Development and prospective shadow evaluation of a domain-specific large language model for emergency…

AI / informaticsNPJ digital medicine· Apr 2026

Development and prospective shadow evaluation of a domain-specific large language model for emergency neurological diagnosis.

Yibing Guo, Xiangbin Meng, Erlan Yu … Chuanjie Wu

Emergency MedicineAI / informaticsDiagnosisQ1IF 18.0

Large language model achieved 79.4% accuracy in emergency neurology, outperforming physicians.

Development and prospective shadow evaluation of a domain-specific large language model for emergency neurological diagnosis.

Yibing Guo … Chuanjie Wu

NPJ digital medicine · Apr 2026 · Q1 in General Medicine

Background

Large language models (large language models) show promise in emergency medicine; however, their role in emergency neurology remains unclear.

Methods

We developed a customized large language models, Xuanwu-NeuroAid, and prospectively enrolled 433 patients.

n = 433 patients

Results

79.4%

the model correctly identified the right diagnosis for brain and nerve emergencies

n = 433 patients

More results

The diagnostic outputs of the model and emergency physicians were compared with confirmed diagnoses, and an expert panel performed blinded evaluations of the recommendations generated by both the model and physicians.

More results

Blinded expert assessments indicated that the model's recommendations for examinations and treatments were significantly more comprehensive, accurate, and clinically applicable than those of physicians (p < 0.001).

“

Conclusion

Our findings highlight the potential of the large language models to enhance diagnostic precision and support decision-making in emergency neurology under simulated clinical conditions.

Development and prospective shadow evaluation of a domain-specific large language model for emergency neurological diagnosis.

Development and prospective shadow evaluation of a domain-specific large language model for emergency neurological diagnosis.

Related papers