Search

Electronic health records naturally contain most of the medical information in the form of doctor's notes as unstructured or semi-structured texts. Current deep learning text analysis approaches allow researchers to reveal the inner semantics of text information and even identify hidden consequences that can offer extra decision support to doctors. In the presented article, we offer a new automated analysis of Polish summary texts of patient hospitalizations. The presented models were found to be able to predict the final diagnosis with almost 70% accuracy based just on the patient's medical history (only 132 words on average), with possible accuracy increases when adding further sentences from hospitalization results; even one sentence was found to improve the results by 4%, and the best accuracy of 78% was achieved with five extra sentences. In addition to detailed descriptions of the data and methodology, we present an evaluation of the analysis using more than 50,000 Polish cardiology patient texts and dive into a detailed error analysis of the approach. The results indicate that the deep analysis of just the medical history summary can suggest the direction of diagnosis with a high probability that can be further increased just by supplementing the records with further examination results.

The electrophysiology-guided noninvasive cardiac radioablation, also known as STAR (stereotactic arrhythmia radioablation) is an emerging treatment method for persistent ventricular tachycardia. Since its first application in 2012 in Stanford Cancer Institute, and a year later in University Hospital Ostrava, Czech Republic, the authors from all around the world have published case reports and case series, and several prospective trials were established. In this article, we would like to discuss the available clinical evidence, analyze the potentially clinically relevant differences in methodology, and address some of the unique challenges that come with this treatment method.

Introduction: Advances in the acute treatment of myocardial infarction (AMI) substantially reduced in-hospital mortality, but the post-discharge prognosis is still unacceptable. The Managed Care in Acute Myocardial Infarction (MC-AMI) is a program of Poland's National Health Fund that aims at comprehensive post-AMI care to improve long-term prognosis. The aim of the study was to assess the effect of MC-AMI on all-cause mortality in one-year follow-up., Methods: MC-AMI includes acute MI treatment, complex revascularization, cardiac rehabilitation (CR), scheduled one-year outpatient follow-up, and prevention of sudden cardiac death. In this retrospective observational study performed in a province of Silesia, Poland, we analyzed 3893 MC-AMI participants, and compared them to 6946 patients in the control group. After propensity score matching, we compared two groups of 3551 subjects each. To assess the effect of MC-AMI and other variables on mortality, we preformed a Cox regression., Results: MC-AMI was related with mortality reduction by 38% in a 12-month observation period and the effect persisted even after. Multivariable Cox regression analysis revealed MC-AMI participation to be inversely associated with 1-year mortality (HR 0.52, 95%CI 0.42-0.65, p < 0.001). Besides that, older age (HR 1.47/10 y), ST-elevation AMI (HR 1.41), heart failure (HR 2.08), diabetes (HR 1.52), and dialysis (HR 2.38) were significantly associated with the primary endpoint. Among MC-AMI components, cardiac rehabilitation (HR 0.34) and strict outpatient care (HR 0.42) are the crucial factors affecting mortality reduction., Conclusions: Participation in MC-AMI reduced 1-year mortality by 38% and the effect persisted after the program had been completed.

Background: Diagnosis of myocardial infarction with non-obstructive coronary arteries (MINOCA) requires both clinical evidence of acute myocardial infarction (AMI) and demonstration of non-obstructive coronary arteries using angiography. We compared the clinical features, treatments, and three-year outcomes in patients with MINOCA and myocardial infarction with obstructive coronary artery disease (MI-CAD)., Methods: We retrospectively analyzed data for 205,606 hospitalized patients with AMI. MINOCA was indicated as a working diagnosis in 6063 patients (2.94% of all AMI patients). For the control group we included 160,886 patients with MI-CAD. We evaluated the baseline characteristics, medication management options, outcomes, and readmission causes at 36 months follow-up., Results: Patients in the MINOCA group were younger. Females constituted a greater proportion of patients in the MINOCA group when compared to MI-CAD patients. STEMI during admission was diagnosed less frequently in the MINOCA group when compared to the MI-CAD group. All-cause mortality at 12 months was higher in the MINOCA group (10.94% vs. 9.54%, p < 0.001). At 36 months, there was no difference in the all-cause mortality rates (MINOCA 16.18% vs. MI-CAD 14.93%, p = 0.081). All-cause readmission rates were lower in the MINOCA group when compared to the MI-CAD group at both 12 months (45.19% vs. 54.33%, p < 0.001) and 36 months follow-up (56.42% vs. 66.66%, p < 0.001)., Conclusions: This is the first description of the clinical features, treatments, and three-year outcomes in a large population of Polish patients. The main finding of this study was a relatively low rate of MINOCA, with high rates of adverse events both at 12 and 36 months follow-up.