A computational intelligence tool for the detection of hypertension using empirical mode decomposition.

Hypertension (HPT), also known as high blood pressure, is a precursor to heart, brain or kidney diseases. Some symptoms of HPT include headaches, dizziness and fainting. The potential diagnosis of masked hypertension is of specific interest in this study. In masked hypertension (MHPT), the instantaneous blood pressure appears normal, but the 24-h ambulatory blood pressure is abnormal. Hence patients with MHPT are difficult to identify and thus remain untreated or are treated insufficiently. Hence, a computational intelligence tool (CIT) using electrocardiograms (ECG) signals for HPT and possible MHPT detection is proposed in this work. Empirical mode decomposition (EMD) is employed to decompose the pre-processed signals up to five levels. Nonlinear features are extracted from the five intrinsic mode functions (IMFs) thereafter. Student's t-test is subsequently applied to select a set of highly discriminatory features. This feature set is then input to various classifiers, in which, the best accuracy of 97.70% is yielded by the k-nearest neighbor (k-NN) classifier. The developed tool is evaluated by the 10-fold cross validation technique. Our findings suggest that the developed system is useful for diagnostic computational intelligence tool in hospital settings, and that it enables the automatic classification of HPT versus normal ECG signals.

Tracking excess deaths associated with the COVID-19 epidemic as an epidemiological surveillance strategy-preliminary results of the evaluation of six Brazilian capitals

Abstract INTRODUCTION: In March 2020, the World Health Organization declared the coronavirus disease (COVID-19) outbreak a pandemic. In Brazil, 110 thousand cases and 5,901 deaths were confirmed by the end of April 2020. The scarcity of laboratory resources, the overload on the service network, and the broad clinical spectrum of the disease make it difficult to document all the deaths due to COVID-19. The aim of this study was to assess the mortality rate in Brazilian capitals with a high incidence of COVID-19. METHODS: We assessed the weekly mortality between epidemiological week 1 and 16 in 2020 and the corresponding period in 2019. We estimated the expected mortality at 95% confidence interval by projecting the mortality in 2019 to the population in 2020, using data from the National Association of Civil Registrars (ARPEN-Brasil). RESULTS: In the five capitals with the highest incidence of COVID-19, we identified excess deaths during the pandemic. The age group above 60 years was severely affected, while 31% of the excess deaths occurred in the age group of 20-59 years. There was a strong correlation (r = 0.94) between excess deaths and the number of deaths confirmed by epidemiological monitoring. The epidemiological surveillance captured only 52% of all mortality associated with the COVID-19 pandemic in the cities examined. CONCLUSIONS: Considering the simplicity of the method and its low cost, we believe that the assessment of excess mortality associated with the COVID-19 pandemic should be used as a complementary tool for regular epidemiological surveillance.

Integrating risk management data in quality improvement initiatives within an academic neurosurgery department.

OBJECT While malpractice litigation has had many negative impacts on health care delivery systems, information extracted from lawsuits could potentially guide toward venues to improve care. The authors present a comprehensive review of lawsuits within a tertiary academic neurosurgical department and report institutional and departmental strategies to mitigate liability by integrating risk management data with quality improvement initiatives. METHODS The Comprehensive Risk Intelligence Tool database was interrogated to extract claims/suits abstracts concerning neurosurgical cases that were closed from January 2008 to December 2012. Variables included demographics of the claimant, type of procedure performed (if any), claim description, insured information, case outcome, clinical summary, contributing factors and subfactors, amount incurred for indemnity and expenses, and independent expert opinion in regard to whether the standard of care was met. RESULTS During the study period, the Department of Neurosurgery received the most lawsuits of all surgical specialties (30 of 172), leading to a total incurred payment of $4,949,867. Of these lawsuits, 21 involved spinal pathologies and 9 cranial pathologies. The largest group of suits was from patients with challenging medical conditions who underwent uneventful surgeries and postoperative courses but filed lawsuits when they did not see the benefits for which they were hoping; 85% of these claims were withdrawn by the plaintiffs. The most commonly cited contributing factors included clinical judgment (20 of 30), technical skill (19 of 30), and communication (6 of 30). CONCLUSIONS While all medical and surgical subspecialties must deal with the issue of malpractice and liability, neurosurgery is most affected both in terms of the number of suits filed as well as monetary amounts awarded. To use the suits as learning tools for the faculty and residents and minimize the associated costs, quality initiatives addressing the most frequent contributing factors should be instituted in care redesign strategies, enabling strategic alignment of quality improvement and risk management efforts.