Objectives To describe the factors determining choice of health financing systems. Methods Search words chosen by both health policy experts and the review search coordinators after discussion and pilot. 19 electronic databases, 2 international health institutes websites, 2 grey literature databases, and search engine Google were included in the databases. Any literature about health financing reforms on country level was included. Pre-designed data extraction form was used for collecting the information. The data was analyzed and described by pre-designed analytic framework.Result A total of 59 studies were included in this review. The driving forces included political, economic, social, and health systems factors. Development level of economy was the most crucial factor for transformation of health financing systems. The health system could directly led to the transition between different health systems, both Italy and France transform their financing system from social health insurance to national health system. The key persons such as premier of Thailand and Germany, leader of political and social organization in Israel and Korea are the driving forces of health financing reforms. Conclusion Developing countries can learn from the countries which have achieved universal coverage through health financing reform. Underlying factors influencing formulation of a health financing system need to be considered before taking actions in reforming the current system. Efforts in transforming the health financing systems need to be made from political, economic, and health systems sides.
Automatic detection of pulmonary nodule based on computer tomography (CT) images can significantly improve the diagnosis and treatment of lung cancer. However, there is a lack of effective interactive tools to record the marked results of radiologists in real time and feed them back to the algorithm model for iterative optimization. This paper designed and developed an online interactive review system supporting the assisted diagnosis of lung nodules in CT images. Lung nodules were detected by the preset model and presented to doctors, who marked or corrected the lung nodules detected by the system with their professional knowledge, and then iteratively optimized the AI model with active learning strategy according to the marked results of radiologists to continuously improve the accuracy of the model. The subset 5−9 dataset of the lung nodule analysis 2016(LUNA16) was used for iteration experiments. The precision, F1-score and MioU indexes were steadily improved with the increase of the number of iterations, and the precision increased from 0.213 9 to 0.565 6. The results in this paper show that the system not only uses deep segmentation model to assist radiologists, but also optimizes the model by using radiologists' feedback information to the maximum extent, iteratively improving the accuracy of the model and better assisting radiologists.