Xuanyu Zhou

All Publications

• Red teaming ChatGPT in medicine to yield real-world insights on model behavior. NPJ digital medicine Chang, C. T., Farah, H., Gui, H., Rezaei, S. J., Bou-Khalil, C., Park, Y. J., Swaminathan, A., Omiye, J. A., Kolluri, A., Chaurasia, A., Lozano, A., Heiman, A., Jia, A. S., Kaushal, A., Jia, A., Iacovelli, A., Yang, A., Salles, A., Singhal, A., Narasimhan, B., Belai, B., Jacobson, B. H., Li, B., Poe, C. H., Sanghera, C., Zheng, C., Messer, C., Kettud, D. V., Pandya, D., Kaur, D., Hla, D., Dindoust, D., Moehrle, D., Ross, D., Chou, E., Lin, E., Haredasht, F. N., Cheng, G., Gao, I., Chang, J., Silberg, J., Fries, J. A., Xu, J., Jamison, J., Tamaresis, J. S., Chen, J. H., Lazaro, J., Banda, J. M., Lee, J. J., Matthys, K. E., Steffner, K. R., Tian, L., Pegolotti, L., Srinivasan, M., Manimaran, M., Schwede, M., Zhang, M., Nguyen, M., Fathzadeh, M., Zhao, Q., Bajra, R., Khurana, R., Azam, R., Bartlett, R., Truong, S. T., Fleming, S. L., Raj, S., Behr, S., Onyeka, S., Muppidi, S., Bandali, T., Eulalio, T. Y., Chen, W., Zhou, X., Ding, Y., Cui, Y., Tan, Y., Liu, Y., Shah, N., Daneshjou, R. 2025; 8 (1): 149

  Abstract

  Red teaming, the practice of adversarially exposing unexpected or undesired model behaviors, is critical towards improving equity and accuracy of large language models, but non-model creator-affiliated red teaming is scant in healthcare. We convened teams of clinicians, medical and engineering students, and technical professionals (80 participants total) to stress-test models with real-world clinical cases and categorize inappropriate responses along axes of safety, privacy, hallucinations/accuracy, and bias. Six medically-trained reviewers re-analyzed prompt-response pairs and added qualitative annotations. Of 376 unique prompts (1504 responses), 20.1% were inappropriate (GPT-3.5: 25.8%; GPT-4.0: 16%; GPT-4.0 with Internet: 17.8%). Subsequently, we show the utility of our benchmark by testing GPT-4o, a model released after our event (20.4% inappropriate). 21.5% of responses appropriate with GPT-3.5 were inappropriate in updated models. We share insights for constructing red teaming prompts, and present our benchmark for iterative model assessments.

  View details for DOI 10.1038/s41746-025-01542-0

  View details for PubMedID 40055532

  View details for PubMedCentralID 10564921

• Hsp90 Promotes Gastric Cancer Cell Metastasis and Stemness by Regulating the Regional Distribution of Glycolysis-Related Metabolic Enzymes in the Cytoplasm. Advanced science (Weinheim, Baden-Wurttemberg, Germany) Liu, S., Shen, G., Zhou, X., Sun, L., Yu, L., Cao, Y., Shu, X., Ran, Y. 2024: e2310109

  Abstract

  Heat-shock protein 90 (Hsp90) plays a crucial role in tumorigenesis and tumor progression; however, its mechanism of action in gastric cancer (GC) remains unclear. Here, the role of Hsp90 in GC metabolism is the focus of this research. High expression of Hsp90 in GC tissues can interact with glycolysis, collectively affecting prognosis in clinical samples. Both in vitro and in vivo experiments demonstrate that Hsp90 is able to regulate the migration and stemness properties of GC cells. Metabolic phenotype analyses indicate that Hsp90 influences glycolytic metabolism. Mechanistically, Hsp90 interacts with glycolysis-related enzymes, forming multienzyme complexes to enhance glycolysis efficiency and yield. Additionally, Hsp90 binds to cytoskeleton-related proteins, regulating the regional distribution of glycolytic enzymes at the cell margin and lamellar pseudopods. This effect could lead to a local increase in efficient energy supply from glycolysis, further promoting epithelial-mesenchymal transition (EMT) and metastasis. In summary, Hsp90, through its interaction with metabolic enzymes related to glycolysis, forms multi-enzyme complexes and regulates regional distribution of glycolysis by dynamic cytoskeletal adjustments, thereby promoting the migration and stemness of GC cells. These conclusions also support the potential for a combined targeted approach involving Hsp90, glycolysis, and the cytoskeleton in clinical therapy.

  View details for DOI 10.1002/advs.202310109

  View details for PubMedID 38874476