Deep-Learning Approach to Predict Survival Outcomes Using Wearable Actigraphy Device Among End-Stage Cancer Patients.

Survival prediction is highly valued in end-of-life care clinical practice, and patient performance status evaluation stands as a predominant component in survival prognostication. While current performance status evaluation tools are limited to their subjective nature, the advent of wearable technology enables continual recordings of patients' activity and has the potential to measure performance status objectively. We hypothesize that wristband actigraphy monitoring devices can predict in-hospital death of end-stage cancer patients during the time of their hospital admissions. The objective of this study was to train and validate a long short-term memory (LSTM) deep-learning prediction model based on activity data of wearable actigraphy devices. The study recruited 60 end-stage cancer patients in a hospice care unit, with 28 deaths and 32 discharged in stable condition at the end of their hospital stay. The standard Karnofsky Performance Status score had an overall prognostic accuracy of 0.83. The LSTM prediction model based on patients' continual actigraphy monitoring had an overall prognostic accuracy of 0.83. Furthermore, the model performance improved with longer input data length up to 48 h. In conclusion, our research suggests the potential feasibility of wristband actigraphy to predict end-of-life admission outcomes in palliative care for end-stage cancer patients. Clinical Trial Registration: The study protocol was registered on ClinicalTrials.gov (ID: NCT04883879).

A proposed artificial intelligence workflow to address application challenges leveraged on algorithm uncertainty.

Artificial Intelligence (AI) has achieved state-of-the-art performance in medical imaging. However, most algorithms focused exclusively on improving the accuracy of classification while neglecting the major challenges in a real-world application. The opacity of algorithms prevents users from knowing when the algorithms might fail. And the natural gap between training datasets and the in-reality data may lead to unexpected AI system malfunction. Knowing the underlying uncertainty is essential for improving system reliability. Therefore, we developed a COVID-19 AI system, utilizing a Bayesian neural network to calculate uncertainties in classification and reliability intervals of datasets. Validated with four multi-region datasets simulating different scenarios, our approach was proved to be effective to suggest the system failing possibility and give the decision power to human experts in time. Leveraging on the complementary strengths of AI and health professionals, our present method has the potential to improve the practicability of AI systems in clinical application.

Relationship between meteorological factors, air pollutants and hand, foot and mouth disease from 2014 to 2020 (preprint)

Background: Meteorological factors and air pollutants have been reported to be associated with hand, foot, and mouth disease (HFMD) epidemics before the introduction of vaccine. However, there is limited evidence from studies with long-term dimensions.Methods: We collected the daily HFMD counts, weather and air pollution data from 2014 to 2020 in Chengdu. Distributed lag non-linear models (DLNM) were used to assess the associations of meteorological factors and air pollutants on HFMD cases. Results: From 2014-2020, high relative humidity and precipitation and extremely high and low levels of PM10, O3, SO2 and CO increased the risk of HFMD. In pre-vaccination period, extreme high and low temperatures, PM10 and NO2, low precipitation and high concentrations of PM2.5 and O3 significantly increase the risk of HFMD; In post-vaccination period, low temperature and high relative humidity, O3, NO2 and CO can significantly increase the incidence of HFMD; During the period of COVID-19, only low temperature will significantly increase the risk of HFMD; Low concentration of air pollutants has the greatest impact on the 6-14 age group, while the high concentration of air pollutants has the greatest impact on the 0-1 age group.Conclusions: Our study suggest that high relative humidity and precipitation and extremely high and low levels of PM10, O3, SO2 and CO increased the risk of HFMD from 2014 to 2020. The results of this study provide a reference for local authorities to formulate intervention measures and establish an environment-based disease early warning system.

A novel self-learning semi-supervised deep learning network to detect fake news on social media.

Social media has become a popular means for people to consume and share news. However, it also enables the extensive spread of fake news, that is, news that deliberately provides false information, which has a significant negative impact on society. Especially recently, the false information about the new coronavirus disease 2019 (COVID-19) has spread like a virus around the world. The state of the Internet is forcing the world's tech giants to take unprecedented action to protect the "information health" of the public. Despite many existing fake news datasets, comprehensive and effective algorithms for detecting fake news have become one of the major obstacles. In order to address this issue, we designed a self-learning semi-supervised deep learning network by adding a confidence network layer, which made it possible to automatically return and add correct results to help the neural network to accumulate positive sample cases, thus improving the accuracy of the neural network. Experimental results indicate that our network is more accurate than the existing mainstream machine learning methods and deep learning methods.

The psychological states of people after Wuhan eased the lockdown.

It has been two months since Wuhan eased the lockdown and the people of Wuhan have been under great pressure during COVID-19. The psychological status among healthcare workers and residents were barely know due to the lack of research after Wuhan eased of the lockdown. The purpose of this study was to assess people's mental health and the changes after Wuhan eased the lockdown. A cross-sectional online study among citizens in Wuhan was conducted. Among 1417 participants, 387(27.0%) were frontline healthcare workers and 1035(73.0%) were residents from the general public. Their COVID-19 psychological status was evaluated using Patient Health Questionnaire-9(PHQ-9), Generalized Anxiety Disorder 7-item (GAD-7), and the PTSD Checklist-Civilian Version (PCL-C). Results show that 16.1%,22.3% and 17.2% healthcare workers and 21.2%, 16.7% and 17.2% general public had symptoms of depression, anxiety and PTSD ranging from moderate to severe. Anxiety levels were not significantly different between healthcare workers and the general public. The decreased income and the frequent social media exposure are the risk factors for general public. Compared to the early COVID-19 epidemic period, the proportion of anxiety and depression among both the general public and health workers decreased after Wuhan eased the lockdown. Our finding can be used to help the government of Wuhan to develop psychological interventions to improve the mental health of the population and work as a reference of public health guidelines for other cities with severe COVID-19 outbreak.

Strategies and key points of perioperative management of coronavirus disease 2019 patients

Coronavirus disease 2019 (COVID-19) has become a pandemic threatening public health. Its pathogen, severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2), can be transmitted from person to person through droplets, contact and other ways. How to avoid further spread of the virus when patients with suspected or confirmed COVID-19 receive treatment in the operating rooms or intensive care units has become the focus and difficulty faced by medical staff. Here we discussed the dissemination characteristics of SARS-CoV-2, the perioperative environments, the disease management and infection control measures under specific operation.

Factors Associated with Mental Health Results among Workers with Income Losses Exposed to COVID-19 in China.

The outbreak and worldwide spread of COVID-19 has resulted in a high prevalence of mental health problems in China and other countries. This was a cross-sectional study conducted using an online survey and face-to-face interviews to assess mental health problems and the associated factors among Chinese citizens with income losses exposed to COVID-19. The degrees of the depression, anxiety, insomnia, and distress symptoms of our participants were assessed using the Chinese versions of the Patient Health Questionnaire-9 (PHQ-9), the Generalized Anxiety Disorder-7 (GAD-7), the Insomnia Severity Index-7 (ISI-7), and the revised 7-item Impact of Event Scale (IES-7) scales, respectively, which found that the prevalence rates of depression, anxiety, insomnia, and distress caused by COVID-19 were 45.5%, 49.5%, 30.9%, and 68.1%, respectively. Multivariable logistic regression analysis was performed to identify factors associated with mental health outcomes among workers with income losses during COVID-19. Participants working in Hubei province with heavy income losses, especially pregnant women, were found to have a high risk of developing unfavorable mental health symptoms and may need psychological support or interventions.