China
Africa
Explore chapters and articles related to this topic
Clinical Reasoning and Diagnostic Errors
Published in Paul Cerrato, John Halamka, Reinventing Clinical Decision Support, 2020
Nor are these prerequisites always required to arrive at an accurate diagnosis. In fact, the best clinicians have learned to integrate Type 1 and Type 2 reasoning into their cognitive “toolkit,” and to switch back and forth between the 2 as needed. By way of illustration, consider the diagnostic process required to distinguish non–ST segment elevation myocardial infarction (NSTEMI) from other cardiac syndromes. The former is a heart attack that is characterized by a specific abnormality on a patient’s EKG tracing, referring to the fact that the reading does not include an elevated ST segment. Typically a myocardial infarction is accompanied by an elevated ST segment on an EKG when there is a complete blockage of one of the coronary arteries that feed the heart muscle; an MI that’s accompanied by a non–ST elevation may indicate a partially blocked coronary artery instead.
Electrocardiogram
Published in Kayvan Najarian, Robert Splinter, Biomedical Signal and Image Processing, 2016
Kayvan Najarian, Robert Splinter
Figure 9.11 shows nine sections of a recording in combined Einthoven and Wilson electrode placement of an inferior myocardial infarction. A heart attack can result in various deviating ECG patterns In many heart attack cases, due to the existence of the dying cells in the heart muscle, there will be no significant dip between the QRS complex and the T wave. The period between the S part and the T wave will also seem continuous. This is referred to as ST elevation. Figure 9.12 illustrates the effect of dying cells on the ST potential. The ST elevation is one of the most recognizable indicators of myocardial infarction.
On inlet pressure boundary conditions for CT-based computation of fractional flow reserve: clinical measurement of aortic pressure
Published in Computer Methods in Biomechanics and Biomedical Engineering, 2023
Jincheng Liu, Suqin Huang, Xue Wang, Bao Li, Junling Ma, Yutong Sun, Jian Liu, Youjun Liu
This study enrolled 15 stable angina pectoris patients at Peking University People's Hospital, China. All patients underwent a 256-slice CT scan, transcatheter FFR operation, and the patients’ aortic pressure waveform and clinical physiological parameters during the operation were acquired. Patients inclusion criteria included stable angina disease and coronary heart disease diagnosed by CTA. The exclusion criteria included low CTA image quality (2 patients), coronary artery occlusion (1 patients), patients undergoing thoracotomy with transcatheter aortic valve implantation (1 patients) and ST-elevation myocardial infarction (1 patients). The institutional review boards of the participating centers approved the study protocol, and each patient signed the informed consent. Anonymized data were independently analyzed by the Biomechanics Laboratory of Beijing University of Technology.
Light weight multi-branch network-based extraction and classification of myocardial infarction from 12 lead electrocardiogram images
Published in The Imaging Science Journal, 2023
Jothiaruna Nagaraj, Anny Leema
MI changes can be mainly seen in ST segment like ST-Depression or ST-Elevation [4]. And also these changes are indicated other types of heart diseases, so expertise in this field is needed for accurate diagnosis of heart diseases. For this purpose, Computer-Aided Detection (CAD) methods are used. Usually, ECG is time-series data which is one-dimensional voltage amplitude data [5]. Using CAD with time-series data classification is performed by using machine learning algorithms [6] are Hidden Markov Model [7], Support Vector Machine [8], Adaboost [9], and Naive Bayes [10]. At first, preprocessing of the ECG signal is carried out for removing the noise from the signal using filtering methods. Filtering methods are low pass, high pass, Weiner filter, and butter worth filter. After preprocessing the signal, the detection of the peak in the weaves is carried out using the algorithms like z-scores. Then extraction of features is processed using the methods like statistic parameters. Using the extracted information classification is performed.
A recursive model of residual life prediction for human beings with health information from activities of daily living and memory
Published in Systems Science & Control Engineering, 2021
Kaiye Gao, Tianshi Wang, Kaixiang Peng, Ziwen Wang, Qiong He, Rui Peng
Besides traditional statistical studies, some researchers tried to study life expectancy or mortality using mathematical models (Hashir & Sawhney, 2020; Li et al., 2017; Su et al., 2020). For example, Li et al. used machine learning models to predict in-hospital mortality of ST-elevation myocardial infarction patients (Li et al., 2017). Su et al. developed a clinical prediction model for the mortality of diabetic adults with COVID-19 in Wuhan, China (Su et al., 2020). Hashir and Sawhney attempted to predict mortality with free-text clinical notes (Hashir & Sawhney, 2020). However, these mathematical models are limited to a population with a specific disease, while healthcare requires a comprehensive health assessment or residual life prediction for an average person. Some researchers developed models to estimate age-specific mortality for an average person (Cho et al., 2020). For instance, Cho et al. proposed an age-structured biomass model with an impulsive dynamic system to estimate age-specific natural mortality (Cho et al., 2020), Díaz-Rojo et al. used a multivariate control chart and Lee-Carter models to study mortality changes (Díaz-Rojo et al., 2020).