No abstract

In the last decade, Deep Learning (DL) has revolutionized the use of artificial intelligence, and it has been deployed in different fields of healthcare applications such as image processing, natural language processing, and signal processing. DL models have also been intensely used in different tasks of healthcare such as disease diagnostics and treatments. Deep learning techniques have surpassed other machine learning algorithms and proved to be the ultimate tools for many state-of-the-art applications. Despite all that success, classical deep learning has limitations and their models tend to be very confident about their predicted decisions because it does not know when it makes mistake. For the healthcare field, this limitation can have a negative impact on models predictions since almost all decisions regarding patients and diseases are sensitive. Therefore, Bayesian deep learning (BDL) has been developed to overcome these limitations. Unlike classical DL, BDL uses probability distributions for the model parameters, which makes it possible to estimate the whole uncertainties associated with the predicted outputs. In this regard, BDL offers a rigorous framework to quantify all sources of uncertainties in the model. This study reviews popular techniques of using Bayesian deep learning with their benefits and limitations. It also reviewed recent deep learning architecture such as Convolutional Neural Networks and Recurrent Neural Networks. In particular, the applications of Bayesian deep learning in healthcare have been discussed such as its use in medical imaging tasks, clinical signal processing, medical natural language processing, and electronic health records. Furthermore, this paper has covered the deployment of Bayesian deep learning for some of the widespread diseases. This paper has also discussed the fundamental research challenges and highlighted some research gaps in both the Bayesian deep learning and healthcare perspective.

Background Understanding the perspectives of healthcare workers toward patient safety-related activities is critical in maintaining a healthy safety climate. The objectives of this research are 1) to examine the perception of Patient Safety Culture (PSC) at a university hospital in Palestine, and to highlight areas in need of improvement, and 2) to assess the relationship between the outcome dimensions (frequency of events reported, and overall perceptions of safety) and the other dimensions of PSC, and 3) to determine the relationship among selected demographic variables (gender, age, hospital tenure, work tenure, profession tenure, and hours worked per week) and nurses’ perceptions of PSC. Methods A cross-sectional study design was used with a convenience sample of 107 nurses. Nurses were asked by email to complete the Arabic version of the Hospital Survey of Patients’ Safety Culture (HSOPSC) using the SurveyMonkey® online account form within two weeks. The survey data were analyzed using descriptive and inferential statistics. Univariate and multiple regression were used to examine the relationships. Results The dimensions of patient safety with the highest positive response were organizational learning and continuous improvement (87%) and teamwork within units (86%). The dimension with the lowest positive score was the nonpunitive response to error (22%). Multiple regression revealed that the dimension of communication openness was a predictor of the overall perceptions of safety (β = 0.257, p = 0.019). In addition, the dimension of feedback and communication about error was a predictor of the frequency of the reported events (β = 0.334, p = 0.005). Furthermore, age was found to be a predictor of PSC (p < 0.05). Conclusions This study provides a general assessment of perceived safety among nurses in a hospital. However, we found that nurses negatively perceive a nonpunitive response to error. Therefore, strenuous efforts are required by hospital management to improve the culture of incident reporting.

No abstract