Artificial intelligence-based opportunistic screening for the detection of arterial hypertension through ECG signals.

OBJECTIVES: Hypertension is a major risk factor for cardiovascular disease (CVD), which often escapes the diagnosis or should be confirmed by several office visits. The ECG is one of the most widely used diagnostic tools and could be of paramount importance in patients' initial evaluation. METHODS: We used machine learning techniques based on clinical parameters and features derived from the ECG, to detect hypertension in a population without CVD. We enrolled 1091 individuals who were classified as hypertensive or normotensive, and trained a Random Forest model, to detect the existence of hypertension. We then calculated the values for the Shapley additive explanations (SHAP), a sophisticated feature importance analysis, to interpret each feature's role in the Random Forest's results. RESULTS: Our Random Forest model was able to distinguish hypertensive from normotensive patients with accuracy 84.2%, specificity 78.0%, sensitivity 84.0% and area under the receiver-operating curve 0.89, using a decision threshold of 0.6. Age, BMI, BMI-adjusted Cornell criteria (BMI multiplied by RaVL+SV 3 ), R wave amplitude in aVL and BMI-modified Sokolow-Lyon voltage (BMI divided by SV 1 +RV 5 ), were the most important anthropometric and ECG-derived features in terms of the success of our model. CONCLUSION: Our machine learning algorithm is effective in the detection of hypertension in patients using ECG-derived and basic anthropometric criteria. Our findings open new horizon in the detection of many undiagnosed hypertensive individuals who have an increased CVD risk.

Detection of abnormal left ventricular geometry in patients without cardiovascular disease through machine learning: An ECG-based approach.

Cardiac remodeling is recognized as an important aspect of cardiovascular disease (CVD) progression. Machine learning (ML) techniques were applied to basic clinical parameters and electrocardiographic features, in order to detect abnormal left ventricular geometry (LVG) even before the onset of left ventricular hypertrophy (LVH), in a population without established CVD. The authors enrolled 528 patients with and without essential hypertension, but no other indications of CVD. All patients underwent a full echocardiographic evaluation and were classified into 3 groups; normal geometry (NG), concentric remodeling without LVH (CR), and LVH. Abnormal LVG was identified as increased relative wall thickness (RWT) and/or left ventricular mass index (LVMi). The authors trained supervised ML models to classify patients with abnormal LVG and calculated SHAP values to perform feature importance and interaction analysis. Hypertension, age, body mass index over the Sokolow-Lyon voltage, QRS-T angle, and QTc duration were some of the most important features. Our model was able to distinguish NG from CR+LVH combined, with 87% accuracy on an unseen test set, 75% specificity, 97% sensitivity, and area under the receiver operating curve (AUC/ROC) equal to 0.91. The authors also trained our model to classify NG and CR (NG + CR) against those with LVH, with 89% test set accuracy, 93% specificity, 67% sensitivity, and an AUC/ROC value of 0.89, for a 0.4 decision threshold. Our ML algorithm effectively detects abnormal LVG even at early stages. Innovative solutions are needed to improve risk stratification of patients without established CVD, and ML may enable progress in this direction.

The first 100 days: Modeling the evolution of the COVID-19 pandemic.

A simple analytical model for modeling the evolution of the 2020 COVID-19 pandemic is presented. The model is based on the numerical solution of the widely used Susceptible-Infectious-Removed (SIR) populations model for describing epidemics. We consider an expanded version of the original Kermack-McKendrick model, which includes a decaying value of the parameter ß (the effective contact rate), interpreted as an effect of externally imposed conditions, to which we refer as the forced-SIR (FSIR) model. We introduce an approximate analytical solution to the differential equations that represent the FSIR model which gives very reasonable fits to real data for a number of countries over a period of 100 days (from the first onset of exponential increase, in China). The proposed model contains 3 adjustable parameters which are obtained by fitting actual data (up to April 28, 2020). We analyze these results to infer the physical meaning of the parameters involved. We use the model to make predictions about the total expected number of infections in each country as well as the date when the number of infections will have reached 99% of this total. We also compare key findings of the model with recently reported results on the high contagiousness and rapid spread of the disease.

Olmesartan medoxomil-induced acute renal failure in a premature newborn following maternal exposure during pregnancy: a case report and review of the literature.

Angiotensin-converting enzyme (ACE) inhibitors and angiotensin II (AT II) receptor blockers (ARBs) are widely used antihypertensives with well-recognized renoprotective and cardioprotective effects. Although treatment with these agents generally does not result in adverse metabolic consequences, their use during human pregnancy has been associated with negative reactions. Here we report a premature baby with a history of oligohydramnios and maternal exposure to the ARB olmesartan medoxomil who was transferred to our institution with acute renal failure. Conservative treatment with diuretics and meticulous management of fluids and electrolytes resulted in an improvement in renal function in the patient. We conclude that olmesartan medoxomil may cause reversible renal failure in premature neonates.

Abrupt and durable remission of Henoch-Schönlein purpura nephritis with cyclosporine A.

Henoch-Schönlein purpura glomerulonephritis (HSP-GN) is a common form of systemic small vessel vasculitis in children. Although prognosis is usually favourable, the disease is occasionally associated with a risk of renal insufficiency. Various immunosuppressive agents have been used in patients with severe HSP-GN, but none have shown convincing favourable effects. We report a case of biopsy-proven HSP-related GN in a 4-year-old girl that responded remarkably well to cyclosporine A (CsA), following failure to respond to other immunosuppressive agents. At 8 months post-CsA treatment, repeat renal biopsy findings were consistent with histological improvement. We conclude that CsA treatment not only exerts beneficial effects on resistant HSP-related GN but may also arrest progression of the disease.