Machine Learning of Patient Characteristics to Predict Admission Outcomes in the Undiagnosed Diseases Network.
Machine Learning of Patient Characteristics to Predict Admission Outcomes in the Undiagnosed Diseases Network.
复制标题
DOI：
10.1001/jamanetworkopen.2020.36220
复制
发表时间：
2021-02-01
影响因子：
13.8
通讯作者：
Undiagnosed Diseases Network
中科院分区：
文献类型：
--
作者：
Amiri H;Kohane IS;Undiagnosed Diseases Network
机器学习算法能否重现临床专家在决定是否接受患者到未诊断疾病网络进行广泛基因组规模评估时的表现？这项预后研究使用2421例患者应用程序开发了一个机器学习模型，并通过回顾性和前瞻性验证对该模型进行了评估。用于预测录取结果的接收器操作特征曲线下的面积表明，使用开发的机器学习模型，已接受申请的录取过程可能会加速高达68%。这项研究的结果表明，使用机器学习辅助来优先评估患有未诊断疾病的患者是可行的，并且可能会增加在给定时间范围内处理的申请数量。未诊断疾病网络（UDN）是一个国家网络，评估个体患者的体征和症状一直难以诊断。提供可靠的入院结局估计值可以帮助临床评估人员区分、优先考虑和加速患有未诊断疾病的患者进入UDN。开发计算模型，有效地预测寻求UDN评估的申请人的入院结果，并根据患者进入UDN的可能性对申请进行排名。这项预测研究包括2014年7月至2019年6月提交给UDN的所有申请，其中1209份申请被接受，1212份申请未被接受。主要入选标准是尽管经过医疗保健专业人员的全面评估但仍未确诊的疾病;主要排除标准是解释客观结果的诊断或对提示诊断的记录进行审查。使用从申请表中提取的信息训练分类器，来自医疗保健专业人员的转诊信，以及转诊信和已知孟德尔疾病的文本描述之间的语义相似性。入院标签由UDN的病例审查委员会提供。除了回顾性分析外，还对另外288个在分类器开发时未进行评估的应用程序进行了前瞻性测试。主要结局是患者是否被UDN接受，以及根据入院可能性进行的申请顺序。分类器的性能进行了评估，通过比较其预测对UDN的录取结果，并通过测量的平均处理时间为接受的应用程序的改善。最好的分类器获得的灵敏度为0.843，特异性为0.738，和0.844的受试者工作特征曲线下的面积预测1212个接受和1210个未接受的申请之间的入院结果。此外，分类器可以通过根据申请被接受的可能性对申请进行排序，将已接受申请的当前平均（SD）UDN处理时间从3.29（3.17）个月减少到1.05（3.82）个月（68%的改进）。开发了一个分类系统，可以帮助临床评估人员区分，优先考虑和加速未确诊疾病患者进入UDN。加快入院过程可以改善这些患者的诊断过程，并作为其他资源受限应用程序的分流或转诊部分自动化的模型。这种分类模型明确了目前使用全基因组测序未诊断疾病的一些考虑因素，从而在临床遗传学界引起了更广泛的讨论。这项预后研究评估了机器学习模型预测未诊断疾病网络寻求基因组规模评估的申请人的入学结果的能力。
Can machine learning algorithms reproduce the performance of clinical experts in determining whether to accept patients to the Undiagnosed Diseases Network for extensive genome-scale evaluation? This prognostic study developed a machine learning model using 2421 patient applications and evaluated the model through retrospective and prospective validation. The area under the receiver operating characteristic curve obtained for predicting admission outcomes suggested that the admission process for accepted applications may be accelerated by up to 68% using the developed machine learning model. Findings of this study suggest that the use of machine learning assistance to prioritize the evaluation of patients with undiagnosed diseases is feasible and may increase the number of applications processed in a given time frame. The Undiagnosed Diseases Network (UDN) is a national network that evaluates individual patients whose signs and symptoms have been refractory to diagnosis. Providing reliable estimates of admission outcomes may assist clinical evaluators to distinguish, prioritize, and accelerate admission to the UDN for patients with undiagnosed diseases. To develop computational models that effectively predict admission outcomes for applicants seeking UDN evaluation and to rank the applications based on the likelihood of patient admission to the UDN. This prognostic study included all applications submitted to the UDN from July 2014 to June 2019, with 1209 applications accepted and 1212 applications not accepted. The main inclusion criterion was an undiagnosed condition despite thorough evaluation by a health care professional; the main exclusion criteria were a diagnosis that explained the objective findings or a review of the records that suggested a diagnosis. A classifier was trained using information extracted from application forms, referral letters from health care professionals, and semantic similarity between referral letters and textual description of known mendelian disorders. The admission labels were provided by the case review committee of the UDN. In addition to retrospective analysis, the classifier was prospectively tested on another 288 applications that were not evaluated at the time of classifier development. The primary outcomes were whether a patient was accepted or not accepted to the UDN and application order ranked based on likelihood of admission. The performance of the classifier was assessed by comparing its predictions against the UDN admission outcomes and by measuring improvement in the mean processing time for accepted applications. The best classifier obtained sensitivity of 0.843, specificity of 0.738, and area under the receiver operating characteristic curve of 0.844 for predicting admission outcomes among 1212 accepted and 1210 not accepted applications. In addition, the classifier can decrease the current mean (SD) UDN processing time for accepted applications from 3.29 (3.17) months to 1.05 (3.82) months (68% improvement) by ordering applications based on their likelihood of acceptance. A classification system was developed that may assist clinical evaluators to distinguish, prioritize, and accelerate admission to the UDN for patients with undiagnosed diseases. Accelerating the admission process may improve the diagnostic journeys for these patients and serve as a model for partial automation of triaging or referral for other resource-constrained applications. Such classification models make explicit some of the considerations that currently inform the use of whole-genome sequencing for undiagnosed disease and thereby invite a broader discussion in the clinical genetics community. This prognostic study evaluates the ability of a machine learning model to predict admission outcomes for applicants seeking genome-scale evaluation by the Undiagnosed Diseases Network.
登录
查看更多内容
影响因子：
2.8
作者：
Walley NM;Pena LDM;Hooper SR;Cope H;Jiang YH;McConkie-Rosell A;Sanders C;Schoch K;Spillmann RC;Strong K;McCray AT;Mazur P;Esteves C;LeBlanc K;Undiagnosed Diseases Network;Wise AL;Shashi V
通讯作者：
Shashi V
影响因子：
158.5
作者：
Splinter, K.;Adams, D. R.;Ashley, E. A.
通讯作者：
Ashley, E. A.
影响因子：
7.7
作者：
Haller, Heidemarie;Cramer, Holger;Dobos, Gustav
通讯作者：
Dobos, Gustav
影响因子：
3.5
作者：
Nettleton, S;Watt, I;Duffey, P
通讯作者：
Duffey, P
DOI：
10.4415/ann_11_01_17
发表时间：
2011-01-01
期刊：
Annali dell'Istituto Superiore di Sanità
影响因子：
--
作者：
Taruscio, Domenica;Capozzoli, Fiorentino;Frank, Claudio
通讯作者：
Frank, Claudio