AbstractThe absence of a long COVID (LC) or post-acute sequelae of COVID-19 (PASC) diagnostic has profound implications for research and potential therapeutics given the lack of specificity with symptom-based identification of LC and the overlap of symptoms with other chronic inflammatory conditions.

摘要由于缺乏基于症状的LC鉴定的特异性以及症状与其他慢性炎症的重叠，缺乏长COVID（LC）或COVID-19（PASC）诊断的急性后遗症对研究和潜在治疗具有深远的意义。条件。

Here, we report a machine-learning approach to LC/PASC diagnosis on 347 individuals using cytokine hubs that are also capable of differentiating LC from chronic lyme disease (CLD). We derived decision tree, random forest, and gradient-boosting machine (GBM) classifiers and compared their diagnostic capabilities on a dataset partitioned into training (178 individuals) and evaluation (45 individuals) sets.

在这里，我们报告了一种机器学习方法，使用细胞因子中枢对347名个体进行LC/PASC诊断，这些细胞因子中枢也能够区分LC和慢性莱姆病（CLD）。我们导出了决策树，随机森林和梯度提升机（GBM）分类器，并在划分为训练（178个个体）和评估（45个个体）集的数据集上比较了它们的诊断能力。

The GBM model generated 89% sensitivity and 96% specificity for LC with no evidence of overfitting. We tested the GBM on an additional random dataset (106 LC/PASC and 18 Lyme), resulting in high sensitivity (97%) and specificity (90%) for LC. We constructed a Lyme Index confirmatory algorithm to discriminate LC and CLD..

GBM模型对LC产生了89%的敏感性和96%的特异性，没有过度拟合的证据。。。

IntroductionLC or PASC is a clinical unmet need affecting around 20–30 million Americans and many more worldwide. A non-subjective diagnosis for LC/PASC has remained elusive even after multiple reports of symptoms for LC. Symptom-based classification of immunologic diseases including autoimmune diseases and chronic inflammatory diseases can be difficult because of non-specific or overlapping symptoms1.

简介LC或PASC是一种临床未满足的需求，影响了约2000-3000万美国人，全世界还有更多人。即使在多次报道LC症状后，LC/PASC的非主观诊断仍然难以捉摸。由于非特异性或重叠症状，包括自身免疫性疾病和慢性炎症性疾病在内的免疫性疾病的症状分类可能很困难1。

A recent report suggested the use of cytokine hubs to more precisely categorize autoimmune diseases with the stated oal of using the information as therapeutic targets as the expansion of immune-based therapy grows1. The heterogeneity of immune-mediated inflammatory diseases (IMIDS) described in this publication also applies to post-infectious immune-mediated and inflammatory conditions currently in the discussion of LC/PASC.The symptoms of LC/PASC have been well described in the literature2,3,4 and a recent article2 concluded that fatigue, post-exertional malaise, and brain fog were diagnostic of LC.

最近的一份报告表明，随着基于免疫的疗法的扩展，使用细胞因子中心可以更准确地对自身免疫性疾病进行分类，并将信息用作治疗靶点1。本出版物中描述的免疫介导的炎症性疾病（IMID）的异质性也适用于目前正在讨论LC/PASC的感染后免疫介导的和炎症性疾病。LC/PASC的症状在文献2,3,4中已有很好的描述，最近的一篇文章2得出结论，疲劳，劳累后不适和脑雾是LC的诊断指标。

This conclusion, however, identified symptom presentations of LC/PASC that overlap significantly with chronic lyme disease (CLD), myalgic encephalomyelitis/chronic fatigue syndrome (ME/CFS), and other post-infectious chronic inflammatory disorders5,6,7. Clear etiological and pathophysiological differences exist in these chronic inflammatory conditions that necessitate precision medicine-tailored therapies.We previously used machine learning to distinguish long COVID from active COVID-19 infections using immune/inflammatory biomarkers2.

然而，这一结论确定了LC/PASC的症状表现与慢性莱姆病（CLD），肌痛性脑脊髓炎/慢性疲劳综合征（ME/CFS）和其他感染后慢性炎症性疾病显着重叠5,6,7。在这些慢性炎症中存在明显的病因和病理生理学差异，需要精确的医学定制疗法。我们之前使用机器学习来使用免疫/炎症生物标志物区分长COVID和活动性COVID-19感染2。

Similarly, there are multiple articles on machine learning in acute COVID-19 that focus on forecasting of disease and mortality8,9 or on the analysis of CXR or images10,11,12. Here, we present a very different machine learning/cytokine hub app.

同样，有多篇关于急性新型冠状病毒肺炎机器学习的文章，侧重于疾病和死亡率的预测8,9或CXR或图像的分析10,11,12。在这里，我们介绍了一个非常不同的机器学习/细胞因子中心应用程序。

1.

1.

Fever, cough, sore throat, malaise, headache, myalgia, nausea, diarrhea, loss of taste and smell,

发烧、咳嗽、喉咙痛、不适、头痛、肌痛、恶心、腹泻、味觉和嗅觉丧失，

2.

2.

No sign of pneumonia on chest imaging (CXR or CT Chest),

胸部成像（CXR或CT胸部）无肺炎迹象，

3.

3.

No shortness of breath or dyspnea.

没有呼吸急促或呼吸困难。

Moderate Acute COVID-19:

中度急性新型冠状病毒肺炎：

1.

1.

Radiological findings of pneumonia fever and respiratory symptoms,

肺炎发热和呼吸道症状的放射学表现，

2.

2.

Saturation of oxygen (SpO2) ≥ 94% on room air at sea level.

海平面室内空气中的氧饱和度（SpO2）≥94%。

LC/PASCInclusion criteria for individuals in the LC group were previous confirmed or probable COVID-19 infection (according to World Health Organization guidelines) age ≥ 18 years; and persistent symptoms > 12 weeks after initial COVID-19 infection. Symptoms included those previously described and scored4.Inclusion criteria for healthy controls (HC) were age ≥ 18 years, no previous SARS-CoV-2 infection and a negative history taken as part of registration in the Chronic COVID Treatment Center (CCTC).Chronic lyme disease (CLD)Patients presented to the CCTC with a history of fatigue, brain fog, and post-exertional malaise that pre-dated the SARS-CoV-2 pandemic (pre-2020) and persisted for greater than 6 months (as per the ILADS Working Group)13.Presence of Borrelia Burgdorferi sp were confirmed by 2-tiered immunologic testing which includes immunoblot testing.

LC/PASCInclusion LC组个体的标准是先前确诊或可能的COVID-19感染（根据世界卫生组织指南），年龄≥18岁；初次COVID-19感染后12周出现持续症状。症状包括先前描述和评分的症状4。健康对照（HC）的纳入标准为年龄≥18岁，既往无SARS-CoV-2感染，阴性病史作为慢性冠状病毒治疗中心（CCTC）登记的一部分。慢性莱姆病（CLD）患者向CCTC提交了疲劳，脑雾和劳累后不适的病史，这些病史早于SARS-CoV-2大流行（2020年之前），持续超过6个月（根据ILADS工作组）13。通过包括免疫印迹测试在内的两级免疫测试证实了伯氏疏螺旋体的存在。

Presence of other tick-borne organisms was noted but not required for definition of CLD as previously described13.Multiplex cytokine/chemokine profilingPlasma collected in plasma preparation tubes (PPT, BD Biosciences, San Jose CA) as used for cytokine quantification using acustomized 14-plex bead based flow cytometric assay (IncellKINE, IncellDx, Inc) on a CytoFlex flow cytometer as previously described using the following analytes: TNF-a, IL-4, IL-13, IL-2, GM-CSF, sCD40L, CCL5 (RANTES), CCL3 (MIP-1a), IL-6, IL-10, IFN-g, VEGF, IL-8, and CCL4 (MIP-1b)2.

如前所述，注意到存在其他蜱传生物，但不需要如前所述定义CLD 13。在血浆制备管（PPT，BD Biosciences，San Jose CA）中收集的多重细胞因子/趋化因子谱血浆用于细胞因子定量，如前所述，在CytoFlex流式细胞仪上使用基于14重珠子的流式细胞仪测定（IncellKINE，IncellDx，Inc），使用以下分析物进行细胞因子定量：TNF-α，IL-4，IL-13，IL-2，GM-CSF，sCD40L，CCL5（RANTES），CCL3（MIP-1a），IL-6，IL-10，IFN-g，VEGF，IL-8和CCL4（MIP-1b）2。

For each patient sample, 25 μL of plasma was used in each well of a 96-well plate. Samples were analyzed on a Beckman Coulter CytoFlex LX 3-laser flow cytometer using Kaluza Analysis Software (Beckman-Coulter, Miami, FL). All statistical analysis was performed using the Mann–Whitney test and a P value ≤ 0.05 was considered statistically significant.Data acquisition .

对于每个患者样品，在96孔板的每个孔中使用25μL血浆。使用Kaluza分析软件（Beckman Coulter，Miami，FL）在Beckman Coulter CytoFlex LX 3激光流式细胞仪上分析样品。所有统计分析均使用Mann-Whitney检验进行，P值≤0.05被认为具有统计学意义。数据采集。

(1)

(1)

$$SI= \frac{ \left(IL-6+\frac{sCD40L}{1000}+\frac{VEGF}{10}+(10*IL-10\right)}{\left(IL-2 + IL-8\right)}$$

$$SI=\ frac{\左（IL-6+\ frac{sCD40L}{1000}+\ frac{VEGF}{10}+（10*IL-10 \右）}{\左（IL-2+IL-8 \右）}$$

(2)

(2)

The dataset was then imported into Python using the Pandas library14,15,16. Data was partitioned with stratification using the train_test_split function from the model_selection module sci-kit-learn17. An 80% of the data was for training and a 20% hold-out evaluation split was used to obtain performance metrics and identify overfitting.

然后使用Pandas library14,15,16将数据集导入Python。使用model\u选择模块sci-kit-learn17中的train\u test\u分割功能对数据进行分层。80%的数据用于培训，20%的持续评估用于获得绩效指标并识别过度拟合。

Table 1 contains the number of instances in the pre-split dataset, training, and evaluation partition.Table 1 The number of individuals for each disease state (class) in the full dataset, the training and evaluation partitions.Full size tableConstruction of tree-based machine learning classifiers: decision tree, random forest, and gradient boosting machineIn our study, we employed three tree-based machine learning classifiers: a decision tree, a random forest, and a gradient-boosting machine.

表1包含预分割数据集、训练和评估分区中的实例数。表1完整数据集中每个疾病状态（类别）的个体数量，训练和评估分区。基于树的机器学习分类器的全尺寸表构建：决策树，随机森林和梯度提升机在我们的研究中，我们使用了三种基于树的机器学习分类器：决策树，随机森林和梯度提升机。

The decision tree and random forest were implemented using the sci-kit-learn library, whereas the gradient-boosting machine utilized the LightGBM library. Hyperparameter optimization for each model involved a range of settings. For the decision tree, parameters like criterion, class weight, splitter, maximum depth, minimum samples split, and leaf were adjusted.

决策树和随机森林是使用sci kit学习库实现的，而梯度提升机使用LightGBM库。每个模型的超参数优化涉及一系列设置。对于决策树，调整了标准，类权重，拆分器，最大深度，最小样本拆分和叶子等参数。

The random forest model's parameters included the number of estimators, criterion, maximum depth, minimum samples split and leaf, and bootstrap options. For the gradient-boosting machine, we varied the learning rate, number of estimators, minimum data in leaf, and depth. Hyperparameter tuning was conducted using tenfold cross-validation with three repeats, selecting the best model based on the F1 score.

随机森林模型的参数包括估计量的数量，标准，最大深度，最小样本分裂和叶片以及引导选项。对于梯度提升机，我们改变了学习率，估计器数量，叶片中的最小数据和深度。使用十倍交叉验证和三次重复进行超参数调整，根据F1得分选择最佳模型。

Performance was assessed on a 20% hold-out evaluation split. A custom classification report, which included recall, specificity, precision, negative predictive value, and F1 sc.

表现评估为20%的坚持评估。自定义分类报告，其中包括召回率，特异性，精确度，阴性预测值和F1 sc。

(3)

(3)

$$Lyme \;Index \;Feature \;2= \frac{(TNF-alpha* IL-4) }{(IFN-gamma+IL-2+CCL3)}$$

$$莱姆\；索引\；功能\；2=\ frac{（TNF-α*IL-4）}{（IFN-γ+IL-2+CCL3）}$$

(4)

(4)

The discriminating power of features 1 and 2 was evaluated using a decision tree and a holdout partition of 20%. Further evaluation was done on a a 25-CLD patient dataset. The results indicated a high discriminating power, with 100% sensitivity and specificity when evaluating the holdout set (Table 6).

使用决策树和20%的保持分区评估特征1和2的区分能力。对25-CLD患者数据集进行了进一步评估。结果表明，在评估抵抗集时，具有很高的辨别力，具有100%的敏感性和特异性（表6）。

This effectiveness was confirmed when testing features 1 (TNF-alpha + IL-4)/(IFN-gamma + IL-2) and 2 (TNF-alpha * IL-4)/(IFN-gamma + IL-2 + CCL3) on the 25-CLD dataset, where sensitivity, accuracy, and PPV were 100%. The power of the CLD Index can be attributed to engineering a set of features where relevant CLD cytokines are in the numerator and relevant LC/PASC cytokines are in the dominant.

当在25-CLD数据集上测试特征1（TNF-α+IL-4）/（IFN-γ+IL-2）和2（TNF-α*IL-4）/（IFN-γ+IL-2+CCL3）时，证实了这种有效性，其中灵敏度，准确性和PPV为100%。CLD指数的功效可归因于设计一组特征，其中相关的CLD细胞因子处于分子中，而相关的LC/PASC细胞因子处于主导地位。

This leads to higher CLD Index values for CLD patients and lower values for PASC individuals.Table 6 Performance metrics for the CLD Index (features 1 and 2) on the evaluation partition and the 25-CLD dataset.Full size tableDiscussionAcute COVID causes a constellation of immunologic abnormalities characterized as a “Cytokine Storm”. Frequently lost in this pathology is significant immunosuppression due to low T-cell count, especially CD8 + T-cells, immune exhaustion, and decreased expression of Granzyme A19,20,21,22. Immunosuppression can lead to the reactivation of chronic herpes family viruses such as Epstein-Barr virus (EBV), cytomegalovirus (CMV), Human Herpesvirus-6 (HHV-6), and Herpes Simplex (HSV) among others.

这导致CLD患者的CLD指数较高，而PASC个体的CLD指数较低。表6评估分区和25-CLD数据集上CLD指数（特征1和2）的性能指标。全尺寸表讨论急性新型冠状病毒引起一系列免疫异常，其特征是“细胞因子风暴”。由于T细胞计数低，尤其是CD8+T细胞，免疫衰竭以及颗粒酶A19,20,21,22的表达降低，这种病理学中经常丢失的是显着的免疫抑制。免疫抑制可导致慢性疱疹家族病毒的再激活，如爱泼斯坦-巴尔病毒（EBV），巨细胞病毒（CMV），人类疱疹病毒-6（HHV-6）和单纯疱疹（HSV）等。

In addition, undiagnosed or inadequately treated tick-borne illnesses such as CLD may also recrudesce because of a diminution of immune control. Diagnosis and differentiation of all of these “sequelae” of acute COVID are difficult when SARS-CoV-2 itself can produce a post-infectious condition (LC/PASC) and the symptoms significantly overlap.Cytokine pro.

此外，由于免疫控制的减弱，未经诊断或治疗不充分的蜱传疾病（如CLD）也可能复发。当SARS-CoV-2本身可以产生感染后病症（LC/PASC）并且症状明显重叠时，很难诊断和鉴别所有这些急性新型冠状病毒的“后遗症”。细胞因子pro。

Data availability

数据可用性

All requests for materials and raw data should be addressed to the corresponding author.

所有对材料和原始数据的要求都应寄给通讯作者。

ReferencesSchett, G., McInnes, I. B. & Neurath, M. F. Reframing immune-mediated inflammatory diseases through signature cytokine hubs. N. Engl. J. Med. 385, 628–639 (2021).Article

参考Chett，G.，McInnes，I.B。和Neurath，M.F。通过特征性细胞因子中心重构免疫介导的炎症性疾病。N、 英语。J、 医学385628-639（2021）。文章

CAS

中科院

PubMed

PubMed

Google Scholar

谷歌学者

Patterson, B. K. et al. Immune-based prediction of COVID-19 severity and chronicity decoded using machine learning. Front. Immunol. 12, 700782. https://doi.org/10.3389/fimm.u (2021).Article

Patterson，B.K.等人。使用机器学习解码的基于免疫的COVID-19严重程度和慢性预测。正面。免疫。12700782年。https://doi.org/10.3389/fimm.u（2021年）。文章

CAS

中科院

PubMed

PubMed

PubMed Central

公共医学中心

Google Scholar

谷歌学者

Davis, H. E. et al. Characterizing LC in an international cohort: 7 months of symptoms and their impact. EClinicalMedicine 38, 101019. https://doi.org/10.1016/j.eclinm (2021).Article

Davis，H.E.等人在国际队列中描述LC：7个月的症状及其影响。EClinicalMedicine 38101019。https://doi.org/10.1016/j.eclinm（2021年）。文章

PubMed

PubMed

PubMed Central

公共医学中心

Google Scholar

谷歌学者

Thaweethai, T. et al. Development of a definition of postacute sequelae of SARS-CoV-2 infection. JAMA 329, 1934–1946. https://doi.org/10.1001/jama.2023.8823 (2023).Article

Thaweethai，T。等人。SARS-CoV-2感染后急性后遗症定义的发展。JAMA 3291934-1946年。https://doi.org/10.1001/jama.2023.8823（2023年）。文章

CAS

中科院

PubMed

PubMed

PubMed Central

公共医学中心

Google Scholar

谷歌学者

Wong, K. H., Shapiro, E. D. & Soffer, G. K. A review of post-treatment CLD disease syndrome and chronic CLD disease for the practicing immunologist. Clin. Rev. Allergy Immunol. 62, 264–271. https://doi.org/10.1007/s12016-021-08906-w (2022).Article

Wong，K.H.，Shapiro，E.D。和Soffer，G.K。执业免疫学家对治疗后CLD疾病综合征和慢性CLD疾病的回顾。临床。版本过敏免疫。62264-271。https://doi.org/10.1007/s12016-021-08906-w（2022年）。文章

CAS

中科院

PubMed

PubMed

Google Scholar

谷歌学者

Bateman, L. et al. Myalgic encephalomyelitis/chronic fatigue syndrome: Essentials of diagnosis and management. Mayo Clin. Proc. 96, 2861–2878. https://doi.org/10.1016/j.mayocp.2021.07.004 (2021).Article

。梅奥临床。程序。962861-2878。https://doi.org/10.1016/j.mayocp.2021.07.004（2021年）。文章

PubMed

PubMed

Google Scholar

谷歌学者

Branda, J. A. & Steere, A. C. Laboratory diagnosis of CLD Borreliosis. Clin. Microbiol. Rev. 34, e00018-19. https://doi.org/10.1128/CMR.00018-19 (2021).Article

Branda，J.A。＆Steere，A.C。CLD Borreliosis的实验室诊断。临床。微生物。版本34，e00018-19。https://doi.org/10.1128/CMR.00018-19（2021年）。文章

CAS

中科院

PubMed

PubMed

PubMed Central

公共医学中心

Google Scholar

谷歌学者

Gao, Y. et al. Machine learning based early warning system enables accurate mortality risk prediction for COVID-19. Nat. Commun. 11, 5033. https://doi.org/10.1038/s41467-020-18684-2 (2020).Article

Gao，Y。等人。基于机器学习的早期预警系统能够准确预测COVID-19的死亡风险。国家公社。115033年。https://doi.org/10.1038/s41467-020-18684-2（2020年）。文章

ADS

广告

CAS

中科院

PubMed

PubMed

PubMed Central

公共医学中心

Google Scholar

谷歌学者

Bousquet, A. et al. Deep learning forecasting using time-varying parameters of the SIRD model for COVID-19. Sci. Rep. 12, 3030. https://doi.org/10.1038/s41598-022-06992-0 (2022).Article

Bousquet，A。等人。使用COVID-19 SIRD模型的时变参数进行深度学习预测。科学。代表123030。https://doi.org/10.1038/s41598-022-06992-0（2022年）。文章

ADS

广告

CAS

中科院

PubMed

PubMed

PubMed Central

公共医学中心

Google Scholar

谷歌学者

Miyazaki, A. et al. Computer-aided diagnosis of chest X-ray for COVID-19 diagnosis in external validation study by radiologists with and without deep learning system. Sci. Rep. 13, 17533. https://doi.org/10.1038/s41598-023-44818-9 (2023).Article

Miyazaki，A。等人。放射科医生在有和没有深度学习系统的情况下进行外部验证研究中，胸部X射线计算机辅助诊断新型冠状病毒19诊断。科学。代表1317533。https://doi.org/10.1038/s41598-023-44818-9（2023年）。文章

ADS

广告

CAS

中科院

PubMed

PubMed

PubMed Central

公共医学中心

Google Scholar

谷歌学者

Wang, L., Lin, Z. Q. & Wong, A. COVID-Net: a tailored deep convolutional neural network design for detection of COVID-19 cases from chest X-ray images. Sci. Rep. 10, 19549. https://doi.org/10.1038/s41598-020-76550-z (2020).Article

Wang，L.，Lin，Z。Q。＆Wong，A。COVID Net：一种定制的深度卷积神经网络设计，用于从胸部X射线图像中检测COVID-19病例。科学。众议员1019549。https://doi.org/10.1038/s41598-020-76550-z（2020年）。文章

ADS

广告

CAS

中科院

PubMed

PubMed

PubMed Central

公共医学中心

Google Scholar

谷歌学者

Nishio, M. et al. Deep learning model for the automatic classification of COVID-19 pneumonia, non-COVID-19 pneumonia, and the healthy: A multi-center retrospective study. Sci. Rep. 12, 8214. https://doi.org/10.1038/s41598-022-11990-3 (2022).Article

。科学。代表12，8214。https://doi.org/10.1038/s41598-022-11990-3（2022年）。文章

ADS

广告

CAS

中科院

PubMed

PubMed

PubMed Central

公共医学中心

Google Scholar

谷歌学者

Shor, S. et al. CLD Disease: An evidence-based definition by the ILADS Working Group. Antibiotics 8, 269. https://doi.org/10.3390/antibiotics80402691 (2019).Article

Shor，S.等人，《CLD疾病：ILADS工作组基于证据的定义》。抗生素8269。https://doi.org/10.3390/antibiotics80402691（2019年）。文章

PubMed

PubMed

PubMed Central

公共医学中心

Google Scholar

谷歌学者

Mckinney W. Pandas: a Foundational Python Library for Data Analysis and Statistics. http://pandas.sf.net [Accessed April 17, 2021]Van Rossum G. Python programming language. in USENIX annual technical conference, 1–36.Srinath KR. Python-The fastest growing programming language. Int Res J Eng Technol (2017) www.irjet.net [Accessed June 15, 2023].Kramer, O.

McKinneyW.Pandas：用于数据分析和统计的基础Python库。http://pandas.sf.net[2021年4月17日访问]Van Rossum G.Python编程语言。在USENIX年度技术会议上，1–36.Srinath KR.Python是增长最快的编程语言。Int Res J Eng Technol（2017）www.irjet.net[2023年6月15日访问]。克莱默，O。

Scikit-learn. Stud. Big Data 20, 45–53. https://doi.org/10.1007/978-3-319-33383-05 (2016).Article .

Scikit学习。螺柱。大数据20，45-53。https://doi.org/10.1007/978-3-319-33383-05（2016年）。文章。

Google Scholar

谷歌学者

Antonara, S., Ristow, L., McCarthy, J. & Coburn, J. Effect of Borrelia burgdorferi OspC at the site of inoculation in mouse skin. Infect. Immun. 78, 4723. https://doi.org/10.1128/IAI.00464-10 (2010).Article

Antonara，S.，Ristow，L.，McCarthy，J。＆Coburn，J。伯氏疏螺旋体OspC在小鼠皮肤接种部位的作用。感染。免疫。784723页。https://doi.org/10.1128/IAI.00464-10（2010年）。文章

CAS

中科院

PubMed

PubMed

PubMed Central

公共医学中心

Google Scholar

谷歌学者

Rha, M. S. & Shin, E. C. Activation or exhaustion of CD8+ T cells in patients with COVID-19. Cell. Mol. Immunol. 18, 2325–2333. https://doi.org/10.1038/s41423-021-00750-4 (2021).Article

Rha，M.S.＆Shin，E.C。新型冠状病毒肺炎患者CD8+T细胞的激活或衰竭。细胞。分子免疫。182325-2333。https://doi.org/10.1038/s41423-021-00750-4（2021年）。文章

CAS

中科院

PubMed

PubMed

PubMed Central

公共医学中心

Google Scholar

谷歌学者

Patterson, B. K. et al. CCR5 inhibition in critical COVID-19 patients decreases inflammatory cytokines, increases CD8 T-cells, and decreases SARS-CoV2 RNA in plasma by day 14. Int. J. Infect. Dis. 103, 25–32. https://doi.org/10.1016/j.ijid.2020.10.101 (2021).Article

Patterson，B.K.等人。到第14天，重症COVID-19患者的CCR5抑制可降低炎性细胞因子，增加CD8 T细胞，并降低血浆中的SARS-CoV2 RNA。Int.J.感染。Dis。103，25-32。https://doi.org/10.1016/j.ijid.2020.10.101（2021年）。文章

CAS

中科院

PubMed

PubMed

Google Scholar

谷歌学者

Song, J. W. et al. Immunological and inflammatory profiles in mild and severe cases of COVID-19. Nat. Commun. 8, 3410. https://doi.org/10.1038/s41467-020-17240-2 (2020).Article

Song，J.W.等人。轻度和重度COVID-19病例的免疫学和炎症特征。国家公社。83410个。https://doi.org/10.1038/s41467-020-17240-2（2020年）。文章

ADS

广告

CAS

中科院

Google Scholar

谷歌学者

Turner, J. S. et al. SARS-CoV-2 Viral RNA shedding for more than 87 days in an individual with an impaired CD8+ T cell response. Front. Immunol. 8, 618402. https://doi.org/10.3389/fimmu.2020.618402 (2021).Article

Turner，J.S.等人。CD8+T细胞反应受损的个体中SARS-CoV-2病毒RNA脱落超过87天。正面。免疫。8618402年。https://doi.org/10.3389/fimmu.2020.618402（2021年）。文章

CAS

中科院

Google Scholar

谷歌学者

Castro-Castro, A. C. et al. Difference in mortality rates in hospitalized COVID-19 patients identified by cytokine profile clustering using a machine learning approach: An outcome prediction alternative. Front. Med. 9, 987182. https://doi.org/10.3389/fmed.2022.987182 (2022).Article

Castro-Castro，A.C.等人。使用机器学习方法通过细胞因子谱聚类确定的住院COVID-19患者死亡率的差异：结果预测替代方案。正面。医学9987182。https://doi.org/10.3389/fmed.2022.987182（2022年）。文章

Google Scholar

谷歌学者

Batheja, S., Nields, J. A., Landa, A. & Fallon, B. A. Post-treatment CLD syndrome and central sensitization. J. Neuropsychiatry Clin. Neurosci. 25, 176–186. https://doi.org/10.1176/appi.neuropsych.12090223 (2013).Article

Batheja，S.，Nields，J.A.，Landa，A。＆Fallon，B.A。治疗后CLD综合征和中枢致敏。J、 神经精神病学临床。神经科学。25176-186。https://doi.org/10.1176/appi.neuropsych.12090223。文章

PubMed

PubMed

Google Scholar

谷歌学者

Patterson, B. K. et al. Persistence of SARS-CoV2-2 S1 protein in CD16+ monocytes in post-acute sequelae of COVID-19 (PASC) up to 15 months post-infection. Front. Immunol. 12, 746021. https://doi.org/10.3389/fimmu.2021.746021 (2022).Article

Patterson，B.K.等人。SARS-CoV2-2 S1蛋白在感染后15个月内在COVID-19（PASC）急性后遗症后CD16+单核细胞中的持久性。正面。免疫。12746021年。https://doi.org/10.3389/fimmu.2021.746021（2022年）。文章

CAS

中科院

PubMed

PubMed

PubMed Central

公共医学中心

Google Scholar

谷歌学者

Pietikäinen, A. et al. Cerebrospinal fluid cytokines in CLD neuroborreliosis. J. Neuroinflamm. 18, 273. https://doi.org/10.1186/s12974-016-0745-x (2016).Article

Pietikäinen，A。等人。CLD神经疏螺旋体病中的脑脊液细胞因子。J、 神经炎症。18273页。https://doi.org/10.1186/s12974-016-0745-x（2016年）。文章

CAS

中科院

Google Scholar

谷歌学者

Widhe, M. et al. Borrelia-specific interferon-gamma and interleukin-4 secretion in cerebrospinal fluid and blood during CLD borreliosis in humans: Association with clinical outcome. J. Infect. Dis. 189, 1881–1891. https://doi.org/10.1086/382893 (2004).Article

。J、 感染。Dis。1891881年至1891年。https://doi.org/10.1086/382893（2004年）。文章

CAS

中科院

PubMed

PubMed

Google Scholar

谷歌学者

Jutras, B. L. et al. Borrelia burgdorferi peptidoglycan is a persistent antigen in patients with CLD arthritis. Proc. Natl. Acad. Sci. U. S. A. 116, 13498–13507. https://doi.org/10.1073/pnas.1904170116 (2019).Article

Jutras，B.L.等人，伯氏疏螺旋体肽聚糖是CLD关节炎患者的持久性抗原。程序。纳特尔。阿卡德。科学。U、 S.A.11613498–13507。https://doi.org/10.1073/pnas.1904170116（2019年）。文章

ADS

广告

CAS

中科院

PubMed

PubMed

PubMed Central

公共医学中心

Google Scholar

谷歌学者

Kawasaki, Y., Zhang, L., Cheng, J. K. & Ji, R. R. Cytokine mechanisms of central sensitization: distinct and overlapping role of interleukin-1beta, interleukin-6, and tumor necrosis factor-alpha in regulating synaptic and neuronal activity in the superficial spinal cord. J. Neurosci.

川崎，Y.，张，L.，程，J.K.＆Ji，R.R。中枢致敏的细胞因子机制：白细胞介素-1β，白细胞介素-6和肿瘤坏死因子-α在调节突触和神经元活动中的独特和重叠作用浅表脊髓。J、 神经科学。

28, 5189–5194. https://doi.org/10.1523/JNEUROSCI.3338-07.2008 (2008).Article .

28, 5189–5194.https://doi.org/10.1523/JNEUROSCI.3338-07.2008(2008).第条。

CAS

中科院

PubMed

PubMed

PubMed Central

公共医学中心

Google Scholar

谷歌学者

Yang, J. X. et al. Potential neuroimmune interaction in chronic pain: A review on immune cells in peripheral and central sensitization. Front. Pain Res. 3, 946846. https://doi.org/10.3389/fpain.2022.946846 (2022).Article

Yang，J.X.等。慢性疼痛中潜在的神经免疫相互作用：外周和中枢致敏免疫细胞的综述。正面。疼痛研究3946846。https://doi.org/10.3389/fpain.2022.946846（2022年）。文章

Google Scholar

谷歌学者

Li, T., Chen, X., Zhang, C., Zhang, Y. & Yao, W. An update on reactive astrocytes in chronic pain. J. Neuroinflamm. 16, 140. https://doi.org/10.1186/s12974-019-1524-2 (2019).Article

Li，T.，Chen，X.，Zhang，C.，Zhang，Y。＆Yao，W。慢性疼痛中反应性星形胶质细胞的最新进展。J、 神经炎症。16140页。https://doi.org/10.1186/s12974-019-1524-2（2019年）。文章

Google Scholar

谷歌学者

Zhu, C. B., Blakely, R. D. & Hewlett, W. A. The proinflammatory cytokines interleukin-1beta and tumor necrosis factor-alpha activate serotonin transporters. Neuropsychopharmacology 10, 2121–2131. https://doi.org/10.1038/sj.npp.1301029 (2006).Article

Zhu，C.B.，Blakely，R.D。和Hewlett，W.A。促炎细胞因子白细胞介素-1β和肿瘤坏死因子-α激活血清素转运蛋白。神经精神药理学102121-2131。https://doi.org/10.1038/sj.npp.1301029（2006年）。文章

CAS

中科院

Google Scholar

谷歌学者

Wong, A. C. et al. Serotonin reduction in post-acute sequelae of viral infection. Cell 186(4851–4867), e20. https://doi.org/10.1016/j.cell.2023.09.013 (2023).Article

Wong，A.C.等人。病毒感染后急性后遗症中血清素的减少。细胞186（4851-4867），e20。https://doi.org/10.1016/j.cell.2023.09.013（2023年）。文章

CAS

中科院

Google Scholar

谷歌学者

Costanza, M. Type 2 Inflammatory responses in autoimmune demyelination of the central nervous system: Recent advances. J. Immunol. Res. 8, 4204512. https://doi.org/10.1155/2019/4204512 (2019).Article

Costanza，M。中枢神经系统自身免疫性脱髓鞘中的2型炎症反应：最新进展。J、 免疫。第84204512号决议。https://doi.org/10.1155/2019/4204512（2019年）。文章

CAS

中科院

Google Scholar

谷歌学者

Vasudeva, K. et al. In vivo and systems biology studies implicate IL-18 as a central mediator in chronic pain. J. Neuroimmunol. 283, 43–49. https://doi.org/10.1016/j.jneuroim.2015.04.012 (2015).Article

。J、 神经免疫。283，43-49。https://doi.org/10.1016/j.jneuroim.2015.04.012（2015年）。文章

CAS

中科院

PubMed

PubMed

PubMed Central

公共医学中心

Google Scholar

谷歌学者

Santos, D. et al. TNF-alpha and Notch signaling regulates the expression of HOXB4 and GATA3 during early T lymphopoiesis. In Vitro Cell. Dev. Biol. Anim. 52, 920–934. https://doi.org/10.1007/s11626-016-0055-8 (2016).Article

TNF-α和Notch信号在早期T淋巴细胞生成过程中调节HOXB4和GATA3的表达。体外细胞。开发生物。动画。。https://doi.org/10.1007/s11626-016-0055-8（2016年）。文章

CAS

中科院

Google Scholar

谷歌学者

Celik, M. Ö., Labuz, D., Keye, J., Glauben, R. & Machelska, H. IL-4 induces M2 macrophages to produce sustained analgesia via opioids. JCI Insight 5, e133093. https://doi.org/10.1172/jci.insight.133093 (2020).Article

塞利克，M。，Labuz，D.，Keye，J.，Glauben，R。＆Machelska，H。IL-4诱导M2巨噬细胞通过阿片类药物产生持续镇痛。JCI Insight 5，e133093。https://doi.org/10.1172/jci.insight.133093（2020年）。文章

PubMed

PubMed

PubMed Central

公共医学中心

Google Scholar

谷歌学者

Kipnis, J., Gadani, S. & Derecki, N. C. Pro-cognitive properties of T cells. Nat. Rev. Immunol. 12, 663–669. https://doi.org/10.1038/nri3280 (2012).Article

Kipnis，J.，Gadani，S。＆Derecki，N.C。T细胞的促认知特性。国家免疫修订版。。https://doi.org/10.1038/nri3280（2012年）。文章

CAS

中科院

PubMed

PubMed

PubMed Central

公共医学中心

Google Scholar

谷歌学者

Download referencesAuthor informationAuthors and AffiliationsIncellDx Inc, 30920 Huntwood Ave, San Carlos, Hayward, CA, 94544, USABruce K. Patterson, Jose Guevara-Coto, Edgar B. Francisco, Christopher Beaty & Gwyneth LemasterLab of Tumor Chemosensitivity, Faculty of Microbiology, CIET/CICICA, Universidad de Costa Rica, San José, Costa RicaJavier Mora & Rodrigo A.

下载参考文献作者信息作者和附属机构CellDX Inc，30920 Huntwood Ave，San Carlos，Hayward，CA，94544，USABluce K.Patterson，Jose Guevara Coto，Edgar B.Francisco，Christopher Beaty＆Gwyneth LemasterLab of Tumor Chemosensitics，Faculty of Microbiology，CIET/CICICA，Universidad de Costa，San Jose，Costa Rica Javier Mora＆Rodrigo A。

Mora-RodríguezLawrence General Hospital, Lawrence, MA, USARam YogendraDepartment of Community and Family Medicine, Georgetown University School of Medicine, Washington, DC, USAGary Kaplan DONeurology Specialist Affiliated With Norwalk Hospital, Orange, CT, USAAmiram KatzDepartments of Pediatrics and Microbiology-Immunology, and the International Center for Interdisciplinary Studies of Immunology, Georgetown University Medical Center, Washington, DC, USAJoseph A.

马萨诸塞州劳伦斯市Mora RodríguezLawrence综合医院，华盛顿特区乔治敦大学医学院USARam YogendraDepartment of Community and Family Medicine，华盛顿特区，USAGary Kaplan DONeurology附属诺沃克医院专家，奥兰治州，USAAmiram KATZ儿科和微生物学免疫学系，以及美国华盛顿特区乔治敦大学医学中心国际免疫学跨学科研究中心Joseph A。

BellantiAuthorsBruce K. PattersonView author publicationsYou can also search for this author in.

BellantiAuthorsBruceK.PattersonView作者出版物您也可以在中搜索该作者。

PubMed Google ScholarJose Guevara-CotoView author publicationsYou can also search for this author in

PubMed谷歌学者Jose Guevara CotoView作者出版物您也可以在

PubMed Google ScholarJavier MoraView author publicationsYou can also search for this author in

PubMed Google ScholarJavier MoraView作者出版物您也可以在

PubMed Google ScholarEdgar B. FranciscoView author publicationsYou can also search for this author in

PubMed Google ScholarEdgar B.FranciscoView作者出版物您也可以在

PubMed Google ScholarRam YogendraView author publicationsYou can also search for this author in

PubMed Google ScholarRodrigo A. Mora-RodríguezView author publicationsYou can also search for this author in

PubMed Google ScholarRodrigo A.Mora RodríguezView作者出版物您也可以在

PubMed Google ScholarChristopher BeatyView author publicationsYou can also search for this author in

PubMed Google ScholarChristopher BeatyView作者出版物您也可以在

PubMed Google ScholarGwyneth LemasterView author publicationsYou can also search for this author in

PubMed Google ScholarGwyneth LemasterView作者出版物您也可以在

PubMed Google ScholarGary Kaplan DOView author publicationsYou can also search for this author in

PubMed谷歌学术Kaplan DOView作者出版物您也可以在

PubMed Google ScholarAmiram KatzView author publicationsYou can also search for this author in

PubMed Google ScholarAmiram KatzView作者出版物您也可以在

PubMed Google ScholarJoseph A. BellantiView author publicationsYou can also search for this author in

PubMed谷歌学者Joseph A.BellantiView作者出版物您也可以在

PubMed Google ScholarContributionsR.Y., J.G-C. organized the clinical study and actively recruited patients. B.K.P, C.B., J.G-C., E.B.F, performed experiments and analyzed the data. J.G., R.A.M., C.B., J.M. performed the statistics and bioinformatics B.K.P., J.G., E.B.F, J.M., R.Y.

PubMed谷歌学术贡献。Y、 ，J.G-C。组织了临床研究并积极招募患者。B、 K.P，C.B.，J.G-C.，E.B.F，进行了实验并分析了数据。J、 G.，R.A.M.，C.B.，J.M.进行了统计和生物信息学B.K.P.，J.G.，E.B.F，J.M.，R.Y。

wrote and edited the draft of the manuscript and all authors contributed to revising the manuscript prior to submission.Corresponding authorCorrespondence to.

撰写并编辑了稿件草稿，所有作者都在提交稿件之前对稿件进行了修改。对应作者对应。

Bruce K. Patterson.Ethics declarations

布鲁斯·K·帕特森。道德宣言

Competing interests

相互竞争的利益

B.K.P, C.B., J.G, and E.B.F. are employees of IncellDx, Inc.

B、 。

Additional informationPublisher's noteSpringer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.Rights and permissions

Additional informationPublisher的noteSpringer Nature在已发布地图和机构隶属关系中的管辖权主张方面保持中立。权限和权限

Open Access This article is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License, which permits any non-commercial use, sharing, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if you modified the licensed material.

开放获取本文是根据知识共享署名非商业性NoDerivatives 4.0国际许可证授权的，该许可证允许以任何媒介或格式进行任何非商业性使用，共享，分发和复制，只要您对原始作者和来源给予适当的信任，提供知识共享许可证的链接，并指出您是否修改了许可材料。

You do not have permission under this licence to share adapted material derived from this article or parts of it. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder.

根据本许可证，您无权共享源自本文或其部分的改编材料。本文中的图像或其他第三方材料包含在文章的知识共享许可证中，除非该材料的信用额度中另有说明。如果材料未包含在文章的知识共享许可中，并且您的预期用途不受法律法规的许可或超出许可用途，则您需要直接获得版权所有者的许可。

To view a copy of this licence, visit http://creativecommons.org/licenses/by-nc-nd/4.0/..

要查看此许可证的副本，请访问http://creativecommons.org/licenses/by-nc-nd/4.0/..

Reprints and permissionsAbout this articleCite this articlePatterson, B.K., Guevara-Coto, J., Mora, J. et al. Long COVID diagnostic with differentiation from chronic lyme disease using machine learning and cytokine hubs.

转载和许可本文引用本文Patterson，B.K.，Guevara-Coto，J.，Mora，J。等人。使用机器学习和细胞因子中心区分慢性莱姆病的长COVID诊断。

Sci Rep 14, 19743 (2024). https://doi.org/10.1038/s41598-024-70929-yDownload citationReceived: 09 March 2024Accepted: 22 August 2024Published: 26 August 2024DOI: https://doi.org/10.1038/s41598-024-70929-yShare this articleAnyone you share the following link with will be able to read this content:Get shareable linkSorry, a shareable link is not currently available for this article.Copy to clipboard.

。https://doi.org/10.1038/s41598-024-70929-yDownload引文接收日期：2024年3月9日接受日期：2024年8月22日发布日期：2024年8月26日OI：https://doi.org/10.1038/s41598-024-70929-yShare本文与您共享以下链接的任何人都可以阅读此内容：获取可共享链接对不起，本文目前没有可共享的链接。复制到剪贴板。

Provided by the Springer Nature SharedIt content-sharing initiative

由Springer Nature SharedIt内容共享计划提供

KeywordsCOVID-19PASCLong COVIDCytokinesChronic lyme disease (CLD)Myalgic encephalomyelitis-chronic fatigue syndrome (ME-CFS)Machine Learning/AI

关键词Covid-19PASCLong-Covidcytokines慢性莱姆病（CLD）肌痛性脑脊髓炎慢性疲劳综合征（ME-CFS）机器学习/人工智能

CommentsBy submitting a comment you agree to abide by our Terms and Community Guidelines. If you find something abusive or that does not comply with our terms or guidelines please flag it as inappropriate.

评论通过提交评论，您同意遵守我们的条款和社区指南。如果您发现有虐待行为或不符合我们的条款或准则，请将其标记为不合适。