Monlezun, Dominique

Abstract Artificial intelligence is spreading through public health agencies and healthcare systems faster than workforces are trained to govern it. We describe RHAMI (Responsible Health AI Readiness and Maturity Index), the first human-centered automated composite index for health organizations to score AI readiness and maturity as one measurable system of science, economics and ethics, and the physician certification-to-Master’s pathway built to teach what it measures—both designed jointly by frontline public health professionals, clinicians, ethicists, engineers, leaders, and policy-makers in low- and middle-income countries and high-income countries.

Poor diet is the leading preventable risk factor for death worldwide, associated with over 10 million premature deaths and USD 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 (which 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 that are 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 is built and the analysis and review conducted 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 the top-performing healthcare systems and their nutrition AI, along with leading use cases including multimodal edge AI nutrition assessments as ambient intelligence, the 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 the RHAMI’s application for AI-accelerated public health nutrition are to improve population health, financial efficiency, and societal equity through the global cooperation of the public and private sectors stretching across the Global North and South.

Introduction: Artificial intelligence (AI) and wider digital technologies are accelerating healthcare systems’ attempts to address the financial and moral imperatives of improving health disparities and thus wider population health outcomes. Yet adoption has thus far been slower in less common conditions including carcinoid, its syndrome, and related heart disease especially amid wider system shocks like the COVID-19 pandemic and its lingering effects. This is the first known AI-augmented nationally representative analysis of mortality and disparities for these associations. Methods: Quantum BAyesian Machine learning-augmented Propensity Score translational (QBAM-PS) statistics with multivariable regression was performed on the largest all payor US inpatient dataset, the National Inpatient Sample. Results: Of the 208,257,049 adult hospitalizations from 2016-2022, 124,954 (0.06%) had carcinoid tumors. Of the 71,402 hospitalizations with carcinoid from 2016-2019, 26,711 (37.41%) had metastases, 2,835 (3.97%) had acute heart failure, and 2,042 (2.86%) died. But of the 53,552 hospitalizations with carcinoid from 2020-2022, diagnosed metastases (38.04%) had increased, as did acute heart failure (4.21%) and mortality (3.73%), while 0.04% had diagnosed COVID. In all adult hospitalizations from 2016-2019 by QBAM-PS multivariable regression controlling for clinical confounders and severity, carcinoid and carcinoid syndrome did not significantly increase mortality, but carcinoid was significantly less likely to be diagnosed among Hispanics (OR 0.73) and Asians (OR 0.46) compared to Caucasians, in addition to Medicare (OR 0.71) and VA (OR 0.65) compared to private insurance, and more likely to be diagnosed in the highest versus lowest income quartile (OR 0.124) (all p<0.001). By 2020-2022, carcinoid and its syndrome did not significantly increase the odds of COVID diagnosis. But again carcinoid was significantly less likely to be diagnosed in Hispanics (OR 0.68), Asians (OR 0.61), Medicare (OR 0.78), and VA (OR 0.59), while the highest income again increased diagnosis odds (OR 1.19) (all p<0.01). There were no mortality disparities within carcinoid during either time period. Conclusions: This large multi-year analysis supports improvements in metastatic carcinoid detection and heart disease management, including through the COVID pandemic, though amid persistent racial, insurance, and income disparities.

Poor diet is the top modifiable mortality risk factor globally, accounting for 11 million deaths annually with half being from diet-linked atherosclerotic cardiovascular disease (ASCVD). Yet, most of the world cannot afford a healthy diet—as the hidden costs of the inadequate global food system total over USD 13 trillion annually—let alone the much more clinically, financially, and ecologically costly and resource-intensive medical interventions required to address the disease progression and acute complications of ASCVD. Yet, AI is increasingly understood as a force multiplying revolutionary technology which may catalyze multi-sector efforts in medicine and public health to better address these significant health challenges. This novel narrative review seeks to provide the first known overview of the state-of-the-art in clinical interventions and public health policies in healthy diets for ASCVD, accelerated by health equity-focused AI. It is written from the first-hand practitioner perspective to provide greater relevance and applicability for health professionals and data scientists. The review summarizes the emerging trends and leading use cases in population health risk stratification and precision public health, AI democratizing clinical diagnosis, digital twins in precision nutrition, and AI-enabled culinary medicine as medical education and treatment. This review may, therefore, help inform and advance the evidence-based foundation for more clinically effective, financially efficient, and societally equitable dietary and nutrition interventions for ASCVD.

Background and objectives: Little is known about outcome improvements and disparities in cardiac arrest and active cancer. We performed the first known AI and propensity score (PS)-augmented clinical, cost-effectiveness, and computational ethical analysis of cardio-oncology cardiac arrests including left heart catheterization (LHC)-related mortality reduction and related disparities. Materials and methods: A nationally representative cohort analysis was performed for mortality and cost by active cancer using the largest United States all-payer inpatient dataset, the National Inpatient Sample, from 2016 to 2018, using deep learning and machine learning augmented propensity score-adjusted (ML-PS) multivariable regression which informed cost-effectiveness and ethical analyses. The Cardiac Arrest Cardio-Oncology Score (CACOS) was then created for the above population and validated. The results informed the computational ethical analysis to determine ethical and related policy recommendations. Results: Of the 101,521,656 hospitalizations, 6,656,883 (6.56%) suffered cardiac arrest of whom 61,300 (0.92%) had active cancer. Patients with versus without active cancer were significantly less likely to receive an inpatient LHC (7.42% versus 20.79%, p < 0.001). In ML-PS regression in active cancer, post-arrest LHC significantly reduced mortality (OR 0.18, 95%CI 0.14–0.24, p < 0.001) which PS matching confirmed by up to 42.87% (95%CI 35.56–50.18, p < 0.001). The CACOS model included the predictors of no inpatient LHC, PEA initial rhythm, metastatic malignancy, and high-risk malignancy (leukemia, pancreas, liver, biliary, and lung). Cost-benefit analysis indicated 292 racial minorities and $2.16 billion could be saved annually by reducing racial disparities in LHC. Ethical analysis indicated the convergent consensus across diverse belief systems that such disparities should be eliminated to optimize just and equitable outcomes. Conclusions: This AI-guided empirical and ethical analysis provides a novel demonstration of LHC mortality reductions in cardio-oncology cardiac arrest and related disparities, along with an innovative predictive model that can be integrated within the digital ecosystem of modern healthcare systems to improve equitable clinical and public health outcomes.

Background and Objectives: Cancer and coronary artery disease (CAD) often coexist. Compared to quantitative coronary angiography (QCA), fractional flow reserve (FFR) has emerged as a more reliable method of identifying significant coronary stenoses. We aimed to assess the specific management, safety and outcomes of FFR-guided percutaneous coronary intervention (PCI) in cancer patients with stable CAD. Materials and Methods: FFR was used to assess cancer patients that underwent coronary angiography for stable CAD between September 2008 and May 2016, and were found to have ≥50% stenosis by QCA. Patients with lesions with an FFR > 0.75 received medical therapy alone, while those with FFR ≤ 0.75 were revascularized. Procedure-related complications, all-cause mortality, nonfatal myocardial infarction, or urgent revascularizations were analyzed. Results: Fifty-seven patients with stable CAD underwent FFR on 57 lesions. Out of 31 patients with ≥70% stenosis as measured by QCA, 14 (45.1%) had an FFR ≥ 0.75 and lesions were reclassified as moderate and did not receive PCI nor DAPT. Out of 26 patients with <70% stenosis as measured by QCA, 6 (23%) had an FFR < 0.75 and were reclassified as severe and were treated with PCI and associated DAPT. No periprocedural complications, urgent revascularization, acute coronary syndromes, or cardiovascular deaths were noted. There was a 22.8% mortality at 1 year, all cancer related. Patients who received a stent by FFR assessment showed a significant association with decreased risk of all-cause death (HR: 0.37, 95% CI 0.15–0.90, p = 0.03). Conclusions: Further studies are needed to define the optimal therapeutic approach for cancer patients with CAD. Using an FFR cut-off point of 0.75 to guide PCI translates into fewer interventions and can facilitate cancer care. There was an overall reduction in mortality in patients that received a stent, suggesting increased resilience to cancer therapy and progression.