Background: The detection of dyskalemias—hypokalemia and hyperkalemia—currently depends on laboratory tests. Since cardiac tissue is very sensitive to dyskalemia, electrocardiography (ECG) may be able to uncover clinically important dyskalemias before laboratory results. Objective: Our study aimed to develop a deep-learning model, ECG12Net, to detect dyskalemias based on ECG presentations and to evaluate the logic and performance of this model. Methods: Spanning from May 2011 to December 2016, 66,321 ECG records with corresponding serum potassium (K+) concentrations were obtained from 40,180 patients admitted to the emergency department. ECG12Net is an 82-layer convolutional neural network that estimates serum K+ concentration. Six clinicians—three emergency physicians and three cardiologists—participated in human-machine competition. Sensitivity, specificity, and balance accuracy were used to evaluate the performance of ECG12Net with that of these physicians. Results: In a human-machine competition including 300 ECGs of different serum K+ concentrations, the area under the curve for detecting hypokalemia and hyperkalemia with ECG12Net was 0.926 and 0.958, respectively, which was significantly better than that of our best clinicians. Moreover, in detecting hypokalemia and hyperkalemia, the sensitivities were 96.7% and 83.3%, respectively, and the specificities were 93.3% and 97.8%, respectively. In a test set including 13,222 ECGs, ECG12Net had a similar performance in terms of sensitivity for severe hypokalemia (95.6%) and severe hyperkalemia (84.5%), with a mean absolute error of 0.531. The specificities for detecting hypokalemia and hyperkalemia were 81.6% and 96.0%, respectively. Conclusions: A deep-learning model based on a 12-lead ECG may help physicians promptly recognize severe dyskalemias and thereby potentially reduce cardiac events.

Traumatic brain injury (TBI) can lead to severe adverse clinical outcomes, including death and disability. Early detection of in-hospital mortality in high-risk populations may enable early treatment and potentially reduce mortality using machine learning. However, there is limited information on in-hospital mortality prediction models for TBI patients admitted to emergency departments. The aim of this study was to create a model that successfully predicts, from clinical measures and demographics, in-hospital mortality in a sample of TBI patients admitted to the emergency department. Of the 4881 TBI patients who were screened at the emergency department at a high-level first aid duty hospital in northern Taiwan, 3331 were assigned in triage to Level I or Level II using the Taiwan Triage and Acuity Scale from January 2008 to June 2018. The most significant predictors of in-hospital mortality in TBI patients were the scores on the Glasgow coma scale, the injury severity scale, and systolic blood pressure in the emergency department admission. This study demonstrated the effective cutoff values for clinical measures when using machine learning to predict in-hospital mortality of patients with TBI. The prediction model has the potential to further accelerate the development of innovative care-delivery protocols for high-risk patients.

T cells secrete several inflammatory cytokines that play a critical role in the progression of atherosclerosis. Although green tea epigallocatechin-3-gallate (EGCG) exerts anti-inflammatory and anti-atherosclerotic effects in animals, few studies have identified the mechanism underlying these effects in human primary T cells. This study investigated the pathway involved in EGCG modulation of cytokine secretion in activated human primary T cells. We pre-treated human primary T cells with EGCG (0.1, 1, 5, 10, and 20 μM) for 4 h and incubated them with or without phorbol 12-myristate 13-acetate and ionomycin (P/I) for 20 h. The cytokine production, activator protein (AP)-1 binding activity, and level of mitogen-activated protein kinase (MAPK) were assessed using enzyme-linked immunosorbent assay, electrophoretic mobility shift assay, and Western blotting, respectively. At 10 and 20 μM, EGCG decreased interleukin (IL)-2 levels by 26.0% and 38.8%, IL-4 levels by 41.5% and 55.9%, INF-γ levels by 31.3% and 34.7%, and tumor-necrosis factor (TNF)-α levels by 23.0% and 37.6%, respectively. In addition, the level of phosphorylated c-Jun N-terminal (p-JNK) and extracellular signal-regulated kinase (p-ERK) was decreased, but not the level of p-p38 MAPK. EGCG did not alter any of the total protein amounts, suggesting a selective effect on specific types of MAPKs in stimulated human T cells. EGCG tended to inactivate AP-1 DNA-binding activity. The P/I-induced production of IL-2, IL-4, INF-γ, and TNF-α by human T cells was suppressed by AP-1 inhibitor in a concentration-dependent manner. In conclusion, EGCG suppressed cytokine secretion in activated human primary T cells, and this effect was likely mediated by AP-1 inactivation through the ERK and JNK, but not p38 MAPK, pathways. These results may be related to the mechanisms through which EGCG inhibits immune- or inflammation-related atherogenesis.

Carvedilol (Cav), a nonselective β-blocker with α1 adrenoceptor blocking effect, has been used as a standard therapy for coronary artery disease. This study investigated the effects of Cav on exosome expression and function, ATP-binding cassette transporter A1 (ABCA1) expression, and cholesterol efflux that are relevant to the process of atherosclerosis. Human monocytic (THP-1) cell line and human hepatic (Huh-7) cells were treated with Cav, and cholesterol efflux was measured. Exosomes from cell culture medium or mice serum were isolated using glycan-coated recognition beads. Low-density lipoprotein receptor knockout (ldlr^−/−) mice were fed with high-fat diet and treated with Cav. Cav accentuated cholesterol efflux and enhanced the expressions of ABCA1 protein and mRNA in both THP-1 and Huh-7 cells. In addition, Cav increased expression and function of exosomal ABCA1 in THP-1 macrophage exosomes. The mechanisms were associated with inhibition of nuclear factor-κB (NF-κB) and protein kinase B (Akt). In hypercholesterolemic ldlr^−/− mice, Cav enhanced serum exosomal ABCA1 expression and suppressed atherosclerosis by inhibiting lipid deposition and macrophage accumulation. Cav halts atherosclerosis by enhancing cholesterol efflux and increasing ABCA1 expression in macrophages and in exosomes, possibly through NF-κB and Akt signaling, which provides mechanistic insights regarding the beneficial effects of Cav on atherosclerotic cardiovascular disease.

Statins inhibiting 3-hydroxy-3-methylglutaryl-CoA reductase are the standard treatment for hypercholesterolemia in atherosclerotic cardiovascular disease (ASCVD), mediated by inflammatory reactions within vessel walls. Several studies highlighted the pleiotropic effects of statins beyond their lipid-lowering properties. However, few studies investigated the effects of statins on T cell activation. This study evaluated the immunomodulatory capacities of three common statins, pitavastatin, atorvastatin, and rosuvastatin, in activated human T cells. The enzyme-linked immunosorbent assay (ELISA) and quantitative real time polymerase chain reaction (qRT-PCR) results demonstrated stronger inhibitory effects of pitavastatin on the cytokine production of T cells activated by phorbol 12-myristate 13-acetate (PMA) plus ionomycin, including interleukin (IL)-2, interferon (IFN)-γ, IL-6, and tumor necrosis factor α (TNF-α). Molecular investigations revealed that pitavastatin reduced both activating protein-1 (AP-1) DNA binding and transcriptional activities. Further exploration showed the selectively inhibitory effect of pitavastatin on the signaling pathways of extracellular signal-regulated kinase (ERK) and p38 mitogen-activated protein kinase (MAPK), but not c-Jun N-terminal kinase (JNK). Our findings suggested that pitavastatin might provide additional benefits for treating hypercholesterolemia and ASCVD through its potent immunomodulatory effects on the suppression of ERK/p38/AP-1 signaling in human T cells.

Context Thyrotoxic periodic paralysis (TPP) characterized by acute weakness, hypokalemia, and hyperthyroidism is a medical emergency with a great challenge in early diagnosis since most TPP patients do not have overt symptoms. Objective This work aims to assess artificial intelligence (AI)-assisted electrocardiography (ECG) combined with routine laboratory data in the early diagnosis of TPP. Methods A deep learning model (DLM) based on ECG12Net, an 82-layer convolutional neural network, was constructed to detect hypokalemia and hyperthyroidism. The development cohort consisted of 39 ECGs from patients with TPP and 502 ECGs of hypokalemic controls; the validation cohort consisted of 11 ECGs of TPP patients and 36 ECGs of non-TPP individuals with weakness. The AI-ECG–based TPP diagnostic process was then consecutively evaluated in 22 male patients with TTP-like features. Results In the validation cohort, the DLM-based ECG system detected all cases of hypokalemia in TPP patients with a mean absolute error of 0.26 mEq/L and diagnosed TPP with an area under curve (AUC) of approximately 80%, surpassing the best standard ECG parameter (AUC = 0.7285 for the QR interval). Combining the AI predictions with the estimated glomerular filtration rate and serum chloride boosted the diagnostic accuracy of the algorithm to AUC 0.986. In the prospective study, the integrated AI and routine laboratory diagnostic system had a PPV of 100% and F-measure of 87.5%. Conclusion An AI-ECG system reliably identifies hypokalemia in patients with paralysis, and integration with routine blood chemistries provides valuable decision support for the early diagnosis of TPP.