Citations

Background: Sex and age have long been known to affect the ECG. Several biologic variables and anatomic factors may contribute to sex and age-related differences on the ECG. We hypothesized that a convolutional neural network (CNN) could be trained through a process called deep learning to predict a person’s age and self-reported sex using only 12-lead ECG signals. We further hypothesized that discrepancies between CNN-predicted age and chronological age may serve as a physiological measure of health. Methods: We trained CNNs using 10-second samples of 12-lead ECG signals from 499 727 patients to predict sex and age. The networks were tested on a separate cohort of 275 056 patients. Subsequently, 100 randomly selected patients with multiple ECGs over the course of decades were identified to assess within-individual accuracy of CNN age estimation. Results: Of 275 056 patients tested, 52% were males and mean age was 58.6±16.2 years. For sex classification, the model obtained 90.4% classification accuracy with an area under the curve of 0.97 in the independent test data. Age was estimated as a continuous variable with an average error of 6.9±5.6 years (R-squared =0.7). Among 100 patients with multiple ECGs over the course of at least 2 decades of life, most patients (51%) had an average error between real age and CNN-predicted age of <7 years. Major factors seen among patients with a CNN-predicted age that exceeded chronologic age by >7 years included: low ejection fraction, hypertension, and coronary disease ( P <0.01). In the 27% of patients where correlation was >0.8 between CNN-predicted and chronologic age, no incident events occurred over follow-up (33±12 years). Conclusions: Applying artificial intelligence to the ECG allows prediction of patient sex and estimation of age. The ability of an artificial intelligence algorithm to determine physiological age, with further validation, may serve as a measure of overall health.

AbstractBackground and ObjectivesConclusive evidence in favor of neoadjuvant therapy for those with non‐metastatic pancreatic ductal adenocarcinoma (PDAC) is still lacking. The objective of this study was to evaluate the survival benefit of neoadjuvant therapy vs upfront surgery for patients with non‐metastatic PDAC.MethodsThe study involved 565 patients undergoing neoadjuvant therapy or upfront surgery as the primary treatment for PDAC. Propensity score matching was performed between the neoadjuvant therapy group (NAT group) and the upfront surgery group (UFS group) using 20 clinical variables at diagnosis. Overall survival and surgical pathology were compared between the two treatment groups on an intent‐to‐treat basis.ResultsIn the matched cohort, the NAT group (n = 91) had a longer median overall survival than the UFS group (n = 91) (23.1 months vs 18.5 months, P = .043). The rate of patients undergoing surgical resection was lower in the NAT group (58% vs 80%, P = .001). Regarding surgical pathology, the NAT group had smaller tumor size (2.8 cm vs 4.0 cm, P = .001), lower incidence of positive surgical margins (8% vs 30%, P < .002), and less lymph node metastasis (45% vs 78%, P < .001).ConclusionsThe strategy of neoadjuvant therapy before surgical resection appears to offer pathologic effect and survival benefit for the patients presenting with non‐metastatic PDAC.

While the triple tracer isotope dilution method has enabled accurate estimation of carbohydrate turnover after a mixed meal, use of the simple carbohydrate glucose as the carbohydrate source limits its translational applicability to everyday meals that typically contain complex carbohydrates. Hence, utilizing the natural enrichment of [13C]polysaccharide in commercially available grains, we devised a novel tracer method to measure postprandial complex carbohydrate turnover and indices of insulin action and β-cell function and compared the parameters to those obtained after a simple carbohydrate containing mixed meal. We studied healthy volunteers after either rice ( n = 8) or sorghum ( n = 8) and glucose ( n = 16) containing mixed meals and modified the triple tracer technique to calculate carbohydrate turnover. All meals were matched for calories and macronutrient composition. Rates of meal glucose appearance (2,658 ± 736 vs. 4,487 ± 909 μM·kg−1·2 h−1), endogenous glucose production (−835 ± 283 vs. −1,123 ± 323 μM·kg−1·2 h−1) and glucose disappearance (1,829 ± 807 vs. 3,606 ± 839 μM·kg−1·2 h−1) differed ( P < 0.01) between complex and simple carbohydrate containing meals, respectively. Interestingly, there were significant increase in indices of insulin sensitivity (32.5 ± 3.5 vs. 25.6 ± 3.2 10−5(dl·kg−1·min−2)/pM, P = 0.006) and β-cell responsivity (disposition index: 1,817 ± 234 vs. 1,236 ± 159 10−14(dl·kg−1·min−2)/pM, P < 0.005) with complex than simple carbohydrate meals. We present a novel triple tracer approach to estimate postprandial turnover of complex carbohydrate containing mixed meals. We also report higher insulin sensitivity and β-cell responsivity with complex than with simple carbohydrates in mixed meals of identical calorie and macronutrient compositions in healthy adults.

Abstract Aims Left atrial (LA) function is impaired in heart failure with preserved ejection fraction (HFpEF) and predicts disease severity and risk of adverse outcome. We sought to evaluate whether LA strain could enhance diagnosis of HFpEF. Methods and results Consecutive patients with unexplained exertional dyspnoea and image quality suitable for measuring LA strain underwent invasive cardiopulmonary exercise testing to ascertain the presence of HFpEF or non-cardiac causes of dyspnoea (NCD). LA reservoir strain was measured in all patients, while LA conduit and booster strain were measured in patients with sinus rhythm. LA strain was measurable in 363 of 378 examinations (96.5%; HFpEF: 238, NCD: 125). LA reservoir strain (29 ± 16% vs. 40 ± 13%, P &lt; 0.0001) and conduit strain (18 ± 10% vs. 22 ± 10%, P = 0.0001) were significantly impaired in HFpEF compared to NCD. Of all echocardiographic indices, LA reservoir strain best discriminated HFpEF from NCD [area under the curve (AUC) 0.719, P &lt; 0.0001], outperforming E/e' (AUC difference +0.117, P &lt; 0.0001), LA enlargement (+0.090, P = 0.001), tricuspid regurgitation velocity &gt; 2.8 m/s (+0.082, P = 0.0085), left ventricular hypertrophy (+0.0159, P &lt; 0.0001) and left ventricular global longitudinal strain (+0.0198, P &lt; 0.0001). Indexing LA reservoir strain to estimated LA pressure (E/e') as a surrogate for LA compliance further improved diagnostic performance (AUC 0.772, P &lt; 0.0001; +0.053 compared to LA reservoir strain alone, P = 0.003). Conclusion Left atrial reservoir strain may provide enhanced diagnostic accuracy beyond conventional echocardiographic measures to discriminate HFpEF from NCD. Further study is required to verify the diagnostic utility of LA strain.

AbstractObjectivesWe sought to validate a deep learning algorithm designed to predict an ejection fraction (EF) less than or equal to 35% based on the 12‐lead electrocardiogram (ECG) in a large prospective cohort.BackgroundPatients undergoing routine ECG may have undetected left ventricular (LV) dysfunction that warrants further echocardiographic assessment. However, identification of these patients can be challenging.MethodsWe applied the algorithm to all ECGs interpreted by the Mayo Clinic ECG laboratory in September 2018. The performance of the algorithm was tested among patients with recent echocardiographic assessments of LV function. We also applied the algorithm in patients with no recent echocardiographic assessments of LV function to determine the rate of new “positive screens.”ResultsAmong 16 056 adult patients who underwent routine ECG, 8600 (age 67.1 ± 15.2 years, 45.6% male), had a transthoracic echocardiogram (TTE) and 3874 patients had a TTE and ECG less than 1 month apart. Among these patients, the algorithm was able to detect an EF less than or equal to 35% with 86.8% specificity, 82.5% sensitivity, and 86.5% accuracy, (area under the curve, 0.918). Among 474 “false‐positives screens,” 189 (39.8%) had an EF of 36% to 50%. Among patients with no prior TTE, the algorithm identified 3.5% of the patients with suspected EF less than or equal to 35%. Exploratory analysis suggests false positives could be reduced by assessing NT‐pro‐BNP after the initial “positive screen.”ConclusionsA deep learning algorithm detected depressed LV function with good accuracy in routine practice. Further studies are needed to validate the algorithm in patients with no prior echocardiogram and to assess the impact on echocardiography utilization, cost, and clinical outcomes.

PURPOSE Background parenchymal uptake (BPU), which describes the level of radiotracer uptake in normal fibroglandular tissue on molecular breast imaging (MBI), has been identified as a breast cancer risk factor. Our objective was to develop and validate a deep learning model using image convolution to automatically categorize BPU on MBI. METHODS MBI examinations obtained for clinical and research purposes from 2004 to 2015 were reviewed to classify the BPU pattern using a standardized five-category scale. Two expert radiologists provided interpretations that were used as the reference standard for modeling. The modeling consisted of training and validating a convolutional neural network to predict BPU. Model performance was summarized in data reserved to test the performance of the algorithm at the per-image and per-breast levels. RESULTS Training was performed on 24,639 images from 3,133 unique patients. The model performance on the withheld testing data (6,172 images; 786 patients) was evaluated. Using direct matching on the predicted classification resulted in an accuracy of 69.4% (95% CI, 67.4% to 71.3%), and if prediction within one category was considered, accuracy increased to 96.0% (95% CI, 95.2% to 96.7%). When considering the breast-level prediction of BPU, the accuracy remained strong, with 70.3% (95% CI, 68.0% to 72.6%) and 96.2% (95% CI, 95.3% to 97.2%) for the direct match and allowance for one category, respectively. CONCLUSION BPU provided a robust target for training a convolutional neural network. A validated computer algorithm will allow for objective, reproducible encoding of BPU to foster its integration into risk-stratification algorithms.