评估深度神经网络在手术相关结果遗传风险预测中的价值

Mathias Aagaard Christensen, Arnór Sigurdsson, Alexander Bonde, Simon Rasmussen, Sisse R Ostrowski, Mads Nielsen, Martin Sillesen
{"title":"评估深度神经网络在手术相关结果遗传风险预测中的价值","authors":"Mathias Aagaard Christensen, Arnór Sigurdsson, Alexander Bonde, Simon Rasmussen, Sisse R Ostrowski, Mads Nielsen, Martin Sillesen","doi":"10.1101/2024.01.09.23297913","DOIUrl":null,"url":null,"abstract":"Introduction Postoperative complications affect up to 15% of surgical patients constituting a major part of the overall disease burden in a modern healthcare system. While several surgical risk calculators have been developed, none have so far been shown to decrease the associated mortality and morbidity. Combining deep neural networks and genomics with the already established clinical predictors may hold promise for improvement. Methods The UK Biobank was utilized to build linear and deep learning models for the prediction of surgery relevant outcomes. An initial GWAS for the relevant outcomes was initially conducted to select the Single Nucleotide Polymorphisms for inclusion in the models. Model performance was assessed with Receiver Operator Characteristics of the Area Under the Curve and optimum precision and recall. Feature importance was assessed with SHapley Additive exPlanations. Results Models were generated for atrial fibrillation, venous thromboembolism and pneumonia as genetics only, clinical features only and a combined model. For venous thromboembolism, the ROC-AUCs were 59.6% [59.0%-59.7%], 63.4% [63.2%-63.4%] and 66.1% [65.7%-66.1%] for the linear models and 60.0% [57.8%-61.8%], 63.2% [61.2%-65.0%] and 65.4% [63.6%-67.2%] for the deep learning SNP, clinical and combined models, respectively. For atrial fibrillation, the ROC-AUCs were 60.9% [60.6%-61.0%], 78.7% [78.7%-78.7%] and 80.1% [80.0%-80.1%] for the linear models and 59.9% [.6%-61.3%], 78.8% [77.8%-79.8%] and 79.4% [78.8%-80.5%] for the deep learning SNP, clinical and combined models, respectively. For pneumonia, the ROC-AUCs were 57.3% [56.5%-57.4%], 69.2% [69.1%-69.2%] and 70.5% [70.2%-70.6%] for the linear models and 55.5% [54.1%-56.9%], 69.7% [.5%-70.8%] and 69.9% [68.7%-71.0%] for the deep learning SNP, clinical and combined models, respectively. Conclusion In this report we presented linear and deep learning predictive models for surgery relevant outcomes. Overall, predictability were similar between linear and deep learning models and inclusion of genetics seemed to improve accuracy.","PeriodicalId":501051,"journal":{"name":"medRxiv - Surgery","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2024-01-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"An assessment of the value of deep neural networks in genetic risk prediction for surgically relevant outcomes\",\"authors\":\"Mathias Aagaard Christensen, Arnór Sigurdsson, Alexander Bonde, Simon Rasmussen, Sisse R Ostrowski, Mads Nielsen, Martin Sillesen\",\"doi\":\"10.1101/2024.01.09.23297913\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Introduction Postoperative complications affect up to 15% of surgical patients constituting a major part of the overall disease burden in a modern healthcare system. While several surgical risk calculators have been developed, none have so far been shown to decrease the associated mortality and morbidity. Combining deep neural networks and genomics with the already established clinical predictors may hold promise for improvement. Methods The UK Biobank was utilized to build linear and deep learning models for the prediction of surgery relevant outcomes. An initial GWAS for the relevant outcomes was initially conducted to select the Single Nucleotide Polymorphisms for inclusion in the models. Model performance was assessed with Receiver Operator Characteristics of the Area Under the Curve and optimum precision and recall. Feature importance was assessed with SHapley Additive exPlanations. Results Models were generated for atrial fibrillation, venous thromboembolism and pneumonia as genetics only, clinical features only and a combined model. For venous thromboembolism, the ROC-AUCs were 59.6% [59.0%-59.7%], 63.4% [63.2%-63.4%] and 66.1% [65.7%-66.1%] for the linear models and 60.0% [57.8%-61.8%], 63.2% [61.2%-65.0%] and 65.4% [63.6%-67.2%] for the deep learning SNP, clinical and combined models, respectively. For atrial fibrillation, the ROC-AUCs were 60.9% [60.6%-61.0%], 78.7% [78.7%-78.7%] and 80.1% [80.0%-80.1%] for the linear models and 59.9% [.6%-61.3%], 78.8% [77.8%-79.8%] and 79.4% [78.8%-80.5%] for the deep learning SNP, clinical and combined models, respectively. For pneumonia, the ROC-AUCs were 57.3% [56.5%-57.4%], 69.2% [69.1%-69.2%] and 70.5% [70.2%-70.6%] for the linear models and 55.5% [54.1%-56.9%], 69.7% [.5%-70.8%] and 69.9% [68.7%-71.0%] for the deep learning SNP, clinical and combined models, respectively. Conclusion In this report we presented linear and deep learning predictive models for surgery relevant outcomes. Overall, predictability were similar between linear and deep learning models and inclusion of genetics seemed to improve accuracy.\",\"PeriodicalId\":501051,\"journal\":{\"name\":\"medRxiv - Surgery\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2024-01-10\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"medRxiv - Surgery\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1101/2024.01.09.23297913\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"medRxiv - Surgery","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1101/2024.01.09.23297913","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

摘要

导言:多达 15%的外科手术患者会出现术后并发症,这在现代医疗保健系统中是整个疾病负担的主要部分。虽然已经开发出了几种手术风险计算器,但迄今为止还没有任何一种能降低相关死亡率和发病率。将深度神经网络和基因组学与已经建立的临床预测指标相结合,可能会有改善的希望。方法 利用英国生物库建立线性和深度学习模型,预测手术相关结果。首先对相关结果进行了初步的 GWAS 分析,以选择可纳入模型的单核苷酸多态性。模型性能通过曲线下面积的接收者操作者特征以及最佳精确度和召回率进行评估。特征重要性用 SHapley Additive exPlanations 进行评估。结果 为心房颤动、静脉血栓栓塞和肺炎生成了仅遗传学模型、仅临床特征模型和综合模型。对于静脉血栓栓塞症,线性模型的ROC-AUC分别为59.6% [59.0%-59.7%]、63.4% [63.2%-63.4%]和66.1% [65.7%-66.1%],深度学习SNP模型、临床模型和组合模型的ROC-AUC分别为60.0% [57.8%-61.8%]、63.2% [61.2%-65.0%]和65.4% [63.6%-67.2%]。对于心房颤动,线性模型的ROC-AUC分别为60.9%[60.6%-61.0%]、78.7%[78.7%-78.7%]和80.1%[80.0%-80.1%],深度学习SNP模型、临床模型和组合模型的ROC-AUC分别为59.9%[.6%-61.3%]、78.8%[77.8%-79.8%]和79.4%[78.8%-80.5%]。对于肺炎,线性模型的 ROC-AUC 分别为 57.3% [56.5%-57.4%]、69.2% [69.1%-69.2%] 和 70.5% [70.2%-70.6%],而深度学习 SNP、临床和组合模型的 ROC-AUC 分别为 55.5% [54.1%-56.9%]、69.7% [.5%-70.8%]和 69.9% [68.7%-71.0%]。结论 在本报告中,我们介绍了手术相关结果的线性和深度学习预测模型。总体而言,线性模型和深度学习模型的预测能力相似,纳入遗传学似乎提高了准确性。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
An assessment of the value of deep neural networks in genetic risk prediction for surgically relevant outcomes
Introduction Postoperative complications affect up to 15% of surgical patients constituting a major part of the overall disease burden in a modern healthcare system. While several surgical risk calculators have been developed, none have so far been shown to decrease the associated mortality and morbidity. Combining deep neural networks and genomics with the already established clinical predictors may hold promise for improvement. Methods The UK Biobank was utilized to build linear and deep learning models for the prediction of surgery relevant outcomes. An initial GWAS for the relevant outcomes was initially conducted to select the Single Nucleotide Polymorphisms for inclusion in the models. Model performance was assessed with Receiver Operator Characteristics of the Area Under the Curve and optimum precision and recall. Feature importance was assessed with SHapley Additive exPlanations. Results Models were generated for atrial fibrillation, venous thromboembolism and pneumonia as genetics only, clinical features only and a combined model. For venous thromboembolism, the ROC-AUCs were 59.6% [59.0%-59.7%], 63.4% [63.2%-63.4%] and 66.1% [65.7%-66.1%] for the linear models and 60.0% [57.8%-61.8%], 63.2% [61.2%-65.0%] and 65.4% [63.6%-67.2%] for the deep learning SNP, clinical and combined models, respectively. For atrial fibrillation, the ROC-AUCs were 60.9% [60.6%-61.0%], 78.7% [78.7%-78.7%] and 80.1% [80.0%-80.1%] for the linear models and 59.9% [.6%-61.3%], 78.8% [77.8%-79.8%] and 79.4% [78.8%-80.5%] for the deep learning SNP, clinical and combined models, respectively. For pneumonia, the ROC-AUCs were 57.3% [56.5%-57.4%], 69.2% [69.1%-69.2%] and 70.5% [70.2%-70.6%] for the linear models and 55.5% [54.1%-56.9%], 69.7% [.5%-70.8%] and 69.9% [68.7%-71.0%] for the deep learning SNP, clinical and combined models, respectively. Conclusion In this report we presented linear and deep learning predictive models for surgery relevant outcomes. Overall, predictability were similar between linear and deep learning models and inclusion of genetics seemed to improve accuracy.
求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
自引率
0.00%
发文量
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信