机器学习识别婴儿虐待所致胫骨远端典型干骺端病变:一项初步研究
本研究回顾一家大型三级儿童医院13年内因疑似虐待而行骨骼检查的≤1岁婴儿,以低风险组正常胫骨远端X线片为正常队列、高风险组胫骨远端典型干骺端病变(CML)X线片为异常队列,训练机器学习算法区分正常与异常,五折交叉验证显示总体准确率93%、Kappa 0.84、敏感度88%、特异度96%。
要点
- 模型区分胫骨远端正常与CML的总体准确率93%、Kappa 0.84。
- 模型敏感度88%、特异度96%,特异度高于敏感度。
- 作者认为该模型作为自动识别工具结果令人鼓舞。
核心结论
- 机器学习模型在疑似婴儿虐待骨骼检查中自动识别胫骨远端CML方面显示出令人鼓舞的结果。
研究设计与样本
- 回顾一家大型三级儿童医院过去13年因疑似虐待行骨骼检查的≤1岁婴儿病历,按低风险与高风险分组。
- 低风险组正常胫骨远端X线片177张(来自89名婴儿)构成正常队列,高风险组胫骨远端CML X线片73张(来自35名婴儿)构成异常队列。
- 用上述两队列训练机器学习算法,以五折交叉验证系统评估并统计分析。
诊断标准与关键数值
- 模型总体准确率93%,Kappa 0.84。
- 模型总体敏感度88%,总体特异度96%。
局限性
- 原文未报告局限性。
以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。
英文原文(摘要)· 点击展开
BACKGROUND: The classic metaphyseal lesion (CML) is an injury that is highly specific for infant abuse, and the distal tibia is one of the most common sites of occurrence. A machine learning tool that identifies distal tibial CMLs on infant skeletal surveys could assist radiologists in the diagnosis of infant abuse.
OBJECTIVE: To develop and evaluate a machine learning-based classification algorithm to identify distal tibial CMLs on skeletal surveys performed for suspected infant abuse.
MATERIALS AND METHODS: We reviewed medical records of infants (≤1 year old) who had skeletal surveys for suspected abuse at a large tertiary children's hospital over the past 13 years to identify those at low and high risk for abuse. Normal distal tibial radiographs from the low-risk group formed the normal study cohort; radiographs with distal tibial CMLs from the high-risk group formed the abnormal study cohort. We used these two cohorts to train a machine learning algorithm to classify distal tibial radiographs as normal or abnormal. We systematically evaluated this algorithm using a fivefold cross-validation procedure and statistically analyzed the results.
RESULTS: The normal study cohort consisted of 177 radiographs from 89 infants, and the abnormal study cohort consisted of 73 radiographs from 35 infants. Our machine learning algorithm showed an overall performance accuracy of 93% and Kappa of 0.84. The overall sensitivity and specificity of the model were 88% and 96%, respectively.
CONCLUSION: Our developed machine learning model shows encouraging results as an automated tool to identify CMLs of the distal tibia on skeletal surveys performed for suspected infant abuse.
引用
- Tsai, Kleinman. Machine learning to identify distal tibial classic metaphyseal lesions of infant abuse: a pilot study. Pediatr Radiol. 2022. PMID: 35147714. doi:10.1007/s00247-022-05287-w
供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。