Gut butyrate-producers confer post-infarction cardiac protection.

The gut microbiome and its metabolites are increasingly implicated in several cardiovascular diseases, but their role in human myocardial infarction (MI) injury responses have yet to be established. To address this, we examined stool samples from 77 ST-elevation MI (STEMI) patients using 16 S V3-V4 next-generation sequencing, metagenomics and machine learning. Our analysis identified an enriched population of butyrate-producing bacteria. These findings were then validated using a controlled ischemia/reperfusion model using eight nonhuman primates. To elucidate mechanisms, we inoculated gnotobiotic mice with these bacteria and found that they can produce beta-hydroxybutyrate, supporting cardiac function post-MI. This was further confirmed using HMGCS2-deficient mice which lack endogenous ketogenesis and have poor outcomes after MI. Inoculation increased plasma ketone levels and provided significant improvements in cardiac function post-MI. Together, this demonstrates a previously unknown role of gut butyrate-producers in the post-MI response.

Corrigendum: Artificial intelligence-assisted remote detection of ST-elevation myocardial infarction using a mini-12-lead electrocardiogram device in prehospital ambulance care.

[This corrects the article DOI: 10.3389/fcvm.2022.1001982.].

Implementation of an All-Day Artificial Intelligence-Based Triage System to Accelerate Door-to-Balloon Times.

OBJECTIVE: To implement an all-day artificial intelligence (AI)-based system to facilitate chest pain triage in the emergency department. METHODS: The AI-based triage system encompasses an AI model combining a convolutional neural network and long short-term memory to detect ST-elevation myocardial infarction (STEMI) on electrocardiography (ECG) and a clinical risk score (ASAP) to prioritize patients for ECG examination. The AI model was developed on 2907 twelve-lead ECGs: 882 STEMI and 2025 non-STEMI ECGs. RESULTS: Between November 1, 2019, and October 31, 2020, we enrolled 154 consecutive patients with STEMI: 68 during the AI-based triage period and 86 during the conventional triage period. The mean ± SD door-to-balloon (D2B) time was significantly shortened from 64.5±35.3 minutes to 53.2±12.7 minutes (P=.007), with 98.5% vs 87.2% (P=.009) of D2B times being less than 90 minutes in the AI group vs the conventional group. Among patients with an ASAP score of 3 or higher, the median door-to-ECG time decreased from 30 minutes (interquartile range [IQR], 7-59 minutes) to 6 minutes (IQR, 4-30 minutes) (P<.001). The overall performances of the AI model in identifying STEMI from 21,035 ECGs assessed by accuracy, precision, recall, area under the receiver operating characteristic curve, F1 score, and specificity were 0.997, 0.802, 0.977, 0.999, 0.881, and 0.998, respectively. CONCLUSION: Implementation of an all-day AI-based triage system significantly reduced the D2B time, with a corresponding increase in the percentage of D2B times less than 90 minutes in the emergency department. This system may help minimize preventable delays in D2B times for patients with STEMI undergoing primary percutaneous coronary intervention.

Artificial Intelligence-Enabled Electrocardiogram Improves the Diagnosis and Prediction of Mortality in Patients With Pulmonary Hypertension.

Background: Pulmonary hypertension is a disabling and life-threatening cardiovascular disease. Early detection of elevated pulmonary artery pressure (ePAP) is needed for prompt diagnosis and treatment to avoid detrimental consequences of pulmonary hypertension. Objectives: This study sought to develop an artificial intelligence (AI)-enabled electrocardiogram (ECG) model to identify patients with ePAP and related prognostic implications. Methods: From a hospital-based ECG database, the authors extracted the first pairs of ECG and transthoracic echocardiography taken within 2 weeks of each other from 41,097 patients to develop an AI model for detecting ePAP (PAP > 50 mm Hg by transthoracic echocardiography). The model was evaluated on independent data sets, including an external cohort of patients from Japan. Results: Tests of 10-fold cross-validation neural-network deep learning showed that the area under the receiver-operating characteristic curve of the AI model was 0.88 (sensitivity 81.0%; specificity 79.6%) for detecting ePAP. The diagnostic performance was consistent across age, sex, and various comorbidities (diagnostic odds ratio >8 for most factors examined). At 6-year follow-up, the patients predicted by the AI model to have ePAP were independently associated with higher cardiovascular mortality (HR: 3.69). Similar diagnostic performance and prediction for cardiovascular mortality could be replicated in the external cohort. Conclusions: The ECG-based AI model identified patients with ePAP and predicted their future risk for cardiovascular mortality. This model could serve as a useful clinical test to identify patients with pulmonary hypertension so that treatment can be initiated early to improve their survival prognosis.

Artificial intelligence-assisted remote detection of ST-elevation myocardial infarction using a mini-12-lead electrocardiogram device in prehospital ambulance care.

Objective: To implement an all-day online artificial intelligence (AI)-assisted detection of ST-elevation myocardial infarction (STEMI) by prehospital 12-lead electrocardiograms (ECGs) to facilitate patient triage for timely reperfusion therapy. Methods: The proposed AI model combines a convolutional neural network and long short-term memory (CNN-LSTM) to predict STEMI on prehospital 12-lead ECGs obtained from mini-12-lead ECG devices equipped in ambulance vehicles in Central Taiwan. Emergency medical technicians (EMTs) from the 14 AI-implemented fire stations performed the on-site 12-lead ECG examinations using the mini portable device. The 12-lead ECG signals were transmitted to the AI center of China Medical University Hospital to classify the recordings as "STEMI" or "Not STEMI". In 11 non-AI fire stations, the ECG data were transmitted to a secure network and read by available on-line emergency physicians. The response time was defined as the time interval between the ECG transmission and ECG interpretation feedback. Results: Between July 17, 2021, and March 26, 2022, the AI model classified 362 prehospital 12-lead ECGs obtained from 275 consecutive patients who had called the 119 dispatch centers of fire stations in Central Taiwan for symptoms of chest pain or shortness of breath. The AI's response time to the EMTs in ambulance vehicles was 37.2 ± 11.3 s, which was shorter than the online physicians' response time from 11 other fire stations with no AI implementation (113.2 ± 369.4 s, P < 0.001) after analyzing another set of 335 prehospital 12-lead ECGs. The evaluation metrics including accuracy, precision, specificity, recall, area under the receiver operating characteristic curve, and F1 score to assess the overall AI performance in the remote detection of STEMI were 0.992, 0.889, 0.994, 0.941, 0.997, and 0.914, respectively. During the study period, the AI model promptly identified 10 STEMI patients who underwent primary percutaneous coronary intervention (PPCI) with a median contact-to-door time of 18.5 (IQR: 16-20.8) minutes. Conclusion: Implementation of an all-day real-time AI-assisted remote detection of STEMI on prehospital 12-lead ECGs in the field is feasible with a high diagnostic accuracy rate. This approach may help minimize preventable delays in contact-to-treatment times for STEMI patients who require PPCI.

Usefulness of multi-labelling artificial intelligence in detecting rhythm disorders and acute ST-elevation myocardial infarction on 12-lead electrocardiogram.

Aims: To develop an artificial intelligence-based approach with multi-labelling capability to identify both ST-elevation myocardial infarction (STEMI) and 12 heart rhythms based on 12-lead electrocardiograms (ECGs). Methods and results: We trained, validated, and tested a long short-term memory (LSTM) model for the multi-label diagnosis of 13 ECG patterns (STEMI + 12 rhythm classes) using 60 537 clinical ECGs from 35 981 patients recorded between 15 January 2009 and 31 December 2018. In addition to the internal test above, we conducted a real-world external test, comparing the LSTM model with board-certified physicians of different specialties using a separate dataset of 308 ECGs covering all 13 ECG diagnoses. In the internal test, the area under the curves (AUCs) of the LSTM model in classifying the 13 ECG patterns ranged between 0.939 and 0.999. For the external test, the LSTM model for multi-labelling of the 13 ECG patterns evaluated by AUC was 0.987 ± 0.021, which was superior to those of cardiologists (0.898 ± 0.113, P < 0.001), emergency physicians (0.820 ± 0.134, P < 0.001), internists (0.765 ± 0.155, P < 0.001), and a commercial algorithm (0.845 ± 0.121, P < 0.001). Of note, the LSTM model achieved an accuracy of 0.987, AUC of 0.997, and precision, recall, and F 1 score of 0.952, 0.870, and 0.909, respectively, in detecting STEMI. Conclusions: We demonstrated the usefulness of an LSTM model in the multi-labelling detection of both rhythm classes and STEMI in competitive testing against board-certified physicians. This AI tool exceeding the cardiologist-level performance in detecting STEMI and rhythm classes on 12-lead ECG may be useful in prioritizing chest pain triage and expediting clinical decision-making in healthcare.

Usefulness of Machine Learning-Based Detection and Classification of Cardiac Arrhythmias With 12-Lead Electrocardiograms.

BACKGROUND: Deep-learning algorithms to annotate electrocardiograms (ECGs) and classify different types of cardiac arrhythmias with the use of a single-lead ECG input data set have been developed. It remains to be determined whether these algorithms can be generalized to 12-lead ECG-based rhythm classification. METHODS: We used a long short-term memory (LSTM) model to detect 12 heart rhythm classes with the use of 65,932 digital 12-lead ECG signals from 38,899 patients, using annotations obtained by consensus of 3 board-certified electrophysiologists as the criterion standard. RESULTS: The accuracy of the LSTM model for the classification of each of the 12 heart rhythms was ≥ 0.982 (range 0.982-1.0), with an area under the receiver operating characteristic curve of ≥ 0.987 (range 0.987-1.0). The precision and recall ranged from 0.692 to 1 and from 0.625 to 1, respectively, with an F1 score of ≥ 0.777 (range 0.777-1.0). The accuracy of the model (0.90) was superior to the mean accuracies of internists (0.55), emergency physicians (0.73), and cardiologists (0.83). CONCLUSIONS: We demonstrated the feasibility and effectiveness of the deep-learning LSTM model for interpreting 12 common heart rhythms according to 12-lead ECG signals. The findings may have clinical relevance for the early diagnosis of cardiac rhythm disorders.

Detection and Classification of Cardiac Arrhythmias by a Challenge-Best Deep Learning Neural Network Model.

Electrocardiograms (ECGs) are widely used to clinically detect cardiac arrhythmias (CAs). They are also being used to develop computer-assisted methods for heart disease diagnosis. We have developed a convolution neural network model to detect and classify CAs, using a large 12-lead ECG dataset (6,877 recordings) provided by the China Physiological Signal Challenge (CPSC) 2018. Our model, which was ranked first in the challenge competition, achieved a median overall F1-score of 0.84 for the nine-type CA classification of CPSC2018's hidden test set of 2,954 ECG recordings. Further analysis showed that concurrent CAs were adequately predictive for 476 patients with multiple types of CA diagnoses in the dataset. Using only single-lead data yielded a performance that was only slightly worse than using the full 12-lead data, with leads aVR and V1 being the most prominent. We extensively consider these results in the context of their agreement with and relevance to clinical observations.

NPPD: A Protein-Protein Docking Scoring Function Based on Dyadic Differences in Networks of Hydrophobic and Hydrophilic Amino Acid Residues.

Protein-protein docking (PPD) predictions usually rely on the use of a scoring function to rank docking models generated by exhaustive sampling. To rank good models higher than bad ones, a large number of scoring functions have been developed and evaluated, but the methods used for the computation of PPD predictions remain largely unsatisfactory. Here, we report a network-based PPD scoring function, the NPPD, in which the network consists of two types of network nodes, one for hydrophobic and the other for hydrophilic amino acid residues, and the nodes are connected when the residues they represent are within a certain contact distance. We showed that network parameters that compute dyadic interactions and those that compute heterophilic interactions of the amino acid networks thus constructed allowed NPPD to perform well in a benchmark evaluation of 115 PPD scoring functions, most of which, unlike NPPD, are based on some sort of protein-protein interaction energy. We also showed that NPPD was highly complementary to these energy-based scoring functions, suggesting that the combined use of conventional scoring functions and NPPD might significantly improve the accuracy of current PPD predictions.

A critical assessment of information-guided protein-protein docking predictions.

The structures of protein complexes are increasingly predicted via protein-protein docking (PPD) using ambiguous interaction data to help guide the docking. These data often are incomplete and contain errors and therefore could lead to incorrect docking predictions. In this study, we performed a series of PPD simulations to examine the effects of incompletely and incorrectly assigned interface residues on the success rate of PPD predictions. The results for a widely used PPD benchmark dataset obtained using a new interface information-driven PPD (IPPD) method developed in this work showed that the success rate for an acceptable top-ranked model varied, depending on the information content used, from as high as 95% when contact relationships (though not contact distances) were known for all residues to 78% when only the interface/non-interface state of the residues was known. However, the success rates decreased rapidly to ∼40% when the interface/non-interface state of 20% of the residues was assigned incorrectly, and to less than 5% for a 40% incorrect assignment. Comparisons with results obtained by re-ranking a global search and with those reported for other data-guided PPD methods showed that, in general, IPPD performed better than re-ranking when the information used was more complete and more accurate, but worse when it was not, and that when using bioinformatics-predicted information on interface residues, IPPD and other data-guided PPD methods performed poorly, at a level similar to simulations with a 40% incorrect assignment. These results provide guidelines for using information about interface residues to improve PPD predictions and reveal a bottleneck for such improvement imposed by the low accuracy of current bioinformatic interface residue predictions.

On the use of distance constraints in protein-protein docking computations.

Protein-protein docking (PPD) is a computational process that predicts the structure of a complex of two interacting proteins from their unbound structures. The accuracy of PPD predictions is low, but can be greatly enhanced if experimentally determined distance data are available for incorporation into the prediction. However, the specific effects of distance constraints on PPD predictions are largely uncharacterized. In this study, we systematically simulated the effects of using distance constraints both on a new distance constraint-driven PPD approach, called DPPD, and also, by re-ranking, on a well-established grid-based global search approach. Our results for a PPD benchmark dataset of 84 protein complexes of known structures showed that near 100% docking success rates could be obtained when the number of distance constraints exceeded six, the degrees of freedom of the system, but the success rate was significantly reduced by long distance constraints, large binding-induced conformational changes, and large errors in the distance data. Our results also showed that, under most conditions simulated, even two or three distance constraints were sufficient to achieve a much better success rate than those using a sophisticated physicochemical function to re-rank the results of the global search. Our study provides guidelines for the practical incorporation of experimental distance data to aid PPD predictions.

Preservation of ranking order in the expression of human Housekeeping genes.

Housekeeping (HK) genes fulfill the basic needs for a cell to survive and function properly. Their ubiquitous expression, originally thought to be constant, can vary from tissue to tissue, but this variation remains largely uncharacterized and it could not be explained by previously identified properties of HK genes such as short gene length and high GC content. By analyzing microarray expression data for human genes, we uncovered a previously unnoted characteristic of HK gene expression, namely that the ranking order of their expression levels tends to be preserved from one tissue to another. Further analysis by tensor product decomposition and pathway stratification identified three main factors of the observed ranking preservation, namely that, compared to those of non-HK (NHK) genes, the expression levels of HK genes show a greater degree of dispersion (less overlap), stableness (a smaller variation in expression between tissues), and correlation of expression. Our results shed light on regulatory mechanisms of HK gene expression that are probably different for different HK genes or pathways, but are consistent and coordinated in different tissues.

OPAAS: a web server for optimal, permuted, and other alternative alignments of protein structures.

The large number of experimentally determined protein 3D structures is a rich resource for studying protein function and evolution, and protein structure comparison (PSC) is a key method for such studies. When comparing two protein structures, almost all currently available PSC servers report a single and sequential (i.e. topological) alignment, whereas the existence of good alternative alignments, including those involving permutations (i.e. non-sequential or non-topological alignments), is well known. We have recently developed a novel PSC method that can detect alternative alignments of statistical significance (alignment similarity P-value <10(-5)), including structural permutations at all levels of complexity. OPAAS, the server of this PSC method freely accessible at our website (http://opaas.ibms.sinica.edu.tw), provides an easy-to-read hierarchical layout of output to display detailed information on all of the significant alternative alignments detected. Because these alternative alignments can offer a more complete picture on the structural, evolutionary and functional relationship between two proteins, OPAAS can be used in structural bioinformatics research to gain additional insight that is not readily provided by existing PSC servers.

Alternative alignments from comparison of protein structures.

Comparison of two protein structures often results in not only a global alignment but also a number of distinct local alignments; the latter, referred to as alternative alignments, are however usually ignored in existing protein structure comparison analyses. Here, we used a novel method of protein structure comparison to extensively identify and characterize the alternative alignments obtained for structure pairs of a fold classification database. We showed that all alternative alignments can be classified into one of just a few types, and with which illustrated the potential of using alternative alignments to identify recurring protein substructures, including the internal structural repeats of a protein. Furthermore, we showed that among the alternative alignments obtained, permuted alignments, which included both circular and scrambled permutations, are as prevalent as topological alignments. These results demonstrated that the so far largely unattended alternative alignments of protein structures have implications and applications for research of protein classification and evolution.

Protein structure comparison by probability-based matching of secondary structure elements.

MOTIVATION: Protein structure comparison (PSC) has been used widely in studies of structural and functional genomics. However, PSC is computationally expensive and as a result almost all of the PSC methods currently in use look only for the optimal alignment and ignore many alternative alignments that are statistically significant and that may provide insight into protein evolution or folding. RESULTS: We have developed a new PSC method with efficiency to detect potentially viable alternative alignments in all-against-all database comparisons. The efficiency of the new PSC method derives from the ability to directly home in on a limited number of viable and ranked alignment solutions based on intuitively derived SSE (secondary structure element)-matching probabilities.

Single nucleotide polymorphism mapping using genome-wide unique sequences.

As more and more genomic DNAs are sequenced to characterize human genetic variations, the demand for a very fast and accurate method to genomically position these DNA sequences is high. We have developed a new mapping method that does not require sequence alignment. In this method, we first identified DNA fragments of 15 bp in length that are unique in the human genome and then used them to position single nucleotide polymorphism (SNP) sequences. By use of four desktop personal computers with AMD K7 (1 GHz) processors, our new method mapped more than 1.6 million SNP sequences in 20 hr and achieved a very good agreement with mapping results from alignment-based methods.