Detection of COVID-19 using multimodal data from a wearable device: results from the first TemPredict Study.
Detection of COVID-19 using multimodal data from a wearable device: results from the first TemPredict Study.
复制标题
DOI：
10.1038/s41598-022-07314-0
复制
发表时间：
2022-03-02
影响因子：
4.6
通讯作者：
Smarr BL
中科院分区：
文献类型：
--
作者：
Mason AE;Hecht FM;Davis SK;Natale JL;Hartogensis W;Damaso N;Claypool KT;Dilchert S;Dasgupta S;Purawat S;Viswanath VK;Klein A;Chowdhary A;Fisher SM;Anglo C;Puldon KY;Veasna D;Prather JG;Pandya LS;Fox LM;Busch M;Giordano C;Mercado BK;Song J;Jaimes R;Baum BS;Telfer BA;Philipson CW;Collins PP;Rao AA;Wang EJ;Bandi RH;Choe BJ;Epel ES;Epstein SK;Krasnoff JB;Lee MB;Lee SW;Lopez GM;Mehta A;Melville LD;Moon TS;Mujica-Parodi LR;Noel KM;Orosco MA;Rideout JM;Robishaw JD;Rodriguez RM;Shah KH;Siegal JH;Gupta A;Altintas I;Smarr BL
早期发现 COVID-19 等疾病可能是减少疾病传播的关键工具，可以帮助个人识别何时应该自我隔离、寻求检测并获得早期医疗干预。持续测量生理指标的消费者可穿戴设备有望成为早期疾病检测的工具。我们使用消费者可穿戴设备 (Oura Ring) 收集了 63,153 名参与者的每日问卷数据和生理数据，其中 704 名参与者自我报告可能患有 COVID-19 疾病。我们从这 704 名参与者中选择了 73 名，他们通过 PCR 测试可靠确认了 COVID-19，并使用高质量的生理数据进行算法训练，以使用机器学习分类来识别 COVID-19 的发作。该算法平均在参与者寻求诊断测试前 2.75 天识别出 COVID-19，灵敏度为 82%，特异性为 63%。接收操作特征 (ROC) 曲线下面积 (AUC) 为 0.819 (95% CI [0.809, 0.830])。包括连续温度在内的 AUC 比没有此功能时高 4.9%。为了进一步验证，我们在一部分参与者中获得了 SARS CoV-2 抗体，并确定了另外 10 名自我报告了 COVID-19 疾病且抗体确认的参与者。该算法的总体 ROC AUC 为 0.819 (95% CI [0.809, 0.830])，在这些额外参与者中的敏感性为 90%，特异性为 80%。 最后，我们观察到基于年龄和生物性别的准确性存在显着差异。研究结果强调了包括温度评估、使用连续生理特征进行对齐以及在算法开发中包括不同人群的重要性，以优化可穿戴设备的 COVID-19 检测准确性。
Early detection of diseases such as COVID-19 could be a critical tool in reducing disease transmission by helping individuals recognize when they should self-isolate, seek testing, and obtain early medical intervention. Consumer wearable devices that continuously measure physiological metrics hold promise as tools for early illness detection. We gathered daily questionnaire data and physiological data using a consumer wearable (Oura Ring) from 63,153 participants, of whom 704 self-reported possible COVID-19 disease. We selected 73 of these 704 participants with reliable confirmation of COVID-19 by PCR testing and high-quality physiological data for algorithm training to identify onset of COVID-19 using machine learning classification. The algorithm identified COVID-19 an average of 2.75 days before participants sought diagnostic testing with a sensitivity of 82% and specificity of 63%. The receiving operating characteristic (ROC) area under the curve (AUC) was 0.819 (95% CI [0.809, 0.830]). Including continuous temperature yielded an AUC 4.9% higher than without this feature. For further validation, we obtained SARS CoV-2 antibody in a subset of participants and identified 10 additional participants who self-reported COVID-19 disease with antibody confirmation. The algorithm had an overall ROC AUC of 0.819 (95% CI [0.809, 0.830]), with a sensitivity of 90% and specificity of 80% in these additional participants. Finally, we observed substantial variation in accuracy based on age and biological sex. Findings highlight the importance of including temperature assessment, using continuous physiological features for alignment, and including diverse populations in algorithm development to optimize accuracy in COVID-19 detection from wearables.
登录
查看更多内容
影响因子：
4
作者：
Davis S;Milechin L;Patel T;Hernandez M;Ciccarelli G;Samsi S;Hensley L;Goff A;Trefry J;Johnston S;Purcell B;Cabrera C;Fleischman J;Reuther A;Claypool K;Rossi F;Honko A;Pratt W;Swiston A
通讯作者：
Swiston A
影响因子：
4.6
作者：
Smarr BL;Aschbacher K;Fisher SM;Chowdhary A;Dilchert S;Puldon K;Rao A;Hecht FM;Mason AE
通讯作者：
Mason AE
影响因子：
9.4
作者：
Theel, Elitza S.;Harring, Julie;Granger, Dane
通讯作者：
Granger, Dane
DOI：
10.1186/cc8132
发表时间：
2009
期刊：
Critical care (London, England)
影响因子：
--
作者：
Ahmad S;Tejuja A;Newman KD;Zarychanski R;Seely AJ
通讯作者：
Seely AJ
影响因子：
82.9
作者：
Quer, Giorgio;Radin, Jennifer M.;Steinhubl, Steven R.
通讯作者：
Steinhubl, Steven R.