Abstract Background Over decades, efforts to shave off life-saving minutes from ST-Elevated Myocardial Infarction (STEMI) care centred on reducing door-to-needle and door-to-balloon times. We firmly believe that symptom-to-balloon time should prove a better focus to this end. Challenges come with this goal as it heavily relies on a patient's perception and initiative to seek care, which we deem intelligent and wearable Artificial Intelligence (AI)-driven Single Lead EKG technologies as an attractive solution in modern-day cardiology. Purpose To provide an accurate, accessible, and cost-effective AI-driven Single Lead STEMI detection algorithm that can be embedded into wearable devices and employed in a self-administered fashion. Methods Database: EKG records from Mexico, Colombia, Argentina, and Brazil from April 2014 to December 2019. Dataset: A total of 11,567 12-lead EKG records of 10[s] length with a sampling frequency of 500 Hz, including the following balanced classes: angiographically confirmed and unconfirmed STEMI, branch blocks, non-specific ST-T abnormalities, normal and abnormal (200+ CPT codes, excluding those mentioned above). Cardiologists manually checked the label of each record to ensure precision. Pre-processing: We discard the first and last 250 samples as they may contain a standardisation pulse. The study applied a digital low pass filter of order 5 with a frequency cut-off of 35 Hz. The mean was subtracted from each Lead. Classification: The determined classes were “STEMI” (Including STEMI in different locations of the myocardium – anterior, inferior, and lateral); and “Not-STEMI” (Combination of randomly sample, branch blocks, non-specific ST-T changes, and abnormal records – 25% of each). Training and Testing: A 1-D Convolutional Neural Network was trained and tested with a dataset proportion of 90/10, respectively. A different model was trained and tested for each Lead, using the central 4,500 samples of the records. The last dense layer outputs a probability for each report of being STEMI or Not-STEMI. Lead V2 showed the best overall results. The model was further tested through the same methodology using the best Lead with a subset of the previous data, excluding the unconfirmed STEMI EKG records (Total 7,230 12-lead EKG records for Confirmed Only STEMI dataset). Performance metrics were reported for each experiment and compared. Results Combined STEMI data: Accuracy: 91.2%; Sensitivity: 89.6%; Specificity: 92.9%. Confirmed STEMI Only dataset: Accuracy: 92.4%; Sensitivity: 93.4%; Specificity: 91.4% (Figure 1). Conclusion By assiduously improving the quality of the model's input, we continue to assess our algorithm's performance and reliability for future clinical validation as a potential remote monitoring and early STEMI detection device. Funding Acknowledgement Type of funding sources: None.

In 17 men, aged 27 to 54 years, with myocardial infarction 2 to 10 months before the current exercise study, we aimed to determine whether 3 months of exercise training, at a level designed to elevate high-density lipoprotein cholesterol (HDLC), would be associated with changes in endogenous sex steroid hormones and postheparin lipoprotein and hepatic lipases, and whether the changes in sex hormones, lipids, lipoproteins, apolipoproteins, and physical activity were interrelated. Supervised bicycle ergometry, 30 minutes, 3 days per week, eliciting 75% of maximum heart rate, produced a significant training effect, with a 26% increase in the duration of the exercise test at a standardized, submaximal workload (P less than or equal to .001), and a reduction in heart rate measured at a standardized submaximal workload, P = .08. After 3 months' training, mean HDLC increased 23% (30 to 37 mg/dL), P less than or equal to .001, mean apo A2 increased 19% (43 to 51 mg/dL), P less than or equal to .001, and the ratio of total cholesterol (TC) to HDLC decreased 26% (P less than or equal to .01), while estradiol (E2) levels decreased 45% (50.1 to 27.8 pg/mL), P less than or equal to .0001. After 1 and 2 months' exercise, TC (12% [P less than or equal to .001], 11% [P less than or equal to .01]), and low-density lipoprotein cholesterol (LDLC) (13% [P less than or equal to .01], 12% [P less than or equal to .01]) were reduced. Hepatic lipase decreased 16% (P less than or equal to .01) and 16% (P less than or equal to .05) after 1 and 3 months' exercise. There were no significant changes in apo A1, lipoprotein lipase, testosterone, luteinizing hormone (LH), follicle-stimulating hormone (FSH), or weight. By stepwise regression analysis, after 3 months' training, 66% (P = .0025) of the variance for the increase in HDLC from baseline to day 90 was accounted for independently by a decrease in triglyceride (F = 13.2, P = .003), by reduced heart rate on a fixed submaximal load (F = 12.7, P = .0035), and by a decrease in hepatic lipase (F = 5.5, P = .036). A modest, achievable exercise program can have significant cardiovascular benefit for men after myocardial infarction by ameliorating their hyperestrogenemia, reducing TC and LDLC, improving the TC to HDLC ratio, and elevating HDLC and apo A2. The increment in HDLC was related independently to improved capacity to sustain submaximal exercise and to exercise-induced reductions in triglyceride and postheparin hepatic lipase.

Our aim in the current study of 20 normal controls, 28 overweight, and 26 severely overweight (obese) subjects was to assess interrelationships of obesity, endogenous estradiol (E2) and testosterone (T), and the E2/T ratio with major independent explanatory variables for coronary heart disease (CHD), including lipids, lipoproteins, and apolipoproteins. Most of the lipid and lipoprotein variables (total, high-, low-, and very-low-density lipoprotein cholesterols) as well as apolipoproteins A1, A2, and B did not vary significantly with the presence of obesity. With increasing relative ponderosity, there were, however, increasing levels of total triglycerides and VLDL triglyceride. Levels of FSH, LH, prolactin, and testosterone did not differ significantly with obesity. The obese subjects had the highest E2 and E2/T levels; overweight subjects had intermediate levels which were also significantly higher than in the controls. Using multiple regression analyses, in obese subjects increasing T was associated with increasing apo B, and increasing E2 was correlated with decreasing apo A1. Opposite relationships were found in the normal controls where increasing T and increasing Quetelet indices were associated with diminished apo B and increasing E2 was associated with increasing A1. Obesity's association with increased CHD risk may be mediated through increasing E2 and apo B and reducing apo A1. Since obese subjects have higher E2 levels and often have lower T, they are likely to have a pattern of endogenous sex hormones (higher E2, lower T, higher E2/T ratios) similar to those observed in young men with premature myocardial infarction.

A series of thirty-three Venezuelan men with premature myocardial infarction (mean age (M +/- SEM) 45 +/- 1.5 yrs) and with greater than 50% occlusion of at least 2 coronary arteries, and 19 weight matched control men (age 44 +/- 2 yrs) with normal coronary arteries on coronary angiography were studied. The percentages of significantly abnormal (greater than +/- 2 S.D. of controls) serum or plasma concentrations of various measurements (in decreasing order) were: estradiol (33%), total apolipoprotein (apo)B (24%), estradiol/testosterone ratio (21%), low density lipoprotein (LDL) apo B (19%), apo AI (17%), apo AI/total plasma apo B ratio (17%), total cholesterol (17%), and LDL-cholesterol (LDL-C) (11%). In addition, a multivariate discriminant function analysis showed that only estradiol, apo AI, LDL-C, estradiol/testosterone ratio and total cholesterol were statistically significant independent markers of myocardial infarction with occlusive coronary disease in these patients. Both serum estradiol and estradiol/testosterone ratio correlated positively with plasma apo B and LDL apo B, and inversely with apo AI; serum testosterone correlated inversely with plasma apo B (p less than 0.05). The data suggest that circulating sex hormones (estrogens, testosterone) are not only independent markers of coronary disease but may be pathogenetically linked to apo B and apo AI metabolism.

Total plasma lipoprotein lipase (LPL) activating property, triglycerides, cholesterol, low-density lipoprotein cholesterol (LDL-C), and high-density lipoprotein cholesterol (HDL-C) were measured in 24 normal Venezuelan females and in 71 healthy women (20–35 years) who received one of three different combinations of ethinylestradiol and d-norgestrel for at least 6 months.

Based upon the hypothesis that endogenous testosterone plays a significant role in triglyceride and high density lipoprotein cholesterol metabolism, the specific aim of this study in 9 azoospermic and 10 oligospermic subjects (compared to 20 fertile men) was to examine potential relationships between endogenous testosterone, luteinizing hormone, follicle stimulating hormone, lipids-lipoproteins, and lipoprotein lipases. The azoospermic and oligospermic men had much higher fasting plasma triglyceride levels (mean ± SD; 479 ± 258, 295 ± 119) than did normal controls (105 ± 31 mg/dl, p < 0.001, p < 0.001). The azoospermic and oligospermic subjects also had much lower mean high density lipoprotein cholesterol levels (C-HDL) than normals (27 ± 8 and 29 ± 7 versus 44 ± 7 mg/dl, p < 0.001, p < 0.001). Very low density lipoprotein's (VLDL) in vitro potency to activate lipoprotein lipase (U/mg of VLDL protein) was about one-third normal in the azoospermic subjects (57 ± 26 U/mg), and about one-half normal in the oligospermic subjects (86 ± 27), with values in the normals being 167 ± 58, p < 0.001, p < 0.001. Mean plasma testosterone levels were 3.4 ± 0.7 ng/ml in the azoospermic subjects, considerably lower than mean levels in normals (6.6 ± 2.0, p < 0.001), with intermediate levels in the oligospermic men (5.2 ± 1.7 ng/ml). Pooling the data for the azoospermic, oligospermic, and normal men, plasma testosterone levels were positively correlated with C-HDL (r = .42, p < 0.01) and inversely correlated with triglyceride (r = −.50, p < 0.001) and very low density lipoprotein cholesterol (r = −.37, p < 0.02). Plasma testosterone was also positively correlated with lipoprotein lipase activator potency, (r = .45, p < 0.01). These findings suggest that endogenous physiologic testosterone levels may play a role relative to regulation of triglyceride and C-HDL levels in men, and may also affect the hydrolytic susceptability of very low density lipoprotein molecules. Hypertriglyceridemia and low C-HDL levels in azoospermic and oligospermic men mandate quantitation of lipid-lipoprotein levels in infertility clinics to identify men at putatively increased risk for future coronary heart disease.

Cord blood lipids and lipoproteins were compared in 95 neonates in Merida, Venezuela, and 455 in Cincinnati, Ohio, to determine whether, like Venezuelan children and adults, Venezuelan neonates had higher plasma triglyceride and lower high-density lipoprotein cholesterol (C-HDL) levels. Cord plasma cholesterol and low-density lipoprotein cholesterol (C-LDL) did not differ significantly between Venezuelan and Cincinnati neonates (P > 0.1). Venezuelan neonates of both sexes had higher cord plasma triglyceride (P < 0.004), and lower C-HDL levels (P < 0.001). These cross-cultural differences were not overtly attributable to systematic differences in laboratory methodology, subject selection, or sampling techniques, since these were either similar or identical in the two populations studied. The cross-sectional persistence of lipoprotein differences in Venezuelan neonates, children, and adults (when compared with Americans) could reflect the expression of differing cross-cultural, racial, genetic, nutritional, or environmental factors or their interactions. Since there is a strong inverse correlation of C-HDL with coronary heart disease, the elucidation of any identifiable etiologies of Venezuelan—American differences in C-HDL might have considerable importance in identifying “protective” racial, genetic, nutritional, or environmental differences relative to the development of coronary heart disease.

Plasma lipids, lipoproteins, and anthropometric measurements were assessed in 996 Venezuelan school children (ages 13--18 years) (441 in private, 555 in public schools, Merida, Venezuela) with cross-cultural comparisons to 419 13--18-year-old American school children from suburban Cincinnati, Ohio. Although there were no systematic differences in plasma cholesterol and triglyceride between public and private Venezuelan school children, low density lipoprotein cholesterol (LDL-C) levels were higher and high density lipoprotein cholesterol (HDL-C) levels lower in public than private school children. Within Venezuelan schools, and between sex, female children had consistently higher total plasma cholesterol, marginally higher HDL-C, and appreciably higher LDL-C than males. There were no consistent cross-sectional changes in lipids and lipoproteins in Venezuelan school children with age. Within sex, cross-cultural comparisons with Cincinnati school children revealed 2 major, consistent differences; Venezuelan children had higher fasting plasma triglyceride and lower HDL-C levels, not attributable to systematic differences in Quetelet index, laboratory methodology, subject selection, or sampling technique. Total plasma cholesterol and HDL-C were similar for Venezuelan and Cincinnati school children. Maintenance of comparable LDL-C but lower HDL-C levels by Venezuelan children into adulthood might, speculatively, be associated with augmented risk for coronary heart disease.

To assess the relationship between altitude, atherogenic, and anti-atherogenic lipoprotein cholesterols (low- [C-LDL] and high [C-HDL] density lipoprotein cholesterols, respectively), 136 and 94 Venezuelan Mestizos living at 1,000 and 3,500 in elevation were studied. The two groups did not differ in regard to height, weight, ethnic origin, social or economic status, nutritional patterns, age, or occupation. Both groups had a high level of daily physical exertion, an imperative in their subsistence rural agricultural economy. Due to the mountainous terrain, high altitude residents were thought to have increased levels of physical activity. Males and females at high altitude had significantly lower plasma total cholesterol and C-LDL levels, and slightly lower C-HDL levels than those at low altitudes. It is speculated that reduced coronary heart disease event rates at high altitude might be related to lower levels of the atherogenic lipoprotein cholesterol, C-LDL.