A machine learning analysis of predictors of future hypertension in a young population.

BACKGROUND: Early diagnosis of hypertension (HT) is crucial for preventing end-organ damage. This study aims to identify the risk factors for future HT in young individuals through the application of machine learning (ML) models. METHODS: The study included individuals aged 18-40 years who had not been diagnosed with HT through ambulatory blood pressure monitoring (ABPM). These participants were monitored for hypertension diagnosis from the date of ABPM application until the date of data collection. Hypertension prediction was carried out using three distinct ML methods: Support Vector Machine, Random Forest, and Least Absolute Shrinkage and Selection Operator. The identification of variables significant for future HT was based on the outcomes of these models. RESULTS: This study comprised 516 patients, with a mean follow-up duration of 793.4±58.6 days. Following the integration of demographic data, laboratory results, and ABPM findings into the ML models, age, high-density lipoprotein cholesterol, triglycerides, and the standard deviation of systolic blood pressure (SDsis) were identified as predictors for future HT. A logistic regression with the selected variables (age, diabetes mellitus history, HDL, triglycerides, white blood cell count, and SDsis) using the full data set gave the following log odds 0.0737 (P<0.001), 0.7146 (P<0.001), -0.0160 (P=0.071), 0.0026 (P=0.002), 0.0857 (P=0.069), and 0.0850 (P=0.005), respectively. The corresponding probability values of age, diabetes mellitus history, HDL, triglycerides, white blood cell count, and SDsis were 0.5184, 0.6714, 0.4960, 0.5006, 0.5214, and 0.5212, respectively. This indicates a unit increase in all factors, except diabetes mellitus history, increases the probability of future HT by 50%. A history of diabetes, however, increases the probability of future HT by more than two thirds. The history of diabetes mellitus emerged as the most crucial predictor of future HT across all applied methods. CONCLUSIONS: ML methods appear to be valuable tools for predicting future HT. The widespread adoption of these methods and the refinement of more comprehensive models will lay the groundwork for future studies.

Prolongation of QTc interval due to increased parity and great grand multiparity.

Women are more prone to cardiac arrhythmias. Increased exposure to sex hormones may alter the ventricular repolarisation of the heart as the parity number increases. In this study, we aim to investigate the effect of parity number to electrocardiographic parameters. A total of 205 adult women were included for the study. Nulliparous (NP), primiparous (PP), multiparous (MP), grand multiparous (GMP) and great grand multiparous (GGMP) women constituted the study population. Increased parity has positive correlation with QTc interval (p=.000, r = 0.303). GGMP has significantly higher QTc compared to NP, PP, MP and GMP (p=.001, p=.000, p=.004 and p=.007, respectively). GGMP and parity have explanatory power on QTc (p=.019 and p=.020, respectively). Parity and GGMP affect cardiac repolarisation and prolong the QTc interval most probably due to repeated exposure to sex hormones. This study showed that GGMP and parity are independent risk factors for QTc interval prolongation.Impact StatementWhat is already known on this subject? Increased exposure to sex hormones may alter the ventricular repolarisation of the heart as the parity number increases. Previous studies showed that increased parity (up to 7) deteriorates ventricular diastolic functions, prolongs QTc interval and these conditions cause cardiovascular diseases.What do the results of this study add? In this study, we added great grand multiparity (10 or more parity) (GGMP) group that have never been studied before. We found that GGMP has much more impact on QTc prolongation than fewer parity groups and this result shows us that GGMP deteriorates ventricular functions more.What are the implications of these findings for clinical practice and/or further research? These results show us that women should be discouraged from having more delivery. Also, women with a pregnancy history of five and more (grand multiparity) should be evaluated with an electrocardiography and a cardiology consultation should be performed before re-conception. In the future, larger prospective studies are needed on this subject. In addition, other electrocardiographic parameters (QRS-T angle and Tpe/QTc in electrocardiography, etc.) that related with diastolic functions should be evaluated for comparison of GGMP and non-GGMP populations in future studies.

The atherogenic index of plasma as a predictor of mortality in patients with COVID-19.

BACKGROUND: Coronavirus disease 2019 (COVID-19) has become a global health threat, and thus, an early and effective set of predictors is needed to manage the course of the disease. OBJECTIVES: We aim to determine the effect of SARS-CoV-2 on lipid profile and to evaluate whether the atherogenic index of plasma (AIP) could be used to predict in-hospital mortality in COVID-19 patients. METHODS: In this retrospective chart review study, a total of 139 confirmed COVID-19 patients, whose diagnoses are confirmed by PCR and computerized tomography results, are enrolled. The study population is divided into two groups: the deceased patient group and the survivor group. For each patient, fasting total cholesterol, high-density lipoprotein cholesterol (HDL-C), low-density lipoprotein cholesterol (LDL-C) and the triglyceride values are obtained from the laboratory tests required at the admission to hospital. Finally, the AIP is calculated as the base 10 logarithm of the triglyceride to HDL-C ratio. Distributional normality of the data is checked and depending on the normality of the data, either T test or Mann Whithey U test is employed to compare the two aforementioned study groups. RESULTS: Mean age of the study population is 49.2 ± 20.8 and 61.2% (n = 85) is male. Out of the 139 patients 26 have deceased and the remaining 113 patients survived the disease. Mean age of the deceased patients was 71.8*8.9 and mean age of the survivor patients is 44.0*19.2 (p < 0.001). The deceased group had more patients with hypertension (50.0% vs. 23.0, p = 0.006), diabetes mellitus (35.6% vs. 10.6%, p = 0.002), cardiovascular diseases (23.1% vs. 4.4%, p = 0.001), chronic renal insufficiency (11.5% vs. 0.9%, p = 0.003) and atrial fibrillation (7.7% vs 0%, p = 0.003). The AIP values in the deceased group are found to be statistically higher (p < 0.001) than the survivor group. As a measure of mortality, the area under the operating characteristic curve for the AIP is calculated as 0.850 (95% confidence interval: 0.772-0.928) along with the optimal cut-off value of 0.6285 (78.6% sensitivity and 80.5% specificity). Furthermore, the AIP value is observed to be elevated in patients with pneumonia, intubation history, and intensive care admission during hospital stay (p = 0.002, p < 0.001 and p < 0.001, respectively). Finally, compared to the survivor group, total cholesterol, HDL-C, LDL-C values are lower (p = 0.004, p < 0.001 and p < 0.001, respectively) and triglyceride levels are higher (p < 0.001) in deceased patients. CONCLUSION: In this study, we show that the AIP levels higher than 0.6285 can predict in-hospital mortality for COVID-19 patients. Moreover, the AIP emerges as a good candidate to be used as an early biomarker to predict pneumonia, intubation and intensive care need. Hence, regular check of the AIP levels in COVID-19 patients can improve management of these patients and prevent deterioration of the disease.

Evaluation of the Tp-e interval and Tp-e/QTc ratio in patients with benign paroxysmal positional vertigo in the emergency department compared with the normal population.

INTRODUCTION: Benign paroxysmal positional vertigo (BPPV) is a common diagnosis for dizziness patients admitting to emergency department and for initial diagnosis, cardiac causes of dizziness should be excluded at admittance. Electrocardiography (ECG) is a simple method to detect cardiac arrhythmias for these patients. Tp-e interval and Tp-e/QTc ratio are transmural repolarization parameters and shown to be strongly related to ventricular arrhythmias. With this study, we aim to investigate ventricular repolarization parameters like Tp-e interval and Tp-e/QTc ratio which can be easily evaluated by ECG in BPPV patients. MATERIALS AND METHODS: A total of 84 newly diagnosed BPPV patients and 59 age-sex matched control group without dizziness symptoms compatible with inclusion criteria were included for the study. Patients with previous vertigo, coronary artery disease, renal disease, heart failure, severe valvular disease, arrhythmia history, electrolyte disturbances and patients under 18 years of age were excluded. RESULTS: Mean age of the study population was 44.4 ±â€¯12.1 years, 36.4% were male. There was no significant difference among groups in terms of age, sex, diabetes mellitus, hypertension and hypothyroidism history. When ECG results were evaluated QRS interval, QT interval, Tp-e interval, Tp-e/QT ratio and Tp-e/QTc ratio were statistically higher in BPPV patients compared to control group (p = 0.000, p = 0.047, p = 0.000, p = 0.000 and p = 0.001, respectively). DISCUSSION: As a result of our study, Tp-e and Tp-e/QTc ratio were significantly higher in BPPV patients compared to the control group. These findings suggest that ventricular arrhythmia risk may be higher in BPPV patients. Further evaluation of these patients in terms of ventricular arrhythmia would be beneficial.

Transient ST Segment Elevation Caused by Intracoronary Thrombus after Acute Carbon Monoxide Poisoning.

Carbon monoxide (CO) poisoning is the most common cause of death and injury among all poisonings. Myocardial injury is detected in one-third of CO poisonings. In this Case Report, a previously healthy 41-year-old man was referred for CO poisoning. The initial electrocardiogram (ECG) showed 1mm ST segment elevation in leads DII, DIII, and aVF. As the patient did not describe chest pain and had no cardiac symptoms, ECG was repeated 10 minutes later and it was seen that ST segment elevation disappeared. As the patient had a transient ST segment elevation and elevated high-sensitive Tn-T (HsTn-T), the patient was transferred to the coronary angiography laboratory. The patient's left coronary system was normal, but a thrombus image narrowing the lumen by approximately 60% was observed in the right coronary artery. Intravenous tirofiban was administered for 48 hours. Control coronary angiography showed continuing thrombus formation and a bare metal stent was successfully implanted. This is the first reported case with transient ST segment elevation associated with acute coronary thrombus caused by CO poisoning. It may be recommended that patients with CO poisoning should be followed-up with a 12-lead ECG monitor or 24-hour ECG Holter monitoring, even if they show no cardiac symptoms and echocardiography shows no wall motion abnormality. Early coronary angiography upon detection of such dynamic ECG changes in these recordings as ST segment elevation can reduce the risk of myocardial infarction (MI) and mortality in these patients.