BeCaked: An Explainable Artificial Intelligence Model for COVID-19 Forecasting.

From the end of 2019, one of the most serious and largest spread pandemics occurred in Wuhan (China) named Coronavirus (COVID-19). As reported by the World Health Organization, there are currently more than 100 million infectious cases with an average mortality rate of about five percent all over the world. To avoid serious consequences on people's lives and the economy, policies and actions need to be suitably made in time. To do that, the authorities need to know the future trend in the development process of this pandemic. This is the reason why forecasting models play an important role in controlling the pandemic situation. However, the behavior of this pandemic is extremely complicated and difficult to be analyzed, so that an effective model is not only considered on accurate forecasting results but also the explainable capability for human experts to take action pro-actively. With the recent advancement of Artificial Intelligence (AI) techniques, the emerging Deep Learning (DL) models have been proving highly effective when forecasting this pandemic future from the huge historical data. However, the main weakness of DL models is lacking the explanation capabilities. To overcome this limitation, we introduce a novel combination of the Susceptible-Infectious-Recovered-Deceased (SIRD) compartmental model and Variational Autoencoder (VAE) neural network known as BeCaked. With pandemic data provided by the Johns Hopkins University Center for Systems Science and Engineering, our model achieves 0.98 [Formula: see text] and 0.012 MAPE at world level with 31-step forecast and up to 0.99 [Formula: see text] and 0.0026 MAPE at country level with 15-step forecast on predicting daily infectious cases. Not only enjoying high accuracy, but BeCaked also offers useful justifications for its results based on the parameters of the SIRD model. Therefore, BeCaked can be used as a reference for authorities or medical experts to make on time right decisions.

The Racial Paradox in Multiarterial Conduit Utilization for Coronary Artery Bypass Grafting.

BACKGROUND: It has been established that outcomes for black patients undergoing coronary artery bypass graft surgery (CABG) are inferior to those of their white counterparts. The purpose of this study was to determine (1) whether rates of multiarterial grafting are different among black patients and white patients, and (2) whether racial differences exist in postoperative outcomes after accounting for grafting strategy. METHODS: A retrospective review of black patients (n = 2,810) and white patients (n = 13,569) who underwent isolated, primary CABG from January 2002 to June 2014 at a US academic institution was performed. A modified predicted risk of mortality (M-PROM) score was calculated for each patient using all The Society of Thoracic Surgeons variables for CABG excluding race. Multivariable linear, logistic, and Cox regression analyses were used to assess between-group differences, adjusted for M-PROM. RESULTS: Overall, 16,379 patients underwent CABG, and 2,441 (14.9%) received more than one arterial graft. When adjusted for M-PROM, the odds of blacks undergoing multiarterial CABG were 10% greater than for whites (p = 0.05). Blacks had worse inhospital outcomes, including higher odds of stroke (odds ratio 2.41, 95% confidence interval [CI]: 1.80 to 3.25) and prolonged intubation (odds ratio 2.01, 95% CI: 1.77 to 2.28). The increase in postoperative complications did not translate to a difference in inhospital mortality (p = 0.10) between racial cohorts. Moreover, among patients who underwent multiarterial grafting strategies, blacks had a hazard of mortality that was 34% higher (95% CI: 22% to 51%)) than that of their white counterparts. Among black patients, those who underwent multiarterial grafting strategies showed better long-term survival than those undergoing single grafting strategies (hazard ratio 0.86, 95% CI: 0.78 to 0.96). CONCLUSIONS: Despite similar rates of arterial grafting for black patients and white patients in this large single-center cohort, black patients continued to have significantly worse late survival when compared with white patients. Continued evaluation as to the causes of this disparity is warranted.

Rapid Development and Implementation of an ECMO Program.

Extracorporeal membrane oxygenation (ECMO) is an established therapy in the management of patients with refractory cardiogenic shock or acute respiratory failure. In this report, we describe the rapid development and implementation of an organized ECMO program at a facility that previously provided ad hoc support. The program provides care for patients within the Emory Healthcare system and throughout the Southeastern United States. From September 2014 to February 2015, 16 patients were treated with either venovenous or venoarterial ECMO with a survival to decannulation of 53.3% and survival to intensive care unit discharge of 40%. Of the 16 patients, 10 were transfers from outside facilities of which 2 were remotely cannulated and initiated on ECMO support by our ECMO transport team. Complications included intracerebral hemorrhage, bleeding from other sites, and limb ischemia. The results suggest that a rapidly developed ECMO program can provide safe transport services and provide outcomes similar to those in the existing literature. Key components appear to be an institutional commitment, a physician champion, multidisciplinary leadership, and organized training. Further study is required to determine whether outcomes will continue to improve.

Third-generation continuous flow left ventricular assist devices.

Tremendous advances have been made in the treatment of end-stage heart failure patients with left ventricular assist devices (LVADs). An important factor playing a role in the improved clinical outcomes is the development of continuous flow, rotary LVADs. New technology using magnetic levitation and hydrodynamic suspension to eliminate contact bearings offers the potential of more durable and efficacious mechanical circulatory blood pumps. Clinical trials evaluating these novel "third-generation" LVADs are in progress.

Surgical revascularization for cardiac allograft vasculopathy: Is it still an option?

OBJECTIVES: Cardiac allograft vasculopathy remains a major cause of mortality after cardiac transplantation. Percutaneous revascularization has become the mainstay of therapy given the poor historical outcomes with surgery. Outcomes following surgical revascularization are evaluated to determine whether surgery remains a viable therapeutic option. METHODS: A retrospective analysis was performed of 13 heart transplant recipients who had cardiac allograft vasculopathy requiring coronary artery bypass grafting with or without adjunctive percutaneous coronary intervention for revascularization from 1999 to 2008. RESULTS: Thirteen patients had 14 coronary artery bypass grafting procedures at 141 +/- 66 months after transplantation. The average number of grafts was 2.3. Eight were performed without cardiopulmonary bypass, of which 5 were approached via left thoracotomy and the remainder via repeat sternotomy. One patient had renal failure and a cerebrovascular accident. Percutaneous coronary intervention before or after coronary artery bypass grafting was required in 3 patients. There were no perioperative mortalities. At mean follow-up of 39 +/- 36 months, 3 patients have died, 2 from progressive cardiac allograft vasculopathy and 1 from lung cancer. Kaplan-Meier survival for this group of patients was 92%, 83%, and 83% at 1, 5, and 7 years, respectively. CONCLUSIONS: Surgical revascularization for cardiac allograft vasculopathy remains a viable treatment option for appropriate patients and may be performed safely with good medium-term outcomes. However, patients remain at risk for disease progression and may require percutaneous or surgical reintervention.