众包数字健康指标以预测帕金森病严重程度：帕金森病数字生物标志物DREAM挑战赛
Crowdsourcing digital health measures to predict Parkinson's disease severity: the Parkinson's Disease Digital Biomarker DREAM Challenge.
作者信息
Sieberts Solveig K, Schaff Jennifer, Duda Marlena, Pataki Bálint Ármin, Sun Ming, Snyder Phil, Daneault Jean-Francois, Parisi Federico, Costante Gianluca, Rubin Udi, Banda Peter, Chae Yooree, Chaibub Neto Elias, Dorsey E Ray, Aydın Zafer, Chen Aipeng, Elo Laura L, Espino Carlos, Glaab Enrico, Goan Ethan, Golabchi Fatemeh Noushin, Görmez Yasin, Jaakkola Maria K, Jonnagaddala Jitendra, Klén Riku, Li Dongmei, McDaniel Christian, Perrin Dimitri, Perumal Thanneer M, Rad Nastaran Mohammadian, Rainaldi Erin, Sapienza Stefano, Schwab Patrick, Shokhirev Nikolai, Venäläinen Mikko S, Vergara-Diaz Gloria, Zhang Yuqian, Wang Yuanjia, Guan Yuanfang, Brunner Daniela, Bonato Paolo, Mangravite Lara M, Omberg Larsson
机构信息
Sage Bionetworks, Seattle, WA, USA.
Elder Research, Inc, Charlottesville, VA, USA.
出版信息
NPJ Digit Med. 2021 Mar 19;4(1):53. doi: 10.1038/s41746-021-00414-7.
Consumer wearables and sensors are a rich source of data about patients' daily disease and symptom burden, particularly in the case of movement disorders like Parkinson's disease (PD). However, interpreting these complex data into so-called digital biomarkers requires complicated analytical approaches, and validating these biomarkers requires sufficient data and unbiased evaluation methods. Here we describe the use of crowdsourcing to specifically evaluate and benchmark features derived from accelerometer and gyroscope data in two different datasets to predict the presence of PD and severity of three PD symptoms: tremor, dyskinesia, and bradykinesia. Forty teams from around the world submitted features, and achieved drastically improved predictive performance for PD status (best AUROC = 0.87), as well as tremor- (best AUPR = 0.75), dyskinesia- (best AUPR = 0.48) and bradykinesia-severity (best AUPR = 0.95).
消费级可穿戴设备和传感器是有关患者日常疾病和症状负担的丰富数据来源，尤其是在帕金森病（PD）等运动障碍的情况下。然而，将这些复杂数据解释为所谓的数字生物标志物需要复杂的分析方法，而验证这些生物标志物则需要足够的数据和无偏评估方法。在此，我们描述了利用众包来专门评估和基准化从两个不同数据集中的加速度计和陀螺仪数据得出的特征，以预测PD的存在以及三种PD症状（震颤、异动症和运动迟缓）的严重程度。来自世界各地的40个团队提交了特征，并在PD状态预测（最佳曲线下面积[AUROC]=0.87）以及震颤（最佳精确率-召回率曲线下面积[AUPR]=0.75）、异动症（最佳AUPR=0.48）和运动迟缓严重程度（最佳AUPR=0.95）方面取得了大幅提高的预测性能。
Zotero 插件