Search

Abstract Background Hyperthyroidism is frequently under-recognized and leads to heart failure and mortality. Timely identification of high-risk patients is a prerequisite to effective antithyroid therapy. Since the heart is very sensitive to hyperthyroidism and its electrical signature can be demonstrated by electrocardiography, we developed an artificial intelligence model to detect hyperthyroidism by electrocardiography and examined its potential for outcome prediction. Methods The deep learning model was trained using a large dataset of 47,245 electrocardiograms from 33,246 patients at an academic medical center. Patients were included if electrocardiograms and measurements of serum thyroid-stimulating hormone were available that had been obtained within a three day period. Serum thyroid-stimulating hormone and free thyroxine were used to define overt and subclinical hyperthyroidism. We tested the model internally using 14,420 patients and externally using two additional test sets comprising 11,498 and 596 patients, respectively. Results The performance of the deep learning model achieves areas under the receiver operating characteristic curves (AUCs) of 0.725–0.761 for hyperthyroidism detection, AUCs of 0.867–0.876 for overt hyperthyroidism, and AUC of 0.631–0.701 for subclinical hyperthyroidism, superior to a traditional features-based machine learning model. Patients identified as hyperthyroidism-positive by the deep learning model have a significantly higher risk (1.97–2.94 fold) of all-cause mortality and new-onset heart failure compared to hyperthyroidism-negative patients. This cardiovascular disease stratification is particularly pronounced in subclinical hyperthyroidism, surpassing that observed in overt hyperthyroidism. Conclusions An innovative algorithm effectively identifies overt and subclinical hyperthyroidism and contributes to cardiovascular risk assessment.

Background The electrocardiogram (ECG) may be the most popular test in the management of cardiovascular disease (CVD). Although wide applications of artificial intelligence (AI)-enabled ECG have been developed, an integrating indicator for CVD risk stratification was not investigated. Since mortality may be the most important global outcome, this study aimed to develop a survival deep learning model (DLM) to establish a critical ECG value and explore the associations with various CVD events. Methods We trained a DLM with 451,950 12-lead resting ECGs obtained from 210,552 patients, for whom 23,592 events occurred. The internal validation set included 27,808 patients with one ECG for each patient. The external validations were performed in a community hospital with 33,047 patients and two transnational data sets with 233,647 and 1631 ECGs. We distinguished the cause of mortality and additionally investigated CVD-related outcomes, including new-onset acute myocardial infarction (AMI), stroke (STK), and heart failure (HF). Results The DLM achieved C-indices of 0.858/0.836 in internal/external validation sets by using ECG over a 10-year period. The high-mortality-risk group identified by the proposed DLM presented a hazard ratio (HR) of 14.16 (95% confidence interval (CI): 11.33–17.70) compared to the low-risk group in the internal validation and presented a higher risk of cardiovascular (CV) mortality (HR: 18.50, 95% CI: 9.82–34.84), non-CV mortality (HR: 13.68, 95% CI: 10.76–17.38), AMI (HR: 4.01, 95% CI: 2.24–7.17), STK (HR: 2.15, 95% CI: 1.70–2.72), and HF (HR: 6.66, 95% CI: 4.54–9.77), which was consistent in an independent community hospital. The transnational validation also revealed HRs of 4.91 (95% CI: 2.63–9.16) and 2.29 (95% CI: 2.15–2.44) for all-cause mortality in the SaMi-Trop and Clinical Outcomes in Digital Electrocardiography 15% (CODE15) cohorts. Conclusions The mortality risk by AI-enabled ECG may be applied in passive electronic-health-record-based CVD risk screening, which may identify more asymptomatic and unaware high-risk patients.

Abstract Dyskalemias are common electrolyte disorders associated with high cardiovascular risk. Artificial intelligence (AI)-assisted electrocardiography (ECG) has been evaluated as an early-detection approach for dyskalemia. The aims of this study were to determine the clinical accuracy of AI-assisted ECG for dyskalemia and prognostic ability on clinical outcomes such as all-cause mortality, hospitalizations, and ED revisits. This retrospective cohort study was done at two hospitals within a health system from May 2019 to December 2020. In total, 26,499 patients with 34,803 emergency department (ED) visits to an academic medical center and 6492 ED visits from 4747 patients to a community hospital who had a 12-lead ECG to estimate ECG-K+ and serum laboratory potassium measurement (Lab-K+) within 1 h were included. ECG-K+ had mean absolute errors (MAEs) of ≤0.365 mmol/L. Area under receiver operating characteristic curves for ECG-K+ to predict moderate-to-severe hypokalemia (Lab-K+ ≤3 mmol/L) and moderate-to-severe hyperkalemia (Lab-K+ ≥ 6 mmol/L) were >0.85 and >0.95, respectively. The U-shaped relationships between K+ concentration and adverse outcomes were more prominent for ECG-K+ than for Lab-K+. ECG-K+ and Lab-K+ hyperkalemia were associated with high HRs for 30-day all-cause mortality. Compared to hypokalemic Lab-K+, patients with hypokalemic ECG-K+ had significantly higher risk for adverse outcomes after full confounder adjustment. In addition, patients with normal Lab-K+ but dyskalemic ECG-K+ (pseudo-positive) also exhibited more co-morbidities and had worse outcomes. Point-of-care bloodless AI ECG-K+ not only rapidly identified potentially severe hypo- and hyperkalemia, but also may serve as a biomarker for medical complexity and an independent predictor for adverse outcomes.

BACKGROUND: The B-type natriuretic peptide (BNP) and N-terminal pro-brain natriuretic peptide (pBNP) are predictors of cardiovascular morbidity and mortality. Since the artificial intelligence (AI)-enabled electrocardiogram (ECG) system is widely used in the management of many cardiovascular diseases (CVDs), patients requiring intensive monitoring may benefit from an AI-ECG with BNP/pBNP predictions. This study aimed to develop an AI-ECG to predict BNP/pBNP and compare their values for future mortality. METHODS: The development, tuning, internal validation, and external validation sets included 47,709, 16,249, 4001, and 6042 ECGs, respectively. Deep learning models (DLMs) were trained using a development set for estimating ECG-based BNP/pBNP (ECG-BNP/ECG-pBNP), and the tuning set was used to guide the training process. The ECGs in internal and external validation sets belonging to nonrepeating patients were used to validate the DLMs. We also followed-up all-cause mortality to explore the prognostic value. RESULTS: The DLMs accurately distinguished mild (≥500 pg/mL) and severe (≥1000 pg/mL) an abnormal BNP/pBNP with AUCs of ≥0.85 in the internal and external validation sets, which provided sensitivities of 68.0–85.0% and specificities of 77.9–86.2%. In continuous predictions, the Pearson correlation coefficient between ECG-BNP and ECG-pBNP was 0.93, and they were both associated with similar ECG features, such as the T wave axis and correct QT interval. ECG-pBNP provided a higher all-cause mortality predictive value than ECG-BNP. CONCLUSIONS: The AI-ECG can accurately estimate BNP/pBNP and may be useful for monitoring the risk of CVDs. Moreover, ECG-pBNP may be a better indicator to manage the risk of future mortality.

Background Artificial intelligence-enabled electrocardiogram has become a substitute tool for echocardiography in left ventricular ejection fraction estimation. However, the direct use of artificial intelligence-enabled electrocardiogram may be not trustable due to the uncertainty of the prediction. Objective The study aimed to establish an artificial intelligence-enabled electrocardiogram with a degree of confidence to identify left ventricular dysfunction. Methods The study collected 76,081 and 11,771 electrocardiograms from an academic medical center and a community hospital to establish and validate the deep learning model, respectively. The proposed deep learning model provided the point estimation of the actual ejection fraction and its standard deviation derived from the maximum probability density function of a normal distribution. The primary analysis focused on the accuracy of identifying patients with left ventricular dysfunction (ejection fraction ≤ 40%). Since the standard deviation was an uncertainty indicator in a normal distribution, we used it as a degree of confidence in the artificial intelligence-enabled electrocardiogram. We further explored the clinical application of estimated standard deviation and followed up on the new-onset left ventricular dysfunction in patients with initially normal ejection fraction. Results The area under receiver operating characteristic curves (AUC) of detecting left ventricular dysfunction were 0.9549 and 0.9365 in internal and external validation sets. After excluding the cases with a lower degree of confidence, the artificial intelligence-enabled electrocardiogram performed better in the remaining cases in internal (AUC = 0.9759) and external (AUC = 0.9653) validation sets. For the application of future left ventricular dysfunction risk stratification in patients with initially normal ejection fraction, a 4.57-fold risk of future left ventricular dysfunction when the artificial intelligence-enabled electrocardiogram is positive in the internal validation set. The hazard ratio was increased to 8.67 after excluding the cases with a lower degree of confidence. This trend was also validated in the external validation set. Conclusion The deep learning model with a degree of confidence can provide advanced improvements in identifying left ventricular dysfunction and serve as a decision support and management-guided screening tool for prognosis.

BackgroundAlbumin, an important component of fluid balance, is associated with kidney, liver, nutritional, and cardiovascular diseases (CVD) and is measured by blood tests. Since fluid balance is associated with electrocardiography (ECG) changes, we established a deep learning model (DLM) to estimate albumin via ECG.ObjectiveThis study aimed to develop a DLM to estimate albumin via ECG and explored its contribution to future complications.Materials and MethodsA DLM was trained for estimating ECG-based albumin (ECG-Alb) using 155,078 ECGs corresponding to albumin from 79,111 patients, and another independent 13,335 patients from an academic medical center and 11,370 patients from a community hospital were used for internal and external validation. The primary analysis focused on distinguishing patients with mild to severe hypoalbuminemia, and the secondary analysis aimed to provide additional prognostic value from ECG-Alb for future complications, which included mortality, new-onset hypoalbuminemia, chronic kidney disease (CKD), new onset hepatitis, CVD mortality, new-onset acute myocardial infarction (AMI), new-onset stroke (STK), new-onset coronary artery disease (CAD), new-onset heart failure (HF), and new-onset atrial fibrillation (Afib).ResultsThe AUC to identify hypoalbuminemia was 0.8771 with a sensitivity of 56.0% and a specificity of 90.7% in the internal validation set, and the Pearson correlation coefficient was 0.69 in the continuous analysis. The most important ECG features contributing to ECG-Alb were ordered in terms of heart rate, corrected QT interval, T wave axis, sinus rhythm, P wave axis, etc. The group with severely low ECG-Alb had a higher risk of all-cause mortality [hazard ratio (HR): 2.45, 95% CI: 1.81–3.33] and the other hepatorenal and cardiovascular events in the internal validation set. The external validation set yielded similar results.ConclusionHypoalbuminemia and its complications can be predicted using ECG-Alb as a novel biomarker, which may be a non-invasive tool to warn asymptomatic patients.

BackgroundHeart failure (HF) is a global disease with increasing prevalence in an aging society. However, the survival rate is poor despite the patient receiving standard treatment. Early identification of patients with a high risk of HF is important but challenging. Left ventricular end-diastolic diameter (LV-D) increase was an independent risk factor of HF and adverse cardiovascular (CV) outcomes. In this study, we aimed to develop an artificial intelligence (AI) enabled electrocardiogram (ECG) system to detect LV-D increase early.ObjectiveWe developed a deep learning model (DLM) to predict left ventricular end-diastolic and end-systolic diameter (LV-D and LV-S) with internal and external validations and investigated the relationship between ECG-LV-D and echocardiographic LV-D and explored the contributions of ECG-LV-D on future CV outcomes.MethodsElectrocardiograms and corresponding echocardiography data within 7 days were collected and paired for DLM training with 99,692 ECGs in the development set and 20,197 ECGs in the tuning set. The other 7,551 and 11,644 ECGs were collected from two different hospitals to validate the DLM performance in internal and external validation sets. We analyzed the association and prediction ability of ECG-LVD for CV outcomes, including left ventricular (LV) dysfunction, CV mortality, acute myocardial infarction (AMI), and coronary artery disease (CAD).ResultsThe mean absolute errors (MAE) of ECG-LV-D were 5.25/5.29, and the area under the receiver operating characteristic (ROC) curves (AUCs) were 0.8297/0.8072 and 0.9295/0.9148 for the detection of mild (56 ≦ LV-D < 65 mm) and severe (LV-D ≧ 65 mm) LV-D dilation in internal/external validation sets, respectively. Patients with normal ejection fraction (EF) who were identified as high ECHO-LV-D had the higher hazard ratios (HRs) of developing new onset LV dysfunction [HR: 2.34, 95% conference interval (CI): 1.78–3.08], CV mortality (HR 2.30, 95% CI 1.05–5.05), new-onset AMI (HR 2.12, 95% CI 1.36–3.29), and CAD (HR 1.59, 95% CI 1.26–2.00) in the internal validation set. In addition, the ECG-LV-D presents a 1.88-fold risk (95% CI 1.47–2.39) on new-onset LV dysfunction in the external validation set.ConclusionThe ECG-LV-D not only identifies high-risk patients with normal EF but also serves as an independent risk factor of long-term CV outcomes.

BackgroundThe COVID-19 outbreak has not only changed the lifestyles of people globally but has also resulted in other challenges, such as the requirement of self-isolation and distance learning. Moreover, people are unable to venture out to exercise, leading to reduced movement, and therefore, the demand for exercise at home has increased. ObjectiveWe intended to investigate the relationships between a Nintendo Ring Fit Adventure (RFA) intervention and improvements in running time, cardiac force index (CFI), sleep quality (Chinese version of the Pittsburgh Sleep Quality Index score), and mood disorders (5-item Brief Symptom Rating Scale score). MethodsThis was a randomized prospective study and included 80 students who were required to complete a 1600-meter outdoor run before and after the intervention, the completion times of which were recorded in seconds. They were also required to fill out a lifestyle questionnaire. During the study, 40 participants (16 males and 24 females, with an average age of 23.75 years) were assigned to the RFA group and were required to exercise for 30 minutes 3 times per week (in the adventure mode) over 4 weeks. The exercise intensity was set according to the instructions given by the virtual coach during the first game. The remaining 40 participants (30 males and 10 females, with an average age of 22.65 years) were assigned to the control group and maintained their regular habits during the study period. ResultsThe study was completed by 80 participants aged 20 to 36 years (mean 23.20, SD 2.96 years). The results showed that the running time in the RFA group was significantly reduced. After 4 weeks of physical training, it took females in the RFA group 19.79 seconds (P=.03) and males 22.56 seconds (P=.03) less than the baseline to complete the 1600-meter run. In contrast, there were no significant differences in the performance of the control group in the run before and after the fourth week of intervention. In terms of mood disorders, the average score of the RFA group increased from 1.81 to 3.31 for males (difference=1.50, P=.04) and from 3.17 to 4.54 for females (difference=1.38, P=.06). In addition, no significant differences between the RFA and control groups were observed for the CFI peak acceleration (CFIPA)_walk, CFIPA_run, or sleep quality. ConclusionsRFA could either maintain or improve an individual’s physical fitness, thereby providing a good solution for people involved in distance learning or those who have not exercised for an extended period. Trial RegistrationClinicalTrials.gov NCT05227040; https://clinicaltrials.gov/ct2/show/NCT05227040

The machine learning-assisted electrocardiogram (ECG) is increasingly recognized for its unprecedented capabilities in diagnosing and predicting cardiovascular diseases. Identifying the need for ECG examination early in emergency department (ED) triage is key to timely artificial intelligence-assisted analysis. We used machine learning to develop and validate a clinical decision support tool to predict ED triage patients’ need for ECG. Data from 301,658 ED visits from August 2017 to November 2020 in a tertiary hospital were divided into a development cohort, validation cohort, and two test cohorts that included admissions before and during the COVID-19 pandemic. Models were developed using logistic regression, decision tree, random forest, and XGBoost methods. Their areas under the receiver operating characteristic curves (AUCs), positive predictive values (PPVs), and negative predictive values (NPVs) were compared and validated. In the validation cohort, the AUCs were 0.887 for the XGBoost model, 0.885 for the logistic regression model, 0.878 for the random forest model, and 0.845 for the decision tree model. The XGBoost model was selected for subsequent application. In test cohort 1, the AUC was 0.891, with sensitivity of 0.812, specificity of 0.814, PPV of 0.708 and NPV of 0.886. In test cohort 2, the AUC was 0.885, with sensitivity of 0.816, specificity of 0.812, PPV of 0.659, and NPV of 0.908. In the cumulative incidence analysis, patients not receiving an ECG yet positively predicted by the model had significantly higher probability of receiving the examination within 48 h compared with those negatively predicted by the model. A machine learning model based on triage datasets was developed to predict ECG acquisition with high accuracy. The ECG recommendation can effectively predict whether patients presenting at ED triage will require an ECG, prompting subsequent analysis and decision-making in the ED.

Background: The association between attention-deficit hypersensitivity disorder (ADHD) and the risk of developing colorectal cancer (CRC) is, as yet, to be investigated, and thus, we have conducted this nationwide, cohort study to examine the association in patients from Taiwan.Methods: In this study, 798 individuals with newly diagnosed ADHD and 2,394 (1:3) age-, gender-, and index year- matched controls without ADHD were enrolled, between 2000 and 2013, from the Longitudinal Health Insurance Database, a subset of the National Health Insurance Research Database in Taiwan. The cumulative incidence of CRC was assessed in each cohort by the Kaplan–Meier method. The multivariate Cox proportional hazards model was used to estimate the crude, and the adjusted hazards ratios (HRs) with 95% confidence intervals (CIs), was conducted to estimate the association between ADHD and CRC.Results: The Kaplan–Meier analysis revealed that the cumulative incidence of CRC was significantly higher in patients with ADHD than in those without it (log rank test, p < 0.001). After adjustments for age, gender, comorbidities, and other covariates, the ADHD group was associated with an increased risk of CRC in comparison to the non-ADHD group (adjusted HR = 3.458, 95% CI = 1.640–7.293, p < 0.001). In addition, the usage of methylphenidate was not associated with the risk of developing CRC in patients with ADHD.Conclusion: This retrospective cohort study depicts the evidence that ADHD was associated with the increased risk of CRC. Further studies are needed to confirm the association and the underlying mechanisms.

BACKGROUND: The ejection fraction (EF) provides critical information about heart failure (HF) and its management. Electrocardiography (ECG) is a noninvasive screening tool for cardiac electrophysiological activities that has been used to detect patients with low EF based on a deep learning model (DLM) trained via large amounts of data. However, no studies have widely investigated its clinical impacts. OBJECTIVE: This study developed a DLM to estimate EF via ECG (ECG-EF). We further investigated the relationship between ECG-EF and echo-based EF (ECHO-EF) and explored their contributions to future cardiovascular adverse events. METHODS: There were 57,206 ECGs with corresponding echocardiograms used to train our DLM. We compared a series of training strategies and selected the best DLM. The architecture of the DLM was based on ECG12Net, developed previously. Next, 10,762 ECGs were used for validation, and another 20,629 ECGs were employed to conduct the accuracy test. The changes between ECG-EF and ECHO-EF were evaluated. The primary follow-up adverse events included future ECHO-EF changes and major adverse cardiovascular events (MACEs). RESULTS: The sex-/age-matching strategy-trained DLM achieved the best area under the curve (AUC) of 0.9472 with a sensitivity of 86.9% and specificity of 89.6% in the follow-up cohort, with a correlation of 0.603 and a mean absolute error of 7.436. In patients with accurate prediction (initial difference < 10%), the change traces of ECG-EF and ECHO-EF were more consistent (R-square = 0.351) than in all patients (R-square = 0.115). Patients with lower ECG-EF (≤35%) exhibited a greater risk of cardiovascular (CV) complications, delayed ECHO-EF recovery, and earlier ECHO-EF deterioration than patients with normal ECG-EF (>50%). Importantly, ECG-EF demonstrated an independent impact on MACEs and all CV adverse outcomes, with better prediction of CV outcomes than ECHO-EF. CONCLUSIONS: The ECG-EF could be used to initially screen asymptomatic left ventricular dysfunction (LVD) and it could also independently contribute to the predictions of future CV adverse events. Although further large-scale studies are warranted, DLM-based ECG-EF could serve as a promising diagnostic supportive and management-guided tool for CV disease prediction and the care of patients with LVD.

Background: Left atrium enlargement (LAE) can be used as a predictor of future cardiovascular diseases, including hypertension (HTN) and atrial fibrillation (Afib). Typical electrocardiogram (ECG) changes have been reported in patients with LAE. This study developed a deep learning model (DLM)-enabled ECG system to identify patients with LAE. Method: Patients who had ECG records with corresponding echocardiography (ECHO) were included. There were 101,077 ECGs, 20,510 ECGs, 7611 ECGs, and 11,753 ECGs in the development, tuning, internal validation, and external validation sets, respectively. We evaluated the performance of a DLM-enabled ECG for diagnosing LAE and explored the prognostic value of ECG-LAE for new-onset HTN, new-onset stroke (STK), new-onset mitral regurgitation (MR), and new-onset Afib. Results: The DLM-enabled ECG achieved AUCs of 0.8127/0.8176 for diagnosing mild LAE, 0.8587/0.8688 for diagnosing moderate LAE, and 0.8899/0.8990 for diagnosing severe LAE in the internal/external validation sets. Notably, ECG-LAE had higher prognostic value compared to ECHO-LAE, which had C-indices of 0.711/0.714 compared to 0.695/0.692 for new-onset HTN, 0.676/0.688 compared to 0.663/0.677 for new-onset STK, 0.696/0.695 compared to 0.676/0.673 for new-onset MR, and 0.800/0.806 compared to 0.786/0.760 for new-onset Afib in internal/external validation sets, respectively. Conclusions: A DLM-enabled ECG could be considered as a LAE screening tool and provide better prognostic information for related cardiovascular diseases.

Programming is one of the most crucial abilities for students in science and technology courses. Few studies on programming ability have considered the effect of students' construal levels on their learning performance. Therefore, the effects of students' construal level were explored in this study to fill this research gap and open a new avenue for the improvements in programming ability. The research participants were 110 seventh- and eighth-grade students with basic programming abilities taking an Arduino course. Data were collected from online questionnaires and analyzed using two-way analysis of variance and structural equation modeling to investigate the relationships among construal levels, programming ability, and learning satisfaction. The results revealed that students' construal levels affect their learning satisfaction and programming ability. These findings indicate that teaching strategies could effectively improve the learning satisfaction and programming ability of junior high school students.

Temporal coordination of vocal exchanges between mothers and their infants emerges from a developmental process that relies on the ability of communication partners to co-coordinate and predict each other’s turns. Consequently, the partners engage in communicative niche construction that forms a foundation for language in human infancy. While robust universals in vocal turn-taking have been found, differences in the timing of maternal and infant vocalizations have also been reported across cultures. In this study, we examine the temporal structure of vocal interactions in 38 mother–infant dyads in the first two years across two cultures—American and Lebanese—by studying observed and randomized distributions of vocalizations, focusing on both gaps and overlaps in naturalistic 10-min vocal interactions. We conducted a series of simulations using Kolmogorov–Smirnov (K–S) tests to examine whether the observed responsivity patterns differed from randomly generated simulations of responsivity patterns in both Arabic and English for mothers responding to infants and for infants responding to mothers. Results revealed that both mothers and infants engaged in conversational alternation, with mothers acting similarly across cultures. By contrast, significant differences were observed in the timing of infant responses to maternal utterances, with the Lebanese infants’ tendency to cluster their responses in the first half-second after the offset of the Lebanese mothers’ utterances to a greater extent than their American counterparts. We speculate that the results may be due to potential phonotactic differences between Arabic and English and/or to differing child-rearing practices across Lebanese and American cultures. The findings may have implications for early identification of developmental disorders such as autism spectrum disorders within and across cultures.

(1) Background: While an artificial intelligence (AI)-based, cardiologist-level, deep-learning model for detecting acute myocardial infarction (AMI), based on a 12-lead electrocardiogram (ECG), has been established to have extraordinary capabilities, its real-world performance and clinical applications are currently unknown. (2) Methods and Results: To set up an artificial intelligence-based alarm strategy (AI-S) for detecting AMI, we assembled a strategy development cohort including 25,002 visits from August 2019 to April 2020 and a prospective validation cohort including 14,296 visits from May to August 2020 at an emergency department. The components of AI-S consisted of chest pain symptoms, a 12-lead ECG, and high-sensitivity troponin I. The primary endpoint was to assess the performance of AI-S in the prospective validation cohort by evaluating F-measure, precision, and recall. The secondary endpoint was to evaluate the impact on door-to-balloon (DtoB) time before and after AI-S implementation in STEMI patients treated with primary percutaneous coronary intervention (PPCI). Patients with STEMI were alerted precisely by AI-S (F-measure = 0.932, precision of 93.2%, recall of 93.2%). Strikingly, in comparison with pre-AI-S (N = 57) and post-AI-S (N = 32) implantation in STEMI protocol, the median ECG-to-cardiac catheterization laboratory activation (EtoCCLA) time was significantly reduced from 6.0 (IQR, 5.0–8.0 min) to 4.0 min (IQR, 3.0–5.0 min) (p < 0.01). The median DtoB time was shortened from 69 (IQR, 61.0–82.0 min) to 61 min (IQR, 56.8–73.2 min) (p = 0.037). (3) Conclusions: AI-S offers front-line physicians a timely and reliable diagnostic decision-support system, thereby significantly reducing EtoCCLA and DtoB time, and facilitating the PPCI process. Nevertheless, large-scale, multi-institute, prospective, or randomized control studies are necessary to further confirm its real-world performance.

Medical records scoring is important in a health care system. Artificial intelligence (AI) with projection word embeddings has been validated in its performance disease coding tasks, which maintain the vocabulary diversity of open internet databases and the medical terminology understanding of electronic health records (EHRs). We considered that an AI-enhanced system might be also applied to automatically score medical records. This study aimed to develop a series of deep learning models (DLMs) and validated their performance in medical records scoring task. We also analyzed the practical value of the best model. We used the admission medical records from the Tri-Services General Hospital during January 2016 to May 2020, which were scored by our visiting staffs with different levels from different departments. The medical records were scored ranged 0 to 10. All samples were divided into a training set (n = 74,959) and testing set (n = 152,730) based on time, which were used to train and validate the DLMs, respectively. The mean absolute error (MAE) was used to evaluate each DLM performance. In original AI medical record scoring, the predicted score by BERT architecture is closer to the actual reviewer score than the projection word embedding and LSTM architecture. The original MAE is 0.84 ± 0.27 using the BERT model, and the MAE is 1.00 ± 0.32 using the LSTM model. Linear mixed model can be used to improve the model performance, and the adjusted predicted score was closer compared to the original score. However, the project word embedding with the LSTM model (0.66 ± 0.39) provided better performance compared to BERT (0.70 ± 0.33) after linear mixed model enhancement (p < 0.001). In addition to comparing different architectures to score the medical records, this study further uses a mixed linear model to successfully adjust the AI medical record score to make it closer to the actual physician’s score.

Background: glycated hemoglobin (HbA1c) provides information on diabetes mellitus (DM) management. Electrocardiography (ECG) is a noninvasive test of cardiac activity that has been determined to be related to DM and its complications. This study developed a deep learning model (DLM) to estimate HbA1c via ECG. Methods: there were 104,823 ECGs with corresponding HbA1c or fasting glucose which were utilized to train a DLM for calculating ECG-HbA1c. Next, 1539 cases from outpatient departments and health examination centers provided 2190 ECGs for initial validation, and another 3293 cases with their first ECGs were employed to analyze its contributions to DM management. The primary analysis was used to distinguish patients with and without mild to severe DM, and the secondary analysis was to explore the predictive value of ECG-HbA1c for future complications, which included all-cause mortality, new-onset chronic kidney disease (CKD), and new-onset heart failure (HF). Results: we used a gender/age-matching strategy to train a DLM to achieve the best AUCs of 0.8255 with a sensitivity of 71.9% and specificity of 77.7% in a follow-up cohort with correlation of 0.496 and mean absolute errors of 1.230. The stratified analysis shows that DM presented in patients with fewer comorbidities was significantly more likely to be detected by ECG-HbA1c. Patients with higher ECG-HbA1c under the same Lab-HbA1c exhibited worse physical conditions. Of interest, ECG-HbA1c may contribute to the mortality (gender/age adjusted hazard ratio (HR): 1.53, 95% conference interval (CI): 1.08–2.17), new-onset CKD (HR: 1.56, 95% CI: 1.30–1.87), and new-onset HF (HR: 1.51, 95% CI: 1.13–2.01) independently of Lab-HbA1c. An additional impact of ECG-HbA1c on the risk of all-cause mortality (C-index: 0.831 to 0.835, p < 0.05), new-onset CKD (C-index: 0.735 to 0.745, p < 0.01), and new-onset HF (C-index: 0.793 to 0.796, p < 0.05) were observed in full adjustment models. Conclusion: the ECG-HbA1c could be considered as a novel biomarker for screening DM and predicting the progression of DM and its complications.

The impact of the coronavirus disease 2019 (COVID-19) pandemic on health-care quality in the emergency department (ED) in countries with a low risk is unclear. This study aimed to explore the effects of the COVID-19 pandemic on ED loading, quality of care, and patient prognosis. Data were retrospectively collected from 1 January 2018 to 30 September 2020 at the ED of Tri-service general hospital. Analyses included day-based ED loading, quality of care, and patient prognosis. Data on triage assessment, physiological states, disease history, and results of laboratory tests were collected and analyzed. The number of daily visits significantly decreased after the pandemic, leading to a reduction in the time to examination. Admitted patients benefitted from the pandemic with a reduction of 0.80 h in the length of stay in the ED, faster discharge without death, and reduced re-admission. However, non-admitted visits with chest pain increased the risk of mortality after the pandemic. In conclusion, the COVID-19 pandemic led to a significant reduction in low-acuity ED visits and improved prognoses for hospitalized patients. However, clinicians should be alert about patients with chest pain due to their increased risk of mortality in subsequent admission.

(1) Background: It has rarely been studied whether the severity of diabetic retinopathy (DR) could influence renal disease progression in end-stage renal disease (ESRD) and chronic kidney disease (CKD) in patients with type 2 diabetes. The aim of this study was to evaluate renal disease progression in ESRD and CKD according to DR severity in patients with type 2 diabetes. (2) Methods: We included 1329 patients and divided the cohort into two end-points. The first was to trace the incidence of ESRD in all enrolled participants and the other was to follow their progression to CKD. (3) Results: Significantly higher crude hazard ratios (HRs) of ESRD incidence in all enrolled participants were noted, and this ratio increased in a stepwise fashion. However, after adjustment, DR severity was not associated with ESRD events. Therefore, a subgroup of 841 patients without CKD was enrolled to track their progression to CKD. Compared with no diabetic retinopathy, the progression of CKD increased in a stepwise fashion, from mild nonproliferative diabetic retinopathy (NPDR) to moderate NPDR, to severe NPDR and to proliferative diabetic retinopathy (PDR), both in the crude and adjusted models. (4) Conclusions: The severity of retinopathy appeared to be associated with renal lesions and the development of CKD. Our findings suggest that the severity of DR is a risk factor for progression to CKD. Therefore, diabetic retinopathy is useful for prognosticating the clinical course of diabetic kidney disease.

Background: Controversy exists over whether aggressive surgical resection of the primary tumor without metastasectomy first or chemotherapy first in stage IV colon cancer with unresectable synchronous liver-only-metastases (CLM) improves patients. Materials and Methods: We retrospectively reviewed the outcome of 156 patients initially diagnosed with unresectable synchronous CLM who were under treatment in our institution from January 2004 to December 2012. Patients with extrahepatic diseases or previous hepatic resection were excluded. All patients with a follow-up of at least 3 months were included. Progression-free survival (PFS) and 5-year overall survival (OS) curves were calculated using the Kaplan–Meier method. Results: Among the 156 patients with CLM, 43 (27.56%) received aggressive surgical resection of the primary tumor without metastasectomy first, 113 (72.43%) received systemic chemotherapy first. At 5 years, the adjusted PFS and OS in stage IV colon cancer with inoperable metastases were 24.2% and 20.4%, respectively, in the surgical resection of the primary tumor first group and 46.0% and 16.9% in the chemotherapy first group (P = 0.515 and P= 0.742, respectively). In multivariate analysis, there was no statistical difference in the PFS and 5-year OS between the surgical resection of the primary tumor first group and chemotherapy first. Conclusion: Surgical resection of the primary tumor without metastasectomy first in CLM is not associated with improved survival as compared with chemotherapy first. Additional research is necessary to determine which patients may benefit from this intervention.

The purpose of this study was to estimate the impact of metronomic therapy with oral tegafur-uracil (UFUR) following an intravenous FOLFOX regimen as surgical adjuvant chemotherapy on the overall survival (OS) and disease-free survival (DFS) of stage III colon cancer patients. From the retrospective database of patients who underwent a surgical resection for colorectal cancer at the Tri-Service General Hospital from October 2008 through December 2014, stage III colon carcinomas treated with radical R0 resection were reviewed. One hundred thirty two patients were treated with a FOLFOX regimen (comparison group), and 113 patients were treated with the same regimen followed by additional oral UFUR (UFUR group). The clinical characteristics and mean age of the comparison and UFUR groups were similar. Furthermore, for all study patients, DFS was not significantly different between the two groups. However, 5-year OS rates were 86.8% and 68.5% in the UFUR and comparison groups, respectively (p = 0.0107). Adding UFUR to a FOLFOX regimen was found to significantly improve the OS in patients with stage III colon cancer. UFUR as a maintenance therapy following FOLFOX regimen as an alternative therapeutic option for the treatment of stage III colon cancer patients.

Background: Acute hemorrhagic rectal ulcer (AHRU) can be found in patients with severe comorbid illness, who are bedridden for a long time. Per anal suturing is a quick and feasible treatment. However, recurrent bleeding occurs frequently after suture ligation of a bleeder and can be life-threatening. However, the risk factor for recurrent bleeding is not well known. Our study tries to clarify the risk factor of repeat AHRU in Intensive Care Unit (ICU) patients. Materials and Methods: From January 2004 to December 2009, the medical records of 32 patients, who were admitted to the ICU of the Tri-Service General Hospital, a tertiary referral center in Taiwan, and who underwent per anal suturing of acute hemorrhagic rectal ulcer were retrospectively reviewed. Results: Of the 96 patients who received emergency treatment for acute massive hematochezia, 32 patients were diagnosed with AHRU. Eight (25%) patients had recurrent bleeding following suture ligation of AHRU and underwent a reoperation; no patient had recurrent bleeding after the second operation. The duration from the first hematochezia attack to surgery (P = 0.04), liver cirrhosis (P = 0.002), and coagulopathy (P = 0.01) were the risk factors of recurrent bleeding after suture ligation of a bleeder. Multivariate logistic regression analysis indicated that liver cirrhosis (OR = 37.77, P = 0.014) was an independent risk factor for recurrent bleeding. Conclusion: AHRU could be a major cause of acute massive hematochezia in patients with severe illness. Our data showed that per anal suturing could quickly and effectively control bleeding. We found that liver cirrhosis was an independent risk factor for recurrent bleeding. Therefore, treatment of a liver cirrhosis patient with AHUR should be more aggressive, such as, early detection and proper suture ligation.

Infant-directed speech (IDS) provides an environment that appears to play a significant role in the origins of language in the human infant. Differences have been reported in the use of IDS across cultures, suggesting different styles of infant language-learning. Importantly, both cross-cultural and intra-cultural research suggest there may be a positive relationship between the use of IDS and rates of language development, underscoring the need to investigate cultural differences more deeply. The majority of studies, however, have conceptualized IDS monolithically, granting little attention to a potentially key distinction in how IDS manifests across cultures during the first two years. This study examines and quantifies for the first time differences within IDS in the use of baby register (IDS/BR), an acoustically identifiable type of IDS that includes features such as high pitch, long duration, and smooth intonation (the register that is usually assumed to occur in IDS), and adult register (IDS/AR), the type of IDS that does not include such features and thus sounds as if it could have been addressed to an adult. We studied IDS across 19 American and 19 Lebanese mother-infant dyads, with particular focus on the differential use of registers within IDS as mothers interacted with their infants ages 0-24 months. Our results showed considerable usage of IDS/AR (>30% of utterances) and a tendency for Lebanese mothers to use more IDS than American mothers. Implications for future research on IDS and its role in elucidating how language evolves across cultures are explored.