Zhang Linmei, Zhu Enzhao, Shi Jiaying, Wu Xiao, Cao Shaokang, Huang Sining, Ai Zisheng, Su Jiansheng
Shanghai Engineering Research Center of Tooth Restoration and Regeneration, Tongji Research Institute of Stomatology, Department of Prosthodontics, Shanghai Tongji Stomatological Hospital, Dental School, Tongji University, Shanghai, China.
School of Medicine, Tongji University, Shanghai, China.
Front Med (Lausanne). 2025 Jan 6;11:1478842. doi: 10.3389/fmed.2024.1478842. eCollection 2024.
The conventional treatment for locally advanced head and neck squamous cell carcinoma (LA-HNSCC) is surgery; however, the efficacy of definitive chemoradiotherapy (CRT) remains controversial.
This study aimed to evaluate the ability of deep learning (DL) models to identify patients with LA-HNSCC who can achieve organ preservation through definitive CRT and provide individualized adjuvant treatment recommendations for patients who are better suited for surgery.
Five models were developed for treatment recommendations. Their performance was assessed by comparing the difference in overall survival rates between patients whose actual treatments aligned with the model recommendations and those whose treatments did not. Inverse probability treatment weighting (IPTW) was employed to reduce bias. The effect of the characteristics on treatment plan selection was quantified through causal inference.
A total of 7,376 patients with LA-HNSCC were enrolled. Balanced Individual Treatment Effect for Survival data (BITES) demonstrated superior performance in both the CRT recommendation (IPTW-adjusted hazard ratio (HR): 0.84, 95% confidence interval (CI), 0.72-0.98) and the adjuvant therapy recommendation (IPTW-adjusted HR: 0.77, 95% CI, 0.61-0.85), outperforming other models and the National Comprehensive Cancer Network guidelines (IPTW-adjusted HR: 0.87, 95% CI, 0.73-0.96).
BITES can identify the most suitable treatment option for an individual patient from the three most common treatment options. DL models facilitate the establishment of a valid and reliable treatment recommendation system supported by quantitative evidence.
局部晚期头颈部鳞状细胞癌（LA-HNSCC）的传统治疗方法是手术；然而，根治性放化疗（CRT）的疗效仍存在争议。
本研究旨在评估深度学习（DL）模型识别可通过根治性CRT实现器官保留的LA-HNSCC患者的能力，并为更适合手术的患者提供个性化辅助治疗建议。
开发了五个用于治疗建议的模型。通过比较实际治疗与模型建议一致的患者和治疗不一致的患者之间的总生存率差异来评估其性能。采用逆概率处理加权（IPTW）来减少偏差。通过因果推断量化特征对治疗方案选择的影响。
共纳入7376例LA-HNSCC患者。生存数据的平衡个体治疗效果（BITES）在CRT建议（IPTW调整后的风险比（HR）：0.84，95%置信区间（CI），0.72-0.98）和辅助治疗建议（IPTW调整后的HR：0.77，95%CI，0.61-0.85）方面均表现出卓越性能，优于其他模型和美国国立综合癌症网络指南（IPTW调整后的HR：0.87，95%CI，0.73-0.96）。
BITES可以从三种最常见的治疗方案中为个体患者确定最合适的治疗选择。DL模型有助于建立一个由定量证据支持的有效且可靠的治疗建议系统。
