Analyzing Healthcare Safety Climate Through A Collaborative Filtering of Safety Attitudes Questionnaire for A Hospital Case Study
Huang, H.; Chou, C.-A.; Weng, S.-J.; Wu, C.-L.
Show abstract
BackgroundPatient safety climate in healthcare is an important element to improve quality of current healthcare system globally. Safety Attitudes Questionnaire (SAQ), one of measurable tools for patient safety climate, is applied as an effective research survey to collect opinions and information from medical workers in a long term. MethodSAQ data in this study consists of medical employee scores to 46 questions in 8 aspects or dimensions and personal information during 2014 to 2017 from a teaching hospital. A quantitative analysis with a core user based collaborative filtering method is conducted to analyze the SAQ data for discovering the latent inter-related pattern among different SAQ aspects of sub-sectors in this hospital for four years. ResultsThere are not interrelationships between these 8 independent aspects for wards at different level (A, B and C) consistently across 4 years. The correlation patterns of aspects are not strong consistent over years for wards. ConclusionObservations in this study can be used to support understanding patient safety climate assessment. They are contributed to further study in this area and understand SAQ aspects dynamically in a real hospital case.
Matching journals
The top 7 journals account for 50% of the predicted probability mass.
Similar papers in this journal
Similar papers in this journal
- Identification of Myocardial Infarction (MI) Probability from Imbalanced Medical Survey Data: An Artificial Neural Network (ANN) with Explainable AI (XAI) Insights 95%
- A machine-learning Approach for Stress Detection Using Wearable Sensors in Free-living Environments 95%
- Unsupervised Discovery of Risk Profiles on Negative and Positive COVID-19 Hospitalized Patients 94%
Similar papers in this journal
Similar papers in this journal
- Prediction of Sepsis Mortality in ICU Patients Using Machine Learning Methods 94%
- Construction and application of a revised satisfaction index model for Chinese urban and rural residents basic medical insurance 94%
- On the predictability of postoperative complications for cancer patients: a Portuguese cohort study 94%
Similar papers in this journal
- Predicting mortality, duration of treatment, pulmonary embolism and required ceiling of ventilatory support for COVID-19 inpatients: A Machine-Learning Approach 95%
- Acculturation stressors and academic adjustment among Nepalese students in South Korean higher education institutions 94%
- Variability in physical inactivity responses of university students during COVID-19 pandemic: A monitoring of daily step counts using a smartphone application 94%
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.