Search

The coronary angiogram is the gold standard for evaluating the severity of coronary artery disease stenoses. Presently, the assessment is conducted visually by cardiologists, a method that lacks standardization. This study introduces DeepCoro, a ground-breaking AI-driven pipeline that integrates advanced vessel tracking and a video-based Swin3D model that was trained and validated on a dataset comprised of 182,418 coronary angiography videos spanning 5 years. DeepCoro achieved a notable precision of 71.89% in identifying coronary artery segments and demonstrated a mean absolute error of 20.15% (95% CI: 19.88-20.40) and a classification AUROC of 0.8294 (95% CI: 0.8215-0.8373) in stenosis percentage prediction compared to traditional cardiologist assessments. When compared to two expert interventional cardiologists, DeepCoro achieved lower variability than the clinical reports (19.09%; 95% CI: 18.55-19.58 vs 21.00%; 95% CI: 20.20-21.76, respectively). In addition, DeepCoro can be fine-tuned to a different modality type. When fine-tuned on quantitative coronary angiography assessments, DeepCoro attained an even lower mean absolute error of 7.75% (95% CI: 7.37-8.07), underscoring the reduced variability inherent to this method. This study establishes DeepCoro as an innovative video-based, adaptable tool in coronary artery disease analysis, significantly enhancing the precision and reliability of stenosis assessment.

This paper presents a first comprehensive analysis of long-term measurements of atmospheric aerosol components from aerosol chemical speciation monitor (ACSM) and multiwavelength Aethalometer (AE33) instruments collected between 2015 and 2021 at 13 (sub)urban sites as part of the French CARA (Chemical Characterization of Particles) program. The datasets contain the mass concentrations of major chemical species within submicron aerosols (PM1), namely organic aerosols (OAs), nitrate (NO3-), ammonium (NH4+), sulfate (SO42-), non-sea-salt chloride (Cl−), and equivalent black carbon (eBC). Rigorous quality control, technical validation, and environmental evaluation processes were applied, adhering to both guidance from the French Reference Laboratory for Air Quality Monitoring (LCSQA) and the Aerosol, Clouds, and Trace Gases Research Infrastructure (ACTRIS) standard operating procedures. Key findings include geographical differences in the aerosol chemical composition, seasonal variations, and diel patterns, which are influenced by meteorological conditions, anthropogenic activities, and proximity to emission sources. Overall, OA dominates PM1 at each site (43 %–60 % of total mass), showing distinct seasonality with higher concentrations (i) in winter, due to enhanced residential heating emissions, and (ii) in summer, due to increased photochemistry favoring secondary aerosol formation. NO3 is the second most important contributor to PM1 (15 %–30 %), peaking in late winter and early spring, especially in northern France, and playing a significant role during pollution episodes. SO4 (8 %–14 %) and eBC (5 %–11 %) complement the major fine-aerosol species, with their relative contributions strongly influenced by the origin of air masses and the stability of meteorological conditions, respectively. A comparison with the 3D chemical transport model (CTM) CHIMERE shows high correlations between simulations and measurements, albeit with an OA concentration underestimation of 46 %–76 %. Regional discrepancies in NO3 concentration levels emphasize the importance of these datasets with respect to validating air quality models and tailoring air pollution mitigation strategies. The datasets can be found at https://doi.org/10.5281/zenodo.13318298 (Chebaicheb et al., 2024).

Basal materials in ice cores hold information about paleoclimate conditions, glacial processes, and the timing of past ice-free intervals, all of which aid understanding of ice sheet stability and its contribution to sea level rise in a warming climate. Only a few cores have been drilled through ice sheets into the underlying sediment and bedrock, producing limited material for analysis. The last of three Camp Century ice cores, which the U.S. Army collected in northwestern Greenland from 1963–1966 CE, recovered about 3.5 m of subglacial material, including ice and sediment. Here, we document the scientific history of the Camp Century subglacial material. We present our recent core-cutting, sub-sampling, and processing methodology and results for this unique archive. In 1972 CE, curators at the Buffalo, New York, Ice Core Laboratory cut the original core sections into 32 segments that were each about 10 cm long. Since then, two segments were lost and are unaccounted for, two were thawed, and two were cut as pilot samples in 2019 CE. Except for the two thawed segments, the rest of the extant core has remained frozen since collection. In 2021 CE, we documented, described, and then cut each of the remaining frozen archived segments (n=26). We saved an archival half and cut the working half into eight oriented sub-samples under controlled temperature and light conditions for physical, geochemical, isotopic, sedimentological, magnetic, and biological analyses. Our approach was designed to maximize sample usage for multiproxy analysis, minimize contamination, and preserve archive material for future analyses of this legacy subglacial material. Grain size, bulk density, sedimentary features, magnetic susceptibility, and ice content, as well as pore ice pH and conductivity, suggest that the basal sediment contains five stratigraphic units. We interpret these stratigraphic units as representing different depositional environments in subglacial or ice-free conditions: from bottom to top, a diamicton with subhorizontal ice lenses (Unit 1), vertically fractured ice with dispersed fine-grained sediments (<20 % in mass) (Unit 2), a normally graded bed of pebbles to very fine sand in an icy matrix (Unit 3), bedded very fine to fine sand (Unit 4), and stratified medium to coarse sand (Unit 5). Plant macrofossils are present in all samples and are most abundant in Units 3 and 4; insect remains are present in some samples (Units 1, 3, and 5). Our approach provides a working template for future studies of ice core basal materials because it includes intentional planning of core sub-sampling, processing methodologies, and archiving strategies to optimize the collection of paleoclimate, glacial process, geochemical, geochronological, and sediment properties from archives of limited size. Our work benefited from a carefully curated and preserved archive, allowing the application of analytical techniques not available in 1966 CE. Preserving uncontaminated core material for future analyses that use currently unavailable tools and techniques is an important consideration for rare archive materials such as these from Camp Century.

BackgroundArtificial intelligence (AI) applied to 12-lead electrocardiographs (ECGs) can detect hypertrophic cardiomyopathy (HCM).ObjectivesThe purpose of this study was to determine if AI-enhanced ECG (AI-ECG) can track longitudinal therapeutic response and changes in cardiac structure, function, or hemodynamics in obstructive HCM during mavacamten treatment.MethodsWe applied 2 independently developed AI-ECG algorithms (University of California-San Francisco and Mayo Clinic) to serial ECGs (n = 216) from the phase 2 PIONEER-OLE trial of mavacamten for symptomatic obstructive HCM (n = 13 patients, mean age 57.8 years, 69.2% male). Control ECGs from 2,600 age- and sex-matched individuals without HCM were obtained. AI-ECG output was correlated longitudinally to echocardiographic and laboratory metrics of mavacamten treatment response.ResultsIn the validation cohorts, both algorithms exhibited similar performance for HCM diagnosis, and exhibited mean HCM score decreases during mavacamten treatment: patient-level score reduction ranged from approximately 0.80 to 0.45 for Mayo and 0.70 to 0.35 for USCF algorithms; 11 of 13 patients demonstrated absolute score reduction from start to end of follow-up for both algorithms. HCM scores were significantly associated with other HCM-relevant parameters, including left ventricular outflow tract gradient at rest, postexercise, and with Valsalva, and NT-proBNP level, independent of age and sex (all P < 0.01). For both algorithms, the strongest longitudinal correlation was between AI-ECG HCM score and left ventricular outflow tract gradient postexercise (slope estimate: University of California-San Francisco 0.70 [95% CI: 0.45-0.96], P < 0.0001; Mayo 0.40 [95% CI: 0.11-0.68], P = 0.007).ConclusionsAI-ECG analysis longitudinally correlated with changes in echocardiographic and laboratory markers during mavacamten treatment in obstructive HCM. These results provide early evidence for a potential paradigm for monitoring HCM therapeutic response.

BACKGROUND: Mitral valve prolapse (MVP) is a common valvulopathy, with a subset developing sudden cardiac death or cardiac arrest. Complex ventricular ectopy (ComVE) is a marker of arrhythmic risk associated with myocardial fibrosis and increased mortality in MVP. OBJECTIVES: The authors sought to evaluate whether electrocardiogram (ECG)-based machine learning can identify MVP at risk for ComVE, death and/or myocardial fibrosis on cardiac magnetic resonance (CMR) imaging. METHODS: A deep convolutional neural network (CNN) was trained to detect ComVE using 6,916 12-lead ECGs from 569 MVP patients from the University of California-San Francisco between 2012 and 2020. A separate CNN was trained to detect late gadolinium enhancement (LGE) using 1,369 ECGs from 87 MVP patients with contrast CMR. RESULTS: The prevalence of ComVE was 28% (160/569). The area under the receiver operating characteristic curve (AUC) of the CNN to detect ComVE was 0.80 (95% CI: 0.77-0.83) and remained high after excluding patients with moderate-severe mitral regurgitation [0.80 (95% CI: 0.77-0.83)] or bileaflet MVP [0.81 (95% CI: 0.76-0.85)]. AUC to detect all-cause mortality was 0.82 (95% CI: 0.77-0.87). ECG segments relevant to ComVE prediction were related to ventricular depolarization/repolarization (early-mid ST-segment and QRS from V1, V3, and III). LGE in the papillary muscles or basal inferolateral wall was present in 24% patients with available CMR; AUC for detection of LGE was 0.75 (95% CI: 0.68-0.82). CONCLUSIONS: CNN-analyzed 12-lead ECGs can detect MVP at risk for ventricular arrhythmias, death and/or fibrosis and can identify novel ECG correlates of arrhythmic risk. ECG-based CNNs may help select those MVP patients requiring closer follow-up and/or a CMR.

BACKGROUND: It remains difficult to definitively distinguish supraventricular tachycardia (SVT) mechanisms using a 12-lead electrocardiogram (ECG) alone. Machine learning may identify visually imperceptible changes on 12-lead ECGs and may improve ability to determine SVT mechanisms. OBJECTIVE: We sought to develop a convolutional neural network (CNN) that identifies the SVT mechanism according to the gold standard of SVT ablation and to compare CNN performance against experienced electrophysiologists among patients with atrioventricular nodal re-entrant tachycardia (AVNRT), atrioventricular reciprocating tachycardia (AVRT), and atrial tachycardia (AT). METHODS: All patients with 12-lead surface ECG during sinus rhythm and SVT and had successful SVT ablation from 2013 to 2020 were included. A CNN was trained using data from 1505 surface ECGs that were split into 1287 training and 218 test ECG datasets. We compared the CNN performance against independent adjudication by 2 experienced cardiac electrophysiologists on the test dataset. RESULTS: Our dataset comprised 1505 ECGs (368 AVNRT, 304 AVRT, 95 AT, and 738 sinus rhythm) from 725 patients. The CNN areas under the receiver-operating characteristic curve for AVNRT, AVRT, and AT were 0.909, 0.867, and 0.817, respectively. When fixing the specificity of the CNN to the electrophysiologist adjudicators specificity, the CNN identified all SVT classes with higher sensitivity: (1) AVNRT (91.7% vs 65.9%), (2) AVRT (78.4% vs 63.6%), and (3) AT (61.5% vs 50.0%). CONCLUSION: A CNN can be trained to differentiate SVT mechanisms from surface 12-lead ECGs with high overall performance, achieving similar performance to experienced electrophysiologists at fixed specificities.

BackgroundEngagement with self-monitoring of blood pressure (BP) declines, on average, over time but may vary substantially by individual.ObjectivesWe aimed to describe different 1-year patterns (groups) of self-monitoring of BP behaviors, identify predictors of those groups, and examine the association of self-monitoring of BP groups with BP levels over time.MethodsWe analyzed device-recorded BP measurements collected by the Health eHeart Study-an ongoing prospective eCohort study-from participants with a wireless consumer-purchased device that transmitted date- and time-stamped BP data to the study through a full 12 months of observation starting from the first day they used the device. Participants received no instruction on device use. We applied clustering analysis to identify 1-year self-monitoring, of BP patterns.ResultsParticipants had a mean age of 52 years and were male and White. Using clustering algorithms, we found that a model with three groups fit the data well: persistent daily use (9.1% of participants), persistent weekly use (21.2%), and sporadic use only (69.7%). Persistent daily use was more common among older participants who had higher Week 1 self-monitoring of BP frequency and was associated with lower BP levels than the persistent weekly use or sporadic use groups throughout the year.ConclusionWe identified three distinct self-monitoring of BP groups, with nearly 10% sustaining a daily use pattern associated with lower BP levels.

Introduction The concept of medical student coachability, adapted from athletics and business management, offers a framework for characterizing students’ roles as clinical learners. We defined coachability as effectively seeking, receiving, and using feedback—even negative feedback—to change behavior and reach learning goals. To facilitate success in our clinical clerkships, we sought to empower preclerkship students’ capacity to be coached. Methods Our curriculum comprised two large-group presentations and three small-group seminars totaling approximately 5 hours, distributed over 2 years: a year 1 orientation, a year 2 refresher, and a longitudinal year 2 seminar series. Medical students designed and first implemented the curriculum under faculty supervision in academic year (AY) 2015–2016 and have continuously managed and run it since. The AY 2022–2023 curriculum management team evaluated the curriculum cross-sectionally via student survey and focus groups. Results Approximately 575 students have completed the curriculum since 2015. Immediately following curriculum delivery, AY 2022–2023 year 2 students (response rate: 70%-97%) rated it a valuable educational experience and described plans to implement the lessons learned in their clerkship. Focus group participants (eight clerkship students who participated in the coachability curriculum in AY 2021–2022) reported using coachability strategies to positive effect for their clinical learning and well-being. Discussion Our curriculum's flexible, modular format facilitates adoption by others. Future development could expand coachability offerings across the continuum of medical school. However, the curriculum should remain led by students passionate about medical education and willing to try new things to continuously adapt content and instructional strategies.

Abstract The coronary angiogram is the gold standard for evaluating the severity of coronary artery disease stenoses. Presently, the assessment is conducted visually by cardiologists, a method that lacks standardization. This study introduces DeepCoro, a ground-breaking AI-driven pipeline that integrates advanced vessel tracking and a video-based Swin3D model that was trained and validated on a dataset comprised of 182,418 coronary angiography videos spanning 5 years. DeepCoro achieved a notable precision of 71.89% in identifying coronary artery segments and demonstrated a mean absolute error of 20.15% (95% CI: 19.88–20.40) and a classification AUROC of 0.8294 (95% CI: 0.8215–0.8373) in stenosis percentage prediction compared to traditional cardiologist assessments. When compared to two expert interventional cardiologists, DeepCoro achieved lower variability than the clinical reports (19.09%; 95% CI: 18.55–19.58 vs 21.00%; 95% CI: 20.20–21.76, respectively). In addition, DeepCoro can be fine-tuned to a different modality type. When fine-tuned on quantitative coronary angiography assessments, DeepCoro attained an even lower mean absolute error of 7.75% (95% CI: 7.37–8.07), underscoring the reduced variability inherent to this method. This study establishes DeepCoro as an innovative video-based, adaptable tool in coronary artery disease analysis, significantly enhancing the precision and reliability of stenosis assessment.

Coronary angiography is the primary procedure for diagnosis and management decisions in coronary artery disease (CAD), but ad-hoc visual assessment of angiograms has high variability. Here we report a fully automated approach to interpret angiographic coronary artery stenosis from standard coronary angiograms. Using 13,843 angiographic studies from 11,972 adult patients at University of California, San Francisco (UCSF), between April 1, 2008 and December 31, 2019, we train neural networks to accomplish four sequential necessary tasks for automatic coronary artery stenosis localization and estimation. Algorithms are internally validated against criterion-standard labels for each task in hold-out test datasets. Algorithms are then externally validated in real-world angiograms from the University of Ottawa Heart Institute (UOHI) and also retrained using quantitative coronary angiography (QCA) data from the Montreal Heart Institute (MHI) core lab. The CathAI system achieves state-of-the-art performance across all tasks on unselected, real-world angiograms. Positive predictive value, sensitivity and F1 score are all ≥90% to identify projection angle and ≥93% for left/right coronary artery angiogram detection. To predict obstructive CAD stenosis (≥70%), CathAI exhibits an AUC of 0.862 (95% CI: 0.843-0.880). In UOHI external validation, CathAI achieves AUC 0.869 (95% CI: 0.830-0.907) to predict obstructive CAD. In the MHI QCA dataset, CathAI achieves an AUC of 0.775 (95%. CI: 0.594-0.955) after retraining. In conclusion, multiple purpose-built neural networks can function in sequence to accomplish automated analysis of real-world angiograms, which could increase standardization and reproducibility in angiographic coronary stenosis assessment.

Chest pain is a common clinical complaint for which myocardial injury is the primary concern and is associated with significant morbidity and mortality. To aid providers' decision-making, we aimed to analyze the electrocardiogram (ECG) using a deep convolutional neural network (CNN) to predict serum troponin I (TnI) from ECGs. We developed a CNN using 64,728 ECGs from 32,479 patients who underwent ECG within 2 h prior to a serum TnI laboratory result at the University of California, San Francisco (UCSF). In our primary analysis, we classified patients into groups of TnI

Recent advances in machine learning (ML) have made it possible to analyze high-dimensional and complex data-such as free text, images, waveforms, videos, and sound-in an automated manner by successfully learning complex associations within these data. Cardiovascular medicine is particularly well poised to take advantage of these ML advances, due to the widespread digitization of medical data and the large number of diagnostic tests used to evaluate cardiovascular disease. Various ML approaches have successfully been applied to cardiovascular tests and diseases to automate interpretation, accurately perform measurements, and, in some cases, predict novel diagnoses from less invasive tests, effectively expanding the utility of more widely accessible diagnostic tests. Here, we present examples of some impactful advances in cardiovascular medicine using ML across a variety of modalities, with a focus on deep learning applications.

The Antarctic ice sheet's future contribution to sea level rise is difficult to predict, mostly because of the uncertainty and variability of the surface mass balance (SMB). Ice cores are used to locally (kilometer scale) reconstruct SMB with a very good temporal resolution (up to sub-annual), especially in coastal areas where accumulation rates are high. The number of ice core records has been increasing in recent years, revealing an important spatial variability and different trends of SMB, highlighting the crucial need for greater spatial and temporal representativeness. We present records of density, water stable isotopes (δ18O, δD, and deuterium excess), major ions concentrations (Na+, K+, Mg2+, Ca2+, MSA, Cl−, SO42-, and NO3-), and continuous electrical conductivity measurement (ECM), as well as age models and resulting surface mass balance from the top 120 m of two ice cores (FK17 and TIR18) drilled on two adjacent ice rises located in coastal Dronning Maud Land and dating back to the end of the 18th century. Both environmental proxies and SMB show contrasting behaviors, suggesting strong spatial and temporal variability at the regional scale. In terms of precipitation proxies, both ice cores show a long-term decrease in deuterium excess (d-excess) and a long-term increase in δ18O, although less pronounced. In terms of chemical proxies, the non-sea-salt sulfate (nssSO42-) concentrations of FK17 are twice those of TIR18 and display an increasing trend on the long-term, whereas there is only a small increase after 1950 in TIR18. The SO42-/Na+ ratios show a similar contrast between FK17 and TIR18 and are consistently higher than the seawater ratio, indicating a dominant impact of the nssSO42- on the SO42- signature. The mean long-term SMB is similar for FK17 and TIR18 (0.57 ± 0.05 and 0.56 ± 0.05 mi.e.yr-1, respectively), but the annual records are very different: since the 1950s, TIR18 shows a continuous decrease while FK17 has shown an increasing trend until 1995 followed by a recent decrease. The datasets presented here offer numerous development possibilities for the interpretation of the different paleo-profiles and for addressing the mechanisms behind the spatial and temporal variability observed at the regional scale (tens of kilometers) in East Antarctica. The “Mass2Ant IceCores” datasets are available on Zenodo (https://doi.org/10.5281/zenodo.7848435; Wauthy et al., 2023).

Introduction Hypophosphatasia (HPP) is a rare genetic disease caused by loss-of-function mutations in the ALPL gene encoding the tissue non-specific alkaline phosphatase (ALP). Mild HPP is usually misdiagnosed in adult age. While an elevated serum ALP value draws more attention than a low value, low serum ALP should be better recognised and may lead to HPP detection.Methods Patients were selected from the records of the biochemistry department of six University Hospitals in France. Patients were hospitalised in the departments of rheumatology and internal medicine between 2007 and 2017.Results 56 321 hospitalised patients had at least 2 serum ALP dosages and 664 of these patients had at least 2 low serum ALP≤35 UI/L. Among these 664 patients, 482 (72.6%) had fluctuating low values (mean age 62.9 years; 60% of women) and 182 patients (27.4%) had persistent low values below 35 IU/L (mean age 53.4 years; 67% of women). Among patients with persistent hypophosphatasaemia treated with bisphosphonates, 70.8% never had ALP measurement before treatment and 20.8% were treated despite an abnormal decrease of ALP. Genetic testing was performed in 18 patients and was positive in 11. Genetic diagnosis of HPP was at least 6.0% in persistent hypophosphatasaemia and at least 15.9% in patients with at least three symptoms suggestive of HPP.Conclusion In this 10-year retrospective study, 0.32% of adult patients hospitalised in the rheumatology and internal medicine departments had persistently low serum ALP, and among them, 6% had genetically proven HPP. Reported hypophosphatasaemia represented only 3.6% of hospitalised patients.

Abstract Provenance records from sediments deposited offshore of the West Antarctic Ice Sheet (WAIS) can help identify past major ice retreat, thus constraining ice‐sheet models projecting future sea‐level rise. Interpretations from such records are, however, hampered by the ice obscuring Antarctica's geology. Here, we explore central West Antarctica's subglacial geology using basal debris from within the Byrd ice core, drilled to the bed in 1968. Sand grain microtextures and a high kaolinite content (∼38–42%) reveal the debris consists predominantly of eroded sedimentary detritus, likely deposited initially in a warm, pre‐Oligocene, subaerial environment. Detrital hornblende 40Ar/39Ar ages suggest proximal late Cenozoic subglacial volcanism. The debris has a distinct provenance signature, with: common Permian‐Early Jurassic mineral grains; absent early Ross Orogeny grains; a high kaolinite content; and high 143Nd/144Nd and low 87Sr/86Sr ratios. Detecting this “fingerprint” in Antarctic sedimentary records could imply major WAIS retreat, revealing the WAIS's sensitivity to future warming.

Purpose: The current standard-of-care management of locally advanced triple negative breast cancer (TNBC) is based on neoadjuvant chemo-immunotherapy with pembrolizumab, surgery, radiation therapy (RT), and adjuvant pembrolizumab. However, the safety of combining pembrolizumab with adjuvant breast RT has never been evaluated. This study evaluated the tolerance profile of concurrent pembrolizumab with adjuvant RT in patients with locally advanced TNBC. Methods and Materials: This bicentric ambispective study included all the patients with early and locally advanced TNBC who received neoadjuvant chemo-immunotherapy with pembrolizumab and adjuvant RT as part of their treatment. The tolerance profile of adjuvant RT was evaluated and compared in patients who received concurrent pembrolizumab and in patients for whom pembrolizumab was withheld. Results: Fifty-five patients were included between July 2021 and March 2023. Twenty-eight patients received adjuvant RT with concurrent pembrolizumab (RT+P group), and 27 patients had pembrolizumab withheld while receiving adjuvant RT (RT-only group). Two patients developed grade ≥3 toxicity (1 grade 3 pain in the RT+P group and 1 grade 3 radiodermatitis in the RT-only group), and there were no differences in terms of toxicity between the RT-only and the RT+P groups. No cardiac or pulmonary adverse event was reported during RT. With a median follow-up of 12 months (10-26), no patient relapsed. Conclusions: In this study of limited size, the authors did not find a difference between the RT-only and RT+P groups in terms of toxicity. More studies and longer follow-up may add to the strength of this evidence.