Designing and implementing a bundle of care for patients with early-stage breast cancer: lessons from a pilot program.

We present a case study on the design and implementation of a value-based bundled package of care for patients with early-stage breast cancer treated in the private health sector in Australia. Value-based healthcare is an essential change to how we deliver healthcare, shifting the focus from paying for individual services provided to a focus on the health outcomes gained over a full cycle of care. The Australian health system has unintentionally created barriers to value-based cancer care through fragmented care pathways and complex funding arrangements where patients can unexpectedly encounter high out-of-pocket costs. A team of clinicians, service providers, health systems and funding experts, private health insurers and consumers have collaborated to design and pilot a complete bundled package of care for breast cancer patients which aims to address these challenges. With 40 patients recruited to date, early evaluation results show positive patient experience of 'joined-up' care and financial transparency. This case study provides a high-level overview of the approach taken to design and implement the Breast Cancer Bundle and the lessons learned for its expansion in both public and private settings.

Decision discovery using clinical decision support system decision log data for supporting the nurse decision-making process.

BACKGROUND: Decision-making in healthcare is increasingly complex; notably in hospital environments where the information density is high, e.g., emergency departments, oncology departments, and psychiatry departments. This study aims to discover decisions from logged data to improve the decision-making process. METHODS: The Design Science Research Methodology (DSRM) was chosen to design an artifact (algorithm) for the discovery and visualization of decisions. The DSRM's different activities are explained, from the definition of the problem to the evaluation of the artifact. During the design and development activities, the algorithm itself is created. During the demonstration and evaluation activities, the algorithm was tested with an authentic synthetic dataset. RESULTS: The results show the design and simulation of an algorithm for the discovery and visualization of decisions. A fuzzy classifier algorithm was adapted for (1) discovering decisions from a decision log and (2) visualizing the decisions using the Decision Model and Notation standard. CONCLUSIONS: In this paper, we show that decisions can be discovered from a decision log and visualized for the improvement of the decision-making process of healthcare professionals or to support the periodic evaluation of protocols and guidelines.

Examining inequalities in spatial access to national health insurance fund contracted facilities in Kenya.

BACKGROUND: Kenya aims to achieve universal health coverage (UHC) by 2030 and has selected the National Health Insurance Fund (NHIF) as the 'vehicle' to drive the UHC agenda. While there is some progress in moving the country towards UHC, the availability and accessibility to NHIF-contracted facilities may be a barrier to equitable access to care. We estimated the spatial access to NHIF-contracted facilities in Kenya to provide information to advance the UHC agenda in Kenya. METHODS: We merged NHIF-contracted facility data to the geocoded inventory of health facilities in Kenya to assign facility geospatial locations. We combined this database with covariates data including road network, elevation, land use, and travel barriers. We estimated the proportion of the population living within 60- and 120-minute travel time to an NHIF-contracted facility at a 1-x1-kilometer spatial resolution nationally and at county levels using the WHO AccessMod tool. RESULTS: We included a total of 3,858 NHIF-contracted facilities. Nationally, 81.4% and 89.6% of the population lived within 60- and 120-minute travel time to an NHIF-contracted facility respectively. At the county level, the proportion of the population living within 1-hour of travel time to an NHIF-contracted facility ranged from as low as 28.1% in Wajir county to 100% in Nyamira and Kisii counties. Overall, only four counties (Kiambu, Kisii, Nairobi and Nyamira) had met the target of having 100% of their population living within 1-hour (60 min) travel time to an NHIF-contracted facility. On average, it takes 209, 210 and 216 min to travel to an NHIF-contracted facility, outpatient and inpatient facilities respectively. At the county level, travel time to an NHIF-contracted facility ranged from 10 min in Vihiga County to 333 min in Garissa. CONCLUSION: Our study offers evidence of the spatial access estimates to NHIF-contracted facilities in Kenya that can inform contracting decisions by the social health insurer, especially focussing on marginalised counties where more facilities need to be contracted. Besides, this evidence will be crucial as the country gears towards accelerating progress towards achieving UHC using social health insurance as the strategy to drive the UHC agenda in Kenya.

Ten years of hand hygiene excellence: a summary of outcomes, and a comparison of indicators, from award-winning hospitals worldwide.

BACKGROUND: Hand hygiene is a crucial measure for the prevention of healthcare-associated infections (HAIs). The Hand Hygiene Excellence Award (HHEA) is an international programme acknowledging healthcare facilities for their leadership in implementing hand hygiene improvement programmes, including the World Health Organisation's Multimodal Improvement Strategy. This study aimed at summarising the results of the HHEA campaign between 2010 and 2021 and investigating the relationship between different hand hygiene parameters based on data from participating healthcare facilities. METHODS: A retrospective analysis was performed on datasets from HHEA forms, including data on hand hygiene compliance, alcohol-based handrub (ABHR) consumption, and Hand Hygiene Self-Assessment Framework (HHSAF) scores. Descriptive statistics were reported for each variable. The correlation between variables was inspected through Kendall's test, while possible non-linear relationships between hand hygiene compliance, ABHR consumption and HHSAF scores were sought through the Locally Estimated Scatterplot Smoothing or logistic regression models. A tree-structured partitioning model was developed to further confirm the obtained findings. RESULTS: Ninety-seven healthcare facilities from 28 countries in three world regions (Asia-Pacific, Europe, Latin America) were awarded the HHEA and thus included in the analysis. HHSAF scores indicated an advanced hand hygiene promotion level (median 445 points, IQR 395-480). System change (100 [95-100] points) and institutional safety climate (85 [70-95] points) showed the highest and lowest score, respectively. In most cases, hand hygiene compliance was above 70%, with heterogeneity between countries. ABHR consumption above 20 millilitres per patient-day (ml/PD) was widely reported, with overall increasing trends. HHSAF scores were positively correlated with hand hygiene compliance (τ = 0.211, p = 0.007). We observed a positive correlation between compliance rates and ABHR consumption (τ = 0.193, p < 0.001), although the average predicted consumption was stable around 55-60 ml/PD for compliance rates above 80-85%. Logistic regression and partitioning tree analyses revealed that higher HHSAF scores were more likely in the high-ABHR consumption group at cut-offs around 57-59 ml/PD. CONCLUSION: Ten years after its inception, the HHEA proves to be a valuable hand hygiene improvement programme in healthcare facilities worldwide. Consistent results were provided by the different hand hygiene indicators and the HHSAF score represents a valuable proxy measure of hand hygiene compliance.

Central venous access device terminologies, complications, and reason for removal in oncology: a scoping review.

BACKGROUND: Lack of agreed terminology and definitions in healthcare compromises communication, patient safety, optimal management of adverse events, and research progress. The purpose of this scoping review was to understand the terminologies used to describe central venous access devices (CVADs), associated complications and reasons for premature removal in people undergoing cancer treatment. It also sought to identify the definitional sources for complications and premature removal reasons. The objective was to map language and descriptions used and to explore opportunities for standardisation. METHODS: A systematic search of MedLine, PubMed, Cochrane, CINAHL Complete and Embase databases was performed. Eligibility criteria included, but were not limited to, adult patients with cancer, and studies published between 2017 and 2022. Articles were screened and data extracted in Covidence. Data charting included study characteristics and detailed information on CVADs including terminologies and definitional sources for complications and premature removal reasons. Descriptive statistics, tables and bar graphs were used to summarise charted data. RESULTS: From a total of 2363 potentially eligible studies, 292 were included in the review. Most were observational studies (n = 174/60%). A total of 213 unique descriptors were used to refer to CVADs, with all reasons for premature CVAD removal defined in 84 (44%) of the 193 studies only, and complications defined in 56 (57%) of the 292 studies. Where available, definitions were author-derived and/or from national resources and/or other published studies. CONCLUSION: Substantial variation in CVAD terminology and a lack of standard definitions for associated complications and premature removal reasons was identified. This scoping review demonstrates the need to standardise CVAD nomenclature to enhance communication between healthcare professionals as patients undergoing cancer treatment transition between acute and long-term care, to enhance patient safety and rigor of research protocols, and improve the capacity for data sharing.

Decentralising DOT for drug-susceptible TB from the health facilities to the community level in Togo.

In Togo, the COVID-19 pandemic paved the way for decentralising directly observed treatment (DOT) to the community level through the evaluation of two innovative community-based DOT approaches-a community health worker-based (CHW-DOT) and family-based (FB-DOT). METHODS We conducted an observational prospective study from April 2021 to January 2022. Sputum conversion at Month 2 and favourable treatment outcomes at Month 6 were assessed and compared between the two groups. Sociodemographic and clinical factors related to these outcomes were identified. RESULTS A total of 182 TB patients were enrolled. The CHW-DOT group had significantly increased odds of sputum conversion (aOR 2.95, 95% CI 1.09-7.98) and lower odds of unsuccessful treatment outcomes (aOR 0.37, 95% CI 0.13-1.1). Non-smokers had 4.85 higher odds of converting than smokers (aOR 4.85, 95% CI 1.76-13.42) and lower odds of an unsuccessful treatment than smokers (aOR 0.11, 95% CI 0.04-0.32). CONCLUSION CHW-DOT is associated with higher sputum smear conversion rates and a more favourable treatment outcome. The use of tobacco, significantly associated with outcomes, also suggests that a smoking cessation component may be a valuable adjunct to a CHW-DOT approach during TB treatment..

Knowledge mapping of immunotherapy for breast cancer: A bibliometric analysis from 2013 to 2022.

Breast cancer is the leading cause of cancer-related death among women globally. Immunotherapy has emerged as a major milestone in contemporary oncology. This study aims to conduct a bibliometric analysis in the field of immunotherapy for breast cancer, providing a comprehensive overview of the current research status, identifying trends and hotspots in research topics. We searched and retrieved data from the Web of Science Core Collection, and performed a bibliometric analysis of publications on immunotherapy for breast cancer from 2013 to 2022. Current status and hotspots were evaluated by co-occurrence analysis using VOSviewer. Evolution and bursts of knowledge base were assessed by co-citation analysis using CiteSpace. Thematic evolution by bibliometrix package was used to discover keywords trends. The attribution and collaboration of countries/regions, institutions and authors were also explored. A total of 7,975 publications were included. In co-occurrence analysis of keywords, 6 major clusters were revealed: tumor microenvironment, prognosis biomarker, immune checkpoints, novel drug delivery methods, immune cells and therapeutic approaches. The top three most frequently mentioned keywords were tumor microenvironment, triple-negative breast cancer, and programmed cell death ligand 1. The most productive country, institution and author were the USA (2926 publications), the University of Texas MD Anderson Cancer Center (219 publications), and Sherene Loi (28 publications), respectively. There has been a rapid growth in studies on immunotherapy for breast cancer worldwide. This research area has gained increasing attention from different countries and institutions. With the rising incidence of breast cancer, immunotherapy represents a research field of significant clinical value and potential.

A distributed feature selection pipeline for survival analysis using radiomics in non-small cell lung cancer patients.

Predictive modelling of cancer outcomes using radiomics faces dimensionality problems and data limitations, as radiomics features often number in the hundreds, and multi-institutional data sharing is ()often unfeasible. Federated learning (FL) and feature selection (FS) techniques combined can help overcome these issues, as one provides the means of training models without exchanging sensitive data, while the other identifies the most informative features, reduces overfitting, and improves model interpretability. Our proposed FS pipeline based on FL principles targets data-driven radiomics FS in a multivariate survival study of non-small cell lung cancer patients. The pipeline was run across datasets from three institutions without patient-level data exchange. It includes two FS techniques, Correlation-based Feature Selection and LASSO regularization, and Cox Proportional-Hazard regression with Overall Survival as endpoint. Trained and validated on 828 patients overall, our pipeline yielded a radiomic signature comprising "intensity-based energy" and "mean discretised intensity". Validation resulted in a mean Harrell C-index of 0.59, showcasing fair efficacy in risk stratification. In conclusion, we suggest a distributed radiomics approach that incorporates preliminary feature selection to systematically decrease the feature set based on data-driven considerations. This aims to address dimensionality challenges beyond those associated with data constraints and interpretability concerns.

[The added value of a patient pathway nurse coordinator in prehabilitation and rehabilitation in surgery]. / La plus-value d'un infirmier coordinateur de parcours patient dans la préhabilitation et la réhabilitation en chirurgie.

The nurse coordinator works within a healthcare network to ensure the continuity and quality of the care provided to patients. They act as the interface between medical, paramedical and social care. In some departments, they coordinate the surgical prehabilitation and enhanced rehabilitation program, which aims to optimize the physical, nutritional and psychological state of each patient prior to major surgery. Knowing how to guide patients and their families, advise them and re-explain the medical prescription for discharge sheds light on their situation and reassures them, while enabling them to plan their discharge.

Enhancing the fairness of AI prediction models by Quasi-Pareto improvement among heterogeneous thyroid nodule population.

Artificial Intelligence (AI) models for medical diagnosis often face challenges of generalizability and fairness. We highlighted the algorithmic unfairness in a large thyroid ultrasound dataset with significant diagnostic performance disparities across subgroups linked causally to sample size imbalances. To address this, we introduced the Quasi-Pareto Improvement (QPI) approach and a deep learning implementation (QP-Net) combining multi-task learning and domain adaptation to improve model performance among disadvantaged subgroups without compromising overall population performance. On the thyroid ultrasound dataset, our method significantly mitigated the area under curve (AUC) disparity for three less-prevalent subgroups by 0.213, 0.112, and 0.173 while maintaining the AUC for dominant subgroups; we also further confirmed the generalizability of our approach on two public datasets: the ISIC2019 skin disease dataset and the CheXpert chest radiograph dataset. Here we show the QPI approach to be widely applicable in promoting AI for equitable healthcare outcomes.

Bibliometric analysis of interspinous device in treatment of lumbar degenerative diseases.

In recent years, with the introduction of the concept of lumbar non-fusion, the interspinous device has emerged. The purpose of this study is to bibliometrically analyze the state, areas of interest, and emerging trends in the usage of interspinous devices for the treatment of lumbar degeneration disease, as well as related research fields. Between January 1, 2000 and June 14, 2023, a comprehensive collection of publications on the topic of interspinous devices in the treatment of lumbar degenerative disease (IDTLDD) was procured from the Web of Science. A bibliometric analysis and visualization were subsequently conducted, utilizing various tools including HisCite, VOSviewer, CiteSpace, and bibliometrix package. This process involved the gathering of data on the country, institution, author, journal, reference, and keywords. A comprehensive analysis of 401 publications sourced from 149 journals was conducted, with 1718 authors affiliated with 1188 institutes across 240 countries/regions. Notably, the United States emerged as the leading contributor with 134 published articles on interspinous devices in the treatment of lumbar degenerative disease (33.42%). The most productive institution was Capital Medical University, with (10, 2.49%) publications. The author with the highest publication output was Block, Jon E, with 10 publications. European Spine Journal demonstrated the highest level of productivity, with a publication of (n = 39, 9.73%). The term "X-Stop" was the most frequently utilized keyword, followed by "Lumbar spinal stenosis." The study identified various topics of current interest, such as "Invasive decompression" and "Coflex." The present study provides a comprehensive survey of research trends and developments in the application of interspinous device for the treatment of lumbar degenerative diseases, including relevant research findings and collaborative efforts among authors, institutions, and countries.

Use of improved memory type control charts for monitoring cancer patients recovery time censored data.

Control charts are a statistical approach for monitoring cancer data that can assist discover patterns, trends, and unusual deviations in cancer-related data across time. To detect deviations from predicted patterns, control charts are extensively used in quality control and process management. Control charts may be used to track numerous parameters in cancer data, such as incidence rates, death rates, survival time, recovery time, and other related indicators. In this study, CDEC chart is proposed to monitor the cancer patients recovery time censored data. This paper presents a composite dual exponentially weighted moving average Cumulative sum (CDEC) control chart for monitoring cancer patients recovery time censored data. This approach seeks to detect changes in the mean recovery time of cancer patients which usually follows Weibull lifetimes. The results are calculated using type I censored data under known and estimated parameter conditions. We combine the conditional expected value (CEV) and conditional median (CM) approaches, which are extensively used in statistical analysis to determine the central tendency of a dataset, to create an efficient control chart. The suggested chart's performance is assessed using the average run length (ARL), which evaluates how efficiently the chart can detect a change in the process mean. The CDEC chart is compared to existing control charts. A simulation study and a real-world data set related to cancer patients recovery time censored data is used for results illustration. The proposed CDEC control chart is developed for the data monitoring when complete information about the patients are not available. So, instead of doping the patients information we can used the proposed chart to monitor the patients information even if it is censored. The authors conclude that the suggested CDEC chart is more efficient than competitor control charts for monitoring cancer patients recovery time censored data. Overall, this study introduces an efficient new approach for cancer patients recovery time censored data, which might have significant effect on quality control and process improvement across a wide range of healthcare and medical studies.

A study protocol for integrating outpatient services at the primary health care level as part of the universal health coverage benefit package within the national health insurance program of Pakistan through private health facilities.

Introduction and aim: Pakistan has a mixed-health system where up to 60% of health expenditures are out of pocket. Almost 80% of primary healthcare (PHC) facilities are in the private sector, which is deeply embedded within the country's health system and may account for the unaffordability of healthcare. Since 2016, the existing national health insurance program or Sehat Sahulat Program (SSP), has provided invaluable coverage and financial protection to the millions of low-income families living in Pakistan by providing inpatient services at secondary and tertiary levels. However, a key gap is the non-inclusion of outpatient services at the PHC in the insurance scheme. This study aims to engage a private provider network of general practitioners in select union councils of Islamabad Capital Authority (ICT) of Pakistan to improve access, uptake, and satisfaction and reduce out-of-pocket expenditure on quality outpatient services at the PHC level, including family planning and reproductive health services. Methods and analysis: A 24-month research study is proposed with a 12-month intervention period using a mixed method, two-arm, prospective, quasi-experimental controlled before and after design with a sample of 863 beneficiary families from each study arm, i.e., intervention and control groups (N = 1726) will be selected through randomization at the selected beneficiary family/household level from four peri-urban Union Councils of ICT where no public sector PHC-level facility exists. All ethical considerations will be assured, along with quality assurance strategies. Quantitative pre/post surveys and third-party monitoring are proposed to measure the intervention outcomes. Qualitative inquiry with beneficiaries, general practitioners and policymakers will assess their knowledge and practices. Conclusion and knowledge contribution: PHC should be the first point of contact for accessing health services and appears to serve as a programmatic engine for universal health coverage (UHC). The research aims to study a service delivery model which harnesses the private sector to deliver an essential package of health services as outpatient services under SSP, ultimately facilitating UHC. Findings will provide a blueprint referral system to reduce unnecessary hospital admissions and improve timely access to healthcare. A robust PHC system can improve population health, lower healthcare expenditure, strengthen the healthcare system, and ultimately make UHC a reality.

Men's sociotechnical imaginaries of artificial intelligence for prostate cancer diagnostics - A focus group study.

Artificial intelligence (AI) is increasingly used for diagnostic purposes in cancer care. Prostate cancer is one of the most prevalent cancers affecting men worldwide, but current diagnostic approaches have limitations in terms of specificity and sensitivity. Using AI to interpret MR images in prostate cancer diagnostics shows promising results, but raises questions about implementation, user acceptance, trust, and doctor-patient communication. Drawing on approaches from the sociology of expectations and theories about sociotechnical imaginaries, we explore men's expectations of artificial intelligence for prostate cancer diagnostics. We conducted ten focus groups with 48 men aged 54-85 in Norway with various experiences of prostate cancer diagnostics. Five groups of men had been treated for prostate cancer, one group was on active surveillance, two groups had been through prostate cancer diagnostics without having a diagnosis, and two groups of men had no experience with prostate cancer diagnostics or treatment. Data was subject to reflexive thematic analysis. Our analysis suggests that men's expectations of AI for prostate cancer diagnostics come from two perspectives: Technology-centered expectations that build on their conceptions of AI's form and agency, and human-centered expectations of AI that build on their perceptions of patient-professional relationships and decision-making processes. These two perspectives are intertwined in three imaginaries of AI: The tool imaginary, the advanced machine imaginary, and the intelligence imaginary - each carrying distinct expectations and ideas of technologies and humans' role in decision-making processes. These expectations are multifaceted and simultaneously optimistic and pessimistic; while AI is expected to improve the accuracy of cancer diagnoses and facilitate more personalized medicine, AI is also expected to threaten interpersonal and communicational relationships between patients and healthcare professionals, and the maintenance of trust in these relationships. This emphasizes how AI cannot be implemented without caution about maintaining human healthcare relationships.

Abnormal Colorectal Cancer Test Follow-Up: A Quality Improvement Initiative at a Federally Qualified Health Center.

INTRODUCTION/OBJECTIVES: Colonoscopy completion rates after an abnormal fecal immunochemical test (FIT) are suboptimal, resulting in missed opportunities for early detection and prevention of colorectal cancer. Patient navigation and structured follow-up may improve colonoscopy completion, but implementation of these strategies is not widespread. METHODS: We conducted a quality improvement study using a Plan-Do-Study-Act (PDSA) Model to increase colonoscopy completion after abnormal FIT in a large federally qualified health center serving a diverse and low-income population. Intervention components included patient navigation, and a checklist to promote completion of key steps required for abnormal FIT follow-up. Primary outcome was proportion of patients achieving colonoscopy completion within 6 months of abnormal FIT, assessed at baseline for 156 patients pre-intervention, and compared to 208 patients during the intervention period from April 2017 to December 2019. Drop offs at each step in the follow-up process were assessed. RESULTS: Colonoscopy completion improved from 21% among 156 patients with abnormal FIT pre-intervention, to 38% among 208 patients with abnormal FIT during the intervention (P < .001; absolute increase: 17%, 95% CI: 6.9%-25.2%). Among the 130 non-completers during the intervention period, lack of completion was attributable to absence of colonoscopy referral for 7.7%; inability to schedule a pre-colonoscopy specialist visit for 71.5%; failure to complete a pre-colonoscopy visit for 2.3%; the absence of colonoscopy scheduling for 9.2%; failure to show for a scheduled colonoscopy for 9.2%. CONCLUSIONS: Patient navigation and structured follow-up appear to improve colonoscopy completion after abnormal FIT. Additional strategies are needed to achieve optimal rates of completion.

Is the national health insurance scheme a pathway to sustained access to medicines in Nigeria?

OBJECTIVE: The debate surrounding access to medicines in Nigeria has become increasingly necessary due to the high cost of essential medicine drugs and the prevalence of counterfeit medicines in the country. The Nigerian government has proposed the implementation of the National Health Insurance Scheme (NHIS) to address these issues and guarantee universal access to essential medicines. Access was investigated using the 3 A's (accessibility, affordability, and availability). This paper investigates whether the NHIS is a viable pathway to sustained access to medicines in Nigeria. DESIGN: This was a cross-sectional study using a mixed-methods design. Both qualitative and quantitative methods were utilized for the study. SETTING: This study was conducted at NHIS-accredited public and private facilities in Enugu State. PARTICIPANTS: 296 randomly selected enrollees took part in the quantitative component, while, 6 participants were purposively selected for the qualitative component, where in-depth interviews (IDIs) were conducted face-to-face with NHIS desk officers in selected public and private health facilities. RESULTS: The quantitative findings showed that 94.9% of respondents sought medical help. Our data shows that 78.4% of the respondents indicated that the scheme improved their access to care (accessibility, affordability, and availability). The qualitative results from the NHIS desk officers showed that respondents across all the socio-economic groups reported that the NHIS had marginally improved access to medicine over the years. It was also observed that most of the staff in NHIS-accredited facilities were not adequately trained on the scheme's requirements and that most times, essential drugs were not readily available at the accredited facilities. CONCLUSION: The study findings revealed that although the NHIS has successfully expanded access to medicines, there remain several challenges to its effective implementation and sustainability. Additionally, the scheme's coverage of essential medicines is could be improved even more, leading to reduced access to needed drugs for many Nigerians. A focus on the 3As for the scheme means that all facility categories (private and public) and their interests (where necessary) must be considered in further planning of the scheme to ensure that things work out well.

Digital twins in medicine.

Medical digital twins, which are potentially vital for personalized medicine, have become a recent focus in medical research. Here we present an overview of the state of the art in medical digital twin development, especially in oncology and cardiology, where it is most advanced. We discuss major challenges, such as data integration and privacy, and provide an outlook on future advancements. Emphasizing the importance of this technology in healthcare, we highlight the potential for substantial improvements in patient-specific treatments and diagnostics.

Ophthalmic care may not align with patient need: An analysis on state-wide patient needs and provider density between 2008 and 2022.

PURPOSE: This study aims to assess the extent to which the demand for ophthalmologic care among patients at the state level is reflected in Google Trends data, serving as an indicator of patient desire in ophthalmology. METHODS: For each state, patient interest in ophthalmologic care was estimated using the Google Trends resource measuring web search and YouTube search rates for multiple ophthalmologic terms. We compared the change in search for ophthalmologic terms over time and used ordinary least squares regression to evaluate whether search interest for ophthalmologic terms was able to predict the rate of practicing ophthalmologists in each state. We also compare the changing rates of searches across the web and YouTube to evaluate the resources patients are most likely to utilize. RESULTS: From 2008 to 2022, web search rates for general ophthalmology related terms increased by 43.98%, while search interest for retinal specific terms increased by 19.51%. YouTube specific results for general ophthalmology terms increased by 55.83% while search for retinal terms fell by 58.48%. Ophthalmologic and retinal specific search interest was not significantly associated with either outcome. CONCLUSIONS: Our findings suggest that patient information needs, demographic elements, and the educational backgrounds of residents and fellows - those important factors - are surprisingly poorly correlated with ophthalmology provider density. Furthermore, we observed no noteworthy correlation between the search interest in ophthalmology and the overall density of ophthalmologists or retinal specialists. This implies that there is a pressing need to explore and implement strategies aimed at better aligning these influencing factors the choices made by ophthalmologists in selecting their practice locations to bridge the gap between healthcare availability and public interest.

Can I trust my fake data - A comprehensive quality assessment framework for synthetic tabular data in healthcare.

BACKGROUND: Ensuring safe adoption of AI tools in healthcare hinges on access to sufficient data for training, testing and validation. Synthetic data has been suggested in response to privacy concerns and regulatory requirements and can be created by training a generator on real data to produce a dataset with similar statistical properties. Competing metrics with differing taxonomies for quality evaluation have been proposed, resulting in a complex landscape. Optimising quality entails balancing considerations that make the data fit for use, yet relevant dimensions are left out of existing frameworks. METHOD: We performed a comprehensive literature review on the use of quality evaluation metrics on synthetic data within the scope of synthetic tabular healthcare data using deep generative methods. Based on this and the collective team experiences, we developed a conceptual framework for quality assurance. The applicability was benchmarked against a practical case from the Dutch National Cancer Registry. CONCLUSION: We present a conceptual framework for quality assuranceof synthetic data for AI applications in healthcare that aligns diverging taxonomies, expands on common quality dimensions to include the dimensions of Fairness and Carbon footprint, and proposes stages necessary to support real-life applications. Building trust in synthetic data by increasing transparency and reducing the safety risk will accelerate the development and uptake of trustworthy AI tools for the benefit of patients. DISCUSSION: Despite the growing emphasis on algorithmic fairness and carbon footprint, these metrics were scarce in the literature review. The overwhelming focus was on statistical similarity using distance metrics while sequential logic detection was scarce. A consensus-backed framework that includes all relevant quality dimensions can provide assurance for safe and responsible real-life applications of synthetic data. As the choice of appropriate metrics are highly context dependent, further research is needed on validation studies to guide metric choices and support the development of technical standards.