• HSOPSC
• data mining
• healthcare system
• linear regression
• random forest

• experiential learning
• multidisciplinary teamwork
• professional development
• radiography
• safety culture
• work readiness

• The study was self-funded

• Adverse events
• Hospital
• Patient safety culture

• Diabetes
• Health service utilization
• Influence factors
• Random forest

• 2019-FWZX-11 "Health Gansu" construction response of health service changes during the decade of the new medical reform
• 2022620005002671 A study on accounting of health expenditure in Gansu Province in 2022
• 20211008-(21)0555 a study on the correlation between health service utilization and disease economic risk of diabetes patients in Gansu Province, China

• COVID-19
• Hospitals teaching
• Nursing
• Organisational culture
• Surgicentres

• E-26/010.100932/2018 Fundação Carlos Chagas Filho de Amparo à Pesquisa do Estado do Rio de Janeiro

• Artificial Intelligence (AI)
• Covid-19
• Discrete-Event Simulation (DES)
• Healthcare
• Intensive Care Unit (ICU)
• Random Forest (RF)

• machine learning
• patient anxiety
• patient data
• patient experience
• patient frustration
• patient satisfaction
• patient stress
• quality
• random forest

• Humans
• Frustration
• Anxiety
• Anxiety Disorders
• Surveys and Questionnaires
• Patient Outcome Assessment

• Adverse events
• Correlation analysis
• Descriptive study
• Hospitals
• Patient safety culture
• Saudi Arabia
• Sentinel events

• Humans
• Organizational Culture
• Saudi Arabia/epidemiology
• Patient Safety
• Safety Management
• Hospitals
• Surveys and Questionnaires

• hemodialysis
• kidney care
• medical error
• patient safety
• quality improvement
• safety culture

• Explainable machine learning
• Healthcare
• Interpretable machine learning
• Trustworthiness

Individual and group beliefs, attitudes, perceptions, competences, and behavioral patterns all contribute to the safety culture of a healthcare company. The study’s goal is to assess nurses’ perceptions of elements that influence patient safety culture in order to promote long-term nursing practice. A descriptive cross-sectional study design was done among a sample of 146 nurses who were recruited from one hospital in Egypt. They completed a self-administered, printed questionnaire. The questionnaire assessed participants’ socio-demographic data and their perception regarding patient safety culture for sustainable nursing practices. The findings revealed that nursing staff had a high perception regarding patient safety culture a with mean score (159.94 ± 7.864). Also, the highest percentage (74.66%) of had no safety events reported yearly. Creating a unit-specific patient safety culture suited to the competences of the unit’s RNs in patient safety practice would be crucial to increasing and sustaining high levels of patient safety attitudes, skills, and knowledge among the unit’s RNs, influencing patient safety. When implementing interventions to promote patient safety and reporting culture in hospitals, policymakers, hospital administrators, and nurse executives should take the current findings into account. A multidimensional network intervention addressing many elements of patient safety culture and integrating different organizational levels should be implemented to enhance patient safety and a no-blame culture.

• Bayesian Network
• healthcare operations
• medical errors
• patient safety
• risk

• Bayes Theorem
• Hospitals
• Humans
• Medical Errors
• Patient Safety
• Surveys and Questionnaires

Increasingly available open medical and health datasets encourage data-driven research with a promise of improving patient care through knowledge discovery and algorithm development. Among efficient approaches to such high-dimensional problems are a number of machine learning methods, which are applied in this paper to pressure ulcer prediction in modular critical care data. An inherent property of many health-related datasets is a high number of irregularly sampled time-variant and scarcely populated features, often exceeding the number of observations. Although machine learning methods are known to work well under such circumstances, many choices regarding model and data processing exist. In particular, this paper address both theoretical and practical aspects related to the application of six classification models to pressure ulcers, while utilizing one of the largest available Medical Information Mart for Intensive Care (MIMIC-IV) databases. Random forest, with an accuracy of 96%, is the best-performing approach among the considered machine learning algorithms.

• Machine learning
• Occupational safety
• Text mining
• Transfer learning
• Word embeddings

• Accidents
• Construction Industry
• Data Mining
• Humans
• Machine Learning
• Occupational Health

The severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2), which caused the coronavirus disease 2019 (COVID-19) pandemic, has affected more than 400 million people worldwide. With the recent rise of new Delta and Omicron variants, the efficacy of the vaccines has become an important question. The goal of various studies has been to limit the spread of the virus by utilizing wireless sensing technologies to prevent human-to-human interactions, particularly for healthcare workers. In this paper, we discuss the current literature on invasive/contact and non-invasive/non-contact technologies (including Wi-Fi, radar, and software-defined radio) that have been effectively used to detect, diagnose, and monitor human activities and COVID-19 related symptoms, such as irregular respiration. In addition, we focused on cutting-edge machine learning algorithms (such as generative adversarial networks, random forest, multilayer perceptron, support vector machine, extremely randomized trees, and k-nearest neighbors) and their essential role in intelligent healthcare systems. Furthermore, this study highlights the limitations related to non-invasive techniques and prospective research directions.

•

This article describes cutting-edge technology (invasive/non-invasive) and its role in the recognition of COVID-19 symptoms.

• Artificial intelligence
• COVID-19
• Machine learning
• Non-contact sensing
• Non-invasive healthcare

Assessments of the culture surrounding patient safety can inform healthcare settings on how their structures and processes impact patient outcomes. This study investigated patient safety culture in Primary Health Care Centres in Kuwait, and benchmarked the findings against regional and international results. This study also examined the association between predictors and outcomes of patient safety culture in these settings.

This cross-sectional quantitative study used the Medical Office Survey on Patient Safety Culture. The study was targeted at staff of all the Primary Health Care Centres in Kuwait with at least one year of experience. Data were analysed using SPSS 23 at a significance level of ≤ .05. Univariate (means, standard deviations, frequencies, percentages) and bivariate (chi-squared tests, student t-tests, ANOVA F-tests, Kruskal–Wallis tests, Spearman’s correlation) analyses provided an overview of participant socio-demographics and the association between patient safety culture composites and outcomes. We undertook a multivariate regression analysis to predict the determinants of patient safety culture. Results were benchmarked against similar local (Kuwait, 2014), regional (Yemen, 2015) and international (US, 2018) studies.

The responses of 6602 employees from 94 centres were included in the study, with an overall response rate of 78.7%. The survey revealed Teamwork (87.8% positive ratings) and Organisational Learning (78.8%) as perceived areas of strength. Communication about Error (57.7%), Overall Perceptions of Patient Safety and Quality (57.4%), Communication Openness (54.4%), Owner/Managing Partner/Leadership Support for Patient Safety (53.8%) and Work Pressure and Pace (28.4%) were identified as areas requiring improvement. Benchmarking analysis revealed that Kuwait centres are performing at benchmark levels or better on four and six composites when compared to international and regional findings, respectively. Regression modelling highlighted significant predictions regarding patient safety outcomes and composites.

This is the first major study addressing the culture of patient safety in public Primary Health Care Centres regionally. Improving patient safety culture is critical for these centres to improve the quality and safety of the healthcare services they provide. The findings of this study can guide country-level strategies to develop the systems that govern patient safety practices.

The online version contains supplementary material available at 10.1186/s12913-021-07199-1.

• Kuwait
• MOSPSC
• Patient safety
• Primary care
• Safety culture

Patient safety is an issue of global concern; however, health-care organizations have lately observed to pay more attention to the importance of establishing a culture of safety. The study aimed to assess the level of patient safety culture and associated factors among health-care providers at the University of Gondar comprehensive specialized hospital, Northwest Ethiopia, 2020.

A cross-sectional study design supported by the qualitative approach was conducted from March 15 to May 15/2020. A stratified simple sampling technique was used to select 575 study participants. The standardized tool, which measures 12 safety culture dimensions, was used for data collection. Bivariate and multivariable linear regression analyses performed using SPSS version 23. The significance level was obtained at 95% CI and p-value <0.05. For the qualitative part, a semi-structured interview guide with probing was used. Data were analyzed thematically using open code software version 4.02.

The overall level of positive patient safety culture was 45.3% (95% CI: 44.7, 45.9) with a response rate of 92.2%. Factor analysis indicated that female, masters, participation in patient safety program, adverse event report, hospital management encourage reporting event and resource were positively associated with the patient safety culture. Whereas divorced/widowed, midwives, anesthetist, medicine, pediatrics, emergency, outpatient, pharmacy, direct contact with patients, and hospital management blame when medical errors happened were negatively associated. The in-depth interview revealed that teamwork, health-care professionals’ attitude toward patient safety and patient involvement as important factors that influence patient safety culture.

The overall level of positive patient safety culture was low. All variables except age, training, working hour, and working experience were factors significantly associated with the patient safety culture. Health-care policy-makers and managers should consider patient safety culture a top priority, and also create a blame-free environment that promotes event reporting.

• Ethiopia
• health care providers
• patient safety
• patient safety culture

• Healthcare
• Risk analysis
• STPA
• System safety

• Delivery of Health Care
• Humans
• Risk Assessment
• Safety Management
• Sepsis
• Systems Analysis

Patient satisfaction is a multi-dimensional concept that provides insights into various quality aspects in healthcare. Although earlier studies identified a range of patient and provider-related determinants, their relative importance to patient satisfaction remains unclear.

We used a tree-based machine-learning algorithm, random forests, to estimate relationships between patient and provider-related determinants and satisfaction level in two of the main patient journey stages, registration and consultation, through survey data from 411 patients at a hospital in Abu Dhabi, UAE. Radar charts were also generated to determine which type of questions—demographics, time, behaviour, and procedure—influence patient satisfaction.

Our results showed that the ‘age’ attribute, a patient-related determinant, is the leading driver of patient satisfaction in both stages. ‘Total time taken for registration’ and ‘attentiveness and knowledge of the doctor/physician while listening to your queries’ are the leading provider-related determinants in each model developed for registration and consultation stages, respectively. The radar charts revealed that ‘demographics’ are the most influential type in the registration stage, whereas ‘behaviour’ is the most influential in the consultation stage.

Generating valuable results, the random forest model provides significant insights on the relative importance of different determinants to overall patient satisfaction. Healthcare practitioners, managers and researchers can benefit from applying the model for prediction and feature importance analysis in their particular healthcare settings and areas of their concern.

• Data analytics
• Healthcare operations
• Machine learning
• Patient experience
• Patient satisfaction
• Quality
• Random forests

• Framingham risk attributes
• Framingham risk score (FRS)
• applications of medicine
• cardiovascular disease
• entropy-based rule model
• machine learning techniques