An Artificial Intelligence Oracle for Proactive Population Health Quality Improvement

APhA advances provider status initiative

IntroductionThe purpose of this scoping review was to investigate in the literature how a learning health system (LHS) can be implemented in cases of complex, costly, chronic (3C) conditions.MethodsA scoping review of literature published in English since 2007 was conducted using Medline, Cumulative Index to Nursing and Allied Health Literature, and Scopus. Two authors screened the resulting articles and two authors extracted study details on the structure, process, and outcome of each LHS. Eligibility criteria included studies of LHSs that focused on populations experiencing a complex chronic health condition. A narrative synthesis of data was conducted using deductive qualitative methods.ResultsApplication of the authors’ search strategy resulted in 656 publications that were analyzed for this review. The authors included 17 studies that focused on 13 LHSs. The structure of the LHSs had many components, and many included data from either patient surveys or patient charts. The processes varied widely, from engaging patients in the process to exclusively analyzing the data. The outcomes were largely patient-reported, though several clinical outcomes were also used to benchmark the success of the LHS.DiscussionOur review shows that LHS definitions, structures, processes, and outcomes in 3C applications vary widely. Many have shown substantial potential to be implemented and improve care in 3C populations. To deliver on this goal, future work will need to focus on better specification, formalization, and definition of LHS approaches, as well as better design of their structures, processes, and outcomes to fit the needs of the intended population.

Patient Perspectives on Artificial Intelligence in Radiology

ObjectiveA learning health system (LHS) uses data to generate evidence and answer questions required to continually improve system performance and patient care. Given the complexities of practice transformation, an area...

Diabetes mellitus is a rapidly growing global health challenge, with over 589 million affected individuals and a projected prevalence exceeding 853 million by 2050. The complexity of its management, involving continuous monitoring, multifactorial interventions, and long-term complication prevention, has highlighted the need for innovative approaches. Artificial intelligence (AI), encompassing machine learning (ML), deep learning (DL), and natural language processing (NLP), is increasingly applied in diverse domains of diabetes care. AI supports early diagnosis, individualized treatment, prediction of complications, and patient engagement through digital health platforms. Moreover, AI-driven closed-loop insulin delivery systems represent a paradigm shift toward personalized, automated glucose regulation. This narrative review synthesizes the current evidence regarding the applications, benefits, and limitations of AI in diabetes management. Emphasis is given to diagnostic prediction models, glycemic control, complication surveillance, digital coaching, and integration into healthcare systems. Challenges such as data heterogeneity, algorithmic bias, and regulatory frameworks are critically analyzed. Future perspectives include federated learning, multimodal precision diabetology, and ethical frameworks for equitable implementation. The integration of AI into clinical practice offers transformative potential, but requires rigorous validation, patient-centered design, and interdisciplinary collaboration.

This AI driven case study explores the misdiagnosis of Nicholas David Mirisola, focusing on the complexities surrounding psychiatric evaluations, artificial intelligence (AI) applications in diagnostics, and the unique aspects of Mirisola’s psychological profile. It emphasizes the need for individualized assessments, acknowledging the interplay between creativity, intelligence, and mental health conditions such as Schizoaffective Disorder and PTSD. The misdiagnosis of psychiatric disorders has been a critical concern, highlighting the intricacies of psychiatric evaluations. The case study of Nicholas (Nick) David Mirisola serves as an exemplar, shedding light on the challenges of diagnosing complex mental health conditions. This paper aims to establish a framework examining the historical context of psychiatric misdiagnosis and its implications on current practices. A significant aspect of this exploration includes the misdiagnosis experienced by Mirisola, where individual psychological factors lead to challenges. The importance of recognizing high intelligence and creativity as complicating factors in psychiatric diagnoses is crucial. The intersection of traditional methods and AI technologies offers new avenues for individualized treatment paradigms. The complexities of diagnosing conditions like Schizoaffective Disorder necessitate analyzing existing theoretical frameworks and empirical insights. Traditional criteria have struggled to encapsulate the unique psychological profiles associated with this condition, emphasizing the need for a nuanced approach that considers an individual’s life experiences and cognitive profiles. Research shows that creativity and intelligence may overlap with psychiatric symptoms, challenging standard diagnostic paradigms. Recent advancements in technology, particularly AI, demonstrate promise in enhancing diagnostic accuracy and therapeutic efficacy. However, significant gaps exist regarding the psychological experiences of individuals with complex mental health needs. The exploration of these themes is crucial for improving clinical practices. This study employs a mixed-methods approach, combining qualitative interviews and quantitative metrics to gain a holistic understanding of Mirisola’s psychological profile. Qualitative data focuses on personal experiences, while AI-driven analytics evaluate the effectiveness of traditional versus AI-based diagnostic tools through metrics such as sensitivity and specificity. The methodology aims to explore the nuances of misdiagnosis and the necessary consideration for integrative assessments. The findings suggest that traditional assessments fall short compared to AI diagnostics in accurately reflecting complex psychological profiles. Mirisola’s experiences reveal discrepancies between his internal perceptions and the interpretations of mental health professionals. Genetic factors like the MTHFR gene variant and personalized interventions contribute to understanding his mental health challenges. Interventions aimed at improving overall well-being resulted in measurable reductions in acute episodes, illustrating the significance of personalized treatment approaches. The interplay between intelligence, creativity, and psychiatric diagnoses reveals an urgent need for a revised understanding of how to evaluate high-functioning individuals. Mirisola’s case illustrates the inadequacies of traditional psychiatric frameworks when addressing the unique experiences of highly intelligent individuals. Personalized treatment methodologies are crucial to accurately capturing the complex intersections between creativity, intelligence, and mental health. The research calls for a reevaluation of diagnostic practices, integrating AI while addressing biases inherent in these technologies. The need for holistic understanding within psychiatric evaluations remains paramount. The misdiagnosis of Nicholas David Mirisola underscores the pressing need for more nuanced approaches to psychiatric care. Implementing individualized assessments that recognize the distinct interplay of intelligence and creativity can enhance the efficacy of psychiatric interventions. A commitment to understanding the complexities of psychiatric evaluations will contribute to improving treatments and fostering better patient outcomes while integrating AI capabilities responsibly.

Public health informatics is an evolving domain in which practices constantly change to meet the demands of a highly complex public health and healthcare delivery system. Given the emergence of various concepts, such as learning health systems, smart health systems, and adaptive complex health systems, health informatics professionals would benefit from a common set of measures and capabilities to inform our modeling, measuring, and managing of health system “smartness.” Here, we introduce the concepts of organizational complexity, problem/issue complexity, and situational awareness as three codependent drivers of smart public health systems characteristics. We also propose seven smart public health systems measures and capabilities that are important in a public health informatics professional's toolkit.

Recent transformations of healthcare analytics with artificial intelligence, machine learning, and modern big data have helped in guiding clinical decision-making, allocating resources, and improving clinical outcomes. Healthcare organizations are challenged with managing the rapid inflow of electronic health records, medical imaging, genomic sequencing, wearable technologies, and real-time patient monitoring devices, which require analytics infrastructures beyond what traditional systems can handle. Cloud-native architectures, distributed computing models, and scalable data stores enable the new generation of predictive analytics for anticipatory care models, which leverage cutting-edge artificial intelligence algorithms such as deep learning, natural language processing, and time-series analysis to extract insights from multi-dimensional and heterogeneous healthcare data and generate predictions of clinical deterioration, readmissions, and operational bottlenecks. Health systems show real-world implementations can reduce mortality, enhance intensive care unit capability and flow from the emergency department, and increase operating room capacity. Organizations with more advanced analytics capabilities and experience can achieve greater clinical impact, operational efficiencies, and cost reductions while remaining regulatory compliant and acting ethically. The ultimate vision for AI-enabled transformation in healthcare is a learning health system, in which clinical data continuously collected from the real world feed into predictive models to inform clinical decision-making across the individual patient population. Achieving this vision requires active cultural, cross-domain (clinical/technical/regulatory/ethical), and technological advancement.

As healthcare systems navigate increasing complexity, the need to embed quality improvement (QI) into organizational culture has never been greater. In alignment with national trends emphasizing a shift from compliance-driven quality to shared responsibility and excellence, the University of California Los Angeles (UCLA) Health launched its inaugural Quality Symposium, led by the Department of Medicine. The event aimed to cultivate a Learning Health System community by strengthening shared learning, accelerating system improvement, and increasing the visibility and adoption of QI across clinical settings. The symposium featured a keynote presentation on artificial intelligence (AI) and healthcare transformation, followed by nine Technology, Entertainment, Design (TED)-style talks organized across three modules: ambulatory care quality, inpatient care quality, and research and education. Attendees completed pre- and post-event evaluations assessing satisfaction, perceived learning, and actionable takeaways. The symposium drew 218 registrants and approximately 160 attendees (73%), both in person and online, including physicians, nurses, administrators, and trainees. Among post-survey respondents (62 of approximately 160 attendees, 39%), 52 (88%) reported gaining at least one actionable insight applicable to their work. Qualitative analysis identified themes emphasizing the value of interprofessional storytelling, visible leadership engagement in QI initiatives, and the integration of behavioral science and technology to support improvement efforts. This learning report describes the design, implementation, and perceived educational impact of a health system-wide symposium, framed as a descriptive program evaluation. Findings suggest that narrative-driven education, behavioral insight, and cross-disciplinary engagement may support system learning and collaboration within academic health systems.

Overview Oncology informatics in the era of precision oncology is challenging because no unified comprehensive system exists linking Health Information Technology (HIT) deployed in clinical settings to the translational needs of researchers. Many advanced informatics solutions have been developed for clinical trials, biobanking, cancer imaging, and high‐throughput‐omic technologies. These are fundamentally transforming the treatment and management of cancer patients. However, the lack of fully developed interoperable cancer research informatics and HIT technologies to move between the bench and the bedside remains a significant challenge. Oncologists and translational cancer investigators require knowledge of informatics, data science, and advanced machine learning (artificial intelligence) as these are the major change agents influencing the development of new therapies, especially in the era of Precision Medicine and Learning Health Systems for oncology. In addition, cancer care delivery is very dependent on new developments in clinical practice and requires a thorough, systematic reevaluation of the electronic health records (EHRs) in use today. The ability (through mobile computing) to have information “on demand” during daily oncology practice is reshaping our thinking of how we record, document, and share data toward the common purpose of improving cancer outcomes for the patients we serve. This article looks at HIT and clinical, translational, and research informatics for oncologists and cancer researchers and begins to paint a picture of what an “ideal” environment for cancer care delivery would look like to support Precision Oncology and Learning Health Systems.

Generative techniques in artificial intelligence (AI) and large language models in particular have proliferated in recent months and years. Automation of traditionally human tasks introduces efficiencies, sometimes radically reducing the time required for certain jobs or eliminating them altogether. But the c20onsequences of automation are uneven. For AI to be a net positive for society, it must enhance social productivity and push the frontier of production and services further outward. In these discussions, hyperbole frequently overshadows calm reflection about AI?s broader impact, whether for good or ill. Some parties have warned that this new technology is not only fundamentally altering how humans create, work, and interact but, unless restricted, poses a risk not just to the future of work but also to human civilization itself. Others view it as an opportunity to reach previously unattainable levels of productivity and social and human progress. A balanced perspective demands asking how AI is affecting the delivery of health care a domain in which many processes can theoretically be automated, providing opportunities for exceeding previous levels of productivity and human experience. Until recently, the solution to such questions lay mostly in speculation. Indeed, conversations about AI and health care almost always revolved around technology and machine learning development. Yet clinicians, care teams, and hospitals worldwide are now using AI tools and, in some cases, responding to them as virtual team members. As this use of AI tools in health care spreads, it becomes possible to compare pre-AI and post-AI situations. In principle, such comparisons should focus on the predefined substantive impact framework of health care delivery rather than on speculating about AI?s potential influence on future delivery.

As health systems incorporate artificial intelligence (AI) into various aspects of patient care, there is growing interest in understanding how to ensure transparent and trustworthy implementation. However, little attention has been given to what information patients need about these technologies to promote transparency of their use. We conducted three asynchronous online focus groups with 42 patients across the United States discussing perspectives on their information needs for trust and uptake of AI, focusing on its use in cardiovascular care. Data were analyzed using a rapid content analysis approach. Our results suggest that patients have a set of core information needs, including specific information factors pertaining to the AI tool, oversight, and healthcare experience, that are relevant to calibrating trust as well as perspectives concerning information delivery, disclosure, consent, and physician AI use. Identifying patient information needs is a critical starting point for calibrating trust in healthcare AI systems and designing strategies for information delivery. These findings highlight the importance of patient-centered engagement when developing AI model documentation and communicating and provisioning information about these technologies in clinical encounters.

Will ChatGPT undermine ethical values in nursing education, research, and practice?

Developing a health system intervention that helps to improve primary care in a low-income and middle-income country (LMIC) is a considerable challenge; finding ways to spread that intervention to other...

Artificial Intelligence (AI) is reshaping the global health landscape by introducing advanced computational tools capable of analyzing complex and large-scale health data. In public health, AI is increasingly used for disease surveillance, predictive modeling, health system optimization, environmental monitoring, and behavioral interventions. This multidisciplinary review critically examines the conceptual foundations, applications, benefits, limitations, and ethical implications of AI integration into public health systems. The article synthesizes evidence from global health literature, highlighting both technological promise and governance challenges. While AI enables precision public health and data-driven policymaking, it simultaneously raises concerns related to privacy, equity, algorithmic bias, accountability, and sustainability. A balanced and ethically guided approach is essential to ensure that AI strengthens health systems without widening existing disparities. This paper argues that AI should function as a complementary analytical tool rather than a replacement for public health expertise. Through interdisciplinary collaboration and responsible governance, AI has the potential to transform population health management in the coming decades.