Bo Kang

Bio: Bo Kang is an academic researcher from Tianjin University. The author has contributed to research in topics: Gold standard (test) & Medicine. The author has an hindex of 2, co-authored 3 publications receiving 729 citations.

A deep learning algorithm using CT images to screen for Corona Virus Disease (COVID-19)

Abstract: Background The outbreak of Severe Acute Respiratory Syndrome Coronavirus 2 (SARS-COV-2) has caused more than 2.5 million cases of Corona Virus Disease (COVID-19) in the world so far, with that number continuing to grow. To control the spread of the disease, screening large numbers of suspected cases for appropriate quarantine and treatment is a priority. Pathogenic laboratory testing is the gold standard but is time-consuming with significant false negative results. Therefore, alternative diagnostic methods are urgently needed to combat the disease. Based on COVID-19 radiographical changes in CT images, we hypothesized that Artificial Intelligence’s deep learning methods might be able to extract COVID-19’s specific graphical features and provide a clinical diagnosis ahead of the pathogenic test, thus saving critical time for disease control. Methods and Findings We collected 1,065 CT images of pathogen-confirmed COVID-19 cases (325 images) along with those previously diagnosed with typical viral pneumonia (740 images). We modified the Inception transfer-learning model to establish the algorithm, followed by internal and external validation. The internal validation achieved a total accuracy of 89.5% with specificity of 0.88 and sensitivity of 0.87. The external testing dataset showed a total accuracy of 79.3% with specificity of 0.83 and sensitivity of 0.67. In addition, in 54 COVID-19 images that first two nucleic acid test results were negative, 46 were predicted as COVID-19 positive by the algorithm, with the accuracy of 85.2%. Conclusion These results demonstrate the proof-of-principle for using artificial intelligence to extract radiological features for timely and accurate COVID-19 diagnosis. Author summary To control the spread of the COVID-19, screening large numbers of suspected cases for appropriate quarantine and treatment measures is a priority. Pathogenic laboratory testing is the gold standard but is time-consuming with significant false negative results. Therefore, alternative diagnostic methods are urgently needed to combat the disease. We hypothesized that Artificial Intelligence’s deep learning methods might be able to extract COVID-19’s specific graphical features and provide a clinical diagnosis ahead of the pathogenic test, thus saving critical time. We collected 1,065 CT images of pathogen-confirmed COVID-19 cases along with those previously diagnosed with typical viral pneumonia. We modified the Inception transfer-learning model to establish the algorithm. The internal validation achieved a total accuracy of 89.5% with specificity of 0.88 and sensitivity of 0.87. The external testing dataset showed a total accuracy of 79.3% with specificity of 0.83 and sensitivity of 0.67. In addition, in 54 COVID-19 images that first two nucleic acid test results were negative, 46 were predicted as COVID-19 positive by the algorithm, with the accuracy of 85.2%. Our study represents the first study to apply artificial intelligence to CT images for effectively screening for COVID-19.

A deep learning algorithm using CT images to screen for Corona virus disease (COVID-19).

Abstract: The outbreak of Severe Acute Respiratory Syndrome Coronavirus 2 (SARS-COV-2) has caused more than 26 million cases of Corona virus disease (COVID-19) in the world so far. To control the spread of the disease, screening large numbers of suspected cases for appropriate quarantine and treatment are a priority. Pathogenic laboratory testing is typically the gold standard, but it bears the burden of significant false negativity, adding to the urgent need of alternative diagnostic methods to combat the disease. Based on COVID-19 radiographic changes in CT images, this study hypothesized that artificial intelligence methods might be able to extract specific graphical features of COVID-19 and provide a clinical diagnosis ahead of the pathogenic test, thus saving critical time for disease control. We collected 1065 CT images of pathogen-confirmed COVID-19 cases along with those previously diagnosed with typical viral pneumonia. We modified the inception transfer-learning model to establish the algorithm, followed by internal and external validation. The internal validation achieved a total accuracy of 89.5% with a specificity of 0.88 and sensitivity of 0.87. The external testing dataset showed a total accuracy of 79.3% with a specificity of 0.83 and sensitivity of 0.67. In addition, in 54 COVID-19 images, the first two nucleic acid test results were negative, and 46 were predicted as COVID-19 positive by the algorithm, with an accuracy of 85.2%. These results demonstrate the proof-of-principle for using artificial intelligence to extract radiological features for timely and accurate COVID-19 diagnosis. • The study evaluated the diagnostic performance of a deep learning algorithm using CT images to screen for COVID-19 during the influenza season. • As a screening method, our model achieved a relatively high sensitivity on internal and external CT image datasets. • The model was used to distinguish between COVID-19 and other typical viral pneumonia, both of which have quite similar radiologic characteristics.

Rapid Implementation of COVID-19 AI Assisted Diagnosis System Based on Supercomputing Platform

Abstract: As a global pandemic, New Coronary Pneumonia (COVID-19) has infected more than 10 million people worldwide. In the initial stage of outbreaks that lacks detection capabilities of nucleic acid testing, it become important approach to achieve the initial screening of patients through the application of artificial intelligence and other technologies. We proposed a technical solution to quickly establish a COVID-19 AI assisted diagnosis system by using the Tianhe artificial intelligence innovation integrated platform deployed on the Tianhe-1A supercomputer. The AI supported platform mainly includes three main parts: (1) the large-scale model training development and implementation environment that ensures the rapid training of the new crown AI-assisted diagnostic model; (2) the integration of artificial intelligence basic algorithm library that provides a shortcut for the selection of various artificial intelligence models of COVID-19 CT image classification; (3) the design and implementation of the artificial intelligence R&D cloud platform that realizes the online full life cycle management on modeling, training and deployment. Firstly, the data preprocessing and interactive modeling design are provided during the model building phase. Secondly, in the training phase, it provides huge computing source pool supporting parallel and concurrent tasks. Finally, after the model training is completed, the online deployment framework support is provided for public service. Based on the Tianhe artificial intelligence integrated platform, the whole process of modeling-training-validation-deployment activities of COVID-19 AI model development is realized. As a public welfare platform, the COVID-19 AI assisted diagnosis system has been adopted by more than 100 hospitals and research institutes around the world, and has contributed to the fight against the epidemic, which provides a technical reference for the rapid response to an outbreak.

[Control study of the intelligent calculation method and the traditional calculation method in risk assessments of hospitalization].

Abstract: OBJECTIVE To explore the accuracy of intelligent calculation (IC) method for risk assessment of hospitalization for patients, aiming to build a more advantageous risk assessment system. METHODS The "Search Engine" program was developed based on hospital information system (HIS) of the Fifth Center Hospital in Tianjin, which automatically captured patient information and generated nutritional risk screening 2002 (NRS 2002) score, Caprini thrombosis risk assessment model and Padua thrombosis risk assessment model for venous thromboembolism (VTE), the CHA2DS2-VASc for predicting stroke risk stratification in atrial fibrillation and the HAS-BLED for predicting bleeding risk in anticoagulated patients with atrial fibrillation. A randomized controlled trial was conducted. According to the applicable conditions of each risk assessment, 100 risk scores from "Search Engine" program belonged to each risk assessment were randomly selected, defined as the IC group. Manual scoring with the data of the same case at the same time, defined as the traditional calculation (TC) group, compared the consistency of the scores and the difference in time-consuming between the two groups. RESULTS The Bland-Altman plots showed that the 95% limits of agreement (95%LoA) of NRS 2002 score, Caprini score, Padua score, CHA2DS2-VASc score and HAS-BLED score was -0.46 to 0.41, -0.49 to 0.52, -0.50 to 0.41, -0.67 to 0.60, -0.44 to 0.43, respectively, all P > 0.05. In this study, the Bland-Altman plot showed that 95%, 96%, 97%, 97%, 95% plots fell within the 95%LoA in NRS 2002 score, Caprini score, Padua score, wwCHA2DS2-VASc score and HAS-BLED score by the two methods, respectively. The all plots of 95%LoA were within the clinically acceptable range (-0.5 to 0.5 scores). The time-consuming of NRS 2002 score, Caprini score, Padua score, CHA2DS2-VASc score and HAS-BLED score in IC group were significantly shorter than those in TC group [0.72 (0.71, 0.73) seconds vs. 361.02 (322.41, 361.02) seconds, 0.72 (0.72, 0.73) seconds vs. 196.68 (179.99, 291.20) seconds, 0.72 (0.72, 0.73) seconds vs. 105.75 (92.32, 114.70) seconds, 0.72 (0.71, 0.72) seconds vs. 72.66 (56.24, 84.20) seconds, 0.72 (0.71, 0.72) seconds vs. 51.30 (38.88, 57.15) seconds, respectively, all P < 0.001]. CONCLUSION For the above five risk assessments, the TC method and IC method has good consistency in scores, and the IC method is faster, which has good application prospect for clinical application.

[Study of hospitalization risk indicators for intensive care unit patients evaluated by intelligent calculation method].

Abstract: OBJECTIVE To explore the characteristics of the changes in risk score for intensive care unit (ICU) patients during hospitalization by the intelligent calculation method, and to provide evidence for the risk prevention. METHODS In this retrospective study, ICU patients of the Fifth Central Hospital in Tianjin from November 3, 2021 to March 28, 2022 were enrolled and divided into ≥ 14 days group, 10-13 days group, 7-9 days group, and 3-6 days group according to the ICU length of stay. Risk scores assessed by the intelligent calculation method of the ICU patients were collected, including nutritional risk screening 2002 (NRS 2002), Caprini score and Padua score. NRS 2002 score for all patients, Caprini score for surgical patients and Padua score for internal medicine patients were selected. Trends in change of each score were compared between patients admitted to ICU 1, 3, 7 (if necessary), 10 (if necessary), and 14 days (if necessary). RESULTS A total of 138 patients were involved, including 79 males and 59 females, with an average age of (61.71±18.86) years and an average hospital stay of [6.00 (4.00, 9.25)] days. (1) in the group with ICU length of stay ≥ 14 days (21 cases): there was no significant change in the NRS 2002 scores of the patients within 10 days, but the NRS 2002 score was significantly decreased in 14 days as compared with 1 day [3.00 (2.50, 3.50) vs. 4.00 (3.00, 5.00), P < 0.05]; both Caprini and Padua score were increased with prolonged hospital stay and compared with 1 day, the scores at the other time points were significantly increased, especially at 14 days [Caprini score: 5.00 (3.25,7.00) vs. 2.50 (1.25, 5.50), Padua score: 6.00 (6.00, 7.00) vs. 3.00 (1.00, 3.00), both P < 0.05]. (2) in the group with ICU length of stay from 10-13 days (15 cases): with the prolonged hospital stay, there was no significant change in NRS 2002 score, but both Caprini and Padua score were increased at 3, 7, 10 days, especially at 10 days [Caprini score: 3.00 (2.00, 4.75) vs. 2.00 (0.25, 2.75), Padua score: 5.00 (3.50, 6.00) vs. 2.00 (0.50, 4.00), both P < 0.05]. (3) in the group with ICU length of stay from 7-9 days (23 cases): compared with 1 day, the NRS 2002 score at 3 days and7 days were decreased, but the Caprini and Padua score were increased, especially at 7 days [NRS 2002 score: 2.00 (1.00, 4.00) vs. 2.00 (2.00, 4.00), Caprini score: 3.00 (2.00, 5.50) vs. 2.00 (0.25, 3.00), Padua score: 5.00 (4.00, 6.00) vs. 2.00 (0,2.00),all P < 0.05]. (4) in the group with ICU length of stay from 3-6 days (79 cases): compared with 1 day, the NRS 2002 score at 3 days was decreased [NRS 2002 score: 2.00 (1.00, 3.00) vs. 2.00 (1.00, 3.00), P < 0.05], Caprini and Padua score were significantly increased [Caprini score: 3.00 (2.00, 4.00) vs. 2.00 (1.00, 3.00), Padua score: 5.00 (4.00, 5.00) vs. 2.00 (1.00, 3.00), both P < 0.05]. CONCLUSIONS Based on dynamic assessment of intelligent calculation methods, the risk of thrombosis in ICU patients increased with hospital length of stay, and the nutritional risk was generally flat or reducing in different hospitalization periods.

Clinical course and risk factors for mortality of adult inpatients with COVID-19 in Wuhan, China: a retrospective cohort study

Abstract: Summary Background Since December, 2019, Wuhan, China, has experienced an outbreak of coronavirus disease 2019 (COVID-19), caused by the severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2). Epidemiological and clinical characteristics of patients with COVID-19 have been reported but risk factors for mortality and a detailed clinical course of illness, including viral shedding, have not been well described. Methods In this retrospective, multicentre cohort study, we included all adult inpatients (≥18 years old) with laboratory-confirmed COVID-19 from Jinyintan Hospital and Wuhan Pulmonary Hospital (Wuhan, China) who had been discharged or had died by Jan 31, 2020. Demographic, clinical, treatment, and laboratory data, including serial samples for viral RNA detection, were extracted from electronic medical records and compared between survivors and non-survivors. We used univariable and multivariable logistic regression methods to explore the risk factors associated with in-hospital death. Findings 191 patients (135 from Jinyintan Hospital and 56 from Wuhan Pulmonary Hospital) were included in this study, of whom 137 were discharged and 54 died in hospital. 91 (48%) patients had a comorbidity, with hypertension being the most common (58 [30%] patients), followed by diabetes (36 [19%] patients) and coronary heart disease (15 [8%] patients). Multivariable regression showed increasing odds of in-hospital death associated with older age (odds ratio 1·10, 95% CI 1·03–1·17, per year increase; p=0·0043), higher Sequential Organ Failure Assessment (SOFA) score (5·65, 2·61–12·23; p Interpretation The potential risk factors of older age, high SOFA score, and d-dimer greater than 1 μg/mL could help clinicians to identify patients with poor prognosis at an early stage. Prolonged viral shedding provides the rationale for a strategy of isolation of infected patients and optimal antiviral interventions in the future. Funding Chinese Academy of Medical Sciences Innovation Fund for Medical Sciences; National Science Grant for Distinguished Young Scholars; National Key Research and Development Program of China; The Beijing Science and Technology Project; and Major Projects of National Science and Technology on New Drug Creation and Development.

COVID-Net: a tailored deep convolutional neural network design for detection of COVID-19 cases from chest X-ray images.

Abstract: The Coronavirus Disease 2019 (COVID-19) pandemic continues to have a devastating effect on the health and well-being of the global population. A critical step in the fight against COVID-19 is effective screening of infected patients, with one of the key screening approaches being radiology examination using chest radiography. It was found in early studies that patients present abnormalities in chest radiography images that are characteristic of those infected with COVID-19. Motivated by this and inspired by the open source efforts of the research community, in this study we introduce COVID-Net, a deep convolutional neural network design tailored for the detection of COVID-19 cases from chest X-ray (CXR) images that is open source and available to the general public. To the best of the authors' knowledge, COVID-Net is one of the first open source network designs for COVID-19 detection from CXR images at the time of initial release. We also introduce COVIDx, an open access benchmark dataset that we generated comprising of 13,975 CXR images across 13,870 patient patient cases, with the largest number of publicly available COVID-19 positive cases to the best of the authors' knowledge. Furthermore, we investigate how COVID-Net makes predictions using an explainability method in an attempt to not only gain deeper insights into critical factors associated with COVID cases, which can aid clinicians in improved screening, but also audit COVID-Net in a responsible and transparent manner to validate that it is making decisions based on relevant information from the CXR images. By no means a production-ready solution, the hope is that the open access COVID-Net, along with the description on constructing the open source COVIDx dataset, will be leveraged and build upon by both researchers and citizen data scientists alike to accelerate the development of highly accurate yet practical deep learning solutions for detecting COVID-19 cases and accelerate treatment of those who need it the most.

Prediction models for diagnosis and prognosis of covid-19: systematic review and critical appraisal

Abstract: Objective To review and appraise the validity and usefulness of published and preprint reports of prediction models for diagnosing coronavirus disease 2019 (covid-19) in patients with suspected infection, for prognosis of patients with covid-19, and for detecting people in the general population at increased risk of covid-19 infection or being admitted to hospital with the disease. Design Living systematic review and critical appraisal by the COVID-PRECISE (Precise Risk Estimation to optimise covid-19 Care for Infected or Suspected patients in diverse sEttings) group. Data sources PubMed and Embase through Ovid, up to 1 July 2020, supplemented with arXiv, medRxiv, and bioRxiv up to 5 May 2020. Study selection Studies that developed or validated a multivariable covid-19 related prediction model. Data extraction At least two authors independently extracted data using the CHARMS (critical appraisal and data extraction for systematic reviews of prediction modelling studies) checklist; risk of bias was assessed using PROBAST (prediction model risk of bias assessment tool). Results 37 421 titles were screened, and 169 studies describing 232 prediction models were included. The review identified seven models for identifying people at risk in the general population; 118 diagnostic models for detecting covid-19 (75 were based on medical imaging, 10 to diagnose disease severity); and 107 prognostic models for predicting mortality risk, progression to severe disease, intensive care unit admission, ventilation, intubation, or length of hospital stay. The most frequent types of predictors included in the covid-19 prediction models are vital signs, age, comorbidities, and image features. Flu-like symptoms are frequently predictive in diagnostic models, while sex, C reactive protein, and lymphocyte counts are frequent prognostic factors. Reported C index estimates from the strongest form of validation available per model ranged from 0.71 to 0.99 in prediction models for the general population, from 0.65 to more than 0.99 in diagnostic models, and from 0.54 to 0.99 in prognostic models. All models were rated at high or unclear risk of bias, mostly because of non-representative selection of control patients, exclusion of patients who had not experienced the event of interest by the end of the study, high risk of model overfitting, and unclear reporting. Many models did not include a description of the target population (n=27, 12%) or care setting (n=75, 32%), and only 11 (5%) were externally validated by a calibration plot. The Jehi diagnostic model and the 4C mortality score were identified as promising models. Conclusion Prediction models for covid-19 are quickly entering the academic literature to support medical decision making at a time when they are urgently needed. This review indicates that almost all pubished prediction models are poorly reported, and at high risk of bias such that their reported predictive performance is probably optimistic. However, we have identified two (one diagnostic and one prognostic) promising models that should soon be validated in multiple cohorts, preferably through collaborative efforts and data sharing to also allow an investigation of the stability and heterogeneity in their performance across populations and settings. Details on all reviewed models are publicly available at https://www.covprecise.org/. Methodological guidance as provided in this paper should be followed because unreliable predictions could cause more harm than benefit in guiding clinical decisions. Finally, prediction model authors should adhere to the TRIPOD (transparent reporting of a multivariable prediction model for individual prognosis or diagnosis) reporting guideline. Systematic review registration Protocol https://osf.io/ehc47/, registration https://osf.io/wy245. Readers’ note This article is a living systematic review that will be updated to reflect emerging evidence. Updates may occur for up to two years from the date of original publication. This version is update 3 of the original article published on 7 April 2020 (BMJ 2020;369:m1328). Previous updates can be found as data supplements (https://www.bmj.com/content/369/bmj.m1328/related#datasupp). When citing this paper please consider adding the update number and date of access for clarity.

Virology, Epidemiology, Pathogenesis, and Control of COVID-19.

Abstract: The outbreak of emerging severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) disease (COVID-19) in China has been brought to global attention and declared a pandemic by the World Health Organization (WHO) on March 11, 2020. Scientific advancements since the pandemic of severe acute respiratory syndrome (SARS) in 2002~2003 and Middle East respiratory syndrome (MERS) in 2012 have accelerated our understanding of the epidemiology and pathogenesis of SARS-CoV-2 and the development of therapeutics to treat viral infection. As no specific therapeutics and vaccines are available for disease control, the epidemic of COVID-19 is posing a great threat for global public health. To provide a comprehensive summary to public health authorities and potential readers worldwide, we detail the present understanding of COVID-19 and introduce the current state of development of measures in this review.