Poor diet is the leading preventable risk factor for death worldwide, associated with over 10 million premature deaths and $8 trillion related costs every year. Artificial intelligence or AI is rapidly emerging as the most historically disruptive, innovatively dynamic, rapidly scaled, cost efficient, and economically productive technology (that is increasingly providing transformative countermeasures to these negative health trends, especially in low- and middle-income countries (LMICs) and underserved communities which bear the greatest burden from them). Yet widespread confusion persists among healthcare systems and policymakers on how to best identify, integrate, and evolve the safe, trusted, effective, affordable, and equitable AI solutions right for their communities, especially in public health nutrition. We therefore provide here the first known global, comprehensive, and actionable narrative review of the state-of-the-art of AI-accelerated nutrition assessment and healthy eating for healthcare systems, generated by the first automated end-to-end empirical index for responsible health AI readiness and maturity: the Responsible Health AI readiness and Maturity Index (RHAMI). The index, analysis, and review are built by a multi-national team spanning the Global North and South, consisting of front-line clinicians, ethicists, engineers, executives, administrators, public health practitioners, and policymakers. RHAMI analysis identified top performing healthcare systems and their nutrition AI, along with leading use cases including multimodal edge AI nutrition assessments as ambient intelligence, strategic scaling of practical embedded precision nutrition platforms, and sovereign swarm agentic AI social networks for sustainable healthy diets. This index-based review is meant to facilitate standardized, continuous, automated, and real-time multi-disciplinary and multi-dimensional strategic planning, implementation, and optimization of AI capabilities and functionalities worldwide, aligned with healthcare systems’ strategic objectives, practical constraints, and local cultural values. The ultimate strategic objectives of RHAMI starting in AI-accelerated public health nutrition are to improve population health, financial efficiency, and societal equity through a global cooperation of the public and private sectors stretching across the Global North and South.

We conducted the first comprehensive evaluation of the therapeutic value and safety profile of transcatheter mitral edge-to-edge repair (TEER) and transcatheter mitral valve replacement (TMVR) in individuals concurrently afflicted with cancer. Utilizing the National Inpatient Sample (NIS) dataset, we analyzed all adult hospitalizations between 2016 and 2020 (n = 148,755,036). The inclusion criteria for this retrospectively analyzed prospective cohort study were all adult hospitalizations (age 18 years and older). Regression and machine learning analyses in addition to model optimization were conducted using ML-PSr (Machine Learning-augmented Propensity Score adjusted multivariable regression) and BAyesian Machine learning-augmented Propensity Score (BAM-PS) multivariable regression. Of all adult hospitalizations, there were 5,790 (0.004%) TMVRs and 1,705 (0.001%) TEERs. Of the total TMVRs, 160 (2.76%) were done in active cancer. Of the total TEERs, 30 (1.76%) were done in active cancer. After the comparable rates of TEER/TMVR in active cancer in 2016, the prevalence of TEER/TMVR was significantly less in active cancer from 2017-2020 (2.61% versus 7.28% p <0.001). From 2017-2020, active cancer significantly decreased the odds of receiving TEER or TMVR (OR 0.28, 95%CI 0.13-0.68, p=0.008). In patients with active cancer who underwent TMVR/TEER, there were no significant differences in socio-economic disparities, mortality or total hospitalization costs. The presence of malignancy does not contribute to increased mortality, length of stay or procedural costs in TMVR or TEER. Whereas the prevalence of TMVR has increased in patients with active cancer, the utilization of TEER in the context of active cancer is declining despite a growing patient population.

Seasonal Variations of Arrhythmias and Their Impact on Mortality in Cancer Patients with Health Disparities: A Propensity Score Adjusted Machine Learning Analysis of over 100 Million Hospitalizations Across 3 Years

Background and objective Recommendations of first-line therapies for metastatic hormone-sensitive (mHSPC), nonmetastatic castrate-resistant (M0CRPC), and metastatic castrate-resistant (mCRPC) prostate cancer do not account for cardiotoxicity due to a lack of clear prior evidence. This manuscript assesses cardiotoxicity of these therapies. Methods We searched Ovid Medline, Elsevier Embase, and the Cochrane Library for randomized clinical trials (RCTs) from database inception to January 14, 2024. Network meta-analyses of first-line mHSPC, M0CRPC, and mCRPC therapies were constructed for the five cardiotoxicity metrics defined by the International Cardio-Oncology Society: heart failure, myocarditis, vascular toxicity, hypertension, and arrhythmias. Additional Bayesian network meta-analyses also accounted for prior treatment history. Key findings and limitations Thirteen RCTs (16 292 patients) were included. For mHSPC, androgen deprivation therapy (ADT) plus docetaxel (DTX) plus abiraterone acetate (AA) with prednisone (P) demonstrated a significant increase in hypertension and arrhythmias versus ADT + DTX (risk ratio [RR] 2.85, 95% confidence interval [CI] 1.67–4.89, and RR 2.01, 95% CI 1.17–3.44, respectively); however, no corresponding differences were observed between ADT + DTX plus darolutamide (DAR) and ADT + DTX (RR 1.55, 95% CI 0.73–3.30, and RR 0.94, 95% CI 0.63–1.40, respectively). For mCRPC assuming a history of mHSPC treatment, ADT + AA + P plus olaparib (OLA) demonstrated a statistically significant decrease in hypertension versus ADT + AA + P (RR 0.20, 95% CI 0.16–0.26). M0CRPC results were unremarkable. Conclusions and clinical implications For mHSPC, ADT + DTX + DAR demonstrates less cardiotoxicity than ADT + DTX + AA + P due to a lower risk of hypertension and arrhythmias from decreased mineralocorticoid excess. In addition, OLA counterintuitively offers decreased hypertension when superimposed on ADT + AA + P for mCRPC treatment after prior androgen deprivation from mHSPC therapy.

INTRODUCTION:We conducted the first comprehensive evaluation of the therapeutic value and safety profile of transcatheter mitral edge-to-edge repair (TEER) and transcatheter mitral valve replacement (TMVR) in individuals concurrently afflicted with cancer. METHODS:Utilizing the National Inpatient Sample (NIS) dataset, we analyzed all adult hospitalizations between 2016 and 2020 (n = 148,755,036). The inclusion criteria for this retrospectively analyzed prospective cohort study were all adult hospitalizations (age 18 years and older). Regression and machine learning analyses in addition to model optimization were conducted using ML-PSr (Machine Learning-augmented Propensity Score adjusted multivariable regression) and BAyesian Machine learning-augmented Propensity Score (BAM-PS) multivariable regression. RESULTS:Of all adult hospitalizations, there were 5790 (0.004%) TMVRs and 1705 (0.001%) TEERs. Of the total TMVRs, 160 (2.76%) were done in active cancer. Of the total TEERs, 30 (1.76%) were done in active cancer. After the comparable rates of TEER/TMVR in active cancer in 2016, the prevalence of TEER/TMVR was significantly less in active cancer from 2017 to 2020 (2.61% versus 7.28% p < 0.001). From 2017 to 2020, active cancer significantly decreased the odds of receiving TEER or TMVR (OR 0.28, 95%CI 0.13-0.68, p = 0.008). In patients with active cancer who underwent TMVR/TEER, there were no significant differences in socio-economic disparities, mortality or total hospitalization costs. CONCLUSION:The presence of malignancy does not contribute to increased mortality, length of stay or procedural costs in TMVR or TEER. Whereas the prevalence of TMVR has increased in patients with active cancer, the utilization of TEER in the context of active cancer is declining despite a growing patient population.

A recent Scientific Statement published in the Journal of American College of Cardiology in December 2023 highlighted racial and sex-specific disparities in treatment for peripheral artery disease (PAD) using data from up to 20 years ago. We sought to evaluate disparities in endovascular PAD treatment with more recent data from 2016 to 2020. Bayesian machine learning-augmented propensity score translational (BAM-PS) statistics with multivariable regression was conducted for the largest US all-payor inpatient dataset, the National Inpatient Sample (NIS), from 2016 to 2020. Of 148,755,036 adult hospitalizations from 2016-2020, there were 17,173,000 (11.54%) with PAD, of whom 680,025 (3.96%) underwent inpatient endovascular revascularization (ER). ER prevalence from 2016-2020 increased steadily (0.46% to 0.49%) (p <0.001). In BAM-PS multivariable regression adjusting for several clinical and demographic variables, female sex (OR 0.54, 95% CI 0.53-0.56) and Asian versus Caucasian race (OR 0.66, 95% CI 0.60-0.73) significantly decreased the odds of ER. Medicare versus commercial insurance (OR 1.17, 95% CI 0.13-1.22) significantly increased the odds of ER (p<0.001). There were no significant differences in ER mortality and cost when analyzed by sex, race, and income (p>0.05 for all). This nationally representative analysis suggests that significant racial and sex-specific disparities persist in ER for PAD. Clinicians must actively strive to alleviate these disparities using a multidisciplinary approach.

Background and Aim: For metastatic castrate-resistant prostate cancer (mCRPC), the European Association of Urology recommends multiple therapies as first-line. However, these recommendations do not account for additional cardiotoxicity of the therapies for prior stages of the disease, such as the metastatic hormone-sensitive prostate cancer (mHSPC) stage. We seek to adjudicate the cardiotoxicities of first-line mCRPC therapies assuming history of mHSPC treatment based on the five International Cardio-Oncology Society (IC-OS) cardiotoxicity domains: heart failure, myocarditis, vascular toxicity, hypertension, and arrhythmias. Methods: Ovid Medline, Elsevier Embase, and the Cochrane Library were searched for randomized clinical trials (RCTs) of mCRPC and mHSPC patients from inception until January 2024. Studies reporting at least one first-line therapy and effect size of at least one cardiotoxicity domain were included. Network meta-analyses with indirect treatment comparison with multivariate multi-level analysis were performed for each cardiotoxicity domain to estimate relative risk (RR) with 95% confidence intervals (CI) for mCRPC and mHSPC therapies. A Bayesian model was then constructed using the mHSPC network as a prior for informing the RRs and 95% CIs of mCRPC first-line therapies. Results: Network meta-analyses of mHSPC treatment cardiotoxicity, mCRPC treatment cardiotoxicity assuming no treatment history, and mCRPC treatment cardiotoxicity assuming prior mHSPC treatment are provided in Images 1-2. We did not find any studies assessing myocarditis. For patients with mHSPC treatment history, olaparib (OLA) plus androgen deprivation therapy (ADT) plus abiraterone with prednisone (AA+P) decreased hypertensive risk relative to ADT+AA+P (RR 0.20, 95% CI 0.16-0.26). Conclusion: OLA may offer a protective antihypertensive effect when superimposed on ADT+AA+P for mCRPC treatment after prior androgen deprivation from mHSPC therapy.

El aumento de los costos sanitarios y financieros de las enfermedades, las discapacidades y las disparidades respalda la aceleración mundial de los intereses y las inversiones en IA (inteligencia artificial) sanitaria para lograr soluciones sanitarias mejores, más baratas, más rápidas y justas a escala mundial y local. Sin embargo, no existe un consenso sobre la aplicación práctica de los principios de la IA responsable en diversos sectores, estados y sistemas de creencias de todo el mundo. Este estudio de prueba de concepto utiliza el marco ético pluralista global (el Contrato Social Personalista) para proporcionar, por tanto, el primer análisis conocido de ética computacional (AiCE, por sus siglas en inglés) y política basado en IA aumentada bayesiana que integra análisis clínicos, de rentabilidad y de disparidades en la atención sanitaria con datos representativos a nivel nacional para estimar el costo global de las disparidades en la atención sanitaria en la colonoscopia (CS, por sus siglas en inglés) y el ahorro de la CS habilitada por IA para reducirlas. El estudio sugiere que revertir las disparidades raciales, en particular entre hispanos y asiáticos, puede ahorrar a los sistemas sanitarios estadounidenses 17.610 millones de dólares al año, con un ahorro potencial de 625,40 millones de dólares para los hispanos y 289 millones de dólares para los asiáticos en particular (con un ahorro similar para las comunidades vulnerables en países de ingresos medios y bajos). Los resultados anteriores respaldan el imperativo de ahorro de costos que supone la inversión estratégica y de capacitación en estas medidas impulsadas por la IA para mejorar los objetivos estratégicos de sostenibilidad, eficacia, eficiencia y equidad (SEEE) de la atención sanitaria. Estos resultados empíricos informan el argumento bioético global más amplio de las dimensiones gemelas de la dignidad y la seguridad humanas (arraigadas en el relato personalista, multicultural y metafísico de la persona como miembro de la familia humana global) para destacar el imperativo ético de la IA para optimizar el rendimiento del ecosistema sanitario digital global. Semejante fin instrumental es un medio decisivo para avanzar hacia el fin último del bien común, en el que se salvaguarda el bien individual de cada persona y en el que éste encuentra su realización trabajando hacia él.

Introduction: The incidence of cardio-oncology disease, arrest, and inpatient mortality among adolescent and pediatric versus adult patients is largely unknown, which undermines optimal care of these high-risk patients. Methods: BAyesian Machine learning-augmented Propensity Score (BAM-PS) translational statistics with multivariable regression was performed on the National Inpatient Sample. Results: Of the 142,651,868 hospitalizations from 2017-2020, 13.69% were pediatric (0-13 years old), 1.13% were adolescent (14-17 years old), and 85.18% were adult patients (over 17 years old). Adults were significantly more likely than adolescent and pediatric patients to have cancer and cardiac disease (99.37% versus 0.15% versus 0.47%, p<0.001). The most common primary malignancies among adolescent or pediatric patients with cardio-oncology disease were leukemia (39.66% versus 52.60%), bone/connective (27.00% versus 12.43%), brain/nervous (8.02% versus 13.80%), Hodgkin lymphoma (7.17% versus 1.09%), and renal (6.01% versus 1.27%). In active cardio-oncology disease by BAM-PS multivariable regression controlling for clinical confounders and severity, adolescent and pediatric patients had comparable mortality odds to adults. Outside of active cardio-oncology disease, pediatric patients (OR 4.95, 95%CI 4.70-5.20, p<0.001) had significantly greater mortality odds than adults, as did adolescent patients but with less magnitude of increased odds (OR 2.03, 95%CI 1.78-2.31, p<0.001). In active cardio-oncology disease, pediatric patients (OR 0.17, 95%CI 0.04-0.68, p=0.013) had significantly lower odds of arrest compared to adults, with adolescents having comparable arrest odds versus adults. Among adolescent and pediatric patients with active cardio-oncology disease, African American versus Caucasians (OR 4.67, 95%CI 1.18-18.42, p=0.028) had significantly greater mortality odds. Conclusions: This machine learning multi-year national study suggests the existence of increased mortality in African American adolescent and pediatric patients with concomitant cancer and cardiovascular disease. Overall, adolescent and pediatric patients with cardio-oncology have better outcomes with more effective long-term management.

Amyloid cardiomyopathy (ACM) is associated with a poor prognosis. Previous reports have suggested unfavorable post-heart transplant (HT) survival in this population compared with other HT recipients.Data from the United Network for Organ Sharing (UNOS) registry were used to study outcomes among ACM patients undergoing HT in the modern era (Era 2, 2008 to 2013) as compared with the historical era (Era 1, 1987 to 2007).One hundred eighty-eight ACM patients underwent primary single-organ HT. Ninety-seven patients (51.6%) were transplanted in Era 1 and 91 (48.4%) in Era 2. ACM patients undergoing HT in Era 2 were older (p < 0.0001), had higher body mass index (p = 0.008) and longer ischemic times (p = 0.02), and were more likely to be African-American (p < 0.0001), UNOS Status 1A (p < 0.0001), male (p = 0.01) and highly sensitized (p < 0.0001) compared with those in Era 1. Compared with patients with other etiologies of restrictive cardiomyopathy (RCM; n = 339 in Era 1, n = 164 in Era 2), adjusted hazard ratios (HRs) for post-HT mortality of ACM were 2.08 (p < 0.0001) in Era 1 and 1.22 (p = not statistically significant) in Era 2. Adjusted HRs for mortality of ACM vs all other diagnoses (n = 36,334 in Era 1, n = 9,225 in Era 2) were 1.84 (p < 0.0001) in Era 1 and 1.38 (p = NS) in Era 2. Although post-HT survival did not change with time among non-ACM RCM patients, post-HT mortality was lower in Era 2 compared with Era 1 among ACM patients (HR 0.49, p = 0.03).Although historically associated with inferior survival, post-HT outcomes in ACM patients in the modern era are now approaching those of non-ACM patients. Changes in patients’ demographics suggest that this may be related to improved patient selection, including an increased proportion of patients with transthyretin ACM. HT should be considered for appropriate candidates with ACM.