Suppr超能文献

一种使用简约实验室指标集预测新冠肺炎患者严重程度的深度学习方法。

A deep learning approach for predicting severity of COVID-19 patients using a parsimonious set of laboratory markers.

作者信息

Singh Vivek, Kamaleswaran Rishikesan, Chalfin Donald, Buño-Soto Antonio, San Roman Janika, Rojas-Kenney Edith, Molinaro Ross, von Sengbusch Sabine, Hodjat Parsa, Comaniciu Dorin, Kamen Ali

机构信息

Siemens Healthineers, Digital Technology and Innovation, 755 College Road East, Princeton, NJ 08540, USA.

Emory University School of Medicine WMB, 1010 Woodruff Circle, Suite 4127, Atlanta, GA 30322, USA.

出版信息

iScience. 2021 Dec 17;24(12):103523. doi: 10.1016/j.isci.2021.103523. Epub 2021 Nov 27.

Abstract

The SARS-CoV-2 virus has caused tremendous healthcare burden worldwide. Our focus was to develop a practical and easy-to-deploy system to predict the severe manifestation of disease in patients with COVID-19 with an aim to assist clinicians in triage and treatment decisions. Our proposed predictive algorithm is a trained artificial intelligence-based network using 8,427 COVID-19 patient records from four healthcare systems. The model provides a severity risk score along with likelihoods of various clinical outcomes, namely ventilator use and mortality. The trained model using patient age and nine laboratory markers has the prediction accuracy with an area under the curve (AUC) of 0.78, 95% CI: 0.77-0.82, and the negative predictive value NPV of 0.86, 95% CI: 0.84-0.88 for the need to use a ventilator and has an accuracy with AUC of 0.85, 95% CI: 0.84-0.86, and the NPV of 0.94, 95% CI: 0.92-0.96 for predicting in-hospital 30-day mortality.

摘要

严重急性呼吸综合征冠状病毒2(SARS-CoV-2)病毒在全球造成了巨大的医疗负担。我们的重点是开发一个实用且易于部署的系统,以预测2019冠状病毒病(COVID-19)患者的疾病严重表现,旨在协助临床医生进行分诊和治疗决策。我们提出的预测算法是一个基于人工智能的网络,它使用了来自四个医疗系统的8427份COVID-19患者记录进行训练。该模型提供了一个严重程度风险评分以及各种临床结果的可能性,即使用呼吸机和死亡的可能性。使用患者年龄和九个实验室指标训练的模型,对于是否需要使用呼吸机的预测准确性,曲线下面积(AUC)为0.78,95%置信区间(CI):0.77-0.82,阴性预测值(NPV)为0.86,95%CI:0.84-0.88;对于预测30天院内死亡率,准确性的AUC为0.85,95%CI:0.84-0.86,NPV为0.94,95%CI:0.92-0.96。

相似文献

1
A deep learning approach for predicting severity of COVID-19 patients using a parsimonious set of laboratory markers.
iScience. 2021 Dec 17;24(12):103523. doi: 10.1016/j.isci.2021.103523. Epub 2021 Nov 27.
6
Deep-learning artificial intelligence analysis of clinical variables predicts mortality in COVID-19 patients.
J Am Coll Emerg Physicians Open. 2020 Aug 25;1(6):1364-1373. doi: 10.1002/emp2.12205. eCollection 2020 Dec.
7
Emergency department triage prediction of clinical outcomes using machine learning models.
Crit Care. 2019 Feb 22;23(1):64. doi: 10.1186/s13054-019-2351-7.
8
Deep learning-based triage and analysis of lesion burden for COVID-19: a retrospective study with external validation.
Lancet Digit Health. 2020 Oct;2(10):e506-e515. doi: 10.1016/S2589-7500(20)30199-0. Epub 2020 Sep 22.

引用本文的文献

1
Evaluating the impact of common clinical confounders on performance of deep-learning-based sepsis risk assessment.
Front Artif Intell. 2025 Jul 15;8:1452471. doi: 10.3389/frai.2025.1452471. eCollection 2025.
4
Concordance and generalization of an AI algorithm with real-world clinical data in the pre-omicron and omicron era.
Heliyon. 2024 Feb 2;10(3):e25410. doi: 10.1016/j.heliyon.2024.e25410. eCollection 2024 Feb 15.
6
Diagnosis of COVID-19 Using Chest X-ray Images and Disease Symptoms Based on Stacking Ensemble Deep Learning.
Diagnostics (Basel). 2023 Jun 5;13(11):1968. doi: 10.3390/diagnostics13111968.
7
The COVID-19 pandemic in various restriction policy scenarios based on the dynamic social contact rate.
Heliyon. 2023 Mar;9(3):e14533. doi: 10.1016/j.heliyon.2023.e14533. Epub 2023 Mar 16.
9
Overt and Occult Hypoxemia in Patients Hospitalized With COVID-19.
Crit Care Explor. 2023 Jan 20;5(1):e0825. doi: 10.1097/CCE.0000000000000825. eCollection 2023 Jan.
10
Prediction of COVID-19 Patients' Survival by Deep Learning Approaches.
Med J Islam Repub Iran. 2022 Nov 29;36:144. doi: 10.47176/mjiri.36.144. eCollection 2022.

本文引用的文献

2
The role of C-reactive protein as a prognostic marker in COVID-19.
Int J Epidemiol. 2021 May 17;50(2):420-429. doi: 10.1093/ije/dyab012.
3
Prognostic value of lymphocyte count in severe COVID-19 patients with corticosteroid treatment.
Signal Transduct Target Ther. 2021 Mar 2;6(1):106. doi: 10.1038/s41392-021-00517-3.
5
Myocardial injury in hospitalized patients with COVID-19 infection-Risk factors and outcomes.
PLoS One. 2021 Feb 26;16(2):e0247800. doi: 10.1371/journal.pone.0247800. eCollection 2021.
6
Renal dysfunction and prognosis of COVID-19 patients: a hospital-based retrospective cohort study.
BMC Infect Dis. 2021 Feb 8;21(1):158. doi: 10.1186/s12879-021-05861-x.
10
Eosinophilia in critically ill COVID-19 patients: a French monocenter retrospective study.
Crit Care. 2020 Nov 3;24(1):635. doi: 10.1186/s13054-020-03361-z.

文献AI研究员

20分钟写一篇综述,助力文献阅读效率提升50倍。

立即体验

用中文搜PubMed

大模型驱动的PubMed中文搜索引擎

马上搜索

文档翻译

学术文献翻译模型,支持多种主流文档格式。

立即体验