Your browser doesn't support javascript.
Show: 20 | 50 | 100
Results 1 - 20 de 31
Filter
Add filters

Journal
Year range
1.
International Joint Conference on Neural Networks (IJCNN) ; 2021.
Article in English | Web of Science | ID: covidwho-1612803

ABSTRACT

Federated Learning (FL) creates an ecosystem for multiple agents to collaborate on building models with data privacy consideration. The method for contribution measurement of each agent in the FL system is critical for fair credits allocation but few are proposed. In this paper, we develop a real-time contribution measurement method FedCM that is simple but powerful. The method defines the impact of each agent, comprehensively considers the current round and the previous round to obtain the contribution rate of each agent with attention aggregation. Moreover, FedCM updates contribution every round, which enable it to perform in real-time. Real-time is not considered by the existing approaches, but it is critical for FL systems to allocate computing power, communication resources, etc. Compared to the state-of-the-art method, the experimental results show that FedCM is more sensitive to data quantity and data quality under the premise of real-time. Furthermore, we developed federated learning open-source software based on FedCM. The software has been applied to identify COVID-19 based on medical images.

2.
Nature Machine Intelligence ; 3(12):1081-1089, 2021.
Article in English | Web of Science | ID: covidwho-1585763

ABSTRACT

Artificial intelligence provides a promising solution for streamlining COVID-19 diagnoses;however, concerns surrounding security and trustworthiness impede the collection of large-scale representative medical data, posing a considerable challenge for training a well-generalized model in clinical practices. To address this, we launch the Unified CT-COVID AI Diagnostic Initiative (UCADI), where the artificial intelligence (AI) model can be distributedly trained and independently executed at each host institution under a federated learning framework without data sharing. Here we show that our federated learning framework model considerably outperformed all of the local models (with a test sensitivity/specificity of 0.973/0.951 in China and 0.730/0.942 in the United Kingdom), achieving comparable performance with a panel of professional radiologists. We further evaluated the model on the hold-out (collected from another two hospitals without the federated learning framework) and heterogeneous (acquired with contrast materials) data, provided visual explanations for decisions made by the model, and analysed the trade-offs between the model performance and the communication costs in the federated training process. Our study is based on 9,573 chest computed tomography scans from 3,336 patients collected from 23 hospitals located in China and the United Kingdom. Collectively, our work advanced the prospects of utilizing federated learning for privacy-preserving AI in digital health. The COVID-19 pandemic sparked the need for international collaboration in using clinical data for rapid development of diagnosis and treatment methods. But the sensitive nature of medical data requires special care and ideally potentially sensitive data would not leave the organization which collected it. Xiang Bai and colleagues present a privacy-preserving AI framework for CT-based COVID-19 diagnosis and demonstrate it on data from 23 hospitals in China and the United Kingdom.

3.
Preprint in English | PUBMED | ID: ppcovidwho-293214

ABSTRACT

Artificial intelligence (AI) provides a promising substitution for streamlining COVID-19 diagnoses. However, concerns surrounding security and trustworthiness impede the collection of large-scale representative medical data, posing a considerable challenge for training a well-generalised model in clinical practices. To address this, we launch the Unified CT-COVID AI Diagnostic Initiative (UCADI), where the AI model can be distributedly trained and independently executed at each host institution under a federated learning framework (FL) without data sharing. Here we show that our FL model outperformed all the local models by a large yield (test sensitivity /specificity in China: 0.973/0.951, in the UK: 0.730/0.942), achieving comparable performance with a panel of professional radiologists. We further evaluated the model on the hold-out (collected from another two hospitals leaving out the FL) and heterogeneous (acquired with contrast materials) data, provided visual explanations for decisions made by the model, and analysed the trade-offs between the model performance and the communication costs in the federated training process. Our study is based on 9,573 chest computed tomography scans (CTs) from 3,336 patients collected from 23 hospitals located in China and the UK. Collectively, our work advanced the prospects of utilising federated learning for privacy-preserving AI in digital health.

4.
Preprint in English | PUBMED | ID: ppcovidwho-292843

ABSTRACT

Artificial intelligence (AI) provides a promising substitution for streamlining COVID-19 diagnoses. However, concerns surrounding security and trustworthiness impede the collection of large-scale representative medical data, posing a considerable challenge for training a well-generalised model in clinical practices. To address this, we launch the Unified CT-COVID AI Diagnostic Initiative (UCADI), where the AI model can be distributedly trained and independently executed at each host institution under a federated learning framework (FL) without data sharing. Here we show that our FL model outperformed all the local models by a large yield (test sensitivity /specificity in China: 0.973/0.951, in the UK: 0.730/0.942), achieving comparable performance with a panel of professional radiologists. We further evaluated the model on the hold-out (collected from another two hospitals leaving out the FL) and heterogeneous (acquired with contrast materials) data, provided visual explanations for decisions made by the model, and analysed the trade-offs between the model performance and the communication costs in the federated training process. Our study is based on 9,573 chest computed tomography scans (CTs) from 3,336 patients collected from 23 hospitals located in China and the UK. Collectively, our work advanced the prospects of utilising federated learning for privacy-preserving AI in digital health.

5.
Preprint in English | PUBMED | ID: ppcovidwho-292827

ABSTRACT

The recent outbreak of the severe acute respiratory syndrome coronavirus-2 (SARS-CoV-2), which causes coronavirus disease 2019 (COVID-19), has led to a worldwide pandemic. One week after initial symptoms develop, a subset of patients progresses to severe disease, with high mortality and limited treatment options. To design novel interventions aimed at preventing spread of the virus and reducing progression to severe disease, detailed knowledge of the cell types and regulating factors driving cellular entry is urgently needed. Here we assess the expression patterns in genes required for COVID-19 entry into cells and replication, and their regulation by genetic, epigenetic and environmental factors, throughout the respiratory tract using samples collected from the upper (nasal) and lower airways (bronchi). Matched samples from the upper and lower airways show a clear increased expression of these genes in the nose compared to the bronchi and parenchyma. Cellular deconvolution indicates a clear association of these genes with the proportion of secretory epithelial cells. Smoking status was found to increase the majority of COVID-19 related genes including ACE2 and TMPRSS2 but only in the lower airways, which was associated with a significant increase in the predicted proportion of goblet cells in bronchial samples of current smokers. Both acute and second hand smoke were found to increase ACE2 expression in the bronchus. Inhaled corticosteroids decrease ACE2 expression in the lower airways. No significant effect of genetics on ACE2 expression was observed, but a strong association of DNA- methylation with ACE2 and TMPRSS2- mRNA expression was identified in the bronchus.

6.
American Journal of Gastroenterology ; 116(SUPPL):S149-S150, 2021.
Article in English | EMBASE | ID: covidwho-1534641

ABSTRACT

Introduction: Clinical trials often have low enrollment of minorities, particularly African-Americans (AAs), which may limit the generalizability of research findings. Previously identified barriers to AAs recruitment include historical abuses leading to mistrust, communication issues with providers, socio-economic factors, and a lack of access to clinical trials. In a Historically Black College and University (HBCU) serving a primarily AA population at a large safe-net hospital, we evaluated the enrollment of eligible AA patients for a colorectal cancer (CRC) screening clinical trial. This was compared to the enrollment rates across other study sites. Methods: A large, prospective, multi-centered clinical trial to validate a blood-based test for early detection of CRC (PREEMPT-CRC) was initiated at a HBCU, where 84% of patients are AAs. To maximize study recruitment, culturally sensitive methods were employed including racially congruent recruitment staff as well as synchronized timing of consent/study procedures with preendoscopy COVID testing/clinic visits. Detailed information for all eligible subjects was recorded. Demographic and socio-economic data including census information for enrolled and not enrolled subjects were compared. The enrollment rate (defined as enrolled/eligible patients) over the first 6 weeks at the HBCU and that of the other study sites providing screening logs was analyzed. Results: The enrollment rate at the HBCU was 55% (44 out of 80 eligible patients;95% CI 43.5- 66.2%), compared to 49.8% (258 out of 518 eligible patients;95% CI 45.4- 54.2%) at the other 26 study sites. While age and gender of enrolled patients at the HBCU were comparable to other sites, the main difference was race: at the HBCU the study participants were 79.5% AAs and 9.1% whites, while at the other sites the participants were 11.5% AAs and 82.8% whites (p< 0.001). At the HBCU, the demographic characteristics and socio-demographic data including income, marital status insurance status/type, and census tract median household income of the 44 enrolled and 36 notenrolled subjects were similar (Table 1). Conclusion: Contrary to conventional belief that AAs do not want to be involved in clinical trials, we find their enrollment is similar to a predominant white study population when offered the opportunity in a culturally sensitive setting. Future trials should consider including HBCU sites in order to attain adequate AA enrollment to improve the generalizability of research findings. (Table Presented).

7.
40th IEEE Conference on Computer Communications (IEEE INFOCOM) ; 2021.
Article in English | Web of Science | ID: covidwho-1522583

ABSTRACT

Coronavirus disease 2019 (COVID-19) has resulted in an ongoing pandemic. Since COVID-19 spreads mainly via close contact among people, social distancing has become an effective manner to slow down the spread. However, completely forbidding close contact can also lead to unacceptable damage to the society. Thus, a system that can effectively monitor people's social distance and generate corresponding alerts when a high infection probability is detected is in urgent need. In this paper, we propose SmartDistance, a smartphone based software framework that monitors people's interaction in an effective manner, and generates a reminder whenever the infection probability is high. Specifically, SmartDistance dynamically senses both the relative distance and orientation during social interaction with a well-designed relative positioning system. In addition, it recognizes different events (e.g., speaking, coughing) and determines the infection space through a droplet transmission model. With event recognition and relative positioning, SmartDistance effectively detects risky social interaction, generates an alert immediately, and records the relevant data for close contact reporting. We prototype SmartDistance on different Android smartphones, and the evaluation shows it reduces the false positive rate from 33% to 1% and the false negative rate from 5% to 3% in infection risk detection.

8.
Chinese Journal of New Drugs ; 30(19):1768-1774, 2021.
Article in Chinese | EMBASE | ID: covidwho-1473128

ABSTRACT

As the first mRNA-based COVID-19 vaccine received Emergency Use Authorization (EUA) in 2020, its great safety profile and high protection efficacy has been well demonstrated. As a result of its unique advantage in the mechanism of action, mRNA can effectively trigger strong humoral and cellular immune response. Of note, many other prophylactic or therapeutic mRNA vaccines developed for preventing different infectious diseases or treatment of cancer are under clinical trial investigations. mRNA-based protein supplementation and gene therapy also begin to emerge. There will be bigger stage for the development of mRNA technology-based products, posing a revolutionary effect in the field of biopharmaceuticals.

11.
Indoor and Built Environment ; 2021.
Article in English | EMBASE | ID: covidwho-1458132

ABSTRACT

The global spread of the coronavirus disease 2019 (COVID-19) has increased the demand of effective control of the disease transmission between people, especially when they are in close distance between each other. The microenvironment between the people in short distance contains multiple airflow patterns that directly affect the disease transmission. By understanding and respecting this special localized environment, the airborne cross-infection at both short and long distance can be minimized. This paper gives an overview of the flow fields in human microenvironment. The exhalation flow from different respiratory activities, e.g. normal breathing, speaking, coughing or sneezing is considered as a part of the microenvironment. The dynamics of the exhalation flow and the contained droplets or aerosols are summarized from previous studies. The factors influencing the flow fields in human microenvironment are discussed, including both the physiological factors of the occupants and the environmental factors in the ventilated context (macroenvironment). Effective control of these influencing factors can be helpful to mitigate airborne transmission risk between individuals. This paper highlights the importance of better understanding of the dynamics and transmission routes of the expelled virus-laden droplets or aerosols, which are largely affected by complex flow interactions in human microenvironment.

12.
3rd EAI International Conference on Multimedia Technology and Enhanced Learning, ICMTEL 2021 ; 388:331-337, 2021.
Article in English | Scopus | ID: covidwho-1446002

ABSTRACT

To investigate the relationship between emotional status and physical activity in adolescents during the epidemic period of Corona Virus Disease 2019. 600 junior and senior high school students from three municipal middle schools were randomly selected as the research objects. The self-evaluation of anxiety and depression and the evaluation of physical activity were carried out in the form of questionnaire survey. A total of 600 questionnaires were put in and 562 were recovered. The scores of SDS and SAS were 49.30 ± 7.02, and 53.42 ± 5.37 respectively. According to different age groups, there was significant difference in SAS among the three groups in different age groups (P <0.05). The total score of PA was (3.24 ± 0.98). According to different age groups, there were significant differences in PA total score, MVPA activities, physical education activities, weekend activities and one week total activities among the three groups (P <0.05). The total score of anxiety was negatively correlated with the total score of PA (r = −0.54, P = 0.024), MVPA (r = −0.38, P = 0.049) and physical education (r = −0.62, P = 0.016), and the total score of one week was negatively correlated (r = −0.44, P = 0.041). During the period of Corona Virus Disease 2019 epidemic, the anxiety level of adolescents increases with age, while the physical activity status decreases gradually, and is negatively correlated with anxiety. It is necessary to strengthen sports activities and protect emotional health in this special period. © 2021, ICST Institute for Computer Sciences, Social Informatics and Telecommunications Engineering.

13.
Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies ; 5(3), 2021.
Article in English | Scopus | ID: covidwho-1438132

ABSTRACT

Using wireless signals to monitor human vital signs, especially heartbeat information, has been intensively studied in the past decade. This non-contact sensing modality can drive various applications from cardiac health, sleep, and emotion management. Under the circumstance of the COVID-19 pandemic, non-contact heart monitoring receives increasingly market demands. However, existing wireless heart monitoring schemes can only detect limited heart activities, such as heart rate, fiducial points, and Seismocardiography (SCG)-like information. In this paper, we present CardiacWave to enable a non-contact high-definition heart monitoring. CardiacWave can provide a full spectrum of Electrocardiogram (ECG)-like heart activities, including the details of P-wave, T-wave, and QRS complex. Specifically, CardiacWave is built upon the Cardiac-mmWave scattering effect (CaSE), which is a variable frequency response of the cardiac electromagnetic field under the mmWave interrogation. The CardiacWave design consists of a noise-resistant sensing scheme to interrogate CaSE and a cardiac activity profiling module for extracting cardiac electrical activities from the interrogation response. Our experiments show that the CardiacWave-induced ECG measures have a high positive correlation with the heart activity ground truth (i.e., measurements from a medical-grade instrument). The timing difference of P-waves, T-waves, and QRS complex is 0.67%, 0.71%, and 0.49%, respectively, and a mean cardiac event difference is within a delay of 5.3 milliseconds. These results indicate that CaridacWave offers high-fidelity and integral heart clinical characteristics. Furthermore, we evaluate the CardiacWave system with participants under various conditions, including heart and breath rates, ages, and heart habits (e.g., tobacco use). © 2021 ACM.

14.
Pharmacoepidemiology and Drug Safety ; 30:79-80, 2021.
Article in English | Web of Science | ID: covidwho-1381622
15.
Jundishapur Journal of Microbiology ; 14(2), 2021.
Article in English | EMBASE | ID: covidwho-1359387

ABSTRACT

Introduction: Mycobacterium mucogenicum belongs to the rapidly growing mycobacteria, and it is a rare conditional pathogen. Although recent studies suggested that the incidence of M. mucogenicum infection was increased worldwide, there are no case reports of M. mucogenicum and Klebsiella pneumoniae pulmonary infection. Case Presentation: A 32-year-old non-smoking male was diagnosed with congenital atrial septal defect and pulmonary arterial hypertension. After cardiac surgery, lung infections were observed in the patient and then rapidly developed acute respiratory distress syndrome. The cefoperazone and sulbactam, vancomycin, ceftazidime, carbapenem, tigecycline, and micafungin were used for the treatment of pulmonary infection but did not affect. Ultimately, M. mucogenicum and K. pneumoniae were identified as pathogens by using next-generation sequencing. The patient was treated successfully with the administration of clarithromycin, linezolid, tigecycline, and ceftazidime-avibactam. The clinical outcome of this patient was favorable without relapse of infection. Conclusions: This case demonstrates that M. mucogenicum pulmonary infection may result in severe outcomes. The next-generation sequencing technology is important for the identification of M. mucogenicum. Additionally, the clinicians and clinical pharmacists should remain awareness in dealing with M. mucogenicum infection to avoid delaying appropriate treatment.

16.
Asian Journal of Gerontology and Geriatrics ; 16(1):56, 2021.
Article in English | Scopus | ID: covidwho-1341941
17.
China Cdc Weekly ; 3(2):21-24, 2021.
Article in English | Web of Science | ID: covidwho-1340002

ABSTRACT

What is already known about this topic? The World Health Organization has estimated the impact of reductions in the performance of global tuberculosis (TB) detection and care on TB deaths. However, the actual impact of COVID-19 pandemic on TB deaths in China remains unclear. What is added by this report? The stringent public interventions to fight COVID-19 including lockdown led to more than 20% decrease of TB detection in China. It was predicted that the reduction of TB detection might result in 11,700 excess deaths based on assumption of no detection rebound. Based on the prediction the total deaths will be 51,100 in 2020 which might surpass the deaths in 2011. What are the implications for public health practice? Rapid restoration of TB diagnosis and care services is critical for minimizing the potential effects on TBrelated deaths and bringing TB burden back to control. It is urgent to ramp up case detection including active case finding and to provide an uninterrupted supply of quality-assured treatment and care for TB cases in postCOVID-19 outbreak.

18.
2021 International Conference on Management of Data, SIGMOD 2021 ; : 2389-2393, 2021.
Article in English | Scopus | ID: covidwho-1299242

ABSTRACT

The eruption of a pandemic, such as COVID-19, can cause an unprecedented global crisis. Contact tracing, as a pillar of communicable disease control in public health for decades, has shown its effectiveness on pandemic control. Despite intensive research on contact tracing, existing schemes are vulnerable to attacks and can hardly simultaneously meet the requirements of data integrity and user privacy. The design of a privacy-preserving contact tracing framework to ensure the integrity of the tracing procedure has not been sufficiently studied and remains a challenge. In this paper, we propose P2B-Trace, a privacy-preserving contact tracing initiative based on blockchain. First, we design a decentralized architecture with blockchain to record an authenticated data structure of the user's contact records, which prevents the user from intentionally modifying his local records afterward. Second, we develop a zero-knowledge proximity verification scheme to further verify the user's proximity claim while protecting user privacy. We implement P2B-Trace and conduct experiments to evaluate the cost of privacy-preserving tracing integrity verification. The evaluation results demonstrate the effectiveness of our proposed system. © 2021 ACM.

19.
Micromachines ; 12(4):14, 2021.
Article in English | MEDLINE | ID: covidwho-1209541

ABSTRACT

A rapid, sensitive and simple microflow cytometry-based agglutination immunoassay (MCIA) was developed for point-of-care (POC) quantitative detection of SARS-CoV-2 IgM and IgG antibodies. The antibody concentration was determined by using the transit time of beads aggregates. A linear relationship was established between the average transit time and the concentration of SARS-CoV-2 IgM and IgG, respectively. The limit of detection (LOD) of SARS-CoV-2 IgM and IgG by the MCIA measurement are 0.06 mg/L and 0.10 mg/L, respectively. The 10 microL sample consumption, 30 min assay time and the compact setup make this technique suitable for POC quantitative detection of SARS-CoV-2 antibodies.

20.
Cancer Research ; 81(4 SUPPL), 2021.
Article in English | EMBASE | ID: covidwho-1186410

ABSTRACT

Background The outbreak of COVID-19 pandemic in China has greatly impacted the radiotherapy (RT) strategy forbreast cancer (BC) patients, which might lead to an increased distressing psychological symptom. Thus, we performa multi-center cross-section survey aiming to investigate the prevalence of fears of cancer recurrence (FCR) andexplore predictors for FCR in BC patients referred for RT during pandemic. Methods: 542 BC patients who referredfor RT between 24 Jan and 30 April 2020 during pandemic were consecutively enrolled from 14 hospitals aroundChina including Yangtze Delta River Region, Guangdong and Shanxi province. Patients' sociodemographic,treatment information as well as psychological characteristics were collected using an information sheet, Fear ofprogression questionnaire-short form (FoP-Q-SF), Hospital Anxiety and Depression Scale ( HADS) and EORTCQLQ-C30. The influence of pandemic on RT schedule was divided into four categories: “delay” was defined as >12weeks from surgery to RT in patients without chemotherapy or >8 weeks from last time of anti-tumor therapy(including chemotherapy and surgery) to RT in patients with chemotherapy;“Special normal” was defined thatpatients themselves believed to have delayed RT initiation but actually not;“Interruption” was defined as anyunplanned gaps in original RT regime and all other would be classified into “normal”. Another type of influence on th th Advertisement RT strategy was that patients had to shift planned RT hospital from Grade-A tertiary hospital to local hospitals.Univariable analyses of FCR were performed in a one-way analysis of variance (ANOVA) or student t-test orPearson correlation analyses and candidate variables with P<0.2 were included Hierarchical multiple regressionmodels to investigate predictors for FCR. Guangdong province was chosen as reference in models. Results 488patients with complete data were eligible for the present analysis and none of patients and their family members hadbeen diagnosed as COVID-19. The RT strategy was affected in 265 (54.3%) patients, including 143 with delayed RTinitiation, 66 with “special normal” schedule, 24 (4.9%) with RT interruptions, 19 shifting to local hospitals for RT, andthe remaining 13 being influenced on both RT schedule and planned RT hospitals. Most of patients with affected RTstrategy occurred in late January and February, when was peak of COVID-19 pandemic in China. The mean FCRscores was 24.83 (SD=8.554) and 84 patients (17.3%) were classified as dysfunctional level of FCR (sum score≥34). In univariable analyses, FCR were significantly higher in patients who received RT in Guangdong provinceand in hospitals with < 100 BC cases per year. In term of during pandemic, a significant difference in FCR wasobserved in terms of influence on RT schedule (p<0.001). and changes of hospital levels(p=0.009). There weresignificant correlations between FCR and anxiety/depressive in HADS or all five function scales (physical, role,emotional, cognitive and social) and global QoL in QLQ-C30 (p<0.001). Finally, the model explained 59.7% ofobserved variances in FCR and showed that influence of RT strategy during pandemic had significantly impacted onFCR (ΔR2=0.01, ΔF=2.966, p=0.019). Hospitals in Shanxi province (β=-0.117, p=0.001), emotional function(β=-0.19, p<0.001), social function (β=-0.111, p=0.006), anxiety (β=0.434, p<0.001) and RT interruption (β=0.071,p=0.035) were independent predictors for FCR. Conclusions RT strategy for BC patients was greatly influencedduring pandemic. RT interruption is an independent predictor for high FCR. Our findings emphasize the necessity toensure the continuum of RT in BC patients, and efforts should be taken to alleviate the FCR through psychologicalinterventions.

SELECTION OF CITATIONS
SEARCH DETAIL
...