Search

Objectives: This study explored the familiarity, perceptions and confidence of Australian radiology clinicians involved in reading screening mammograms, regarding artificial intelligence (AI) applications in breast cancer detection. Methods: Sixty-five radiologists, breast physicians and radiology trainees participated in an online survey that consisted of 23 multiple choice questions asking about their experience and familiarity with AI products. Furthermore, the survey asked about their confidence in using AI outputs and their preference for AI modes applied in a breast screening context. Participants' responses to questions were compared using Pearson's χ 2 test. Bonferroni-adjusted significance tests were used for pairwise comparisons. Results: Fifty-five percent of respondents had experience with AI in their workplaces, with automatic density measurement powered by machine learning being the most familiar AI product (69.4%). The top AI outputs with the highest ranks of perceived confidence were 'Displaying suspicious areas on mammograms with the percentage of cancer possibility' (67.8%) and 'Automatic mammogram classification (normal, benign, cancer, uncertain)' (64.6%). Radiology and breast physicians preferred using AI as second-reader mode (75.4% saying 'somewhat happy' to 'extremely happy') over triage (47.7%), pre-screening and first-reader modes (both with 26.2%) (P < 0.001). Conclusion: The majority of screen readers expressed increased confidence in utilising AI for highlighting suspicious areas on mammograms and for automatically classifying mammograms. They considered AI as an optimal second-reader mode being the most ideal use in a screening program. The findings provide valuable insights into the familiarities and expectations of radiologists and breast clinicians for the AI products that can enhance the effectiveness of the breast cancer screening programs, benefitting both healthcare professionals and patients alike. What is known about the topic? Artificial intelligence (AI) holds promise in providing computer-aided detection in health care, however, current research suggests that standalone AI applications in clinical practice fall short of matching the accuracy of a single radiologist. What does this paper add? The study showed a significant preference among clinicians for using AI as a supplementary tool, serving as a second-reader. Such an integrated approach, where AI aids in flagging suspicious areas on mammograms or offers automatic classification, reflects the ideal cooperation between breast screening readers and AI systems. What are the implications for practitioners? These insights shed light on clinicians' familiarity with and expectations of AI tools that can boost the effectiveness of breast screening programs. [ABSTRACT FROM AUTHOR]

Background: Cross-sectoral collaborations are considered necessary to address detrimental health, social, educational and economic outcomes that impact marginalised and disadvantaged populations. There is a strong relationship between the health of children and their educational attainment; good health promotes positive learning. This paper reports cross-sectoral executive and senior management level systems changes required to enable the design of a collaborative primary healthcare service model for children and young people in rural Australia. Methods: A descriptive qualitative design was used. Data were collected from executive and senior managers from three organisations (Education, Health and a University Department of Rural Health [ n = 6]) through individual semi-structured interviews. Data were analysed using an inductive, thematic approach. The study draws on Lewin's Model of Change. Results: Three overarching themes were generated from the data: an embedded challenge and experimental solutions; building a shared language and understanding; and the role of relationships and trust. Despite the unique geographical and social context of the study area, strategies emerged from the data on how a solution to an embedded challenge, through design of a primary healthcare model, was established and how the strategies described could be transferred and scaled to other rural and remote communities. Conclusion: Contextual differences make each rural and remote area unique. In this study, strategies that are described in the managing change literature were evident. The authors conclude that drawing on strong management of change principles could mean that a service model designed for one remote community might be transferrable to other communities. There is a strong relationship between children's health and their educational attainment. Poorer health, educational and social attainment are experienced by children and young people residing within the study area. Despite unique geographical contexts and demography, strategies that align strong leadership and effective management of change across three organisations were key and may make it possible to transfer a primary health care model designed to improve health and education outcomes for children and young people to other rural and remote communities. [ABSTRACT FROM AUTHOR]

Objectives: This study aimed to conduct a learning and development needs analysis of quality improvement partnership capabilities of staff and consumers on partnership committees at an Australian metropolitan hospital and health service. Objectives were to compare consumer and staff self-rated capability importance, performance, and learning needs; to investigate if years of partnership experience influenced ratings; and to ascertain staff and consumer preferred learning strategies. Methods: An online cross-sectional survey was adapted from the Hennessy–Hicks Training Needs Analysis questionnaire. Participants self-rated the importance of, and their performance on, 10 capabilities, across four domains, of an internationally validated co-produced capability development framework. They also rated preferences regarding learning approaches and media. Results: A total of 199 members from 41 committees (174 staff; 25 consumers; response rate 35.38%) participated. There was a statistically significant learning and development need across all capabilities (P < 0.01). The highest learning need was for influencing organisational systems and policy (mean = −0.96; s.d. = 1.23), followed by equalising power and leadership (mean = −0.91; s.d. = 1.22), and then implementing partnership best practices (mean = −0.89; s.d. = 1.22). There were no statistically significant differences between consumers and staff on ratings, or correlations between years of partnership experience and ratings (P < 0.01). A combination of learning approaches was preferred, followed by learning through experience. Self-reflection was least preferred, which is concerning given it may promote equalising power and leadership. Face-to-face then videoconferencing were the preferred learning media. Conclusions: Continuous co-learning for staff and consumers about QI partnerships is essential. Committee members needed more feedback regarding their influence and to be engaged in innovative co-design practices. What is known about the topic? Staff and consumer capabilities are essential for effective collaboration on quality improvement (QI) committees, however, research is lacking. What does this paper add? This learning and development needs analysis provides direction for effective design of education and support programs. What are the implications for practitioners? Staff and consumers should continuously develop QI partnership capabilities together, and through multiple learning approaches. Increased exposure to innovative co-design strategies is needed to enhance capabilities and influence on organisational systems and policies. Sharing power and leadership was also a high learning need with self-reflection being vital. [ABSTRACT FROM AUTHOR]

Objective: To quantify patterns of overtime among doctors-in-training in New South Wales and to explore the reasons doctors-in-training cite for not claiming overtime worked. Methods: A confidential online self-reporting survey was conducted of post-graduate doctors-in-training, working in hospitals in NSW, from post-graduate year 1 through to completion of specialist training. Questions sought to determine the average amount of overtime worked, overtime claiming patterns, and reasons why overtime was not claimed. Comparisons were made by level of training and specialty training pathway. Results: A total of 1351 valid responses were received. Unrostered overtime was extremely common, as was underpayment for work completed. Though 73.5% of respondents reported working at least 5 h of unrostered overtime per fortnight, only 15.6% of respondents reported claiming all their unrostered overtime, and among those who did claim overtime, only 45.5% reported being paid the amount in full. Common reasons for not claiming overtime included workplace cultural expectations (37.0%), and overtime not falling under approved reasons (32.6%). There were statistically significant differences (P < 0.001) in all response categories between critical care, physician and surgical training pathways. Conclusions: The survey data demonstrated a significant disconnect between expectations and reality of working hours among doctors-in-training. This is indicative of concerns regarding loss of income, impaired ability to plan workforce allocation due to hidden workload, and possibly impaired wellbeing. What is known about the topic? Among Australian doctors-in-training, there appears to be a significant discrepancy between contracted working hours, actual expectations for working hours, and remuneration for hours worked. What does this paper add? This paper outlines and analyses patterns of overtime claiming among Australian doctors‐in‐training. Notably, doctors‐in‐training worked significant quantities of unrostered overtime, demonstrating a discrepancy between formal expectations set out by rosters, and the reality of workplace demands. What are the implications for practitioners? These findings have significant implications for healthcare economics, workforce planning and improving junior doctor wellbeing. [ABSTRACT FROM AUTHOR]