Performance of artificial intelligence in 7533 consecutive prevalent screening mammograms from the BreastScreen Australia program.

OBJECTIVES: To assess the performance of an artificial intelligence (AI) algorithm in the Australian mammography screening program which routinely uses two independent readers with arbitration of discordant results. METHODS: A total of 7533 prevalent round mammograms from 2017 were available for analysis. The AI program classified mammograms into deciles on the basis of breast cancer (BC) risk. BC diagnoses, including invasive BC (IBC) and ductal carcinoma in situ (DCIS), included those from the prevalent round, interval cancers, and cancers identified in the subsequent screening round two years later. Performance was assessed by sensitivity, specificity, positive and negative predictive values, and the proportion of women recalled by the radiologists and identified as higher risk by AI. RESULTS: Radiologists identified 54 women with IBC and 13 with DCIS with a recall rate of 9.7%. In contrast, 51 of 54 of the IBCs and 12/13 cases of DCIS were within the higher AI score group (score 10), a recall equivalent of 10.6% (a difference of 0.9% (CI -0.03 to 1.89%, p = 0.06). When IBCs were identified in the 2017 round, interval cancers classified as false negatives or with minimal signs in 2017, and cancers from the 2019 round were combined, the radiologists identified 54/67 and 59/67 were in the highest risk AI category (sensitivity 80.6% and 88.06 % respectively, a difference that was not different statistically). CONCLUSIONS: As the performance of AI was comparable to that of expert radiologists, future AI roles in screening could include replacing one reader and supporting arbitration, reducing workload and false positive results. CLINICAL RELEVANCE STATEMENT: AI analysis of consecutive prevalent screening mammograms from the Australian BreastScreen program demonstrated the algorithm's ability to match the cancer detection of experienced radiologists, additionally identifying five interval cancers (false negatives), and the majority of the false positive recalls. KEY POINTS: • The AI program was almost as sensitive as the radiologists in terms of identifying prevalent lesions (51/54 for invasive breast cancer, 63/67 when including ductal carcinoma in situ). • If selected interval cancers and cancers identified in the subsequent screening round were included, the AI program identified more cancers than the radiologists (59/67 compared with 54/67, sensitivity 88.06 % and 80.6% respectively p = 0.24). • The high negative predictive value of a score of 1-9 would indicate a role for AI as a triage tool to reduce the recall rate (specifically false positives).

Collaboration and Context in the Design of Community-Engaged Research Training.

Collaboration between academic researchers and community members, clinicians, and organizations is valued at all levels of the program development process in community-engaged health research (CEnR). This descriptive study examined a convenience sample of 30 projects addressing training in CEnR methods and strategies within the Clinical and Translational Science Awards (CTSA) consortium. Projects were selected from among posters presented at an annual community engagement conference over a 3-year period. Study goals were to learn more about how community participation in the design process affected selection of training topics, how distinct community settings influenced the selection of training formats, and the role of evaluation in preparing training participants to pursue future health research programming. Results indicated (1) a modest increase in training topics that reflected community health priorities as a result of community (as well as academic) participation at the program design stage, (2) a wide range of community-based settings for CEnR training programs, and (3) the majority of respondents conducted evaluations, which led in turn to revisions in the curricula for future training sessions. Practice and research implications are that the collaboration displayed by academic community teams around CEnR training should be traced to see if this participatory practice transfers to the design of health promotion programs. Second, collaborative training design tenets, community formats and settings, and evaluation strategies should be disseminated throughout the CTSA network and beyond. Third, common evaluative metrics and indicators of success for CEnR training programs should be identified across CTSA institutions.

Prevalence of Cervical Cancer Overscreening: Review of a Wellness Registry.

Appropriately matching preventive health services and screenings with patient risk is an important quality indicator. Adherence by both providers and patients to cervical cancer screening guidelines has been inconsistent, resulting in overscreening and increased costs. This study examined the prevalence of cervical cancer overscreening following changes in screening guidelines in a wellness registry database. Cervical cancer overscreening after guideline implementation decreased for 18- to 20-year-old patients from 26.8% to 24.8% (P < .001) and increased for those aged 65 years and older from 11.1% to 12.5% (P = .0005). Black race, Hispanic ethnicity, Medicaid insurance, and the presence of a personal health record were associated with overscreening. Reliability and accuracy of data are a concern when data intended for one purpose, such as clinical care, are used for research. Correctly identifying screening tests in the electronic health record is important so that appropriate screening can be reliably assessed. In this study on the prevalence of cervical cancer overscreening, we used a focused chart review to identify whether screening Pap tests were accurately identified in the electronic medical record. Pap tests were correctly identified as screening in 85% of those aged 18 to 20, and in 74% of those aged 65 and older.

Pilot trial of digital breast tomosynthesis (3D mammography) for population-based screening in BreastScreen Victoria.

OBJECTIVES: To estimate detection measures for tomosynthesis and standard mammography; to assess the feasibility of using tomosynthesis in population-based screening for breast cancer. DESIGN, SETTING: Prospective pilot trial comparing tomosynthesis (with synthesised 2D images) and standard mammography screening of women attending Maroondah BreastScreen, a BreastScreen Victoria service in the eastern suburbs of Melbourne. PARTICIPANTS: Women at least 40 years of age who presented for routine breast screening between 18 August 2017 and 8 November 2018. MAIN OUTCOME MEASURES: Cancer detection rate (CDR); proportion of screens that led to recall for further assessment. RESULTS: 5018 tomosynthesis and 5166 standard mammography screens were undertaken in 10 146 women; 508 women (5.0% of screens) opted not to undergo tomosynthesis screening. With tomosynthesis, 49 cancers (40 invasive, 9 in situ) were detected (CDR, 9.8 [95% CI, 7.2-13] per 1000 screens); with standard mammography, 34 cancers (30 invasive, 4 in situ) were detected (CDR, 6.6 [95% CI, 4.6-9.2] per 1000 screens). The estimated difference in CDR was 3.2 more detections (95% CI, -0.32 to 6.8) per 1000 screens with tomosynthesis; the difference was greater for repeat screens and for women aged 60 years or more. The recall rate was greater for tomosynthesis (4.2%; 95% CI, 3.6-4.8%) than standard mammography (3.0%; 95% CI, 2.6-3.5%; estimated difference, 1.2%; 95% CI, 0.46-1.9%). The median screen reading time for tomosynthesis was 67 seconds (interquartile range [IQR] 46-105 seconds); for standard mammography, 16 seconds (IQR, 10-29 seconds). CONCLUSIONS: Breast cancer detection, recall for assessment, and screen reading time were each higher for tomosynthesis than for standard mammography. Our preliminary findings could form the basis of a large scale comparative evaluation of tomosynthesis and standard mammography for breast screening in Australia. TRIAL REGISTRATION: Australian New Zealand Clinical Trials Registry, ACTRN12617000947303.

Using High-Fidelity Simulation to Assess Knowledge, Skills, and Attitudes in Nurses Performing CRRT.

Continuous renal replacement therapy (CRRT) is an acute therapy for critically ill patients. There are many life-threatening complications that can occur; therefore, it is imperative that nurses are highly trained in the use and troubleshooting of CRRT. A structured simulation exercise was added to an existing CRRT education program by developing and implementing an annual assessment of knowledge, skills, and attitudes (KSAs) using high-fidelity simulation. The use of high-fidelity simulation as an intervention during annual evaluation of KSAs was shown to be effective in increasing nurse satisfaction, understanding of CRRT principles, and critical thinking skills with the operation of CRRT.

Data sharing across osteoarthritis research groups and disciplines: Opportunities and challenges.

Background: Osteoarthritis is a heterogeneous condition characterised by a wide variety of factors and represents a worldwide healthcare challenge. There are multiple clinical and research specialisms involved in the diagnosis, prognosis and treatment of osteoarthritis, and there may be opportunities to share or pool data which are currently not being utilised. However, there are challenges to doing so which require carefully structured solutions and partnership working. Methods: Interviews were conducted with nine experts from various fields within osteoarthritis research. A semi-structured approach was used, and thematic analysis applied to the results. Results: Generally, osteoarthritis researchers were supportive of data sharing, provided it is done responsibly and without impacting data integrity. Benefits identified included increasing typically low-powered data, the potential for machine learning opportunities, and the potential for improved patient outcomes. However, a number of challenges were identified, relating to: data security, data harmonisation, storage costs, ethical considerations and governance. Conclusions: There is clear support for increased data sharing and partnership working in osteoarthritis research. Further investigation will be required to navigate the complex issues identified; however, it is clear that collaborative opportunities should be better facilitated and there may be innovative ways to do this. It is also clear that nomenclature within different disciplines could be better streamlined, to improve existing opportunities to harmonise data.

Driving health promotion into the community: an initiative evaluated.

Health promotion and lifestyle advice is traditionally undertaken within health centres and general practices. However, evidence indicates that it can have modest impact on preventing disease. More contemporary ideas emphasize a community-based approach to health promotion activities and ultimately focus any screening performance according to the needs of the public. Utilizing a multi-level community approach to health promotion and screening activity within the Black Country is highlighted as being highly successful in shaping a dynamic local community initiative.

Factors involved in treatment decision making for women diagnosed with ductal carcinoma in situ: A qualitative study.

Whilst some of the diversity in management of women with ductal carcinoma in situ (DCIS) may be explained by tumour characteristics, the role of patient preference and the factors underlying those preferences have been less frequently examined. We have used a descriptive qualitative study to explore treatment decisions for a group of Australian women diagnosed with DCIS through mammographic screening. Semi-structured telephone interviews were performed with 16 women diagnosed with DCIS between January 2012 and December 2018, recruited through the LifePool dataset (a subset of BreastScreen participants who have agreed to participate in research). Content analysis using deductive coding identified three themes: participants did not have a clear understanding of their diagnosis or prognosis; reported involvement in decision making about management varied; specific factors including the psychosexual impact of mastectomy and perceptions of radiotherapy, could act as barriers or facilitators to specific decisions about treatment. The treatment the women received was not simply determined by the characteristics of their disease. Interaction with the managing clinician was pivotal, however many other factors played a part in individual decisions. Recognising that decisions are not purely a function of disease characteristics is important for both women with DCIS and the clinicians who care for them.

Evaluation of patient perception towards dynamic health data sharing using blockchain based digital consent with the Dovetail digital consent application: A cross sectional exploratory study.

BACKGROUND: New patient-centric integrated care models are enabled by the capability to exchange the patient's data amongst stakeholders, who each specialise in different aspects of the patient's care. This requires a robust, trusted and flexible mechanism for patients to offer consent to share their data. Furthermore, new IT technologies make it easier to give patients more control over their data, including the right to revoke consent. These characteristics challenge the traditional paper-based, single-organisation-led consent process. The Dovetail digital consent application uses a mobile application and blockchain based infrastructure to offer this capability, as part of a pilot allowing patients to have their data shared amongst digital tools, empowering patients to manage their condition within an integrated care setting. OBJECTIVE: To evaluate patient perceptions towards existing consent processes, and the Dovetail blockchain based digital consent application as a means to manage data sharing in the context of diabetes care. METHOD: Patients with diabetes at a General Practitioner practice were recruited. Data were collected using focus groups and questionnaires. Thematic analysis of the focus group transcripts and descriptive statistics of the questionnaires was performed. RESULTS: There was a lack of understanding of existing consent processes in place, and many patients did not have any recollection of having previously given consent. The digital consent application received favourable feedback, with patients recognising the value of the capability offered by the application. Patients overwhelmingly favoured the digital consent application over existing practice. CONCLUSIONS: Digital consent was received favourably, with patients recognising that it addresses the main limitations of the current process. Feedback on potential improvements was received. Future work includes confirmation of results in a broader demographic sample and across multiple conditions.

Perspectives on Precision Health Among Racial/Ethnic Minority Communities and the Physicians That Serve Them.

Background: In order for precision health to address health disparities, engagement of diverse racial/ethnic minority communities and the physicians that serve them is critical. Methods: A community-based participatory research approach with mixed methods was employed to gain a deeper understanding of precision health research and practice among American Indian, African American, Latino, Chinese, and Vietnamese groups and physicians that serve these communities. A survey assessed demographics and opinions of precision health, genetic testing, and precision health research. Focus groups (n=12) with each racial/ethnic minority group and physicians further explored attitudes about these topics. Results: One hundred community members (American Indian [n=17], African American [n=13], Chinese [n=17], Latino [n=27], and Vietnamese [n=26]) and 14 physicians completed the survey and participated in the focus groups. Familiarity with precision health was low among community members and high among physicians. Most groups were enthusiastic about the approach, especially if it considered influences on health in addition to genes (eg, environmental, behavioral, social factors). Significant concerns were expressed by African American and American Indian participants about precision health practice and research based on past abuses in biomedical research. In addition, physician and community members shared concerns such as security and confidentiality of genetic information, cost and affordability of genetic tests and precision medicine, discrimination and disparities, distrust of medical and research and pharmaceutical institutions, language barriers, and physician's specialty. Conclusions: Engagement of racial/ethnic minority communities and the providers who serve them is important for advancing a precision health approach to addressing health disparities.