Search

Introduction Over the past 10 years, the number of publications on artificial intelligence and machine learning related to health financing tasks has markedly increased, (1) in line with the trend [...], There is increasing use of machine learning for the health financing functions (revenue raising, pooling and purchasing), yet evidence lacks for its effects on the universal health coverage (UHC) objectives. This paper provides a synopsis of the use cases of machine learning and their potential benefits and risks. The assessment reveals that the various use cases of machine learning for health financing have the potential to affect all the UHC intermediate objectives--the equitable distribution of resources (both positively and negatively); efficiency (primarily positively); and transparency (both positively and negatively). There are also both positive and negative effects on all three UHC final goals, that is, utilization of health services in line with need, financial protection and quality care. When the use of machine learning facilitates or simplifies health financing tasks that are counterproductive to UHC objectives, there are various risks--for instance risk selection, cost reductions at the expense of quality care, reduced financial protection or over-surveillance. Whether the effects of using machine learning are positive or negative depends on how and for which purpose the technology is applied. Therefore, specific health financing guidance and regulations, particularly for (voluntary) health insurance, are needed. To inform the development of specific health financing guidance and regulation, we propose several key policy and research questions. To gain a better understanding of how machine learning affects health financing for UHC objectives, more systematic and rigorous research should accompany the application of machine learning. Alors que l'apprentissage machine connait un usage croissant pour les fonctions de financement de la sante (collecte de revenus, mise en commun et achat), les preuves manquent quant a ses effets sur les objectifs de la couverture sanitaire universelle (CSU). Ce document presente une synthese des cas d'utilisation de l'apprentissage machine et de leurs avantages et risques potentiels. [(evaluation revele que les differents cas d'utilisation de l'apprentissage machine pour le financement de la sante sont susceptibles d'affecter tous les objectifs intermediaires de la CSU: la distribution equitable des ressources (a la fois positivement et negativement), l'efficacite (principalement positivement) et la transparence (a la fois positivement et negativement). Il existe egalement des effets positifs et negatifs sur les trois objectifs finaux de la CSU, a savoir l'utilisation des services de sante en fonction des besoins, la protection financiere et la qualite des soins. Lorsque l'utilisation de l'apprentissage machine facilite ou simplifie des taches de financement de la sante qui vont a lencontre des objectifs de la CSU, differents risques se font jour, comme la selection des risques, la reduction des couts au detriment de la qualite des soins, la reduction de la protection financiere ou la surveillance excessive. Les effets positifs ou negatifs de l'utilisation de l'apprentissage machine dependent de la maniere dont la technologie est appliquee et de l'objectif poursuivi. C'est pourquoi s'imposent des orientations et des reglementations specifiques en matiere de financement de la sante, en particulier pour l'assurance maladie (volontaire). Afin d'eclairer l'elaboration de telles orientations et reglementations, nous proposons plusieurs questions cles en matiere de politique et de recherche. Pour mieux comprendre la facon dont l'apprentissage machine affecte le financement de la sante dans le cadre des objectifs de la CSU, une recherche plus systematique et plus rigoureuse devrait accompagner la mise en oeuvre de l'apprentissage machine. Aunque el uso del aprendizaje automatico para las funciones de financiacion sanitaria (recaudacion de ingresos, mancomunacion y compra) es cada vez mayor, no hay evidencias de sus efectos sobre los objetivos de la cobertura sanitaria universal (CSU). Este documento ofrece una sinopsis de los casos de uso del aprendizaje automatico y sus posibles beneficios y riesgos. La evaluacion revela que los diversos casos de uso del aprendizaje automatico para la financiacion sanitaria tienen el potencial de afectar a todos los objetivos intermedios de la CSU: la distribucion equitativa de los recursos (tanto positiva como negativamente), la eficiencia (principalmente positiva) y la transparencia (tanto positiva como negativamente). Tambien hay efectos positivos y negativos en los tres objetivos finales de la CSU, es decir, la utilizacion de los servicios sanitarios en funcion de las necesidades, la proteccion financiera y la atencion de calidad. El uso del aprendizaje automatico para facilitar o simplificar tareas de financiacion sanitaria contraproducentes para los objetivos de la CSU plantea diversos riesgos, como la seleccion de riesgos, la reduccion de costes a expensas de la calidad de la atencion, la disminucion de la proteccion financiera o el exceso de vigilancia. El caracter positivo o negativo de los efectos del aprendizaje automatico depende de como y con que fin se aplique la tecnologia. Por lo tanto, se necesitan directrices y reglamentos especificos para la financiacion sanitaria, en particular para los seguros de salud (voluntarios). Proponemos varias preguntas clave en materia de politica e investigacion para contribuir a la elaboracion de directrices y reglamentos especificos sobre financiacion sanitaria. A fin de comprender mejor como afecta el aprendizaje automatico al logro de los objetivos de la CSU en el ambito de la financiacion sanitaria, la aplicacion del aprendizaje automatico deberia ir acompanada de una investigacion mas sistematica y rigurosa.

Author(s): Arun Chougule (corresponding author) [1,2,3]; Gourav Kumar Jain [4] Author: The IAEA officers responsible for this publication were M. Carrara and E. Titovich of the Division of Human Health [...]

Pravin Vazirani, Assistant Vice President, Chetu 09.26.24 Artificial intelligence (AI) is revolutionizing industries worldwide, and the hospital operating room is no exception. While there's been a push against this disruptive [...]

Author(s): Matthieu Komorowski [sup.1] [sup.5], Maria del Pilar Arias López [sup.2] [sup.3], Anthony C. Chang [sup.4] Author Affiliations: (1) grid.7445.2, 0000 0001 2113 8111, Division of Anaesthetics, Pain Medicine, and [...]

Introduction Delirium is a syndrome characterized by an acute change in mental status, marked by inattention and global cognitive dysfunction. (1,2) As many as 50% of older adults (aged [greater [...], Background: Delirium is a critically underdiagnosed syndrome of altered mental status affecting more than 50% of older adults admitted to hospital. Few studies have incorporated speech and language disturbance in delirium detection. We sought to describe speech and language disturbances in delirium, and provide a proof of concept for detecting delirium using computational speech and language features. Methods: Participants underwent delirium assessment and completed language tasks. Speech and language disturbances were rated using standardized clinical scales. Recordings and transcripts were processed using an automated pipeline to extract acoustic and textual features. We used binomial, elastic net, machine learning models to predict delirium status. Results: We included 33 older adults admitted to hospital, of whom 10 met criteria for delirium. The group with delirium scored higher on total language disturbances and incoherence, and lower on category fluency. Both groups scored lower on category fluency than the normative population. Cognitive dysfunction as a continuous measure was correlated with higher total language disturbance, incoherence, loss of goal and lower category fluency. Including computational language features in the model predicting delirium status increased accuracy to 78%. Limitations: This was a proof-of-concept study with limited sample size, without a set-aside cross-validation sample. Subsequent studies are needed before establishing a generalizable model for detecting delirium. Conclusion: Language impairments were elevated among patients with delirium and may also be used to identify subthreshold cognitive disturbances. Computational speech and language features are promising as accurate, noninvasive and efficient biomarkers of delirium.

Author(s): Amie J. Goodin [a,b,c]; Phuong T. Tran [a]; Sam McKee [a,c]; Ruba Sajdeya [c,d]; Jeevan Jyot [a,c]; Robert L. Cook [c,d,e]; Yan Wang [c,d]; Almut G. Winterstein [a,b,c] Introduction [...], The Consortium for Medical Marijuana Clinical Outcomes Research, a multi-university collaboration established by the state of Florida in the USA, hosted its third annual Cannabis Clinical Outcomes Research Conference (CCORC) in May 2023. CCORC was held as a hybrid conference, with a scientific program consisting of in-person sessions, with some sessions livestreamed to virtual attendees. CCORC facilitated and promoted up-to-date research on the clinical effects of medical cannabis, fostering collaboration and active involvement among scientists, policymakers, industry professionals, clinicians, and other stakeholders. Three themes emerged from conference sessions and speaker presentations: (1) disentangling conflicting evidence for the effects of medical cannabis on public health, (2) seeking solutions to address barriers faced when conducting clinical cannabis research - especially with medical cannabis use in special populations such as those who are pregnant, and (3) unpacking the data behind cannabis use and mental health outcomes. The fourth annual CCORC is planned for the summer of 2024 in Florida, USA. Keywords: Mental health, Public health, Cannabis Clinical Outcomes Research Conference, Conference proceedings, Medical marijuana, Cannabis, Cannabinoids, Cannabidiol, Marijuana efficacy, Marijuana clinical outcomes

Introduction The prevalence and benefits of youth sports have been thoroughly documented, with over 45 million youth participating in sports across the United States (Open Access Journal of Sports Medicine, [...], Within the United States, millions of youth participate in recreational athletics, and approximately 7%-10% will have some type of hidden disability (HD), such as attention deficit hyperactivity disorder, specific learning disability, or autism spectrum. Youth athletes with HD, and youth without a diagnosed disability, also may exhibit characteristics of these disabilities that can impact their behavior. This study investigated recreational leaders (RLs') perceptions of athletes exhibiting challenging behaviors in a youth sport setting. Specifically, this study explored (a) RLs' perceptions of athletes' challenging behaviors, (b) RL's proposed actions in addressing these difficulties, and (c) RL's efficacy towards effectively managing challenging behavior. Forty-three RLs reviewed four videos, described athletes' behaviors, and proposed behavior management solutions. Results indicated RLs tended to blame athletes when instructions were not followed, or when athletes were not on task, rather than consider their own role in delivering appropriate instruction or practice. Consequently, a need exists for improved recreation youth coaching training regarding HD and pedagogical techniques, specifically through the integration of research-validated strategies used within the academic and physical activity setting such as Universal Design for Learning (UDL; Meyer et al., 2014). Teaching RLs how to understand and use UDL may help provide RLs with the necessary skills to individualize feedback and better incorporate strategies for learning sport skills. Keywords: Youfh sporfs, parks and recreafion leaders, hidden disabilify, Universal Design for Learning, coaching educafion