Mahdi Mahdavi

Background: The clinical value of artificial intelligence (AI)–based diagnostic systems depends not only on their accuracy but also on how well their outputs integrate with clinicians’ judgments in practice. Critical knowledge gaps remain regarding diagnostic concordance between AI and clinicians in stress echocardiography interpretation, patient characteristics predicting discordance, and how cardiologists respond when AI recommendations conflict with their clinical diagnoses. Objective: This study examined the diagnostic alignment between an AI-driven stress echocardiography system (EchoGo Pro [EGP]) and cardiologists’ diagnoses of coronary artery disease (CAD), identified predictors of concordance and AI scan rejection, and explored cardiologists’ decision-making strategies when disagreements arise. Methods: We conducted mixed methods research. The quantitative study analyzed concordance between EGP and cardiologists using data from 854 participants with suspected CAD in the multicenter PROTEUS randomized controlled trial. Logistic regression identified predictors of agreement, disagreement, and scan rejection, adjusting for age, sex, smoking status, BMI, and cardiovascular risk factors (hypertension, hypercholesterolemia, diabetes, family history of CAD, and prior CAD events). To gain deeper insight into discordance, we conducted a qualitative study analyzing survey responses from 61 UK consultant cardiologists recruited via Qualtrics, exploring their perceptions of AI tools, the risks of following discordant AI recommendations, and their typical responses to AI-clinician disagreement. Results: EGP and cardiologists agreed in 60% (512/854) of the cases, but agreement was significantly lower among patients with hypertension (OR 0.58, 95% CI 0.38‐0.89; P =.01), diabetes (OR 0.56, 95% CI 0.35‐0.90; P =.02), and pre-existing CAD (OR 0.48, 95% CI 0.30‐0.77; P =.002). EGP rejected 26.1% (222/854) of the scans due to insufficient image quality, with rejection significantly more common in male patients ( β =0.35; P =.03) and those with a family history of CAD. If a positive CAD diagnosis was assigned when either cardiologists or EGP identified CAD, the proportion of positive cases increased from 17.9% (153/854) to 22.1% (189/854), potentially identifying additional at-risk patients. Survey respondents (50/60, 85% male; 26/57, 46% aged 40-49 years; 39/61, 64% White) required 65% to 69% confidence in their initial diagnosis to justify disregarding contradictory AI recommendations. The survey findings revealed cardiologists treated AI recommendations as advisory rather than definitive. When facing discordance, they retained confidence in their judgment and sought corroboration through additional testing, data review, or second opinions rather than deferring to AI. Paradoxically, cardiologists with higher confidence in AI tools required greater confidence in their own diagnosis to disregard AI recommendations ( β =7.73; P =.02). Cardiologists attributed discordance primarily to AI’s inability to incorporate patient history, comorbidities, and broader clinical context. Conclusions: EGP shows promise as an adjunctive tool but struggles with multimorbid patients and exhibits high, uneven rejection rates. Cardiologists use AI to prompt scrutiny, not replace judgment. Future systems need to integrate wider patient data with imaging and minimize bias through representative training to avoid exacerbating inequities.

Introduction The use and value of artificial intelligence (AI)-driven tools and techniques are under investigation in detecting coronary artery disease (CAD). EchoGo Pro is a patented AI-driven stress echocardiography analysis system produced by Ultromics Ltd. (henceforth Ultromics) to support clinicians in detecting cardiac ischaemia and potential CAD. This manuscript presents the research protocol for a field study to independently evaluate the accuracy, acceptability, implementation barriers, users’ experience and willingness to pay, cost-effectiveness and value of EchoGo Pro. Methods and analysis The ‘Evaluating AI-driven stress echocardiography analysis system’ (EASE) study is a mixed-method evaluation, which will be conducted in five work packages (WPs). In WP1, we will examine the diagnostic accuracy by comparing test reports generated by EchoGo Pro and three manual raters. In WP2, we will focus on interviewing clinicians, innovation/transformation staff, and patients within the National Health Service (NHS), and staff within Ultromics, to assess the acceptability of this technology. In this WP, we will determine convergence and divergence between EchoGo Pro recommendations and cardiologists’ interpretations and will assess what profile of cases is linked with convergence and divergence between EchoGo Pro recommendations and cardiologists’ interpretations and how these link to outcomes. In WP4, we will conduct a quantitative cross-sectional survey of trust in AI tools applied to cardiac care settings among clinicians, healthcare commissioners and the general public. Lastly, in WP5, we will estimate the cost of deploying the EchoGo Pro technology, cost-effectiveness and willingness to pay cardiologists, healthcare commissioners and the general public. The results of this evaluation will support evidence-informed decision-making around the widespread adoption of EchoGo Pro and similar technologies in the NHS and other health systems. Ethics approval and dissemination This research has been approved by the NHS Health Research Authority (IRAS No: 315284) and the London South Bank University Ethics Panel (ETH2223-0164). Alongside journal publications, we will disseminate study methods and findings in conferences, seminars and social media. We will produce additional outputs in appropriate forms, for example, research summaries and policy briefs, for diverse audiences in NHS.

The significance of establishing and strengthening a national research system to meet the demands of a health system was emphasised at the 2008 Global Ministerial Meeting on Research for Health, held in Bamako, Mali [1]. In recent years, the role of research evidence in response to the coronavirus disease 2019 (COVID-19) pandemic has highlighted the […]

Background: Providing valid evidence to policy-makers is a key factor in the development of evidence-informed policy-making (EIPM). This study aims to review interventions used to promote researchers’ and knowledge-producing organizations’ knowledge and skills in the production and translation of evidence to policy-making and explore the interventions at the individual and institutional level in the Iranian health system to strengthen EIPM. Methods: The study was conducted in two main phases: a systematic review and a qualitative study. First, to conduct the systematic review, the PubMed and Scopus databases were searched. Quality appraisal was done using the Joanna Briggs Institute checklists. Second, semi-structured interviews and document review were used to collect local data. Purposive sampling was used and continued until data saturation. A qualitative content analysis approach was used for data analysis. Results: From a total of 11,514 retrieved articles, 18 papers were eligible for the analysis. Based on the global evidence, face-to-face training workshops for researchers was the most widely used intervention for strengthening researchers’ capacity regarding EIPM. Target audiences in almost all of the training programmes were researchers. Setting up joint training sessions that helped empower researchers in understanding the needs of health policy-makers had a considerable effect on strengthening EIPM. Based on the local collected evidence, the main interventions for individual and institutional capacity-building were educational and training programmes or courses related to the health system, policy-making and policy analysis, and research cycle management. To implement the individual and institutional interventions, health system planners and authorities and the community were found to have a key role as facilitating factors. Conclusion: The use of evidence-based interventions for strengthening research centres, such as training health researchers on knowledge translation and tackling institutional barriers that can prevent well-trained researchers from translating their knowledge, as well as the use of mechanisms and networks for effective interactions among policy-makers at the macro and meso (organizational) level and the research centre, will be constructive for individual and institutional capacity-building. The health system needs to strengthen its strategic capacity to facilitate an educational and training culture in order to motivate researchers in producing appropriate evidence for policy-makers.

Background: The institutionalization of evidence-informed health policy-making (EIHP) is complex and complicated. It is complex because it has many players and is complicated because its institutionalization will require many changes that will be challenging to make. Like many other issues, strengthening EIHP needs a road map, which should consider challenges and address them through effective, harmonized and contextualized strategies. This study aims to develop a road map for enhancing EIHP in Iran based on steps of planning. Methods: This study consisted of three phases: (1) identifying barriers to EIHP, (2) recognizing interventions and (3) measuring the use of evidence in Iran's health policy-making. A set of activities was established for conducting these, including foresight, systematic review and policy dialogue, to identify the current and potential barriers for the first phase. For the second phase, an evidence synthesis was performed through a scoping review, by searching the websites of benchmark institutions which had good examples of EIHP practices in order to extract and identify interventions, and through eight policy dialogues and two broad opinion polls to contextualize the list of interventions. Simultaneously, two qualitative-quantitative studies were conducted to design and use a tool for assessing EIHP in the third phase. Results: We identified 97 barriers to EIHP and categorized them into three groups, including 35 barriers on the “generation of evidence” (push side), 41 on the “use of evidence” (pull side) and 21 on the “interaction between these two” (exchange side). The list of 41 interventions identified through evidence synthesis and eight policy dialogues was reduced to 32 interventions after two expert opinion polling rounds. These interventions were classified into four main strategies for strengthening (1) the education and training system (6 interventions), (2) the incentives programmes (7 interventions), (3) the structure of policy support organizations (4 interventions) and (4) the enabling processes to support EIHP (15 interventions). Conclusion: The policy options developed in the study provide a comprehensive framework to chart a path for strengthening the country’s EIHP considering both global practices and the context of Iran. It is recommended that operational plans be prepared for road map interventions, and the necessary resources provided for their implementation. The implementation of the road map will require attention to the principles of good governance, with a focus on transparency and accountability.

Background: SASHA, which stands for "evidence-informed health policy-making (EIHP)" in Persian, is a national project to draw a roadmap for strengthening EIHP in Iran. As a part of SASHA, this research aimed to develop evidence-based and context-aware policy options for increasing the capacity of decision-makers to apply EIHP in Iran. Methods: This was a qualitative study, which was informed by a literature review of pull efforts’ capacity building programs. Based on the review, we developed policy options and validated them through an expert panel that involved twelve experts. Data were analyzed using a content analysis method. Results: We extracted data from 11 articles. The objectives of capacity building programs were: single-skill development, personal/professional development, and organizational development. According to these objectives, the contents and training methods of the programs vary. Capacity building programs have shown positive impacts on individual knowledge/attitudes to use EIHP. However, the impacts of programs at the organizational or the health system level remain under-researched. We followed several threads from the literature review through to the expert panel that included training the management team, instead of training managers, training for problem-solving skills, and designing tailored programs. Barriers of capacity building for EIHP regard the context of the health system (weak accountability and the widespread conflict of interest) and healthcare organizational structures (decision support systems, knowledge management infrastructures, and lack of management team). Experts suggested interventions on the barriers, particularly on resolving the conflict of interests before launching new programs. A proposed framework to increase the capacity of health policy-makers incorporates strategies at three levels: capacity building program, organizational structure, and health system context. Conclusion: To prepare the context of Iranian healthcare organizations for capacity building programs, the conflict of interests needs to be resolved, decision-makers should be made more accountable, and healthcare organizations need to provide more knowledge management infrastructures and decision support systems.

Background: This research analyzed the Sixth Five-Year Economic, Social, and Cultural Development Plan of the Islamic Republic of Iran (6NPD) to shed light on how the plan addresses the Universal Health Coverage (UHC).Methods: This research was a qualitative study. We systematically analyzed ‘Secs. 14 -Health, Insurance, Health & Women, and Family’ in the 6NPD. Through a content analysis, we converted this section into meaning units and coded them. Coding was guided through the conceptual framework ‘Six Building Blocks of Health System’ and the key principles of UHC.Results: Six themes and twenty-one subthemes were identified. The subthemes offinancinginclude a fair and secured process of resource pooling, payment methods, revenue generation for the health sector, and a definition of a basic benefits package. The subthemes ofgovernance and leadershipconsist of social insurance policies’ integration, compliance of providers, a designation of the Ministry of Health and Medical Education (MoHME) as the regulator and the steward of health resources, a payer-provider split, and stakeholders’ participation. The subthemesof health workforceemphasizes balancing the quality and quantity of the health workforce with populations’ health needs and the health system’s requirements. The subthemes ofhealth information systems consist of the electronic health records for Iranians, information systems for organization and delivery functions, and information systems for the financing function. The subthemes of theorganization and deliveryconsider improving effectiveness and efficiency of healthcare delivery, strengthening the family physician program and referral system, and extending the pre-hospital emergency system. Lastly,access to medicinefocuses on the design and implementation of an essential drug list and drug systems for approving the coverage and provision of generic medicine.Conclusions: The 6NPD introduced policies for strengthening the 6 building blocks of the health system. It introduced policies to improve financing particularly resource pooling and the sustainability of financial resources. As mandated by 6NPD, centering the health system’s governance/leadership in MoHME may exacerbate the existing conflict of interests and provoke various arguments, which impede the enforcement of rules and regulation. The 6NPD is a step forward in terms of improving financial protection, yet several other policies need to be made to adequately meet the requirement of UHC regarding equity and effective coverage.

Background: Facing limited health resources, healthcare providers need to rely on health service delivery models that produce the best clinical outcomes and patient experience. We aimed to contribute to developing a patient experience-based type 2 diabetes service delivery model by identifying operational structures and processes of care that were associated with clinical outcome, health experience, and service experience. Methods: We conducted a cross-sectional survey of type 2 diabetes patients between January 2019 to February 2020. Having adjusted for demand variables, we examined relationships between independent variables (behaviours, services/processes, and structures) and three categories of dependent variables; clinical outcomes (HbA1c and fasting blood glucose), health experience (EuroQol quality of life (EQ-5D), evaluation of quality of life (visual analgene scale of EQ-5D), and satisfaction with overall health status), and service experience (evaluation of diabetes services in comparison with worst and best imaginable diabetes services and satisfaction with diabetes services). We analysed data using multivariate linear regression models using Stata software. Results: After adjusting for demand variables; structures, diabetes-specific health behaviours, and processes explained up to 22, 12, and 9% of the variance in the outcomes, respectively. Based on significant associations between the diabetes service operations and outcomes, the components of an experience-based service delivery model included the structural elements (continuity of care, redistribution of task to low-cost resources, and improved access to provider), behaviours (improved patient awareness and adherence), and process elements (reduced variation in service utilization, increased responsiveness, caring, comprehensiveness of care, and shared decision-making). Conclusions: Based on the extent of explained variance and identified significant variables, health services operational factors that determine patient-reported outcomes for patients with type 2 diabetes in Iran were identified, which focus on improving continuity of care and access to providers at the first place, improving adherence to care at the second, and various operational process variables at the third place.

Patient experience is assumed pivotal for improving health services operations. The patient experience of healthcare services in Iran has been mostly assessed through the satisfaction and quality of single services or activities at individual providers, clinical departments, or health facilities. However, given the rise of chronic and multi‐morbid conditions, health services for these conditions consist of several activities and interactions through a journey that patients take in the health system. To fill in this gap, we propose focusing on the assessment of patient experience on the patient journey through the health system. We advocate that there is much potential for improving the patient experience by rethinking the operations management of health services to embrace the patient experience of the healthcare journey. Rethinking health operations management may include an exhaustive list of interventions. Concisely, at the strategic level, policy‐makers while understanding the need for shifting towards the patient experience, make sure that operational level management is experience oriented. This would be pursued through a strategic approach to patient experience, reconsidering qualifications for operational management, and benchmarking to identify and share best practices. Lessons learnt from previous quality improvement programmes are also considered as a capacity to establish the experience orientation.

Background. Facing limited health resources, healthcare providers need to rely on health service delivery models that produce the best clinical outcomes and patient experience. We aimed to contribute to developing a patient experience-based type 2 diabetes service delivery model by identifying operational structures and processes of care that were associated with clinical outcome, health experience, and service experience. Methods. We conducted a cross-sectional survey of type 2 diabetes patients between Jan 2019 to Feb 2020. Having adjusted for demand variables, we examined relationships between independent variables (behaviors, services/processes, and structures) and three categories of dependent variables; clinical outcomes (HbA1c and fasting blood glucose), health experience (EuroQol quality of life (EQ-5D), evaluation of quality of life (visual analgene scale of EQ-5D), and satisfaction with overall health status), and service experience (evaluation of diabetes services in comparison with worst and best imaginable diabetes services and satisfaction with diabetes services). We analysed data using multivariate linear regression models. Results. After adjusting for demand variables; structures, diabetes-specific health behaviours, and processes explained up to 22%, 12%, and 9% of variance in the outcomes, respectively. Based on significant associations between the diabetes service operations and outcomes, the components of an experience-based service delivery model included the structural elements (continuity of care, redistribution of task to low-cost resources, and improved access to provider), behaviours (improved patient awareness and adherence), and process elements (reduced variation in service utilization, increased responsiveness, caring, comprehensiveness of care, and shared decision-making). Conclusions. Based on the extent of explained variance and identified significant variables, health services operational factors that determine patient reported outcomes for patients with type 2 diabetes in Iran were identified, which focus on improving continuity of care and access to providers at the first place, improving adherence to care at the second, and various operational process variables at the third place.