Development and Validation of a Deep Learning Method to Predict Cerebral Palsy From Spontaneous Movements in Infants at High Risk.
Development and Validation of a Deep Learning Method to Predict Cerebral Palsy From Spontaneous Movements in Infants at High Risk.
复制标题
根据高危婴儿的自发活动预测脑性瘫痪的深度学习方法的开发和验证。
DOI：
10.1001/jamanetworkopen.2022.21325
复制
发表时间：
2022-07-01
影响因子：
13.8
通讯作者：
Stoen, Ragnhild
中科院分区：
文献类型：
--
作者：
Groos, Daniel;Adde, Lars;Aubert, Sindre;Boswell, Lynn;de Regnier, Raye-Ann;Fjortoft, Toril;Gaebler-Spira, Deborah;Haukeland, Andreas;Loennecken, Marianne;Msall, Michael;Moinichen, Unn Inger;Pascal, Aurelie;Peyton, Colleen;Ramampiaro, Heri;Schreiber, Michael D.;Silberg, Inger Elisabeth;Songstad, Nils Thomas;Thomas, Niranjan;Van den Broeck, Christine;Oberg, Gunn Kristin;Ihlen, Espen A. F.;Stoen, Ragnhild
基于深度学习的方法预测脑瘫（CP）的外部有效性是什么？该方法基于婴儿在9至18周矫正年龄时的自发运动。在这项对557名围产期脑损伤高危婴儿的预后研究中，基于深度学习的方法早期预测CP的灵敏度为71%，特异性为94%，阳性预测值为68%，阴性预测值为95%。基于深度学习方法的CP预后与CP儿童的后期功能水平和CP亚型相关。这项研究的结果表明，基于深度学习的评估可以支持高危婴儿CP的早期检测。早期识别脑瘫（CP）对于早期干预非常重要，但基于专家的评估不允许广泛使用，传统的机器学习替代方案缺乏有效性。开发并评估一种基于深度学习的新方法的外部有效性，该方法基于9至18周校正年龄的婴儿自发运动视频来预测CP。这项基于深度学习的方法预测CP的预后研究涉及557名具有围产期脑损伤高风险的婴儿，这些婴儿在2001年9月10日至2018年10月25日期间在比利时，印度，挪威和美国的13家医院进行了先前的研究。分析在2020年2月11日至2021年9月23日期间进行。纳入的婴儿在9至18周龄的校正年龄的烦躁运动期间记录了可用的视频，通过一般运动评估（GMA）工具确定的烦躁运动的可用分类，以及12个月或以上校正年龄的CP状态的可用数据。共有418名婴儿（75.0%）被随机分配到模型开发（训练和内部验证）样本，139名（25.0%）被随机分配到外部验证样本（1个测试集）。自发运动的视频记录。主要结局是CP的预测。基于深度学习的CP预测是从单个视频自动执行的。次要结局包括预测相关功能水平和CP亚型。评估了敏感性、特异性、阳性和阴性预测值以及准确性。在557名婴儿（310名[55.7%]男性）中，评估时的中位（IQR）校正年龄为12（11-13）周，84名婴儿（15.1%）在平均（SD）年龄3.4（1.7）岁时被诊断为CP。未报告人种和种族数据，因为既往研究（婴儿样本来源）使用了不同的研究方案，这些数据的收集不一致。在外部验证中，基于深度学习的CP预测方法的灵敏度为71.4%（95% CI，47.8%-88.7%），特异性为94.1%（95% CI，88.2%-97.6%），阳性预测值为68.2%（95% CI，45.1%-86.1%），阴性预测值为94.9%（95% CI，89.2%-98.1%）。相比之下，GMA工具的灵敏度为70.0%（95% CI，45.7%-88.1%），特异性为88.7%（95% CI，81.5%-93.8%），阳性预测值为51.9%（95% CI，32.0%-71.3%），阴性预测值为94.4%（95% CI，88.3%-97.9%）。深度学习方法实现了比传统机器学习方法更高的准确性（90.6% [95% CI，84.5%-94.9%] vs 72.7% [95% CI，64.5%-79.9%]; P < .001），但与GMA工具相比，未观察到准确性的显著改善（85.9%; 95% CI，78.9%-91.3%; P = .11）。深度学习预测模型在患有卧床CP的婴儿中具有更高的灵敏度（100%; 95% CI，63.1%-100%）vs动态CP（58.3%; 95% CI，27.7%-84.8%; P = 0.02）和痉挛性双侧CP（92.3%; 95% CI，64.0%-99.8%）与痉挛性单侧CP（42.9%; 95% CI，9.9%-81.6%; P < .001）。在这项预后研究中，一种基于深度学习的方法预测9至18周校正年龄的CP在外部验证中具有预测准确性，这表明使用基于深度学习的软件在临床环境中提供CP的客观早期检测的可能途径。这项预后研究描述了一种基于深度学习的方法的开发，该方法基于9至18周矫正年龄的婴儿自发运动的视频来预测脑瘫，并评估了深度学习预测模型的外部有效性。
What is the external validity of a deep learning–based method to predict cerebral palsy (CP) based on infants’ spontaneous movements at 9 to 18 weeks’ corrected age? In this prognostic study of 557 infants with a high risk of perinatal brain injury, a deep learning–based method for early prediction of CP had sensitivity of 71%, specificity of 94%, positive predictive value of 68%, and negative predictive value of 95%. Prognosis of CP based on the deep learning–based method was associated with later functional level and CP subtype in children with CP. This study’s findings suggest that deep learning–based assessments could support early detection of CP in infants at high risk. Early identification of cerebral palsy (CP) is important for early intervention, yet expert-based assessments do not permit widespread use, and conventional machine learning alternatives lack validity. To develop and assess the external validity of a novel deep learning–based method to predict CP based on videos of infants’ spontaneous movements at 9 to 18 weeks’ corrected age. This prognostic study of a deep learning–based method to predict CP at a corrected age of 12 to 89 months involved 557 infants with a high risk of perinatal brain injury who were enrolled in previous studies conducted at 13 hospitals in Belgium, India, Norway, and the US between September 10, 2001, and October 25, 2018. Analysis was performed between February 11, 2020, and September 23, 2021. Included infants had available video recorded during the fidgety movement period from 9 to 18 weeks’ corrected age, available classifications of fidgety movements ascertained by the general movement assessment (GMA) tool, and available data on CP status at 12 months’ corrected age or older. A total of 418 infants (75.0%) were randomly assigned to the model development (training and internal validation) sample, and 139 (25.0%) were randomly assigned to the external validation sample (1 test set). Video recording of spontaneous movements. The primary outcome was prediction of CP. Deep learning–based prediction of CP was performed automatically from a single video. Secondary outcomes included prediction of associated functional level and CP subtype. Sensitivity, specificity, positive and negative predictive values, and accuracy were assessed. Among 557 infants (310 [55.7%] male), the median (IQR) corrected age was 12 (11-13) weeks at assessment, and 84 infants (15.1%) were diagnosed with CP at a mean (SD) age of 3.4 (1.7) years. Data on race and ethnicity were not reported because previous studies (from which the infant samples were derived) used different study protocols with inconsistent collection of these data. On external validation, the deep learning–based CP prediction method had sensitivity of 71.4% (95% CI, 47.8%-88.7%), specificity of 94.1% (95% CI, 88.2%-97.6%), positive predictive value of 68.2% (95% CI, 45.1%-86.1%), and negative predictive value of 94.9% (95% CI, 89.2%-98.1%). In comparison, the GMA tool had sensitivity of 70.0% (95% CI, 45.7%-88.1%), specificity of 88.7% (95% CI, 81.5%-93.8%), positive predictive value of 51.9% (95% CI, 32.0%-71.3%), and negative predictive value of 94.4% (95% CI, 88.3%-97.9%). The deep learning method achieved higher accuracy than the conventional machine learning method (90.6% [95% CI, 84.5%-94.9%] vs 72.7% [95% CI, 64.5%-79.9%]; P < .001), but no significant improvement in accuracy was observed compared with the GMA tool (85.9%; 95% CI, 78.9%-91.3%; P = .11). The deep learning prediction model had higher sensitivity among infants with nonambulatory CP (100%; 95% CI, 63.1%-100%) vs ambulatory CP (58.3%; 95% CI, 27.7%-84.8%; P = .02) and spastic bilateral CP (92.3%; 95% CI, 64.0%-99.8%) vs spastic unilateral CP (42.9%; 95% CI, 9.9%-81.6%; P < .001). In this prognostic study, a deep learning–based method for predicting CP at 9 to 18 weeks’ corrected age had predictive accuracy on external validation, which suggests possible avenues for using deep learning–based software to provide objective early detection of CP in clinical settings. This prognostic study describes the development of a deep learning–based method to predict cerebral palsy based on videos of infants’ spontaneous movements at 9 to 18 weeks’ corrected age and assesses the external validity of the deep learning prediction model.
登录
查看更多内容
DOI：
10.1136/archdischild-2020-321309
发表时间：
2022-01
期刊：
Archives of disease in childhood. Fetal and neonatal edition
影响因子：
--
作者：
Aker K;Thomas N;Adde L;Koshy B;Martinez-Biarge M;Nakken I;Padankatti CS;Støen R
通讯作者：
Støen R
影响因子：
3.3
作者：
Einspieler, Christa;Peharz, Robert;Marschik, Peter B.
通讯作者：
Marschik, Peter B.
影响因子：
8
作者：
Grunt, Sebastian;Mazenauer, Lea;Steinlin, Maja
通讯作者：
Steinlin, Maja
影响因子：
2.9
作者：
Adde L;Brown A;van den Broeck C;DeCoen K;Eriksen BH;Fjørtoft T;Groos D;Ihlen EAF;Osland S;Pascal A;Paulsen H;Skog OM;Sivertsen W;Støen R
通讯作者：
Støen R
影响因子：
2.5
作者：
Einspieler C;Yang H;Bartl-Pokorny KD;Chi X;Zang FF;Marschik PB;Guzzetta A;Ferrari F;Bos AF;Cioni G
通讯作者：
Cioni G