Article record

人工智能驱动的颅面摄影测量分析用于儿童阻塞性睡眠呼吸暂停

Artificial Intelligence-Powered Craniofacial Photogrammetry Analysis of Pediatric Obstructive Sleep Apnea.

AI/ML鼻科IF 2.9Q1

文献信息

PMID	42808580
原文	在 PubMed 查看原文 ↗
发表日期	2026
作者	Wan-Yi Hsueh 查看其他 5 位作者 Kun-Tai Kang；Shih-Hsu Huang；Chia-Jo Lin；Chih-Wen Su；Wei-Chung Hsu
作者单位	Department of Otolaryngology, Hsinchu Cathay General Hospital, Hsinchu, Taiwan. 查看其他 6 条单位信息 Department of Otolaryngology and Sleep Center, Taipei Hospital, Ministry of Health and Welfare, New Taipei City, Taiwan.；Department of Otolaryngology, National Taiwan University Hospital and Children's Hospital, Taipei, Taiwan.；Department of Electronic Engineering, Chung Yuan Christian University, Taoyuan, Taiwan.；Department of Information & Computer Engineering, Chung Yuan Christian University, Taoyuan, Taiwan.；Department of Otolaryngology, College of Medicine, National Taiwan University, Taipei, Taiwan.；Sleep Center, National Taiwan University Hospital, Taipei, Taiwan.
期刊	Otolaryngology--head and neck surgery : official journal of American Academy of Otolaryngology-Head and Neck Surgery
SCI 分区	Q1
IF	2.9
研究类型	AI/ML · 临床
所属专科	鼻科

中文摘要

目的： 开发一种人工智能（AI）系统，利用摄影测量进行儿童阻塞性睡眠呼吸暂停（OSA）的颅面形态分析。
研究设计： 前瞻性、横断面研究。
地点： 三级医疗医院。
方法： 纳入3至18岁有OSA相关症状的儿童，接受整夜多导睡眠监测（PSG）和标准化颅面摄影测量。儿童中重度OSA定义为PSG中呼吸暂停低通气指数（AHI）≥5次/小时。使用Dlib工具的AI模型识别面部标志点，Hough变换根据这些坐标计算变量。比较人工测量、AI模型和手动调整AI模型的测量结果。随机森林识别OSA预测模型的前10个变量重要性。
结果： 纳入43名中重度OSA儿童和43名年龄、性别和肥胖匹配的对照。各模型共有的预测因子为下颌平面角、上颌-下颌关系、下面部长度和下面部比例。AI模型的额外预测因子包括下面部和中面部突出度，而调整后的AI模型增加了中面部突出度、下颌后缩和颈颏角。中重度OSA预测的曲线下面积（AUC）在人工、AI模型和调整后AI模型之间相似（0.74 vs 0.71 vs 0.70，ΔAUC的P > 0.05）。AI模型显著缩短了测量时间（人工 vs AI vs 调整后AI = 511.4 vs 0.85 vs 15.8秒，P < .001）。
结论： AI驱动的摄影测量分析系统是一种快速可靠的工具，在评估儿童OSA方面与人工测量具有相当的性能。

英文摘要

OBJECTIVES: To develop an artificial intelligence (AI) system for craniofacial morphology analysis in pediatric obstructive sleep apnea (OSA) using photogrammetry.
STUDY DESIGN: Prospective, cross-sectional study.
SETTING: Tertiary medical hospital.
METHODS: Children aged 3 to 18 years with OSA-related symptoms were enrolled and underwent overnight polysomnography (PSG) and standardized craniofacial photogrammetry. Moderate-to-severe OSA in children was defined as an apnea-hypopnea index (AHI) ≥ 5 events/h in PSG. An AI model using the Dlib tool identified facial landmarks, and the Hough transform calculated variables from these coordinates. Measurements by humans, the AI model, and a manually adjusted AI model were compared. Random forest identified the top 10 variable importance for the OSA prediction model.
RESULTS: Forty-three children with moderate-to-severe OSA and 43 age-, gender-, and obesity-matched controls were included. Shared predictors across models were mandibular plane angle, maxillary-mandibular relationship, lower facial length, and lower facial proportion. Additional predictors for the AI model included lower- and mid-face projection, while the adjusted AI model added mid-face projection, retrusive mandible, and cervicomental angle. The area under the curve (AUC) values for moderate-to-severe OSA prediction were similar in human, AI model, and adjusted AI model (0.74 vs 0.71 vs 0.70, P for ΔAUC > 0.05). The AI model significantly reduced measurement time (human vs AI vs adjusted AI = 511.4 vs 0.85 vs 15.8 seconds, P < .001).
CONCLUSION: The AI-powered photogrammetry analysis system is a rapid and reliable tool with comparable performance to human measurements in evaluating pediatric OSA.