Citations

Photoplethysmography (PPG) is a non-invasive optical technique commonly used to measure heart rate and oxygen saturation, but its waveform contains additional physiological information that can be analyzed using artificial intelligence (AI). This narrative review summarizes the emerging applications of AI-based PPG in cardiovascular, respiratory, sleep, hemodynamic, pregnancy-related, and portal-hypertension assessment, with the aim of evaluating its potential beyond conventional monitoring and identifying barriers to clinical translation. The literature search was conducted using PubMed, Google Scholar, IEEE Xplore, ScienceDirect, and SpringerLink. Additional relevant studies were identified through screening the reference lists of included articles. Studies published between 2002 and 2026 were identified to capture the development of PPG from conventional monitoring to newer AI-based applications. Human studies were prioritized, while relevant computational, simulated, synthetic, ex vivo, and technical studies were also included. Studies unrelated to PPG, duplicates, and studies with limited relevance were excluded. A total of 96 references were included, covering AI approaches such as convolutional and deep neural networks, ensemble methods, transfer learning, U-Net, generative adversarial networks, and Transformer-based models. Overall, the reviewed evidence suggests that AI-based PPG may support blood pressure estimation, atrial fibrillation detection, sleep and respiratory monitoring, vascular aging assessment, pulmonary hypertension screening, preeclampsia assessment, volume-status and compensatory-reserve assessment, and exploratory assessment related to portal hypertension. However, clinical translation remains limited by motion artifacts, sensor and measurement-site variability, skin-pigmentation-related bias, physiological and environmental influences, heterogeneous methods, limited external validation, and inconsistent clinical and regulatory standards.

e17594 Background: Cardiovascular disease (CVD) is the leading cause of death among women with ovarian cancer. This study investigates cardiovascular mortality in women with ovarian cancer across the United States, assessing trends by geography and urbanization. Methods: Mortality data from the CDC WONDER database (1999–2020) were analyzed. Females with ovarian cancer listed on the death certificate and cardiovascular disease as the cause of death were identified using ICD-10 codes. Age-adjusted mortality rates (per 100,000) were calculated and stratified by census region and urbanization. Trends were evaluated using Average Annual Percent Change (AAPC) calculated by the Joinpoint Regression Program V5.4.0. Results: From 1999 to 2018, cardiovascular mortality in ovarian cancer patients declined, with an APC of –2.09%, consistent across regions and urbanization levels. However, from 2018 to 2020, a concerning reversal occurred, with mortality increasing by +3.79% per year. The abrupt rise in mortality is observed in the Midwest region, with an APC of +3.99, and in small and medium metro regions, with APCs of +7.38 and +6.46, respectively. This reversal in cardiovascular mortality in ovarian cancer from 2018 to 2020 is likely due to the COVID-19 pandemic that disrupted screening and treatment. Conclusions: This 21-year analysis demonstrates a long-term decline in cardiovascular mortality among women with ovarian cancer, followed by a sharp reversal from 2018 to 2020. This increase suggests the urgent need for public health interventions to reduce cardiovascular risk among ovarian cancer patients.

e17524 Background: Cervical cancer remains one of the leading causes of female cancer mortality, while heart failure drives chronic disease burden. Their coexistence complicates outcomes through shared risk factors, cardiotoxicity, and mortality. This study examined cervical cancer mortality trends in patients with heart failure, assessed disparities, and aimed to inform integrated management strategies. Methods: We analyzed death certificates from CDC WONDER Database (1999–2020), using ICD-10 C53 (cervical cancer) and I50 (heart failure). Female mortality was stratified by race and urbanization. Joinpoint Regression Program V5.4.0 calculated Annual Percent Change (APC) and Average Annual Percent Change (AAPC). Results: A total of 5,534 deaths were identified. Age-adjusted mortality rates (AAMR) declined overall, but trends varied. Among females, mortality fell from 0.1102 per 100,000 in 1999 to 0.076 in 2020 (AAPC -1.28%). Three phases emerged: a modest decline (1999-2006, APC -1.45%), a rapid decline (2006-2009, APC -17.6%), and a concerning reversal (2009-2020, APC +3.27%). The latter increase may reflect reduced screening, declining vaccination rates, or COVID-19 disruptions.By urbanization, large central metropolitan areas showed a steady decline (APC -4.13%). By race, White women demonstrated a consistent reduction (APC -2.61%), indicating sustained benefits of screening and vaccination. Conclusions: Cervical cancer mortality in heart failure patients declined from 1999-2020, reflecting prevention and healthcare advances. However, disparities persist, with notable increases among women since 2009. These findings highlight successes but stress the urgent need for vaccination and screening.

e17104 Background: Prostate cancer is a commonly diagnosed malignancy among men. Sepsis continues to pose a significant threat to outcomes. Patients with are particularly vulnerable to sepsis due to immunosuppression from the malignancy itself, advanced age, and treatment-related factors including catheter use. Sepsis is associated with high short-term mortality, and worsened overall outcomes, underscoring the need for epidemiological and clinical evaluation. Methods: We analyzed death certificates from 1990-2023 from CDC Wonder Database. We used ICD-10 codes, C61 for malignant neoplasm of prostate and C56 for sepsis to identify related deaths. Mortality rates were compared by urbanization, sex and census region. Joinpoint Regression Program V5.4.0 computed Annual Percent Change with 95% CIs. p value < 0.05 was considered statistically significant. Results: Between 1999 and 2023, 39,801 deaths were recorded. Overall age-adjusted mortality rates (AAMRs) changed little over time, remaining near 2 deaths per 100,000 population (2.02 in 1999 and 2.00 in the most recent year). Clear differences were seen across demographic groups.In 1999, AAMRs among Black or African American was highest with value of 6.80 compared to white and hispanic or latino individual with AAMR vales 1.67 and 1.89 respectively.In 2023, mortality among Black individuals fell to 5.06; however, rates were still higher than those seen among White (1.76) and Hispanic/Latino (1.92) populations. Geographic differences were also evident.The mortality rate in the South, decreasing from 2.43 in 1999 to 2.16 in 2023, was highest among all the other census regions.Mortality rates declined across both metropolitan and nonmetropolitan areas, falling from 2.02 to 1.84 in metropolitan regions and from 2.05 to 1.73 in nonmetropolitan regions in year 2020. Conclusions: Overall sepsis-related mortality has remained relatively unchanged over the two decades, with significant racial and geographic disparities. Black individuals continue to experience disproportionately higher mortality, and Southern region showed consistently elevated rates. Both metropolitan and non-metropolitan areas saw modest declines. These findings highlight the continued need for targeted preventive measures and management strategies to reduce mortality and improve outcomes. Prostate cancer with sepsis AAMRs. variable AAMR 1999 AAMR 2023 Overall / Male 2.02 (1.91-2.14) 2.00 (1.92-2.09) Race Black or African American 6.80 (6.04-7.56) 5.06 (4.60-5.53) White 1.67 (1.56-1.78) 1.76 (1.67-1.85) Hispanic or Latino 1.89 (1.39-2.50) 1.92 (1.65-2.20) Census Region Northeast 2.25 (2.00-2.51) 1.99 (1.80-2.18) Midwest 1.71 (1.50-1.92) 1.65 (1.49-1.81) South 2.43 (2.22-2.63) 2.16 (2.02-2.30) West 1.54 (1.33-1.76) 2.12 (1.94-2.30) Urbanization AAMR 2020 Metro 2.02 (1.90-2.15) 1.84 (1.75-1.93) Non-metro 2.05 (1.79-2.30) 1.73 (1.54-1.92)

e16067 Background: Gastric carcinoma remains a significant cause of cancer mortality in the United States. Although overall mortality rates have declined, persistent disparities exist across racial, age, and geographic groups. For cancer patients, sepsis—a life-threatening infection response—is a major fatal complication. Analyzing linked mortality data is crucial for identifying high-risk populations, understanding the burden of cancer-associated infections, and guiding targeted prevention and treatment strategies to improve outcomes and achieve health. Methods: This cross-sectional study used CDC WONDER mortality data from 1999–2020 for adults aged 25 years and older. Causes of death were identified using ICD-10 codes, and age-adjusted mortality rates (AAMRs) were calculated across sex, race/ethnicity, age, census regions, and urban–rural categories. Mortality trends were assessed using Joinpoint regression to estimate average annual percentage changes (AAPC) with 95% confidence intervals (CIs) and statistical significance. Results: From 1999 to 2020, U.S. stomach cancer mortality declined overall, with AAMRs decreasing from 0.29 to 0.22 per 100,000 (AAPC = –0.8%, 95% CI: –1.64 to 0.04). Significant declines occurred among adults aged 65–74 (APC = –1.7%, 95% CI: –2.32 to –1.05), 75–84 (APC = –1.9%, 95% CI: –2.65 to –1.05), and ≥85 years (APC = –3.0%, 95% CI: –4.02 to –1.99). Adults 45–54 years experienced increasing mortality after 2005 (APC = 5.1%, 95% CI: 2.82 to 7.46), while rates among 55–64 years remained stable. Male mortality declined significantly (AAPC = –1.24%, 95% CI: –1.93 to –0.54), whereas female mortality showed no significant long term change (AAPC = –0.93%, 95% CI: –2.44 to 0.60). Black (AAPC = –2.25%, 95% CI: –3.02 to –1.47) and Hispanic/Latino populations (AAPC = –1.50%, 95% CI: –2.26 to –0.74) experienced significant declines. Regionally, the Northeast showed the largest decline (AAPC = –2.30%, 95% CI: –3.52 to –1.07), while the Midwest, South, and West demonstrated no significant long term trends. Metropolitan areas declined from 1999–2011 (APC = –2.80%, 95% CI: –4.44 to –1.14). Conclusions: While overall U.S. gastric cancer mortality declined from 1999–2020, this progress is uneven. Significant increases among adults aged 45–54 and stable rates for those 55–64 highlight an emerging concern. Furthermore, declining trends are concentrated in specific demographic groups and regions, such as the Northeast, revealing persistent disparities. These findings underscore the need for targeted prevention and research focused on younger adults and lagging geographic areas.

Background: The medial femoral trochlea flap is used for treating recalcitrant scaphoid proximal pole nonunions. Although this requires resecting a substantial portion of the scapholunate interosseous ligament, the intercarpal angular relationships are preserved. Studies have demonstrated that lunate alignment is preserved despite loss of the scapholunate ligament because the scaphoid is reconstructed with an osteochondral flap that is larger than the resected nonunited proximal scaphoid. The technique of purposeful expansion of the scaphoid height has been termed scaphoid overstuffing . The purpose of this study is to characterize the effect of scaphoid overstuffing on force transmission across the scaphoid and lunate facets of the radius. Methods: Eleven fresh frozen cadaveric upper extremities without ligament instability were selected. The radiocarpal joint was exposed via a dorsal approach, and electronic pressure sensors were introduced. Three different states of the wrist were evaluated: native, scapholunate dissociation (SLD), and overstuffed (OS). Pressures were measured in 4 positions: 30° flexion, full wrist extension, 30° extension, and clenched fist. Pressures were measured in kPa and contact areas in mm 2 . Results: In all functional positions, the OS state had higher peak pressures across the scaphoid facet. This included 30° wrist flexion (OS 383 ± 221 kPa, P = .033), full wrist extension (OS 1068 ± 767 kPa, P = .022), 30° wrist extension (OS 880 ± 518 kPa, P < .001), and clenched fist (OS 1040 ± 736 kPa, P = .02). Conclusions: In functional wrist positions, overstuffing the scaphoid increases scaphoid facet peak contact pressures. Further study is needed to examine the long-term clinical consequences of these changes and the potential for accelerated cartilage degeneration.

ABSTRACT Background Acute heart failure (AHF) exhibits marked heterogeneity in diastolic hemodynamics, yet comprehensive echocardiographic assessment of diastolic function (DF) and filling pressure (FP) is often infeasible. We evaluated whether artificial intelligence–enabled electrocardiography (AI-ECG) could provide scalable DF grading and FP estimation in hospitalized AHF patients. Methods We retrospectively studied adults hospitalized for AHF across Mayo Clinic sites (2013–2023) who received ≥1 dose of intravenous loop diuretic and had paired 12-lead ECG and TTE. The previously validated AI-ECG DF model was applied without retraining to generate four DF grades and a continuous FP probability. Clinical outcomes were all-cause mortality and heart failure rehospitalization. Associations with clinical severity markers and echocardiographic indices were examined. Kaplan–Meier survival analysis and adjusted multivariable Cox proportional hazards models were performed. Exploratory analyses examine the kinetics of change in FP probability and impact on mortality. Results Among 11,513 patients (median age 75 years, 39% female), AI-ECG DF grading was feasible in 100%, whereas echocardiographic DF was indeterminate in 44% of clinically eligible patients. In 2,582 patients with determinate echocardiographic DF, AI-ECG FP probability discriminated TTE Grade 2–3 dysfunction with AUC 0.85 (95% CI 0.83 – 0.86). Higher AI-ECG DF grades were associated with higher comorbidity burden, worse NYHA class, elevated NT-proBNP, higher MAGGIC scores, elevated PCWP, and more advanced structural remodeling. After multivariable adjustment, AI-ECG DF remained independently associated with mortality (hazard ratio [HR] 1.25, 95% CI 1.16–1.35 for Grade 2; HR 1.44, 95% CI 1.33–1.56 for Grade 3 versus Normal/Grade 1). Combining AI-ECG DF with MAGGIC scores yielded ordered risk gradients, with highest mortality in patients with both high MAGGIC and Grade 2–3 DF. Among patients with serial ECGs, improvement in FP probability was independently associated with lower mortality (HR 0.85, 95% CI 0.79–0.91), whereas worsening did not show a consistent adverse gradient beyond baseline DF. Conclusions In a large, geographically diverse AHF cohort, AI-ECG DF grading was universally feasible, correlated with established hemodynamic severity markers, and provided independent prognostic information beyond established risk factors, supporting its role as a pragmatic, scalable diastolic biomarker in AHF. CLINICAL PERSPECTIVE What Is New? In 11,513 hospitalized acute heart failure (HF) patients, artificial intelligence-enabled electrocardiography provided diastolic function grading in 100% of patients from a single 12-lead ECG without requiring additional clinical variables, compared with 56% feasibility for guideline-based echocardiography grading. AI-ECG diastolic function grades correlated with established marker of severity (NYHA functional class, NT-proBNP, MAGGIC risk scores, and pulmonary capillary wedge pressure) and remained independently associated with both mortality and HF rehospitalization after multivariable adjustment. Serial AI-ECG measurements identified post-discharge filling pressure trajectories, with improvement independently associated with 15% lower mortality, a first demonstration that longitudinal ECG assessment can track post-discharge hemodynamic recovery. What Are the Clinical Implications? AI-ECG transforms the universally obtained 12-lead ECG into an actionable hemodynamic biomarker that addresses the critical gap when echocardiographic diastolic function assessment is indeterminate or unavailable in acute HF patients. Despite markedly different hemodynamic severity and long-term outcomes across AI-ECG diastolic function grades, hospitalization length of stay did not differ, suggesting advanced diastolic dysfunction represents occult risk not easily recognized during routine acute care and highlighting the need for improved post-discharge risk stratification. The continuous filling pressure probability metric enables longitudinal monitoring of post-discharge hemodynamic status using serial routine ECGs, potentially identifying patients requiring intensified follow-up or specialist referral.

ABSTRACT Magnetic Resonance Spectroscopy Imaging (MRSI) offers spatially-resolved, neurometabolic information, acquired non-invasively at whole-brain scales from human subjects. Analysis of MRSI however, is extremely challenging. The metabolic information is highly convolved, and sparsely distributed across millions of spatial-spectral datapoints, allowing for little direct human interpretation. Conversely, the overall low signal-to-noise with high-intensity artifacts can confound unsupervised machine learning approaches. These technical barriers have left much of the potential of MRSI unrealized. We acquired MRSI data from 4 human subjects with a diagnosis of multiple sclerosis (MS), incorporating experimental design into an informed machine learning approach. MRSI acquisitions were registered to anatomical MRI to label 105k spectra from brain tissue and 162 spectra from white matter hyperintensities (WMHs), an imaging biomarker associated with MS lesions. Spectral labels were then used in contrastive principal component analysis (cPCA) to filter artifacts and background features in the MRSI data from lesion salient features and clustered into statistically significant states based on features that could be interpreted from the original data. Our approach renders MRSI data into testable representations of neurometabolism, enabling the method for fundamental and clinical research. Graphical Abstract Analysis workflow for neurometabolic profiling of MS lesions. MRSI and anatomical MRI is acquired and processed in parallel for spectral data and anatomical labels. Spectra are then labeled and separated into experimental vs background data for contrastive PCA. Spectra are clustered for similarity, further labeled, and projected onto a brain atlas for a neurometabolic view.

Introduction: Embolic stroke of undetermined source (ESUS) is a clinical construct encompassing heterogenous possible mechanisms of incident stroke, potentially with variable responsiveness to anticoagulation and antiplatelet treatment. This study aims to identify differences in recurrent stroke risk based on phenotypic clusters in an ESUS population, and whether some clusters may benefit relatively more from anticoagulation over antiplatelet therapy. Methods: We identified patient phenotypes from a multicenter, retrospective cohort study of 1909 ESUS patients by dividing them into groups using Partitioning Around Medoids (PAM) with correlation-weighted Gower distance over 23 baseline demographic, clinical, laboratory, radiographic, and cardiac features. We confirmed optimal clustering at 3 groups. We assessed cluster associations with time to recurrent stroke using Kaplan-Meier survival analysis. We then employed a causal survival forest to estimate conditional average treatment effects (CATE) of anticoagulation versus antiplatelet therapy using the same baseline features as predictors with a 365-day horizon for restricted mean survival time differences. Finally, we used best linear projection to identify baseline features predictive of treatment effect and assessed whether effects differed significantly by cluster. Results: Cluster 1 (n=542) identified a low-risk, younger sample with minimal baseline disability and comorbidity burden. Cluster 2 (n=743) comprised a moderate-risk phenotype with intermediate comorbidity. Cluster 3 (n=626) represented the oldest and highest-risk phenotype. Kaplan-Meier analysis demonstrated significant differences in stroke-free survival across patient clusters (p < 0.001), where Cluster 1 experienced the lowest recurrent stroke rate and Cluster 3 had the highest. The clustering algorithm successfully identified clinically meaningful phenotypes with distinct risk profiles. While CATE varied across clusters, the differences were not statistically significant. Conclusion: In a multicenter ESUS population, we identified 3 distinct phenotypic clusters, each comprising nearly one-third of the sample and with a differential risk of recurrent stroke. Although cluster was not a significant effect modifier, substantial CATE variability by cluster was observed. Future clinical trials may consider evaluating secondary stroke prevention therapies among phenotypically similar patients who may respond differentially to novel therapies.

Abstract Aims Obesity, particularly visceral adiposity, is a key driver of cardiovascular mortality (CVM), yet conventional measures such as body mass index (BMI) inadequately capture fat distribution. The Body Roundness Index (BRI) is a novel anthropometric measure integrating waist circumference and height to better reflect body shape and visceral fat. This study examined the association between BRI and CVM in U.S. adults and across sociodemographic subgroups. Methods and results We analysed data from 31 351 adults (median age 43 yrs, 50% females) aged ≥20 years in NHANES 1999–2018, excluding those with prior cardiovascular disease or cancer. BRI was computed using a validated equation and categorized into quintiles (Q3 as reference). The primary outcome was CVM; secondary outcomes included all-cause, heart disease, and cerebrovascular mortality. Weighted Cox proportional hazards and restricted cubic spline (RCS) models evaluated associations after adjustment for demographic, behavioural, and clinical factors. Subgroup and sensitivity analyses tested consistency and effect modification. During a median follow-up of 10.1 years (IQR: 5.3–14.9 years), 883 cardiovascular deaths occurred. In fully adjusted models, participants in the highest BRI quintile had a 54% higher risk of CVM (HR, 1.54; 95% CI, 1.13–2.08; P = 0.006) vs. Q3. This risk remained high even among those with normal BMI. RCS analysis indicated a modest U-shaped association. Stronger effects were observed among middle-aged adults (45–64 years) and those with higher educational attainment. Conclusion Higher BRI is independently associated with increased cardiovascular mortality, particularly among middle aged adults and those with normal BMI, underscoring its potential as a practical, noninvasive tool for cardiovascular risk stratification. Incorporating BRI into clinical and public health assessment may improve identification of individuals at elevated risk.