Review of Transfer Learning Applied to Diagnosis of COVID-19

Since the outbreak of the coronavirus disease 2019 (COVID-19) epidemic, the number of infections and deaths caused by the epidemic has continued to increase due to its highly contagious nature. The best way to prevent outbreaks of COVID-19 in society is to detect it early in infection through methods such as reverse transcriptionpolymerase chain reaction (RT-PCR) test and manual examination. However, such laboratory procedures are inefficient, and radiologists'diagnosis of X-ray and CT images is time-consuming and prone to diagnostic errors. Researchers have proposed computer-aided diagnostic algorithms based on transfer learning, which can minimize the problems arising from traditional diagnostic methods. But there are few reviews on the application of transfer learning in the imaging of COVID-19. Therefore, this paper summarizes and analyzes the current research results on the diagnosis of COVID-19 based on transfer learning techniques at home and abroad. The model types are categorized and discussed, and six perspectives of dataset sources, data preprocessing methods, transfer learning based diagnostic models, model visualization, evaluation metrics, and model performance are analyzed and compared, respectively. The current challenges and future development directions are also pointed out, laying foundation for further research in the future. © 2023, Journal of Computer Engineering and Applications Beijing Co., Ltd.;Science Press. All rights reserved.

A privacy-preserving blockchain-based tracing model for virus-infected people in cloud

The outbreak of COVID-19 has exposed the privacy of positive patients to the public, which will lead to violations of users' rights and even threaten their lives. A privacy-preserving scheme involving virus-infected positive patients is proposed by us. The traditional ciphertext policy attribute-based encryption (CP-ABE) has the features of enhanced plaintext security and fine-grained access control. However, the encryption process requires the high computational performance of the device, which puts a high strain on resource-limited devices. After semi-honest users successfully decrypt the data, they will get the real private data, which will cause serious privacy leakage problems. Traditional cloud-based data management architectures are extremely vulnerable in the face of various cyberattacks. To address the above challenges, a verifiable ABE scheme based on blockchain and local differential privacy is proposed, using LDP to perturb the original data locally to a certain extent to resist collusion attacks, outsourcing encryption and decryption to corresponding service providers to reduce the pressure on mobile terminals, and deploying smart contracts in combination with blockchain for fair execution by all parties to solve the problem of returning wrong search results in a semi-honest cloud server. Detailed security proofs are performed through the defined security goals, which shows that the proposed scheme is indeed privacy-protective. The experimental results show that the scheme is optimized in terms of data accuracy, computational overhead, storage performance, and fairness. In terms of efficiency, it greatly reduces the local load, enhances personal privacy protection, and has high practicality as well as reliability. As far as we know, it is the first case of applying the combination of LDP technology and blockchain to a tracing system, which not only mitigates poisoning attacks on user data, but also improves the accuracy of the data, thus making it easier to identify infected contacts and making a useful contribution to health prevention and control efforts. © 2022 Elsevier Ltd

Dynamical characteristics of Amphan and its impact on COVID-19 cases in Bangladesh

In May 2020, a category-5 tropical cyclone (TC) Amphan formed in the Bay of Bengal and struck the coasts of India and Bangladesh. In this study, the relevant dynamic characteristics and aftermaths of Amphan are documented. Through detailed investigation of the reanalysis and observation data, spatiotemporal varying characteristics of the atmospheric and oceanic parameters during the Amphan propagation process were analyzed. Due to a wide range of high sea surface temperature anomaly, Amphan developed rapidly and ultimately led to the local heavy precipitation and strong winds in the coastal areas during its passage. It is also noted that the recorded wave height, wave period, and current speed all amplified when Amphan passed by and the characteristics of wave and current directions are also consistent with the temporal variation of the corresponding wind field. Meanwhile, Amphan occurred in accompany with the ongoing COVID-19 pandemic. In Khulna Division of Bangladesh, the number of newly confirmed COVID-19 cases increased rapidly after Amphan landing, which however was almost nil before the event, indicating there might exist a possible correlation between Amphan and the intensive outbreak of the local COVID-19, and particular attentions should be paid to deal with the multi-type, coexisting disasters if different or even conflicting measures are required. © 2023, The Author(s), under exclusive licence to Springer-Verlag GmbH Austria, part of Springer Nature.

The development and implementation of training mode for diabetes educators amid normalization stage of novel coronavirus pandemic prevention and control

Objective To develop an program for training diabetes educators amid normalization stage of novel coronavirus pandemic prevention and control, and provide reference for clinical teaching under special circumstances. Methods From January 2020 to June 2021, The head member of Diabetes Education and Management Committee of Hunan Health Management Association Xiangya Hospital of Central South University, developed and implemented a program based on core competencies of diabetes educators. It included 26 online courses, one to one education demonstration video with 7 themes, one diabetes conversation map and simulation, and three-week clinical practice. From April 2021 to June 2021, 55 health workers participated in the program. Theoretical tests, video feedback and questionnaires were used to evaluate the trainees′ diabetes knowledge, educational skills and satisfaction with the training program. Results A total of 55 health workers participated in the program. All the participants completed the online courses and passed the quizzes, the theoretical examination score was (92.93 ± 5.28). Fifty-four participants finished the tasks of clinical practice and obtained the certificate of diabetes educator. Their communication skills and strategies of behavior change were significantly improved (χ2 values were 4.17 - 26.34, all P＜0.05), and all of them were satisfied with the program. Conclusions The training mode based on online training is flexible, convenient and effective,which is suitable for stage of novel coronavirus pandemic prevention and control. © 2022 The authors.

An effective blended online Political teaching and learning strategy during the COVID-19 pandemic

The COVID-19 pandemic has led to new challenges for teachers and students in different countries. International scholars and researchers provide insight into the success of blended learning approaches that foster social and emotional connectedness, affective learning processes, feedback loops, cultural understanding and dialogue. This article will explore how a blended teaching strategy was developed during the COVID-19 pandemic that brings together web-based teaching with face-to-face interaction in order to support the resilience of students from different countries. Online teaching is used primarily for course materials and exams, but increasingly it is being used for other educational activities including helping people to recover from mental illness or disaster. Copyright © 2022 ThinkBiotech LLC. All rights reserved.

Enhancing Trust-based Medical Smartphone Networks via Blockchain-based Traffic Sampling

With more devices being inter- or intra-connected, Internet of Things (IoT) has gradually been adopted in many disciplines, such as healthcare industry, coined as Internet of Medical Things (IoMT). The purpose of IoMT is to facilitate the efficiency and effectiveness of medical operations, i.e., remotely monitoring the status of patients. In such healthcare environments, smartphones have become an important device to communicate with others and update the information of patients, resulting in a special type of IoMT called Medical Smartphone Networks (MSNs). To reinforce the distributed architecture, trust management schemes are often implemented to defend against insider attacks. However, how to maintain the robustness of trust management in heavy traffic networks still remains a challenge, i.e., COVID-19 incident would cause excessive traffic for healthcare organizations and increase the difficulty of validating trustworthiness among MSN nodes. In this work, we focus on this issue and propose a blockchain-enabled adaptive traffic sampling method to help enhance the robustness of trust management under high traffic environments. The use of blockchain technology aims to build a verified database of malicious traffic among all nodes. The evaluation in a real healthcare environment demonstrates the viability and effectiveness of our approach.

MLCT: A multi-level contact tracing scheme with strong privacy

With the outbreak of Covid-19, both people's health and the world economy are facing great challenges. Contact tracing scheme based on Bluetooth of smartphones has been regarded as a viable way to mitigate the spread of Covid-19. The existing schemes mainly belong to the centralized or the decentralized structure, both of which have their own limitations. It is infeasible for the existing schemes to balance the different demands of governments and users for user privacy and tracing efficiency at different periods of the epidemic. In this paper, we propose a hybrid contact tracing scheme named MLCT (multi-level contact tracing scheme) which is mainly based on short group signature. MLCT provides multiple privacy levels by applying anonymous credential technology and secret sharing technology to desensitize user identity privacy and encounter privacy. Comparing to the previous schemes, MLCT fully considers the different demands of the government, patients, and close contacts for user privacy and tracing efficiency in the different stages of Covid-19. The experimental results show viability in terms of the required resource from both server and mobile phone perspectives. And the security analysis demonstrates that MLCT can achieve the five targets security goals. It is expected that MLCT can contribute to the design and development of contact tracing schemes. © 2022 John Wiley & Sons, Ltd.

Adoptive Immune Responses to Sars-Cov2 Vaccination in CART19 Treated Patients

Background: The two FDA approved mRNA-based SARS-CoV2 vaccines have shown >90% efficacy at preventing COVID and eliciting protective immunity in nearly all healthy individuals. However, the extent of vaccine induced antibody and T cell immunity in immunocompromised patients is not well known. Our study objective is to determine if patients with hematologic malignancies treated with B-cell targeting chimeric antigen receptor (CAR) T cell therapies can mount antibody and T cell immune responses to SARS-CoV2 vaccines. A prospective single-center study to evaluate the SARS-CoV2 immune responses in immunocompromised individuals (COVAX Study) was initiated at University of Pennsylvania following the IRB guidelines. The study enrolled 8 healthy adults,12 patients are in remission after treatment (average of 40.6 months) with CART cells targeting either CD19 or CD19+CD22 and received both doses of SARS-CoV2 vaccine. Methods and Results: Serology to SARS-CoV2 spike-receptor binding domain (RBD) IgG, RBD-IgA, RBD-IgM and spike-specific T cell responses were measured prior to vaccination and serially up to 28 days after booster vaccination. RBD-IgG and RBD-IgA were detected in 8/8 and 7/8 healthy subjects compared to 5/12 and 2/12 CART patients, respectively (Figure A). In the CART cohort, several patients who demonstrated an induction of RBD-IgG (57.2/uL +/- 20.2) compared to those who were RBD-IgG-negative (9/uL +/- 10.1, ANOVA with multiple comparisons test p=0.017) have higher level of circulating B cells. No association was found with time since CART infusion, age, disease type, or vaccine manufacturer. All 8 healthy subjects demonstrated induction of SARS-Cov2 spike-specific CD4 + T cell immunity compared to 7 out of 11 CART patients (Figure B). RBD-IgG responses were not correlated with CD4 + T cell activation (Pearson correlation, R=0.21, p=0.53). Indeed, 3 CART patients demonstrated robust CD4 + T cell activation despite absence of antibody induction. Overall, 8/12 CART patients demonstrated induction of either or both humoral and T cell immune responses. Conclusions: We show that immune responses to SARS-CoV2 mRNA vaccines are induced in majority of patients who have been treated with CART therapies targeting B-cell lineage antigens. Induction of vaccine-specific antibody was strongly associated with the level of circulating B cells. However, in CART cohort patients despite severe humoral immune deficiency, strong CD4 + T cell responses were observed suggestive of a sufficient protective immunity. [Formula presented] Disclosures: Frey: Novartis: Research Funding;Sana Biotechnology: Consultancy;Kite Pharma: Consultancy;Syndax Pharmaceuticals: Consultancy. Garfall: Amgen: Honoraria;CRISPR Therapeutics: Research Funding;GlaxoSmithKline: Honoraria;Janssen: Honoraria, Research Funding;Novartis: Research Funding;Tmunity: Research Funding. Porter: American Society for Transplantation and Cellular Therapy: Honoraria;Genentech: Current equity holder in publicly-traded company, Ended employment in the past 24 months;ASH: Membership on an entity's Board of Directors or advisory committees;DeCart: Membership on an entity's Board of Directors or advisory committees;Incyte: Membership on an entity's Board of Directors or advisory committees;Janssen: Membership on an entity's Board of Directors or advisory committees;Kite/Gilead: Membership on an entity's Board of Directors or advisory committees;National Marrow Donor Program: Membership on an entity's Board of Directors or advisory committees;Novartis: Membership on an entity's Board of Directors or advisory committees, Patents & Royalties, Research Funding;Tmunity: Patents & Royalties;Wiley and Sons Publishing: Honoraria. June: AC Immune, DeCART, BluesphereBio, Carisma, Cellares, Celldex, Cabaletta, Poseida, Verismo, Ziopharm: Consultancy;Tmunity, DeCART, BluesphereBio, Carisma, Cellares, Celldex, Cabaletta, Poseida, Verismo, Ziopharm: Current equity holder in publicly-traded company;Novartis: Patents & Royalties.

Lag effect of temperature on the incidence of COVID-19 in Hunan province

Objective To explore the lag effect of daily average temperature on the incidence of coronavirus disease 2019 (COVID-19) in Hunan Province and to provide scientific evidences for effective prevention of COVID-19.  Methods  The meteorological factors, the air quality factors and the data conincidence of COVID-19 reported in Hunan Province during January 21, 2020 to March 2, 2020 were collected. Spearman correlation and distributed lag non-linear model analysis were performed.  Results  A total of 1 018 COVID-19 cases were reported in Hunan Province. The distribution lag non-linear model results showed that the influence of daily average temperature on the incidence of COVID-19 presented a nonlinear relationship. The cumulative relative incidence risk of COVID-19 decreased with the increase of daily average temperature, and the lowest temperature risk of the patients was 0 ℃. Both cold temperature and hot temperature increased incidence risk of COVID-19. It was indicated that the hot effects were immediate, however, the cold effects with obvious lag effect persisted up to 12 days. The highest relative risk of COVID-19 incidence was associated with lag 8-day daily average temperature of -5 ℃(RR=2.20, 95% CI=1.16-4.19). The influence of high temperature(10 ℃) was more significant than that of low temperature(6 ℃).  Conclusion  The daily average temperature, especially cold or hot temperature, was an important influencing factor of the incidence of COVID-19 in Hunan Province, which had lag influence on the incidence of COVID-19. We suggested that some related preventive measures should be adopted to protect vulnerable population and severe patients to reduce the incidence risk. © 2021, Publication Centre of Anhui Medical University. All rights reserved.

From a cotton bud to a pool of blood COVID-19 testing, a double-edged sword?

Introduction: Coronavirus Disease 2019 (COVID-19) testing has grown exponentially in the United States since the dawn of the pandemic, with the vast majority of samples being obtained via nasopharyngeal swab. Although convenient and widely used, the test itself carries potential adverse effects, particularly those at high risk of bleeding. We present a patient who developed several arrays of complications after being tested for COVID-19 using the nasal swab sampling technique. Case Presentation: An 80-yo female presented from home with a complaint of hematuria. Her past medical history includes rheumatic heart disease status post repair on warfarin, atrial fibrillation and stroke. Vital signs were normal. She had benign head and neck exam, clear lung sounds, an irregular heart rhythm and a normal abdominal exam. Labs were at baseline with hemoglobin of 10.4. Chest x-ray and CT abdomen were unremarkable. She received a PCR nasopharyngeal swab in the emergency room and subsequently developed profuse epistaxis. Initial nasal packing and Afrin sprays failed to control the bleeding and she required emergent intubation for airway protection. She also needed vasopressors due to hypotension. Repeat hemoglobin was 7.5 and lactic acid was 10.4. Bleeding eventually stopped after continuous nasal packing, transfusional support and IV vitamin K. In the following days, she developed fever, leukocytosis and lung infiltrates. She received empiric antibiotic coverage, although no growth from cultures. Endoscopy findings were consistent with ischemic colitis. Later, she stabilized hemodynamically but was unable to be liberated from the ventilator. She was discharge to a long-term care facility after 43 days of stay. Discussion: Nasopharyngeal swabs are the mainstay of testing for COVID-19, however, little has been discussed regarding its procedural risks. Common adverse effects include headaches, nasal pain, ear discomfort and rhinorrhea. Recent studies have suggested that the incidence of epistaxis can be as high as 10% after the test. Alternatively, multiple research centers, including Yale and University of Illinois have released promising data on saliva-based testing. Their evidence supported high sensitivity comparable to the nasopharyngeal method with simpler and safer nature. Also, the saliva-based testing can be done at home, which is believed to reduce healthcare cost and lower the risk of cross infection. This case vividly demonstrates that even the most common procedure can result in devastating outcomes. As such, health care providers should be cognizant of these complications and consider alternative testing method when possible.

Hybrid Emotion-aware Monitoring System based on Brainwaves for Internet of Medical Things

Driven by an increasing number of connected medical devices, Internet of Medical Things (IoMT), as an application of Internet of Things (IoT) in healthcare, is developed to help collect, analyze and transmit medical data. During the outbreak of pandemic like COVID-19, IoMT can be useful to monitor the status of patients and detect main symptoms remotely, by using various smart sensors. However, due to the lack of emotional care in current IoMT, it is still a challenge to reach an efficient medical process. Especially under COVID-19, there is a need to monitor emotion status among particular people like elderly. In this work, we propose an emotion-aware healthcare monitoring system in IoMT, based on brainwaves. With the fast development of EEG (electroencephalography) sensors in current headsets and some devices, brainwave-based emotion detection becomes feasible. The IoMT devices are used to capture the brainwaves of a patient in a scenario of smart home. Also, our system involves the analysis of touch behavior as the second layer to enhance the brainwave-based emotion recognition. In the user study with 60 participants, the results indicate the viability and effectiveness of our approach in detecting emotion like comfortable and uncomfortable, which can complement existing emotion-aware healthcare applications and mechanisms. IEEE

AN ISOLATED PLEURAL EFFUSION AS A SEQUELA OF COVID-19 INFECTION

SESSION TITLE: Fellows Chest Infections Posters SESSION TYPE: Fellow Case Report Posters PRESENTED ON: October 18-21, 2020 INTRODUCTION: Since December 2019, the coronavirus disease 2019 (COVID-19) outbreak has resulted in widespread transmission and death. Understanding how this viral pneumonia causes acute lung injury is evolving, but it typically manifests as peripheral bilateral ground glass on chest imaging. We report a unique case of a COVID-19 patient who presented with a new isolated left pleural effusion that is likely a sequela of the infection. CASE PRESENTATION: A 25-year-old female with no co-morbidities was seen in ED at another hospital for flu-like symptoms and found to have COVID-19. At that time, her chest radiograph showed hazy opacities overlying left greater than right lung lobes consistent with multifocal pneumonia. She was discharged home on doxycycline. Patient felt better following discharge but then presented to our hospital four weeks later with left sided pleuritic chest pain of two weeks duration. She denied any fever, cough, recent travel, or sick contacts. Vital signs were: T 99.4 F, HR 97, BP 109/76, RR 20, and 96 % O2 saturation on room air. Physical exam was significant for decreased air entry at left lung base. A comprehensive metabolic panel, complete blood count, troponins, BNP, and LDH were within normal limits. However, D-dimer was elevated. Both chest radiograph and CT chest angiogram showed a new moderate left pleural effusion, but in addition CT showed ground glass opacities in the left upper and right lower lung lobes noted on the CT. Patient was started on empiric antibiotics. Her symptoms improved after 700 cc of serous pleural fluid was drained via a pigtail catheter. Pleural fluid analysis showed an overtly exudative fluid with protein ratio of 0.74 and LDH ratio of 3.08 with fluid LDH of 719. Other pertinent fluid analysis revealed: pH 7.5, WBC 9744 with 60% neutrophils, with no organisms on gram stain or culture. Fluid cytology showed numerous acute and chronic inflammatory cells and few macrophages admixed with degenerated cells. Patient underwent repeat COVID-19 testing via the nasal swab and pleural fluid PCR, which were both negative. DISCUSSION: Pleural effusions can be related to diseases of the lungs and heart or to a systemic disease. To treat pleural effusions, it is important to determine the etiology. In this case, given the patient’s history of COVID-19 infection and exclusion of all other causes, the exudative predominantly neutrophilic pleural effusion most likely reflected a parapneumonic effusion. CONCLUSIONS: COVID-19 can present with non-specific imaging findings;however, to our knowledge, an isolated pleural effusion has not been reported in patients with COVID-19. Reference #1: McIntosh K, Hirsch Martin, Bloom A. Coronavirus disease 2019 (COVID-19): Clinical features and diagnosis. In: Post T, ed. UpToDate. Waltham, Mass.: UpToDate;2020. www.uptodate.com. Accessed May 31, 2020. Reference #2: Hani C et al. COVID-19 pneumonia: A review of typical CT findings and differential diagnosis. Diagn Interv Imaging. 2020;101(5): 263-268. doi: 10.1016/j.diii.2020.03.014 Reference #3: Bernheim A et al. Chest CT Findings in Coronavirus Disease-19 (COVID-19): Relationship to Duration of Infection. Radiology. 2020;295(3): 685-691. doi:10.1148/radiol.2020200463 DISCLOSURES: No relevant relationships by Sharath Bellary, source=Web Response No relevant relationships by Sudipa Chowdhury, source=Web Response No relevant relationships by William Meng, source=Web Response No relevant relationships by Richard Miller, source=Web Response No relevant relationships by SUMITANAND MISHRA, source=Web Response No relevant relationships by Rutwik Patel, source=Web Response No relevant relationships by Hari Sharma, source=Web Response

VINGT MILLE LIEUES SOUS LES MERS: A POISONOUS GUEST FROM THE BLUE SEA TOXIC INHALATION OF CORAL PALYTOXIN

SESSION TITLE: Fellows Chest Infections Posters SESSION TYPE: Fellow Case Report Posters PRESENTED ON: October 18-21, 2020 INTRODUCTION: From Raja Ampat, Indonesia to the Red Sea of Indian Ocean, marine corals have attracted myriad of divers and hobbyists around the world with their rainbow-like colors, assorted shapes and unique symbiotic roles. However, certain species contain some of the deadliest toxins known to human that can subject handlers to health problems and even life-threatening conditions. We report a case of Palythoa coral exposure induced respiratory failure. CASE PRESENTATION: A 44-year-old man with childhood asthma presented to the emergency room with sudden onset of shortness of breath. His symptoms started one hour prior to his arrival and included chills, dyspnea, chest tightness, pleuritic pain and nausea. Further questioning revealed that our patient was cleaning some Palythoa sp. corals out from his saltwater aquarium two hours before he fell sick. He ran a piece of coral over hot water to kill it. It emitted a strong foul odor immediately afterwards. He had never attempted such cleaning process before. He was not wearing any protective equipment but denied using any cleaning chemicals. There was no other pertinent history. Initial vital signs included heart rate of 117, respiratory rate of 28 bpm, blood pressure 123/59, and oxygen saturation of 97% on 75%, 40 liters/min High-Flow Nasal Canula. He was in mild distress. Auscultation revealed decreased bilateral air entry, faint wheezing and mild apical rales. Cardiac, abdominal and neurological exams were otherwise benign. ABG showed pH of 7.42, PaCO2 41, PaO2 52 and HCO3 26. Chest CT revealed diffuse centrilobular ground-glass opacities in an upper-lobe-predominant distribution. Lab studies were significant for lactic acid of 3.4, troponin of 0.44 and BNP at 666 pg/ml. CRP was 293 mg/L and procalcitonin of 15. WBC was 27.3 with 85% neutrophils without eosinophilia. Complete septic workups including atypical pneumonia pathogens, HIV and COVID-19 were negative. Patient’s symptoms subsequently improved with nebulized albuterol treatments, IV steroids and supplemental oxygen. He remained on regular floor with intent for discharge in the following days. DISCUSSION: Palytoxin (PTX), originally described in a Hawaiian legend, is an extremely poisonous substance synthesized by certain species of corals and dinoflagellates. Its lethal power stems from the ability of inactivating the sodium/potassium ATPase pump, thereby destroying cellular ion gradient. Ensuing cardiac, respiratory, renal and hematologic dysfunctions have been observed. Fewer than 300 cases were ever reported worldwide. Most were due to ingestion of contaminated fish, though dermal and inhalational exposure, such as our patient, have been documented. CONCLUSIONS: It thus becomes necessary to take PTX poisoning into consideration, whenever compatible history is provided. While in vitro and in vivo animal studies have been conducted, there is no known antidote. Management is usually supportive. Reference #1: Hamade AK, Deglin SE, McLaughlin JB, et al. Suspected Palytoxin Inhalation Exposures Associated with Zoanthid Corals in Aquarium Shops and Homes - Alaska, 2012-2014. MMWR Morb Mortal Wkly Rep 2015;64:852. Reference #2: Ramos V, Vasconcelos V. Palytoxin and analogs: biological and ecological effects. Mar Drugs. 2010;8(7):2021-2037. Published 2010 Jun 30. doi:10.3390/md8072021 Reference #3: Thakur LK, Jha KK. Palytoxin-induced acute respiratory failure. Respir Med Case Rep. 2016;20:4-6. Published 2016 Oct 21. doi:10.1016/j.rmcr.2016.10.014 DISCLOSURES: No relevant relationships by Mourad Ismail, source=Web Response No relevant relationships by TAWFIQ KARADSHEH, source=Web Response No relevant relationships by William Meng, source=Web Response No relevant relationships by Richard Miller, source=Web Response No relevant relationships by Roberto Solis, source=Web Response No relevant relationships by Yasmeen Sultana, source=Web Response no disclosure on file for Qizhi Wang