Diagnostic Concordance Across Text and Image Workflows in Nine Consumer Multimodal Artificial Intelligence Systems for Cutaneous Vascular Anomalies: A Cross-Sectional Audit.
- 1Department of Hemangioma and Vascular Malformation, Plastic Surgery Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, 33 Badachu Road, Shijingshan District, Beijing 100144, China.
- 2Department of Internal Medicine, Plastic Surgery Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, 33 Badachu Road, Shijingshan District, Beijing 100144, China.
Abstract
Background/Objectives: The reliability of widely accessible multimodal artificial intelligence systems for rare or complex cutaneous vascular anomalies is uncertain. We evaluated diagnostic concordance and expert-rated management outputs across clinical-summary text, clinical-summary text plus images, and image-only workflows. Methods: In this cross-sectional audit, a purposively assembled, nonconsecutive challenge set of 511 published cases was evaluated with nine consumer web systems in new-conversation first-response sessions (13,797 final score records). Outputs were classified as top-1 concordance with the source-reported diagnosis, differential-list-only inclusion, or omission. Two vascular-anomaly specialists independently rated expected management appropriateness and safety on 5-point scales. Paired comparisons used exact McNemar, Friedman, and paired Wilcoxon tests. Results: Image-only top-1 concordance ranged from 0.4% to 7.0%, with omission rates of 71.0% to 97.8%; corresponding clinical-summary-text ranges were 32.9% to 53.0% and 11.5% to 29.4%. Image-only performance was lower than both text-containing workflows for every system. Text-plus-image workflows were not consistently superior to text alone. Conclusions: These date-stamped workflow contrasts do not estimate real-world diagnostic accuracy or isolate the causal contribution of images. They support preservation of clinical context and specialist oversight.
Related
- Theory of Artificial Intelligence Adaptation for Linguistic Concordance: Bridging Gaps in Patient-Centered Communication
- A prebill control plane for record integrity in inpatient artificial intelligence-enabled clinical documentation workflows.
- Toward integrated multimodal artificial intelligence in bone marrow examination: current state and open challenges
- Artificial Intelligence, Multi-Omics, and Multimodal Integration in Precision Radiotherapy for Head and Neck Cancer: From Biological Insights to Treatment Decisions
- CT-Referenced Diagnostic Performance and Complementary Error Patterns of Artificial Intelligence Versus a Single Emergency Physician in Chest Radiograph Interpretation: A Retrospective Paired Diagnostic Accuracy Study
BibTeX
@article{wang2026diagnostic,
title = {{Diagnostic Concordance Across Text and Image Workflows in Nine Consumer Multimodal Artificial Intelligence Systems for Cutaneous Vascular Anomalies: A Cross-Sectional Audit.}},
author = {Guoyong Wang and Hui Bi and Ye Zhang and Weixin Wang and Yingjie Zhu and Chaonan Wang and Xiaonan Yang},
journal = {Diagnostics (Basel, Switzerland)},
year = {2026},
month = sep,
doi = {10.3390/diagnostics16193100},
url = {https://europepmc.org/article/MED/42882255},
note = {CC BY},
}
RIS
TY - JOUR
TI - Diagnostic Concordance Across Text and Image Workflows in Nine Consumer Multimodal Artificial Intelligence Systems for Cutaneous Vascular Anomalies: A Cross-Sectional Audit.
AU - Guoyong Wang
AU - Hui Bi
AU - Ye Zhang
AU - Weixin Wang
AU - Yingjie Zhu
AU - Chaonan Wang
AU - Xiaonan Yang
PY - 2026
DA - 2026/09/24
JO - Diagnostics (Basel, Switzerland)
DO - 10.3390/diagnostics16193100
UR - https://europepmc.org/article/MED/42882255
AB - Background/Objectives: The reliability of widely accessible multimodal artificial intelligence systems for rare or complex cutaneous vascular anomalies is uncertain. We evaluated diagnostic concordance and expert-rated management outputs across clinical-summary text, clinical-summary text plus images, and image-only workflows. Methods: In this cross-sectional audit, a purposively assembled, nonconsecutive challenge set of 511 published cases was evaluated with nine consumer web systems in new-conversation first-response sessions (13,797 final score records). Outputs were classified as top-1 concordance with the source-reported diagnosis, differential-list-only inclusion, or omission. Two vascular-anomaly specialists independently rated expected management appropriateness and safety on 5-point scales. Paired comparisons used exact McNemar, Friedman, and paired Wilcoxon tests. Results: Image-only top-1 concordance ranged from 0.4% to 7.0%, with omission rates of 71.0% to 97.8%; corresponding clinical-summary-text ranges were 32.9% to 53.0% and 11.5% to 29.4%. Image-only performance was lower than both text-containing workflows for every system. Text-plus-image workflows were not consistently superior to text alone. Conclusions: These date-stamped workflow contrasts do not estimate real-world diagnostic accuracy or isolate the causal contribution of images. They support preservation of clinical context and specialist oversight.
SN - 2075-4418
ER -