Adaptive Susceptible-Infectious-Removed Model for Continuous Estimation of the COVID-19 Infection Rate and Reproduction Number in the United States: Modeling Study.

BACKGROUND: The dynamics of the COVID-19 pandemic vary owing to local population density and policy measures. During decision-making, policymakers consider an estimate of the effective reproduction number Rt, which is the expected number of secondary infections spread by a single infected individual. OBJECTIVE: We propose a simple method for estimating the time-varying infection rate and the Rt. METHODS: We used a sliding window approach with a Susceptible-Infectious-Removed (SIR) model. We estimated the infection rate from the reported cases over a 7-day window to obtain a continuous estimation of Rt. A proposed adaptive SIR (aSIR) model was applied to analyze the data at the state and county levels. RESULTS: The aSIR model showed an excellent fit for the number of reported COVID-19 cases, and the 1-day forecast mean absolute prediction error was <2.6% across all states. However, the 7-day forecast mean absolute prediction error approached 16.2% and strongly overestimated the number of cases when the Rt was rapidly decreasing. The maximal Rt displayed a wide range of 2.0 to 4.5 across all states, with the highest values for New York (4.4) and Michigan (4.5). We found that the aSIR model can rapidly adapt to an increase in the number of tests and an associated increase in the reported cases of infection. Our results also suggest that intensive testing may be an effective method of reducing Rt. CONCLUSIONS: The aSIR model provides a simple and accurate computational tool for continuous Rt estimation and evaluation of the efficacy of mitigation measures.

Adversarial Attacks on Time Series.

Time series classification models have been garnering significant importance in the research community. However, not much research has been done on generating adversarial samples for these models. These adversarial samples can become a security concern. In this paper, we propose utilizing an adversarial transformation network (ATN) on a distilled model to attack various time series classification models. The proposed attack on the classification model utilizes a distilled model as a surrogate that mimics the behavior of the attacked classical time series classification models. Our proposed methodology is applied onto 1-nearest neighbor dynamic time warping (1-NN DTW) and a fully convolutional network (FCN), all of which are trained on 42 University of California Riverside (UCR) datasets. In this paper, we show both models were susceptible to attacks on all 42 datasets. When compared to Fast Gradient Sign Method, the proposed attack generates a larger faction of successful adversarial black-box attacks. A simple defense mechanism is successfully devised to reduce the fraction of successful adversarial samples. Finally, we recommend future researchers that develop time series classification models to incorporating adversarial data samples into their training data sets to improve resilience on adversarial samples.

Multivariate LSTM-FCNs for time series classification.

Over the past decade, multivariate time series classification has received great attention. We propose transforming the existing univariate time series classification models, the Long Short Term Memory Fully Convolutional Network (LSTM-FCN) and Attention LSTM-FCN (ALSTM-FCN), into a multivariate time series classification model by augmenting the fully convolutional block with a squeeze-and-excitation block to further improve accuracy. Our proposed models outperform most state-of-the-art models while requiring minimum preprocessing. The proposed models work efficiently on various complex multivariate time series classification tasks such as activity recognition or action recognition. Furthermore, the proposed models are highly efficient at test time and small enough to deploy on memory constrained systems.

A machine learning based model for Out of Hospital cardiac arrest outcome classification and sensitivity analysis.

BACKGROUND: Out-of-hospital cardiac arrest (OHCA) affects nearly 400,000 people each year in the United States of which only 10% survive. Using data from the Cardiac Arrest Registry to Enhance Survival (CARES), and machine learning (ML) techniques, we developed a model of neurological outcome prediction for OHCA in Chicago, Illinois. METHODS: Rescue workflow data of 2639 patients with witnessed OHCA were retrieved from Chicago's CARES. An Embedded Fully Convolutional Network (EFCN) classification model was selected to predict the patient outcome (survival with good neurological outcomes or not) based on 27 input features with the objective of maximizing the average class sensitivity. Using this model, sensitivity analysis of intervention variables such as bystander cardiopulmonary resuscitation (CPR), targeted temperature management, and coronary angiography was conducted. RESULTS: The EFCN classification model has an average class sensitivity of 0.825. Sensitivity analysis of patient outcome shows that an additional 33 patients would have survived with good neurological outcome if they had received lay person CPR in addition to CPR by emergency medical services and 88 additional patients would have survived if they had received the coronary angiography intervention. CONCLUSIONS: ML modeling of the complex Chicago OHCA rescue system can predict neurologic outcomes with a reasonable level of accuracy and can be used to support intervention decisions such as CPR or coronary angiography. The discriminative ability of this ML model requires validation in external cohorts to establish generalizability.

The Heartfile Lodhran CVD prevention project--end of project evaluation.

Mainstream preventive interventions often fail to reach poor populations with a high risk of cardiovascular diseases (CVDs) in Pakistan. A community-based CVD primary prevention project aimed at developing approaches to reduce risk factors in such populations was established by Heartfile in collaboration with the National Rural Support Program in the district of Lodhran. The project implemented a range of activities integrated with existing social and health service mechanisms during a three year intervention period 2000/01-03/04. These were targeted in 4 key settings: community health education, mass media interventions, training of health professionals and health education through Lady Health Workers. The project received support from the Department for International Development, U.K. At the community level, a pre-test-post-test quasi-experimental design was used for examining project outcomes related to the community component of the intervention. Pre and post-intervention (training) evaluations were conducted involving all health care providers in randomly selected workshops in order to determine baseline levels of knowledge and the impact of training on knowledge level. In order to assess practices of physician and non-physician health care providers patient interviews, with control comparisons were conducted at each health care facility. Significant positive changes were observed in knowledge levels at a community level in the district of intervention compared with baseline knowledge levels particularly in relation to a heart healthy diet, beneficial level of physical activity, the causes of high blood pressure and heart attack and the effects of high blood pressure and active and passive smoking on health. Significant changes in behaviors at a practice level were not shown in the district of intervention. However the project played a critical role in spurring national action for the prevention and control of non-communicable diseases and introducing sustainable public health interventions for poor communities in Pakistan.