Probabilistic real-time natural gas jet fire consequence modeling of offshore platforms by hybrid deep learning approach.

Natural gas jet fire induced by igniting blowouts has the potential to cause critical structure damage and great casualties of offshore platforms. Real-time natural gas jet fire plume prediction is essential to support the emergency planning to mitigate subsequent damage consequence and ocean pollution. Deep learning based on a large amount of Computational fluid dynamics (CFD) simulations has recently been applied to real-time fire modeling. However, existing approaches based on point-estimation theory are 'over-confident' when prediction deficiency exists, which reduce robustness and accuracy for emergency planning support. This study proposes probabilistic deep learning approach for real-time natural gas jet fire consequence modeling by integrating variational Bayesian inference with deep learning. Numerical model of natural gas jet fire from offshore platform is built and the natural gas jet fire scenarios are simulated to construct the benchmark dataset. Sensitivity analysis of pre-defined parameters such as MC (Monte Carlo) sampling number m and dropout probability p is conducted to determine the trade-off between model's accuracy and efficiency. The results demonstrated our model exhibits competitive accuracy with R2 = 0.965 and real-time capacity with an inference time of 12 ms. In addition, the predicted spatial uncertainty corresponding to spatial jet fire flame plume provides more comprehensive and reliable support for the following mitigation decision-makings compared to the state-of-the-art point-estimation based deep learning model. This study provides a robust alternative for constructing a digital twin of fire and explosion associated emergency management on offshore platforms.

Advanced Computer Vision-Based Subsea Gas Leaks Monitoring: A Comparison of Two Approaches.

Recent years have witnessed the increasing risk of subsea gas leaks with the development of offshore gas exploration, which poses a potential threat to human life, corporate assets, and the environment. The optical imaging-based monitoring approach has become widespread in the field of monitoring underwater gas leakage, but the shortcomings of huge labor costs and severe false alarms exist due to related operators' operation and judgment. This study aimed to develop an advanced computer vision-based monitoring approach to achieve automatic and real-time monitoring of underwater gas leaks. A comparison analysis between the Faster Region Convolutional Neural Network (Faster R-CNN) and You Only Look Once version 4 (YOLOv4) was conducted. The results demonstrated that the Faster R-CNN model, developed with an image size of 1280 × 720 and no noise, was optimal for the automatic and real-time monitoring of underwater gas leakage. This optimal model could accurately classify small and large-shape leakage gas plumes from real-world datasets, and locate the area of these underwater gas plumes.

Real-world cost-effectiveness associated with infliximab maintenance therapy for moderate to severe Crohn's disease in China.

BACKGROUND: Infliximab was the first approved biologic treatment for moderate to severe Crohn's disease (MS-CD) in China. However, the cost-effectiveness of infliximab maintenance therapy (IMT) for MS-CD relative to conventional maintenance therapy remained unclarified. AIM: To assess the cost-effectiveness of IMT for MS-CD in Chinese patients from the perspective of Chinese public insurance payer. METHODS: A cohort of MS-CD patients managed in a Chinese tertiary care hospital was created to compare IMT with conventional maintenance therapy (CMT) for clinical outcomes and direct medical costs over a 1-year observation time using conventional regression analyses. A decision-analytic model with the generated evidence was constructed to assess the cost-effectiveness of IMT relative to CMT using reimbursed medical costs. RESULTS: Based on the included 389 patients, IMT was associated with significantly higher disease remission chance [odds ratio: 4.060, P = 0.003], lower risk of developing new complications (odds ratio: 0.527, P = 0.010), higher utility value for quality of life (coefficient 0.822, P = 0.008), and lower total hospital costs related to disease management (coefficient -0.378, P = 0.008) than CMT. Base-case cost-effectiveness analysis estimated that IMT could cost Chinese health insurance payers ¥55260 to gain one quality-adjusted life year (QALY). The cost-effectiveness of IMT was mainly driven by the estimate of quality of life, treatment efficacy of maintenance therapy, mortality risk associated with active disease, and unit price of infliximab. The probability that IMT was cost-effective at a willingness-to-pay threshold of three times gross domestic product [2018 Chinese gross domestic product per capita (GDPPC)] was 86.4%. CONCLUSION: IMT significantly improved real-world health outcomes and cost the Chinese public health insurance payers less than one GDPPC to gain one QALY in Chinese MS-CD patients.

Cost-Effectiveness of Reimbursing Infliximab for Moderate to Severe Crohn's Disease in China.

OBJECTIVES: To assess the cost-effectiveness of reimbursing infliximab for moderate-to-severe Crohn's disease (MS-CD) in China from the perspective of public insurance payers. METHODS: A decision-analytic model with a lifetime time horizon was constructed to simulate the disease progression and direct medical costs in Chinese MS-CD patients under two scenarios: reimbursing infliximab vs. not reimbursing infliximab. A cross-sectional study and literature review were conducted to estimate model variables. The constructed decision-analytic model ran the base case, one-way sensitivity, and probabilistic sensitivity analyses (PSA) to assess the cost-effectiveness of reimbursing infliximab using reimbursed medical costs. RESULTS: Base case analysis discounting health benefits and costs estimated that reimbursing infliximab could increase overall survival by 0.604 years, increase total quality-adjusted life years (QALY) by 0.697 QALY, reduce absolute lifetime surgery risk by 13.1%, and increase reimbursed costs by ¥29,409. The incremental cost-effectiveness ratio per gained additional QALY (ICER) based on discounted health benefits and reimbursed medical costs (3% per year) was ¥42,198. The one-way sensitivity analyses identified that the cost-effectiveness of reimbursing infliximab for MS-CD was mainly driven by the treatment efficacies of maintenance therapy, quality of life, and unit price of infliximab. PSA estimated that reimbursing infliximab was associated with a 63.8% chance to be cost-effective under the willingness-to-pay of the 2018 Chinese gross domestic product per capita (GDPPC). CONCLUSION: Reimbursing infliximab for MS-CD in Chinese patients was highly attractive, costing Chinese public insurance payers less than the 2018 Chinese GDPPC to gain 1 QALY.