BackgroundPatient with acute coronary syndrome benefits from early revascularization. However, methods for the selection of patients who require urgent revascularization from a variety of patients visiting the emergency room with chest symptoms is not fully established. Electrocardiogram is an easy and rapid procedure, but may contain crucial information not recognized even by well-trained physicians.ObjectiveTo make a prediction model for the needs for urgent revascularization from 12-lead electrocardiogram recorded in the emergency room.MethodWe developed an artificial intelligence model enabling the detection of hidden information from a 12-lead electrocardiogram recorded in the emergency room. Electrocardiograms obtained from consecutive patients visiting the emergency room at Keio University Hospital from January 2012 to April 2018 with chest discomfort was collected. These data were splitted into validation and derivation dataset with no duplication in each dataset. The artificial intelligence model was constructed to select patients who require urgent revascularization within 48 hours. The model was trained with the derivation dataset and tested using the validation dataset.ResultsOf the consecutive 39,619 patients visiting the emergency room with chest discomfort, 362 underwent urgent revascularization. Of them, 249 were included in the derivation dataset and the remaining 113 were included in validation dataset. For the control, 300 were randomly selected as derivation dataset and another 130 patients were randomly selected for validation dataset from the 39,317 who did not undergo urgent revascularization. On validation, our artificial intelligence model had predictive value of the c-statistics 0.88 (95% CI 0.84–0.93) for detecting patients who required urgent revascularization.ConclusionsOur artificial intelligence model provides information to select patients who need urgent revascularization from only 12-leads electrocardiogram in those visiting the emergency room with chest discomfort.

No abstract

The benefits of inhaling hydrogen gas (H 2 ) have been widely reported but its pharmacokinetics have not yet been sufficiently analyzed. We developed a new experimental system in pigs to closely evaluate the process by which H 2 is absorbed in the lungs, enters the bloodstream, and is distributed, metabolized, and excreted. We inserted and secured catheters into the carotid artery (CA), portal vein (PV), and supra-hepatic inferior vena cava (IVC) to allow repeated blood sampling and performed bilateral thoracotomy to collapse the lungs. Then, using a hydrogen-absorbing alloy canister, we filled the lungs to the maximum inspiratory level with 100% H 2 . The pig was maintained for 30 seconds without resuming breathing, as if they were holding their breath. We collected blood from the three intravascular catheters after 0, 3, 10, 30, and 60 minutes and measured H 2 concentration by gas chromatography. H 2 concentration in the CA peaked immediately after breath holding; 3 min later, it dropped to 1/40 of the peak value. Peak H 2 concentrations in the PV and IVC were 40% and 14% of that in the CA, respectively. However, H 2 concentration decay in the PV and IVC (half-life: 310 s and 350 s, respectively) was slower than in the CA (half-life: 92 s). At 10 min, H 2 concentration was significantly higher in venous blood than in arterial blood. At 60 min, H 2 was detected in the portal blood at a concentration of 6.9-53 nL/mL higher than at steady state, and in the SVC 14-29 nL/mL higher than at steady state. In contrast, H 2 concentration in the CA decreased to steady state levels. This is the first report showing that inhaled H 2 is transported to the whole body by advection diffusion and metabolized dynamically.

Background: Novel targeted treatments increase the need for prompt hypertrophic cardiomyopathy (HCM) detection. However, its low prevalence (0.5%) and resemblance to common diseases present challenges that may benefit from automated machine learning–based approaches. We aimed to develop machine learning models to detect HCM and to differentiate it from other cardiac conditions using ECGs and echocardiograms, with robust generalizability across multiple cohorts. Methods: Single-institution HCM ECG models were trained and validated on external data. Multi-institution models for ECG and echocardiogram were trained on data from 3 academic medical centers in the United States and Japan using a federated learning approach, which enables training on distributed data without data sharing. Models were validated on held-out test sets for each institution and from a fourth academic medical center and were further evaluated for discrimination of HCM from aortic stenosis, hypertension, and cardiac amyloidosis. Last, automated detection was compared with manual interpretation by 3 cardiologists on a data set with a realistic HCM prevalence. Results: We identified 74 376 ECGs for 56 129 patients and 8392 echocardiograms for 6825 patients at the 4 academic medical centers. Although ECG models trained on data from each institution displayed excellent discrimination of HCM on internal test data (C statistics, 0.88–0.93), the generalizability was limited, most notably for a model trained in Japan and tested in the United States (C statistic, 0.79–0.82). When trained in a federated manner, discrimination of HCM was excellent across all institutions (C statistics, 0.90–0.96 and 0.90–0.96 for ECG and echocardiogram model, respectively), including for phenotypic subgroups. The models further discriminated HCM from hypertension, aortic stenosis, and cardiac amyloidosis (C statistics, 0.84, 0.83, and 0.88, respectively, for ECG and 0.93, 0.94, 0.85, respectively, for echocardiogram). Analysis of electrocardiography-echocardiography paired data from 11 823 patients from an external institution indicated a higher sensitivity of automated HCM detection at a given positive predictive value compared with cardiologists (0.98 versus 0.81 at a positive predictive value of 0.01 for ECG and 0.78 versus 0.59 at a positive predictive value of 0.24 for echocardiogram). Conclusions: Federated learning improved the generalizability of models that use ECGs and echocardiograms to detect and differentiate HCM from other causes of hypertrophy compared with training within a single institution.

Background We previously reported that osteopontin plays an essential role in accelerating both reparative fibrosis and clearance of dead cells (efferocytosis) during tissue repair after myocardial infarction (MI) and galectin‐3 hi CD206 + macrophages is the main source of osteopontin in post‐MI heart. Interleukin‐10– STAT3 (signal transducer and activator of transcription 3)–galectin‐3 axis is essential for Spp1 (encoding osteopontin) transcriptional activation in cardiac macrophages after MI. Here, we investigated the more detailed mechanism responsible for functional maturation of osteopontin‐producing macrophages. Methods and Results In post‐MI hearts, Spp1 transcriptional activation occurred almost exclusively in MerTK (Mer tyrosine kinase) + galectin‐3 hi macrophages. The induction of MerTK on galectin‐3 hi macrophages is essential for their functional maturation including efferocytosis and Spp1 transcriptional activity. MerTK + galectin‐3 hi macrophages showed a strong activation of both STAT3 and ERK (extracellular signal‐regulated kinase). STAT3 inhibition suppressed the differentiation of osteopontin‐producing MerTK + galectin‐3 hi macrophages, however, STAT3 activation was insufficient at inducing Spp1 transcriptional activity. ERK inhibition suppressed Spp1 transcriptional activation without affecting MerTK or galectin‐3 expression. Concomitant activation of ERK is required for transcriptional activation of Spp1 . In Il‐10 knockout enhanced green fluorescent protein– Spp1 knock‐in mice subjected to MI, osteopontin‐producing macrophages decreased but did not disappear entirely. Interleukin‐10 and macrophage colony‐stimulating factor synergistically activated STAT3 and ERK and promoted the differentiation of osteopontin‐producing MerTK + galectin‐3 hi macrophages in bone marrow–derived macrophages. Coadministration of anti‐interleukin‐10 plus anti–macrophage colony‐stimulating factor antibodies substantially reduced the number of osteopontin‐producing macrophages by more than anti–interleukin‐10 antibody alone in post‐MI hearts. Conclusions Interleukin‐10 and macrophage colony‐stimulating factor act synergistically to activate STAT3 and ERK in cardiac macrophages, which in turn upregulate the expression of galectin‐3 and MerTK, leading to the functional maturation of osteopontin‐producing macrophages.