Related Experiment Video
Updated: Apr 30, 2026
A Novel Dual-Modal Deep Learning Approach for Real-Time Removal of Hepatic Fluorescence in Indocyanine Green-Guided Laparoscopic Cholecystectomy
Published on: April 17, 2026
Predicting Pediatric Urological Surgery Duration Through Multimodal Patient-Physician Feature Fusion: Deep Learning
Yonggen Zhao1,2, Ruoge Lin3, Yiying Sun1,2
1National Clinical Research Center for Children and Adolescents' Health and Diseases, Children's Hospital, Zhejiang University School of Medicine, 3333 Binsheng Rd, Hangzhou, 310052, China, 86 13588773370.
Background:
Accurate prediction of surgical duration is critical for optimizing operating room scheduling and resource allocation. Existing models, however, exhibit limited applicability in pediatric urology due to the unique anatomical and developmental characteristics of children.
Objective:
This study aimed to develop and validate a specialty-tailored prediction framework for estimating the duration of pediatric urological surgeries.
Methods:
We integrated multisource heterogeneous data, encompassing patient demographics, surgical details, surgeon-specific features, and electronic medical record narratives, to develop a customized prediction system. Large language model techniques were used to extract semantic representations from unstructured clinical text, while a multihead perceptron architecture enabled the efficient fusion of structured and unstructured features. Pediatric-specific clinical variables, such as developmental stage and the severity of urinary tract malformations, were explicitly modeled to capture their impact on surgical duration.
Results:
The proposed approach achieved a mean absolute error of 11.39 minutes and a root mean square error of 15.58 minutes, markedly outperforming existing methods. Comparative analyses demonstrated that the Qwen-based structured preprocessing with text embeddings provided superior feature representation, surpassing both traditional long short-term memory and direct Embedding-3 approaches. Feature importance analysis identified the primary surgical procedure, surgical plan, and preoperative diagnosis as dominant predictive factors.
Conclusions:
By combining innovative feature engineering with a tailored model architecture, the proposed framework substantially improves the accuracy of surgical duration prediction in pediatric urology. These findings offer robust technical support for precision operating room scheduling and hold significant clinical value in enhancing the efficiency of surgical resource utilization.
