Search

Autonomous Artificial Intelligence (AI) has the potential to reduce disparities, improve quality of care, and reduce cost by improving access to specialty diagnoses at the point-of-care. Diabetes and related complications represent a significant source of health disparities. Vision loss is a complication of diabetes, and there is extensive evidence supporting annual eye exams for prevention. Prior to the use of autonomous AI, store-and-forward imaging approaches using remote reading centers (asynchronous telemedicine) attempted to increase diabetes related eye exams with limited success. In 2018, after rigorous clinical validation, the first fully autonomous AI system [LumineticsCore™ (formerly IDx-DR), Digital Diagnostics Inc., Coralville, IA, United States] received U.S. Food and Drug Administration (FDA) De Novo authorization. The system diagnoses diabetic retinopathy (including macular edema) without specialist physician overread at the point-of-care. In addition to regulatory clearance, reimbursement, and quality measure updates, successful adoption requires local optimization of the clinical workflow. The general challenges of frontline care clinical workflow have been well documented in the literature. Because healthcare AI is so new, there remains a gap in the literature about challenges and opportunities to embed diagnostic AI into the clinical workflow. The goal of this review is to identify common workflow themes leading to successful adoption, measured as attainment number of exams per month using the autonomous AI system against targets set for each health center. We characterized the workflow in four different US health centers over a 12-month period. Health centers were geographically dispersed across the Midwest, Southwest, Northeast, and West Coast and varied distinctly in terms of size, staffing, resources, financing and demographics of patient populations. After 1 year, the aggregated number of diabetes-related exams per month increased from 89 after the first month of initial deployment to 174 across all sites. Across the diverse practice types, three primary determinants underscored sustainable adoption: (1) Inclusion of Executive and Clinical Champions; (2) Underlining Health Center Resources; and (3) Clinical workflows that contemplate patient identification (pre-visit), LumineticsCore Exam Capture and Provider Consult (patient visit), and Timely Referral Triage (post-visit). In addition to regulatory clearance, reimbursement and quality measures, our review shows that addressing the core determinants for workflow optimization is an essential part of large-scale adoption of innovation. These best practices can be generalizable to other autonomous AI systems in front-line care settings, thereby increasing patient access, improving quality of care, and addressing health disparities.

Background: The Nuffield Trust’s report on NHS winter pressures highlights a lack of data for primary care, with a consequential focus on secondary care. An increase in data is required on the scale of the winter demand on primary care, so the need for investment in this area can be clearly seen. Aim: To quantify seasonal variation in workload in primary and secondary care. Design & setting: Analysis of data for nine GP practices in Greater Manchester with a patient population of 75 421. Method: Descriptive and comparative analyses were performed for winter and summer periods in 2018–2019. Data were obtained from the North of England Clinical Support Unit (NECSU) via the Rapid Actionable Insight Driving Reform (RAIDR) toolkit, and EMIS Enterprise clinical audit tools. Results: Accident and emergency (A&E) attendances increased by 4% (P = 0.035) during winter with no difference in the number of hospital admissions (P = 0.668). The number of problems (defined as separate diagnoses or causes for a GP consultation, for example, chest infection or medication request) seen in general practice increased by 61% (P

Background: The Nuffield Trust's report on NHS winter pressures highlights a lack of data for primary care, with a consequential focus on secondary care. An increase in data is required on the scale of the winter demand on primary care, so the need for investment in this area can be clearly seen. Aim: To quantify seasonal variation in workload in primary and secondary care. Design & setting: Analysis of data for nine GP practices in Greater Manchester with a patient population of 75 421. Method: Descriptive and comparative analyses were performed for winter and summer periods in 2018-2019. Data were obtained from the North of England Clinical Support Unit (NECSU) via the Rapid Actionable Insight Driving Reform (RAIDR) toolkit, and EMIS Enterprise clinical audit tools. Results: Accident and emergency (A&E) attendances increased by 4% (P = 0.035) during winter with no difference in the number of hospital admissions (P = 0.668). The number of problems (defined as separate diagnoses or causes for a GP consultation, for example, chest infection or medication request) seen in general practice increased by 61% (P<0.001) in winter compared to summer, as did the number of GP consultations, which was also 61% (P<0.001). Respiratory diagnoses saw the greatest seasonal variation accounting for 10% in winter compared with 4% in summer (P<0.001). Self-referral accounted for 66% of all A&E attendance and increased by 16% in winter. GP referral accounted for 7% in winter and 6% in summer (P = 0.002). Conclusion: General practice observed a greater seasonal increase in presenting patients compared with secondary care. Any winter pressures strategy should target both respiratory illness and patients who self-refer to A&E. Transferring 50% of self-referrals in Manchester to GP appointments would achieve a £2.3 million cost saving. Increasing provision in primary care requires funding and increased appointments, but more importantly improved patient opportunities to easily access timely advice and assistance. [ABSTRACT FROM AUTHOR]

Due to the increasing social and economic costs of dementia, there are urgent calls to develop accessible and sustainable care for people with dementia and their caregivers. Multi-component non-pharmacological interventions (NPIs) appear effective in improving or maintaining daily functioning and well-being, but are typically labour-intensive for health care professionals, thus hindering access. The current study aimed to explore the feasibility and acceptability of a novel approach to widen access to NPI by involving caregivers to present part of the intervention and with staff from local support organizations instructed to train the caregivers. Trainers and caregivers were shown to comply with training instructions and the direct intervention costs were low. Feedback from trainers and caregivers was positive and well-being ratings from people with dementia and caregivers remained stable over time and caregivers' sense of competence improved. The findings suggest that involving caregivers and trained non-professionals to provide the intervention is feasible and acceptable and could be a cost-effective solution to improve access to care. [ABSTRACT FROM AUTHOR]

Autonomous Artificial Intelligence (AI) has the potential to reduce disparities, improve quality of care, and reduce cost by improving access to specialty diagnoses at the point-of-care. Diabetes and related complications represent a significant source of health disparities. Vision loss is a complication of diabetes, and there is extensive evidence supporting annual eye exams for prevention. Prior to the use of autonomous AI, store-and-forward imaging approaches using remote reading centers (asynchronous telemedicine) attempted to increase diabetes related eye exams with limited success. In 2018, after rigorous clinical validation, the first fully autonomous AI system [LumineticsCore™ (formerly IDx-DR), Digital Diagnostics Inc., Coralville, IA, United States] received U.S. Food and Drug Administration (FDA) De Novo authorization. The system diagnoses diabetic retinopathy (including macular edema) without specialist physician overread at the point-of-care. In addition to regulatory clearance, reimbursement, and quality measure updates, successful adoption requires local optimization of the clinical workflow. The general challenges of frontline care clinical workflow have been well documented in the literature. Because healthcare AI is so new, there remains a gap in the literature about challenges and opportunities to embed diagnostic AI into the clinical workflow. The goal of this review is to identify common workflow themes leading to successful adoption, measured as attainment number of exams per month using the autonomous AI system against targets set for each health center. We characterized the workflow in four different US health centers over a 12-month period. Health centers were geographically dispersed across the Midwest, Southwest, Northeast, and West Coast and varied distinctly in terms of size, staffing, resources, financing and demographics of patient populations. After 1 year, the aggregated number of diabetes-related exams per month increased from 89 after the first month of initial deployment to 174 across all sites. Across the diverse practice types, three primary determinants underscored sustainable adoption: (1) Inclusion of Executive and Clinical Champions; (2) Underlining Health Center Resources; and (3) Clinical workflows that contemplate patient identification (pre-visit), LumineticsCore Exam Capture and Provider Consult (patient visit), and Timely Referral Triage (post-visit). In addition to regulatory clearance, reimbursement and quality measures, our review shows that addressing the core determinants for workflow optimization is an essential part of large-scale adoption of innovation. These best practices can be generalizable to other autonomous AI systems in front-line care settings, thereby increasing patient access, improving quality of care, and addressing health disparities., Competing Interests: JG, DW, ML, and AJ are employed by Digital Diagnostics Inc., (© 2023 Goldstein, Weitzman, Lemerond and Jones.)

Background The UK military runs a comprehensive mental health service ordinarily accessed via primary care referrals. Aims To evaluate the feasibility of self-referral to mental health services within a military environment. Methods Three pilot sites were identified; one from each service (Royal Navy, Army, Air Force). Sociodemographic information included age, rank, service and career duration. Clinical data included prior contact with general practitioner (GP), provisional diagnosis and assessment outcome. Results Of the 57 self-referrals, 69% (n = 39) had not previously accessed primary care for their current difficulties. After their mental health assessment, 47 (82%) were found to have a formal mental health problem and 41 (72%) were offered a further mental health clinician appointment. The data compared favourably with a large military mental health department that reported 87% of primary care referrals had a formal mental health condition. Conclusions The majority of self-referrals had formal mental health conditions for which they had not previously sought help from primary care; most were offered further clinical input. This supports the view that self-referral may be a useful option to encourage military personnel to seek professional care over and above the usual route of accessing care through their GP. [ABSTRACT FROM AUTHOR]

Purpose – The purpose of this paper is to investigate the treatment effects of Quest cognitive hypnotherapy (QCH) on anxiety and depression, and make comparisons with published data from the Improving Access to Psychological Therapies (IAPT) project. Design/methodology/approach – Adult clients of QCH therapists were invited to enrol in a Practice Research Network (PRN) and completed pre- and post-therapy measures of anxiety (GAD-7) and depression (PHQ-9). Findings – Post-treatment scores were available for 83 of the 106 clients reaching caseness (above the clinical cut-off on either or both measures) on their pre-treatment scores. Totally, 59 clients had moved to recovery, representing 71 per cent of cases where post scores were available and 56 per cent of the intent to treat (ITT) population (106 clients). Additionally, including all cases (both above and below cut-offs) 118 clients had post-treatment measures. In total, 86 (73 per cent) clients improved reliably. The mean number of treatment sessions was between three and four. This compares favourably with 2012-2013 IAPT findings using the same measures. Research limitations/implications – This study was exploratory involving a client group paying privately for treatment. There was no randomised control group or attempt to evaluate the effectiveness of specific components of therapy. Practical implications – QCH may offer a brief effective treatment for clients with clinically significant levels of anxiety and/or depression, widening client choice. Originality/value – As the first study to explore the effectiveness of private QCH this study offers an example of how to use a PRN to compare with published IAPT data using the same measurement tools. [ABSTRACT FROM AUTHOR]

This article describes an audit of national guidelines for cognitive behaviour therapy (CBT) for schizophrenia and other psychoses in a community mental health team. The audit confirmed that the number of referrals for CBT for people under the care of the team with a diagnosis of schizophrenia or psychosis fell short of national guidelines. Barriers to implementation of National Institute for Health and Care Excellence (NICE) guidelines for schizophrenia and other psychoses at the service user, practitioner and organisational levels are outlined in the article and recommendations for ways to address these issues are explored. [ABSTRACT FROM AUTHOR]

Abstract: Although available evidence indicates that vouchers improve service utilization among the target populations, we do not know whether increased utilization results from improved access (new clients who would not have used services without the voucher) or from shifting clients from non-accredited to contracted service providers. This paper examines whether the safe motherhood voucher program in Kenya is associated with improved access to health facility delivery using information on births within two years preceding the survey in voucher and comparison sites. Data were collected in 2010–2011 and in 2012 among 2933 and 3094 women aged 15–49 years reporting 962 and 1494 births within two years before the respective surveys. Analysis entails cross-tabulations and estimation of multilevel random-intercept logit models. The results show that the proportion of births occurring at home declined by more than 10 percentage points while the proportion of births delivered in health facilities increased by a similar margin over time in voucher sites. The increase in facility-based births occurred in both public and private health facilities. There was also a significant increase in the likelihood of facility-based delivery (odds ratios [OR]: 2.04; 95% confidence interval [CI]: 1.40–2.98 in the 2006 voucher arm; OR: 1.72; 95% CI: 1.22–2.43 in the 2010–2011 voucher arm) in voucher sites over time. In contrast, there were no significant changes in the likelihood of facility-based delivery in the comparison arm over time. These findings suggest that the voucher program contributed to improved access to institutional delivery by shifting births from home to health facilities. However, available evidence from qualitative data shows that some women who purchased the vouchers did not use them because of high transportation costs to accredited facilities. The implication is that substantial improvements in service uptake could be achieved if the program subsidized transportation costs as well. [Copyright &y& Elsevier]

Objective: To introduce stepped care as a method of organizing the delivery of treatments, and to consider the factors necessary for implementation. Method: Stepped care is described within the context of strategies such as collaborative care that aim to increase access to mental health care through the improved coordination of care between primary and specialist mental health services. Results from the implementation of stepped care in the United Kingdom and elsewhere are used to highlight the factors required for introducing stepped care into routine services. Issues to address when implementing highvolume services for common mental health problems are derived from this experience. Results: Stepped care sits within the continuum of organizational systems, from situations where responsibility rests almost entirely with primary care clinicians to systems where all patients are managed by specialists for the entire duration of their treatment. Its core principles of delivering low-burden treatments first, followed by careful patient progress monitoring to step patients up to more intensive treatment, are easy to articulate but lead to considerable implementation diversity when services attempt to work in this manner. Services need to ensure they have specific staff competency training, including skills in delivering evidencebased treatments, access to telephony, and smart patient management informatics systems. Conclusions: Stepped care can provide the delivery system for supported self-management. To be successful, health systems need high levels of clinical outcome data and appropriately trained workers. Further attention is required to ensure equity of access and to reduce patient attrition in these systems. [ABSTRACT FROM AUTHOR]

Purpose: We identified sociodemographic characteristics that predict poor disease understanding in low income, uninsured men with prostate cancer. Materials and Methods: A total of 399 low income, uninsured men with prostate cancer participating in the Men’s Health Survey done by researchers at University of California-Los Angeles Jonsson Comprehensive Cancer Center completed questionnaires assessing their knowledge of prostate cancer. Logistic regression was used to identify sociodemographic factors, eg age, education level, language preference, ethnicity and relationship status, associated with poor prostate cancer knowledge. Results: Most subjects were Latino (54% or 213 of 399), spoke English (53% or 213 of 399) and had a high school education or less (86% or 344 of 399). In the multivariate model increasing age (p <0.014) and less than a high school education (p <0.012) were associated with lower knowledge of disease, while Latino ethnicity and relationship status were not. Conclusions: Among low income men with prostate cancer increasing age and less formal education were associated with lower knowledge of disease. Further study is needed to determine the roles of language preference and ethnicity in the understanding of the disease in patients with prostate cancer. [Copyright &y& Elsevier]

The objective of this study was to provide what we believe to be the first report of the establishment of a clinical psychology service to provide accessible psychological assessment, intervention and crisis support, integrated within an existing East London sexual health clinical and outreach service for commercial sex workers (CSWs). Data are presented on referral patterns, demographics, presenting issues to clinical psychology, interventions and outcomes for the first year of the service. Women presented with a range of psychosocial needs. Psychological interventions included direct therapy, signposting to other services and consultation with staff. We concluded that this flexible model of service provision improves access to mental health services within the context of a specialist sexual health and outreach service for CSWs. The provision of a named, female clinical psychologist who provides both the clinical sessions and attends outreach has been an important factor in developing trust and familiarity, leading to better uptake of the clinical psychology service. [ABSTRACT FROM AUTHOR]

Genitourinary medicine services have had to modernize to try to meet the growth in demand. Changes should be audited to ensure standards remain high. We introduced a 'comprehensive care nurse-led service' for patients presenting for asymptomatic screening and as asymptomatic contacts (partners of known positive patients). Following implementation we audited outcomes and patient satisfaction. During the audit period (01/07/2005 to 30/11/2005), 446 patients were seen. A sexual health screen was performed in 433 (216 females: 217 males). Forty-one patients (9.5%) were chlamydia-positive by enzyme-linked immunosorbent assay testing (background clinic rate 8.5%). Forty-six (10.6%) were treated epidemiologically as chlamydia-negative contacts of chlamydia-positive index patients and 18 (4.1%) were treated as chlamydia-negative urethritis/cervicitis. Uptake of HIV testing was 71.2% (311/433). Average wait-to-appointment was three days (background clinic wait 2–3 weeks). Nurse-led clinics were judged successful in terms of outcomes, improving access and patient satisfaction. [ABSTRACT FROM AUTHOR]