Open Access
- 29 October 2026
- Published by JMIR Publications Inc. in JMIR Medical Education
- Vol. 12, e106199
Construct Validity of Frontier Large Language Models on 4 Spanish Health Professions Specialty-Access Examinations (MIR, EIR, PIR, and FIR): Cross-Sectional Benchmarking and Psychometric Study
Background: Large language models (LLMs) achieve high scores on health-professions examinations. Whether these scores support the same interpretations as human scores remains uncertain. Spain uses parallel multiple-choice examinations for entry to specialty training in medicine (Médico Interno Residente [MIR]), nursing (Enfermero Interno Residente [EIR]), psychology (Psicólogo Interno Residente [PIR]), and pharmacy (Farmacéutico Interno Residente [FIR]). Objective: Using the January 2026 MIR, EIR, PIR, and FIR examinations, this study aimed to quantify the correspondence between human and LLM item facility and to describe model accuracy, distractor selection, and performance associated with measured surface features. Methods: We evaluated 839 valid items using 12 configurations: GPT-5.2 at 3 reasoning efforts and Claude Opus, Sonnet, and Haiku 4.5 (Anthropic), each under neutral and expert prompts, with one run per configuration. The primary measure was the Spearman correlation (ρ) between human and machine facility on 828 complete paired items. We examined sensitivity to panel composition, scoring, pooling, and assumed reliability; compared distractor choices with a post hoc plausibility-weighted baseline; and evaluated a surface-feature classifier. Image analyses distinguished supplied from withheld images. An exploratory LLM-judge audit assessed generated explanations. Bootstrap CIs resample items or, for distractor concordance, error events; they exclude run-to-run uncertainty. Results: The highest pooled accuracy was 94.8% (795/839); all 12 configurations answered 668 of 828 paired items correctly (80.7%). Scores clustered near the ceiling among the strongest configurations. Human and machine facility correlated at 0.40 (95% CI 0.34-0.45), with estimates of 0.31 to 0.40 across panel definitions and 0.39 (95% CI 0.33-0.45) after exam-stratified pooling. The observed correlation was lower than predicted by a specified one-axis simulation with a uniform model advantage (0.63; predictive interval 0.59 to 0.66; P <.001). Among 672 model errors, dominant human-distractor selection differed from the plausibility-weighted baseline by –1.25 percentage points (95% CI –4.53 to 2.19), compatible with no difference. Surface-feature accuracy was 34.4% (289/839), similar to selecting the longest option (34.6%, 290/839). The adjusted association with model correctness was uncertain (odds ratio [OR] 0.87, 95% CI 0.72-1.04). Image-associated accuracy was lower both when images were supplied (OR 0.33, 95% CI 0.21-0.53) and when withheld (OR 0.11, 95% CI 0.08-0.16). Conclusions: In this single 2026 cohort, high LLM scores coexisted with limited separation among the strongest configurations and moderate correspondence with human item difficulty. These findings caution against interpreting model scores as equivalent evidence of human competence. They do not establish clinical performance or invalidate the examinations for human candidates.
- 29 October 2026
- Published by JMIR Publications Inc. in JMIR Medical Education
- Vol. 12, e106199
Open AccessConstruct Validity of Frontier Large Language Models on 4 Spanish Health Professions Specialty-Access Examinations (MIR, EIR, PIR, and FIR): Cross-Sectional Benchmarking and Psychometric Study
Background: Large language models (LLMs) achieve high scores on health-professions examinations. Whether these scores support the same interpretations as human scores remains uncertain. Spain uses parallel multiple-choice examinations for entry to specialty training in medicine (Médico Interno Residente [MIR]), nursing (Enfermero Interno Residente [EIR]), psychology (Psicólogo Interno Residente [PIR]), and pharmacy (Farmacéutico Interno Residente [FIR]). Objective: Using the January 2026 MIR, EIR, PIR, and FIR examinations, this study aimed to quantify the correspondence between human and LLM item facility and to describe model accuracy, distractor selection, and performance associated with measured surface features. Methods: We evaluated 839 valid items using 12 configurations: GPT-5.2 at 3 reasoning efforts and Claude Opus, Sonnet, and Haiku 4.5 (Anthropic), each under neutral and expert prompts, with one run per configuration. The primary measure was the Spearman correlation (ρ) between human and machine facility on 828 complete paired items. We examined sensitivity to panel composition, scoring, pooling, and assumed reliability; compared distractor choices with a post hoc plausibility-weighted baseline; and evaluated a surface-feature classifier. Image analyses distinguished supplied from withheld images. An exploratory LLM-judge audit assessed generated explanations. Bootstrap CIs resample items or, for distractor concordance, error events; they exclude run-to-run uncertainty. Results: The highest pooled accuracy was 94.8% (795/839); all 12 configurations answered 668 of 828 paired items correctly (80.7%). Scores clustered near the ceiling among the strongest configurations. Human and machine facility correlated at 0.40 (95% CI 0.34-0.45), with estimates of 0.31 to 0.40 across panel definitions and 0.39 (95% CI 0.33-0.45) after exam-stratified pooling. The observed correlation was lower than predicted by a specified one-axis simulation with a uniform model advantage (0.63; predictive interval 0.59 to 0.66; P <.001). Among 672 model errors, dominant human-distractor selection differed from the plausibility-weighted baseline by –1.25 percentage points (95% CI –4.53 to 2.19), compatible with no difference. Surface-feature accuracy was 34.4% (289/839), similar to selecting the longest option (34.6%, 290/839). The adjusted association with model correctness was uncertain (odds ratio [OR] 0.87, 95% CI 0.72-1.04). Image-associated accuracy was lower both when images were supplied (OR 0.33, 95% CI 0.21-0.53) and when withheld (OR 0.11, 95% CI 0.08-0.16). Conclusions: In this single 2026 cohort, high LLM scores coexisted with limited separation among the strongest configurations and moderate correspondence with human item difficulty. These findings caution against interpreting model scores as equivalent evidence of human competence. They do not establish clinical performance or invalidate the examinations for human candidates.
- 14 October 2026
- Published by Springer Nature in Journal of Imaging Informatics in Medicine
- p. 1-11
SynPAR for Empirical Membership Inference Auditing of Synthetic Radiomic and Embedding Data
To develop and evaluate SynPAR, a framework for reproducible membership-inference auditing and reporting of synthetic radiomic and embedding data. We evaluated feature releases from eight imaging cohorts using distance, density-ratio, and shadow-calibrated attacks. Reference-overlap experiments tested evaluation contamination. Graded exact-copy controls, with separate threshold-calibration and test records, measured discrimination and sensitivity at false-positive-rate (FPR) targets of 1%, 5%, and 10%. Findings informed a seven-item reporting checklist. Reference overlap increased mean density-ratio area under the receiver-operating-characteristic curve (AUC) from 0.502 to 0.809 across five cohorts. Distance-shadow versus shadow-standardized density AUCs were 0.630 versus 0.523 for the conditional variational autoencoder and 0.584 versus 0.521 for the Wasserstein generative adversarial network; both diffusion implementations were near chance under distance-shadow testing. Across 380 controlled release conditions, sensitivity depended on copying fraction and operating point. With complete copying in independent normal-feature experiments, shadow-standardized density achieved AUC 0.967 but sensitivity 0.480 at rank-calibrated target 1% FPR (achieved 1.04%); distance achieved 1.000 for both, with achieved FPR 1.00%. SynPAR links reference checks and measured sensitivity to practical reporting recommendations. The findings support assessing discrimination and sensitivity to known exposure jointly at explicitly evaluated operating points when interpreting attack results.
- 14 October 2026
- Published by Springer Nature in Journal of Imaging Informatics in Medicine
- p. 1-11
SynPAR for Empirical Membership Inference Auditing of Synthetic Radiomic and Embedding Data
To develop and evaluate SynPAR, a framework for reproducible membership-inference auditing and reporting of synthetic radiomic and embedding data. We evaluated feature releases from eight imaging cohorts using distance, density-ratio, and shadow-calibrated attacks. Reference-overlap experiments tested evaluation contamination. Graded exact-copy controls, with separate threshold-calibration and test records, measured discrimination and sensitivity at false-positive-rate (FPR) targets of 1%, 5%, and 10%. Findings informed a seven-item reporting checklist. Reference overlap increased mean density-ratio area under the receiver-operating-characteristic curve (AUC) from 0.502 to 0.809 across five cohorts. Distance-shadow versus shadow-standardized density AUCs were 0.630 versus 0.523 for the conditional variational autoencoder and 0.584 versus 0.521 for the Wasserstein generative adversarial network; both diffusion implementations were near chance under distance-shadow testing. Across 380 controlled release conditions, sensitivity depended on copying fraction and operating point. With complete copying in independent normal-feature experiments, shadow-standardized density achieved AUC 0.967 but sensitivity 0.480 at rank-calibrated target 1% FPR (achieved 1.04%); distance achieved 1.000 for both, with achieved FPR 1.00%. SynPAR links reference checks and measured sensitivity to practical reporting recommendations. The findings support assessing discrimination and sensitivity to known exposure jointly at explicitly evaluated operating points when interpreting attack results.
- 7 October 2026
- Published by Springer Nature in European Radiology
- p. 1-13
Lifting the radiomics performance ceiling: how preprocessing leakage amplifies model multiplicity
- 7 October 2026
- Published by Springer Nature in European Radiology
- p. 1-13
Lifting the radiomics performance ceiling: how preprocessing leakage amplifies model multiplicity
- 1 October 2026
- Published by Springer Nature in Journal of Imaging Informatics in Medicine
- p. 1-11
Validating Radiomic Feature Comparisons with Patient-Specific Image Surrogates
- 1 October 2026
- Published by Springer Nature in Journal of Imaging Informatics in Medicine
- p. 1-11
Validating Radiomic Feature Comparisons with Patient-Specific Image Surrogates
- Open Access
- 6 September 2026
- Published by Elsevier in European Journal of Radiology
- Vol. 205, 113218
Dynamic susceptibility contrast perfusion-weighted imaging (DSC-PWI) vascular and metabolic biomarkers for presurgical diagnosis of adult brain tumors across different acquisition parameters
- 6 September 2026
- Published by Elsevier in European Journal of Radiology
- Vol. 205, 113218
Open AccessDynamic susceptibility contrast perfusion-weighted imaging (DSC-PWI) vascular and metabolic biomarkers for presurgical diagnosis of adult brain tumors across different acquisition parameters
- 14 July 2026
- Published by Springer Nature in European Radiology
- Vol. 36 (10) , 7468-7470
Letter to the Editor: Late gadolinium enhancement synthesis from cardiac cine MRI: physical, methodological, and editorial considerations
- 14 July 2026
- Published by Springer Nature in European Radiology
- Vol. 36 (10) , 7468-7470
Letter to the Editor: Late gadolinium enhancement synthesis from cardiac cine MRI: physical, methodological, and editorial considerations
- 9 July 2026
- Published by Elsevier in European Journal of Radiology
- Vol. 203, 113058
Article 4 and Article 72 in radiological practice: competence and surveillance beyond compliance
- 9 July 2026
- Published by Elsevier in European Journal of Radiology
- Vol. 203, 113058
Article 4 and Article 72 in radiological practice: competence and surveillance beyond compliance