Your browser doesn't support javascript.
Show: 20 | 50 | 100
Results 1 - 20 de 28
Filter
1.
Eur Radiol ; 2022 Jan 06.
Article in English | MEDLINE | ID: covidwho-1606144

ABSTRACT

BACKGROUND: Main challenges for COVID-19 include the lack of a rapid diagnostic test, a suitable tool to monitor and predict a patient's clinical course and an efficient way for data sharing among multicenters. We thus developed a novel artificial intelligence system based on deep learning (DL) and federated learning (FL) for the diagnosis, monitoring, and prediction of a patient's clinical course. METHODS: CT imaging derived from 6 different multicenter cohorts were used for stepwise diagnostic algorithm to diagnose COVID-19, with or without clinical data. Patients with more than 3 consecutive CT images were trained for the monitoring algorithm. FL has been applied for decentralized refinement of independently built DL models. RESULTS: A total of 1,552,988 CT slices from 4804 patients were used. The model can diagnose COVID-19 based on CT alone with the AUC being 0.98 (95% CI 0.97-0.99), and outperforms the radiologist's assessment. We have also successfully tested the incorporation of the DL diagnostic model with the FL framework. Its auto-segmentation analyses co-related well with those by radiologists and achieved a high Dice's coefficient of 0.77. It can produce a predictive curve of a patient's clinical course if serial CT assessments are available. INTERPRETATION: The system has high consistency in diagnosing COVID-19 based on CT, with or without clinical data. Alternatively, it can be implemented on a FL platform, which would potentially encourage the data sharing in the future. It also can produce an objective predictive curve of a patient's clinical course for visualization. KEY POINTS: • CoviDet could diagnose COVID-19 based on chest CT with high consistency; this outperformed the radiologist's assessment. Its auto-segmentation analyses co-related well with those by radiologists and could potentially monitor and predict a patient's clinical course if serial CT assessments are available. It can be integrated into the federated learning framework. • CoviDet can be used as an adjunct to aid clinicians with the CT diagnosis of COVID-19 and can potentially be used for disease monitoring; federated learning can potentially open opportunities for global collaboration.

2.
Value in Health ; 2021.
Article in English | ScienceDirect | ID: covidwho-1559519

ABSTRACT

Objectives Most countries have adopted public activity intervention policies to control the coronavirus disease 2019 (COVID-19) pandemic. Nevertheless, empirical evidence of the effectiveness of different interventions on the containment of the epidemic was inconsistent. Methods We retrieved time-series intervention policy data for 145 countries from the Oxford COVID-19 Government Response Tracker from December 31, 2019, to July 1, 2020, which included 8 containment and closure policies. We investigated the association of timeliness, stringency, and duration of intervention with cumulative infections per million population on July 1, 2020. We introduced a novel counterfactual estimator to estimate the effects of these interventions on COVID-19 time-varying reproduction number (Rt). Results There is some evidence that earlier implementation, longer durations, and more strictness of intervention policies at the early but not middle stage were associated with reduced infections of COVID-19. The counterfactual model proved to have controlled for unobserved time-varying confounders and established a valid causal relationship between policy intervention and Rt reduction. The average intervention effect revealed that all interventions significantly decrease Rt after their implementation. Rt decreased by 30% (22%-41%) in 25 to 32 days after policy intervention. Among the 8 interventions, school closing, workplace closing, and public events cancellation demonstrated the strongest and most consistent evidence of associations. Conclusions Our study provides more reliable evidence of the quantitative effects of policy interventions on the COVID-19 epidemic and suggested that stricter public activity interventions should be implemented at the early stage of the epidemic for improved containment.

4.
Nat Biomed Eng ; 5(6): 509-521, 2021 06.
Article in English | MEDLINE | ID: covidwho-1189229

ABSTRACT

Common lung diseases are first diagnosed using chest X-rays. Here, we show that a fully automated deep-learning pipeline for the standardization of chest X-ray images, for the visualization of lesions and for disease diagnosis can identify viral pneumonia caused by coronavirus disease 2019 (COVID-19) and assess its severity, and can also discriminate between viral pneumonia caused by COVID-19 and other types of pneumonia. The deep-learning system was developed using a heterogeneous multicentre dataset of 145,202 images, and tested retrospectively and prospectively with thousands of additional images across four patient cohorts and multiple countries. The system generalized across settings, discriminating between viral pneumonia, other types of pneumonia and the absence of disease with areas under the receiver operating characteristic curve (AUCs) of 0.94-0.98; between severe and non-severe COVID-19 with an AUC of 0.87; and between COVID-19 pneumonia and other viral or non-viral pneumonia with AUCs of 0.87-0.97. In an independent set of 440 chest X-rays, the system performed comparably to senior radiologists and improved the performance of junior radiologists. Automated deep-learning systems for the assessment of pneumonia could facilitate early intervention and provide support for clinical decision-making.


Subject(s)
COVID-19/diagnostic imaging , Databases, Factual , Deep Learning , SARS-CoV-2 , Tomography, X-Ray Computed , Diagnosis, Differential , Female , Humans , Male , Severity of Illness Index
5.
J Thorac Dis ; 13(3): 1507-1516, 2021 Mar.
Article in English | MEDLINE | ID: covidwho-1175848

ABSTRACT

Background: Several articles have been published about the reorganization of surgical activity during the coronavirus disease 2019 (COVID-19) pandemic but little is known about the operative volume, distribution of cases, or capacity of The Department of Thoracic Surgery to deliver surgical services in the time of COVID-19. Methods: A retrospective operative logbook review was completed in department of thoracic in a designated COVID-19 hospital. We reviewed and analyzed the operative logbook and discussed our countermeasures during the outbreak. A prediction model was established to discuss the time consuming about delayed surgeries during the pandemic. Results: One thousand two hundred and seventy-five operation records were collected. The thoracic surgeries of this year has decreased (43.4%) during the Wuhan lockdown. From Jan 23rd to Apr 8th in 2020, there were 461 surgeries performed in The Department of Thoracic in our hospital with 0 cases of nosocomial COVID-19 infection. Prediction model showed that it will take 6 weeks to solve the backlog if department can reach the 85% of maximum of operations per week. Conclusions: An understanding of operative case volume and distribution is essential in facilitating targeted interventions to strengthen surgical capacity in the time of COVID-19. A proper guideline is imperative to ensure access to safe, timely surgical care. By developing a scientific and effective management of hospital, it is possible to ensure optimal surgical safety during this crisis. Regular updates and a further study include multicenter is required. Clinical trial registry number: ChiCTR2000034346.

6.
Clin Chem ; 67(4): 672-683, 2021 03 31.
Article in English | MEDLINE | ID: covidwho-1165392

ABSTRACT

BACKGROUND: Infectious disease outbreaks such as the COVID-19 (coronavirus disease 2019) pandemic call for rapid response and complete screening of the suspected community population to identify potential carriers of pathogens. Central laboratories rely on time-consuming sample collection methods that are rarely available in resource-limited settings. METHODS: We present a highly automated and fully integrated mobile laboratory for fast deployment in response to infectious disease outbreaks. The mobile laboratory was equipped with a 6-axis robot arm for automated oropharyngeal swab specimen collection; virus in the collected specimen was inactivated rapidly using an infrared heating module. Nucleic acid extraction and nested isothermal amplification were performed by a "sample in, answer out" laboratory-on-a-chip system, and the result was automatically reported by the onboard information platform. Each module was evaluated using pseudovirus or clinical samples. RESULTS: The mobile laboratory was stand-alone and self-sustaining and capable of on-site specimen collection, inactivation, analysis, and reporting. The automated sampling robot arm achieved sampling efficiency comparable to manual collection. The collected samples were inactivated in as short as 12 min with efficiency comparable to a water bath without damage to nucleic acid integrity. The limit of detection of the integrated microfluidic nucleic acid analyzer reached 150 copies/mL within 45 min. Clinical evaluation of the onboard microfluidic nucleic acid analyzer demonstrated good consistency with reverse transcription quantitative PCR with a κ coefficient of 0.979. CONCLUSIONS: The mobile laboratory provides a promising solution for fast deployment of medical diagnostic resources at critical junctions of infectious disease outbreaks and facilitates local containment of SARS-CoV-2 (severe acute respiratory syndrome coronavirus 2) transmission.


Subject(s)
COVID-19 Nucleic Acid Testing/methods , COVID-19/diagnosis , Laboratories , Mobile Health Units , Pathology, Molecular/methods , RNA, Viral/analysis , Adult , Automobiles , COVID-19/epidemiology , COVID-19 Nucleic Acid Testing/instrumentation , Female , Humans , Lab-On-A-Chip Devices , Male , Microfluidic Analytical Techniques/instrumentation , Microfluidic Analytical Techniques/methods , Middle East Respiratory Syndrome Coronavirus/chemistry , Molecular Diagnostic Techniques/instrumentation , Molecular Diagnostic Techniques/methods , Pandemics , Pathology, Molecular/instrumentation , Robotics , SARS-CoV-2/chemistry
7.
J Thorac Dis ; 13(2): 505-510, 2021 Feb.
Article in English | MEDLINE | ID: covidwho-1134645
10.
Chest ; 158(1): 97-105, 2020 07.
Article in English | MEDLINE | ID: covidwho-980155

ABSTRACT

BACKGROUND: The novel coronavirus disease 2019 (COVID-19) has become a global health emergency. The cumulative number of new confirmed cases and deaths are still increasing out of China. Independent predicted factors associated with fatal outcomes remain uncertain. RESEARCH QUESTION: The goal of the current study was to investigate the potential risk factors associated with fatal outcomes from COVID-19 through a multivariate Cox regression analysis and a nomogram model. STUDY DESIGN AND METHODS: A retrospective cohort of 1,590 hospitalized patients with COVID-19 throughout China was established. The prognostic effects of variables, including clinical features and laboratory findings, were analyzed by using Kaplan-Meier methods and a Cox proportional hazards model. A prognostic nomogram was formulated to predict the survival of patients with COVID-19. RESULTS: In this nationwide cohort, nonsurvivors included a higher incidence of elderly people and subjects with coexisting chronic illness, dyspnea, and laboratory abnormalities on admission compared with survivors. Multivariate Cox regression analysis showed that age ≥ 75 years (hazard ratio [HR], 7.86; 95% CI, 2.44-25.35), age between 65 and 74 years (HR, 3.43; 95% CI, 1.24-9.5), coronary heart disease (HR, 4.28; 95% CI, 1.14-16.13), cerebrovascular disease (HR, 3.1; 95% CI, 1.07-8.94), dyspnea (HR, 3.96; 95% CI, 1.42-11), procalcitonin level > 0.5 ng/mL (HR, 8.72; 95% CI, 3.42-22.28), and aspartate aminotransferase level > 40 U/L (HR, 2.2; 95% CI, 1.1-6.73) were independent risk factors associated with fatal outcome. A nomogram was established based on the results of multivariate analysis. The internal bootstrap resampling approach suggested the nomogram has sufficient discriminatory power with a C-index of 0.91 (95% CI, 0.85-0.97). The calibration plots also showed good consistency between the prediction and the observation. INTERPRETATION: The proposed nomogram accurately predicted clinical outcomes of patients with COVID-19 based on individual characteristics. Earlier identification, more intensive surveillance, and appropriate therapy should be considered in patients at high risk.


Subject(s)
Aspartate Aminotransferases/blood , Cardiovascular Diseases/epidemiology , Coronavirus Infections , Dyspnea , Pandemics , Pneumonia, Viral , Procalcitonin/blood , Aged , Betacoronavirus/isolation & purification , COVID-19 , China/epidemiology , Coronavirus Infections/blood , Coronavirus Infections/diagnosis , Coronavirus Infections/mortality , Coronavirus Infections/physiopathology , Correlation of Data , Dyspnea/epidemiology , Dyspnea/etiology , Female , Humans , Male , Nomograms , Pneumonia, Viral/blood , Pneumonia, Viral/diagnosis , Pneumonia, Viral/mortality , Pneumonia, Viral/physiopathology , Prognosis , Risk Assessment/methods , Risk Factors , SARS-CoV-2 , Survival Analysis
11.
Nat Commun ; 11(1): 3543, 2020 07 15.
Article in English | MEDLINE | ID: covidwho-974925

ABSTRACT

The sudden deterioration of patients with novel coronavirus disease 2019 (COVID-19) into critical illness is of major concern. It is imperative to identify these patients early. We show that a deep learning-based survival model can predict the risk of COVID-19 patients developing critical illness based on clinical characteristics at admission. We develop this model using a cohort of 1590 patients from 575 medical centers, with internal validation performance of concordance index 0.894 We further validate the model on three separate cohorts from Wuhan, Hubei and Guangdong provinces consisting of 1393 patients with concordance indexes of 0.890, 0.852 and 0.967 respectively. This model is used to create an online calculation tool designed for patient triage at admission to identify patients at risk of severe illness, ensuring that patients at greatest risk of severe illness receive appropriate care as early as possible and allow for effective allocation of health resources.


Subject(s)
Coronavirus Infections/diagnosis , Coronavirus Infections/pathology , Deep Learning/statistics & numerical data , Pneumonia, Viral/diagnosis , Pneumonia, Viral/pathology , Triage/methods , Betacoronavirus , COVID-19 , Critical Illness , Hospitalization , Humans , Middle Aged , Models, Theoretical , Pandemics , Prognosis , Risk , SARS-CoV-2 , Survival Analysis
12.
BMC Pulm Med ; 20(1): 290, 2020 Nov 09.
Article in English | MEDLINE | ID: covidwho-917926

ABSTRACT

BACKGROUND: The clinical correlates, prognosis and determinants of acute kidney injury (AKI) in patients with coronavirus disease 2019 (Covid-19) remain largely unclear. METHODS: We retrospectively reviewed medical records of all adult patients with laboratory-confirmed Covid-19 who were admitted to the intensive care unit (ICU) between January 23rd 2020 and April 6th 2020 at Wuhan JinYinTan Hospital and The First Affiliated Hospital of Guangzhou Medical University. RESULTS: Among 210 patients, 131 were males (62.4%). The median Age was 64 years (IQR: 56-71). Of 92 (43.8%) patients who developed AKI during hospitalization, 13 (14.1%), 15 (16.3%) and 64 (69.6%) were classified as being at stage 1, 2 and 3, respectively. 54 patients (58.7%) received continuous renal replacement therapy. Age, sepsis, nephrotoxic drug, invasive mechanical ventilation and elevated baseline serum creatinine levels were associated with the occurrence of AKI. Renal recovery during hospitalization was identified among 16 patients with AKI (17.4%), who had a significantly shorter time from admission to AKI diagnosis, lower incidence of right heart failure and higher ratio of partial pressure of oxygen to the fraction of inspired oxygen. Of 210 patients, 93 deceased within 28 days of ICU admission. AKI stage 3, critical disease, greater Age and the lowest ratio of partial pressure of oxygen to the fraction of inspired oxygen being < 150 mmHg were independently associated with death. CONCLUSIONS: Among patients with Covid-19, the incidence of AKI was high. Our findings of the risk factors of the development of AKI and factors associated with renal function recovery may inform clinical management of patients with critical illness of Covid-19.


Subject(s)
Acute Kidney Injury/virology , Betacoronavirus , Coronavirus Infections/complications , Pneumonia, Viral/complications , Acute Kidney Injury/diagnosis , Acute Kidney Injury/epidemiology , Adult , Aged , Aged, 80 and over , COVID-19 , China , Critical Illness , Female , Humans , Incidence , Male , Middle Aged , Pandemics , Prognosis , Retrospective Studies , Risk Factors , SARS-CoV-2
13.
J Infect Dis ; 222(9): 1444-1451, 2020 10 01.
Article in English | MEDLINE | ID: covidwho-851783

ABSTRACT

Corona virus disease 2019 (COVID-19) patients with severe immune abnormalities are at risk of cytokine release syndrome (CRS). The definition, prevention, and treatment of symptoms of CRS in critically ill patients with COVID-19 are important problems. We report a single-center case series of 11 COVID-19 patients with acute respiratory distress syndrome from The First Affiliated Hospital of Guangzhou Medical University in China from 26 January 2020 to 18 February 2020. The termination date of follow-up was 19 February 2020. Eight patients were determined to have characteristics of CRS, including pulmonary inflammation, fever, and dysfunction of nonpulmonary organs. An increase in interleukin-6 in peripheral blood was the highest risk factor and an early indicator of CRS in COVID-19.


Subject(s)
Coronavirus Infections/immunology , Cytokine Release Syndrome/blood , Interleukin-6/blood , Leukocytes, Mononuclear , Pneumonia, Viral/blood , Aged , Betacoronavirus , Biomarkers/blood , COVID-19 , Coronavirus Infections/blood , Coronavirus Infections/complications , Critical Illness , Cytokine Release Syndrome/immunology , Cytokine Release Syndrome/virology , Female , Humans , Male , Middle Aged , Pandemics , Pneumonia, Viral/complications , Pneumonia, Viral/immunology , Pneumonia, Viral/virology , Prognosis , Risk Factors , SARS-CoV-2
15.
Engineering (Beijing) ; 6(10): 1130-1140, 2020 Oct.
Article in English | MEDLINE | ID: covidwho-743961

ABSTRACT

Fast and accurate diagnosis and the immediate isolation of patients infected with severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) are regarded as the most effective measures to restrain the coronavirus disease 2019 (COVID-19) pandemic. Here, we present a high-throughput, multi-index nucleic acid isothermal amplification analyzer (RTisochip™-W) employing a centrifugal microfluidic chip to detect 19 common respiratory viruses, including SARS-CoV-2, from 16 samples in a single run within 90 min. The limits of detection of all the viruses analyzed by the RTisochip™-W system were equal to or less than 50 copies·µL-1, which is comparable to those of conventional reverse transcription polymerase chain reaction. We also demonstrate that the RTisochip™-W system possesses the advantages of good repeatability, strong robustness, and high specificity. Finally, we analyzed 201 cases of preclinical samples, 14 cases of COVID-19-positive samples, 25 cases of clinically diagnosed samples, and 614 cases of clinical samples from patients or suspected patients with respiratory tract infections using the RTisochip™-W system. The test results matched the referenced results well and reflected the epidemic characteristics of the respiratory infectious diseases. The coincidence rate of the RTisochip™-W with the referenced kits was 98.15% for the detection of SARS-CoV-2. Based on these extensive trials, we believe that the RTisochip™-W system provides a powerful platform for fighting the COVID-19 pandemic.

SELECTION OF CITATIONS
SEARCH DETAIL
...