检索结果-南通市图书馆

Machine learning using the extreme gradient boosting (XGBoost) algorithm predicts 5-day delta of SOFA score at ICU admission in COVID-19 patients

引用

Journal of Intensive Medicine 2021年第2期1卷 110-116页

作者： Jonathan Montomoli Luca Romeo Sara Moccia michele bernardini Lucia Migliorelli Daniele Berardini Abele Donati Andrea Carsetti Maria Grazia Bocci Pedro David Wendel Garcia Thierry Fumeaux Philippe Guerci Reto Andreas Schüpbach Can Ince Emanuele Frontoni Matthias Peter Hilty RISC-19-ICU Investigators Department of Anaesthesia and Intensive Care Infermi HospitalAUSL della RomagnaRimini 47923Italy Department of Information Engineering UniversitàPolitecnica delle MarcheAncona 60131Italy The BioRobotics Institute and Department of Excellence in Robotics and AI Scuola Superiore Sant’AnnaPisa 56127Italy Anesthesia and Intensive Care Unit Azienda Ospedaliero Universitaria Ospedali RiunitiAncona 60126Italy Department of Biomedical Sciences and Public Health UniversitàPolitecnica delle MarcheAncona 60126Italy Department of Anaesthesia and Intensive Care Fondazione Policlinico Universitario A.Gemelli IRCCSUniversitàCattolica del Sacro CuoreRome 00168Italy Institute of Intensive Care Medicine University Hospital of ZurichZurich 8091Switzerland Swiss Society of Intensive Care Medicine Basel 4001Switzerland Department of Anesthesiology and Critical Care Medicine University Hospital of NancyNancy 54511France Department of Intensive Care Erasmus MC University Medical Center RotterdamRotterdam3015 GDNetherlands 不详

Background:Accurate risk stratification of critically ill patients with coronavirus disease 2019(COVID-19)is essential for optimizing resource allocation,delivering targeted interventions,and maximizing patient survival *** learning(ML)techniques are attracting increased interest for the development of prediction models as they excel in the analysis of complex signals in data-rich environments such as critical ***:We retrieved data on patients with COVID-19 admitted to an intensive care unit(ICU)between March and October 2020 from the RIsk Stratification in COVID-19 patients in the Intensive Care Unit(RISC-19-ICU)*** applied the Extreme Gradient Boosting(XGBoost)algorithm to the data to predict as a binary out-come the increase or decrease in patients’Sequential Organ Failure Assessment(SOFA)score on day 5 after ICU *** model was iteratively cross-validated in different subsets of the study ***:The final study population consisted of 675 *** XGBoost model correctly predicted a decrease in SOFA score in 320/385(83%)critically ill COVID-19 patients,and an increase in the score in 210/290(72%)*** area under the mean receiver operating characteristic curve for XGBoost was significantly higher than that for the logistic regression model(0.86 vs.0.69,P<0.01[paired t-test with 95%confidence interval]).Conclusions:The XGBoost model predicted the change in SOFA score in critically ill COVID-19 patients admitted to the ICU and can guide clinical decision support systems(CDSSs)aimed at optimizing available resources.

关键词： Machine learning Extreme gradient boosting(XGBoost) COVID-19 Multiple organ failure Clinical decision support system(CDSS) Organ dysfunction score

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Olfactory swab sampling optimization for α-synuclein aggregate detection in patients with Parkinson’s disease

引用

Translational Neurodegeneration 2022年第1期11卷 390-400页

作者： Matilde Bongianni Mauro Catalan Daniela Perra Elena Fontana Francesco Janes Claudio Bertolotti Luca Sacchetto Stefano Capaldi Matteo Tagliapietra Paola Polverino Valentina Tommasini Giulia Bellavita Elham Ataie Kachoie Roberto Baruca Andrea bernardini Mariarosaria Valente michele Fiorini Erika Bronzato Stefano Tamburin Laura Bertolasi Lorenzo Brozzetti Maria Paola Cecchini Gianluigi Gigli Salvatore Monaco Paolo Manganotti Gianluigi Zanusso Department of Neurosciences Biomedicineand Movement SciencesPoliclinico G.B.RossiUniversity of Verona37134 VeronaItaly Neurology Unit Department of MedicineSurgery and Health SciencesOspedale CattinaraUniversity of Trieste34128 TriesteItaly Neurology Unit University of Udine Academic Hospital33100 UdineItaly Department of Surgical Sciences DentistryGynecology and PediatricsUniversity of Verona37134 VeronaItaly Biocrystallography Laboratory Department of BiotechnologyUniversity of Verona37134 VeronaItaly Otolaryngology Unit Department of MedicineSurgery and Health SciencesOspedale CattinaraUniversity of Trieste34128 TriesteItaly.

Background: In patients with Parkinson’s disease (PD), real-time quaking-induced conversion (RT-QuIC) detection of pathological α-synuclein (α-syn) in olfactory mucosa (OM) is not as accurate as in other α-synucleinopathies. It is unknown whether these variable results might be related to a different distribution of pathological α-syn in OM. Thus, we investigated whether nasal swab (NS) performed in areas with a different coverage by olfactory neuroepithelium, such as agger nasi (AN) and middle turbinate (MT), might affect the detection of pathological α-syn. Methods: NS was performed in 66 patients with PD and 29 non-PD between September 2018 and April 2021. In 43 patients, cerebrospinal fluid (CSF) was also obtained and all samples were analyzed by RT-QuIC for α-syn. Results: In the first round, 72 OM samples were collected by NS, from AN (NSAN) or from MT (NSMT), and 35 resulted positive for α-syn RT-QuIC, including 27/32 (84%) from AN, 5/11 (45%) from MT, and 3/29 (10%) belonging to the non-PD patients. Furthermore, 23 additional PD patients underwent NS at both AN and MT, and RT-QuIC revealed α-syn positive in 18/23 (78%) NSAN samples and in 10/23 (44%) NSMT samples. Immunocytochemistry of NS prepara-tions showed a higher representation of olfactory neural cells in NSAN compared to NSMT. We also observed α-syn and phospho-α-syn deposits in NS from PD patients but not in controls. Finally, RT-QuIC was positive in 22/24 CSF samples from PD patients (92%) and in 1/19 non-PD. Conclusion: In PD patients, RT-QuIC sensitivity is significantly increased (from 45% to 84%) when NS is performed at AN, indicating that α-syn aggregates are preferentially detected in olfactory areas with higher concentration of olfactory neurons. Although RT-QuIC analysis of CSF showed a higher diagnostic accuracy compared to NS, due to the non-invasiveness, NS might be considered as an ancillary procedure for PD diagnosis.

关键词： Parkinson disease Alpha-synuclein Real-time quaking-induced conversion assay Olfactory mucosa Cerebrospinal fluid

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Correction: Olfactory swab sampling optimization for α-synuclein aggregate detection in patients with Parkinson’s disease

引用

Translational Neurodegeneration 2022年第1期11卷 389-389页

Correction:Translational Neurodegeneration(2022)11:37 https://***/10.1186/s40035-022-00311-3 In the original publication of this article[1],“AN”is miss-ing in the column heading“Patients underwent NS at the(n=46)”in Table 1 due to a typesetting *** correct column heading should be“Patients underwent NS at the AN(n=46)”.Moreover,the asterisk symbol*in“27(84)*”and“5(45)*”should be *** addition,the phrase“using FLOQBrushes(Copan Italia,Brescia,Italy)”needs be added in the first sentence under the header“OM sample collection”of the Methods section.

关键词： heading optimization removed

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

欢迎您,

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

在线全文

在线全文

在线全文

请选择保存的检索档案：

请选择收藏分类：

通借通还

欢迎您,

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

在线全文

在线全文

在线全文

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：