scholarly journals Nystagmus Estimation for Dizziness Diagnosis by Pupil Detection and Tracking Using Mexican-Hat-Type Ellipse Pattern Matching

Healthcare ◽  
2021 ◽  
Vol 9 (7) ◽  
pp. 885
Author(s):  
Yoanda Alim Syahbana ◽  
Yokota Yasunari ◽  
Morita Hiroyuki ◽  
Aoki Mitsuhiro ◽  
Suzuki Kanade ◽  
...  
Keyword(s):  
Pattern Matching ◽  
Hough Transform ◽  
University Hospital ◽  
Transform Method ◽  
Data Set ◽  
Medical Specialists ◽  
Detection And Tracking ◽  
Mexican Hat ◽  
Pupil Detection ◽  
In The Wild

The detection of nystagmus using video oculography experiences accuracy problems when patients who complain of dizziness have difficulty in fully opening their eyes. Pupil detection and tracking in this condition affect the accuracy of the nystagmus waveform. In this research, we design a pupil detection method using a pattern matching approach that approximates the pupil using a Mexican hat-type ellipse pattern, in order to deal with the aforementioned problem. We evaluate the performance of the proposed method, in comparison with that of a conventional Hough transform method, for eye movement videos retrieved from Gifu University Hospital. The performance results show that the proposed method can detect and track the pupil position, even when only 20% of the pupil is visible. In comparison, the conventional Hough transform only indicates good performance when 90% of the pupil is visible. We also evaluate the proposed method using the Labelled Pupil in the Wild (LPW) data set. The results show that the proposed method has an accuracy of 1.47, as evaluated using the Mean Square Error (MSE), which is much lower than that of the conventional Hough transform method, with an MSE of 9.53. We conduct expert validation by consulting three medical specialists regarding the nystagmus waveform. The medical specialists agreed that the waveform can be evaluated clinically, without contradicting their diagnoses.

Abstract 17847: Gasping is a Valid Predictor Of ROSC and Hospital Discharge for In-hospital Cardiac Arrest Occurring on the Ward

Circulation ◽  
2015 ◽  
Vol 132 (suppl_3) ◽  
Author(s):  
Luca Marengo ◽  
Wolfgang Ummenhofer ◽  
Gerster Pascal ◽  
Falko Harm ◽  
Marc Lüthy ◽  
...  
Keyword(s):  
Cardiac Arrest ◽  
Ventricular Fibrillation ◽  
Hospital Discharge ◽  
Survival Data ◽  
Neurological Outcome ◽  
Rapid Response Team ◽  
Spontaneous Circulation ◽  
University Hospital ◽  
Data Set ◽  
Hospital Cardiac Arrest

Introduction: Agonal respiration has been shown to be commonly associated with witnessed events, ventricular fibrillation, and increased survival during out-of-hospital cardiac arrest. There is little information on incidence of gasping for in-hospital cardiac arrest (IHCA). Our “Rapid Response Team” (RRT) missions were monitored between December 2010 and March 2015, and the prevalence of gasping and survival data for IHCA were investigated. Methods: A standardized extended in-hospital Utstein data set of all RRT-interventions occurring at the University Hospital Basel, Switzerland, from December 13, 2010 until March 31, 2015 was consecutively collected and recorded in Microsoft Excel (Microsoft Corp., USA). Data were analyzed using IBM SPSS Statistics 22.0 (IBM Corp., USA), and are presented as descriptive statistics. Results: The RRT was activated for 636 patients, with 459 having a life-threatening status (72%; 33 missing). 270 patients (59%) suffered IHCA. Ventricular fibrillation or pulseless ventricular tachycardia occurred in 42 patients (16% of CA) and were associated with improved return of spontaneous circulation (ROSC) (36 (97%) vs. 143 (67%; p<0.001)), hospital discharge (25 (68%) vs. 48 (23%; p<0.001)), and discharge with good neurological outcome (Cerebral Performance Categories of 1 or 2 (CPC) (21 (55%) vs. 41 (19%; p<0.001)). Gasping was seen in 128 patients (57% of CA; 46 missing) and was associated with an overall improved ROSC (99 (78%) vs. 55 (59%; p=0.003)). In CAs occurring on the ward (154, 57% of all CAs), gasping was associated with a higher proportion of shockable rhythms (11 (16%) vs. 2 (3%; p=0.019)), improved ROSC (62 (90%) vs. 34 (55%; p<0.001)), and hospital discharge (21 (32%) vs. 7 (11%; p=0.006)). Gasping was not associated with neurological outcome. Conclusions: Gasping was frequently observed accompanying IHCA. The faster in-hospital patient access is probably the reason for the higher prevalence compared to the prehospital setting. For CA on the ward without continuous monitoring, gasping correlates with increased shockable rhythms, ROSC, and hospital discharge.

scholarly journals A Novel Deep Learning–Based System for Triage in the Emergency Department Using Electronic Medical Records: Retrospective Cohort Study

10.2196/27008 ◽  
2021 ◽  
Vol 23 (12) ◽  
pp. e27008
Author(s):  
Li-Hung Yao ◽  
Ka-Chun Leung ◽  
Chu-Lin Tsai ◽  
Chien-Hua Huang ◽  
Li-Chen Fu
Keyword(s):  
Deep Learning ◽  
Electronic Medical Records ◽  
Medical Records ◽  
Severity Index ◽  
University Hospital ◽  
Emergency Severity Index ◽  
National Hospital ◽  
Data Set ◽  
Care Survey ◽  
Ambulatory Medical Care

Background Emergency department (ED) crowding has resulted in delayed patient treatment and has become a universal health care problem. Although a triage system, such as the 5-level emergency severity index, somewhat improves the process of ED treatment, it still heavily relies on the nurse’s subjective judgment and triages too many patients to emergency severity index level 3 in current practice. Hence, a system that can help clinicians accurately triage a patient’s condition is imperative. Objective This study aims to develop a deep learning–based triage system using patients’ ED electronic medical records to predict clinical outcomes after ED treatments. Methods We conducted a retrospective study using data from an open data set from the National Hospital Ambulatory Medical Care Survey from 2012 to 2016 and data from a local data set from the National Taiwan University Hospital from 2009 to 2015. In this study, we transformed structured data into text form and used convolutional neural networks combined with recurrent neural networks and attention mechanisms to accomplish the classification task. We evaluated our performance using area under the receiver operating characteristic curve (AUROC). Results A total of 118,602 patients from the National Hospital Ambulatory Medical Care Survey were included in this study for predicting hospitalization, and the accuracy and AUROC were 0.83 and 0.87, respectively. On the other hand, an external experiment was to use our own data set from the National Taiwan University Hospital that included 745,441 patients, where the accuracy and AUROC were similar, that is, 0.83 and 0.88, respectively. Moreover, to effectively evaluate the prediction quality of our proposed system, we also applied the model to other clinical outcomes, including mortality and admission to the intensive care unit, and the results showed that our proposed method was approximately 3% to 5% higher in accuracy than other conventional methods. Conclusions Our proposed method achieved better performance than the traditional method, and its implementation is relatively easy, it includes commonly used variables, and it is better suited for real-world clinical settings. It is our future work to validate our novel deep learning–based triage algorithm with prospective clinical trials, and we hope to use it to guide resource allocation in a busy ED once the validation succeeds.

Method of Recognition and Feature Rapid Extraction about Multi-Objective Rounds Based on Rotating Scanning

2012 ◽  
Vol 152-154 ◽  
pp. 1840-1845
Author(s):  
Dao Hua Lu ◽  
Song Lian Xie ◽  
Jia Wang
Keyword(s):  
Hough Transform ◽  
Extraction Method ◽  
Contour Extraction ◽  
Transform Method ◽  
Scanning Method ◽  
Multi Objective ◽  
Rapid Extraction

To achieve the target features quick extraction, this paper uses a contour extraction method based on contour mark and outline of rotating scan target filling. It mainly introduces the principle and algorithm of Rand-omized Hough Transform method and rotating scanning method, uses a workpiece as an example to illustrate it with experiment.

EP.FRI.857 Audit and quality improvement project; data entry into the NELA database from Royal Stoke university hospital

2021 ◽  
Vol 108 (Supplement_7) ◽  
Author(s):  
Nandu Nair ◽  
Vasileios Kalatzis ◽  
Madhavi Gudipati ◽  
Anne Gaunt ◽  
Vishnu Machineni
Keyword(s):  
Quality Improvement ◽  
Data Entry ◽  
Quality Improvement Project ◽  
University Hospital ◽  
Emergency Laparotomy ◽  
Data Set ◽  
Improvement Project ◽  
Hospital Database ◽  
Case Ascertainment ◽  
Project Data

Abstract Aims During the period December-2018 to November-2019 a total of 84 cases were entered on the NELA website, corresponding to HES data suggesting 392 laparotomies. This suggests a possible case acquisition of 21% prompting us to look at our data acquisition in detail. Methods Interrogation of the NELA data from January–March 2020 was done from NELA website and hospital records. Results Analysis revealed that during this period 45 patients had laparotomy recorded whereas hospital database recorded 68 laparotomies. Of the 45 cases entered on the NELA database, only 1 patient had a complete data set entered.  22 cases had 87% data entry and 22 cases had &lt;50% of the data fields completed. Firstly, we were not capturing all patients who underwent an emergency laparotomy and secondly our data entry for the patients we did report was incomplete.  This led us to engage in a quality improvement project with following measures - Conclusions We re-assessed the case ascertainment and completeness of data collection in the period April 2020 – June 2020 and case ascertainment rate increased to 54% and all the entries were complete and locked.

A Predictive E-Health Information System

2016 ◽  
pp. 451-469
Author(s):  
Ahmad Al-Khasawneh ◽  
Haneen Hijazi
Keyword(s):  
Clinical Decision Support System ◽  
World Wide ◽  
Health Information System ◽  
Clinical Decision ◽  
Developed Countries ◽  
University Hospital ◽  
Data Set ◽  
Validation Technique ◽  
Artificial Neural ◽  
Hidden Layer

Diabetes Mellitus is a chronic disease and a major cause of several severe complications and death in both developing and developed countries. The number of diabetes cases world-wide has been climbed up drastically over last decades. Hence, it was of utmost important to manage this illness and to develop tools that help clinicians do their job professionally. Artificial neural networks play a major role herein. In this research, a clinical decision support system that helps in diagnosing diabetes has been developed. The system was implemented using a multilayer perceptron artificial neural network. Due to the fact that there is no systematic way to follow in order to determine the number of hidden layers and neurons in MLP, an algorithm was proposed and followed based on the rules-of-thumb previously defined around this issue. As a result, two different topologies were trained and verified using cross validation technique. The topology that exhibited the best averaged accuracy was that of one hidden layer. The data set was obtained from King Abdullah University Hospital in Jordan.

scholarly journals Edge Prior Multilayer Segmentation Network Based on Bayesian Framework

2020 ◽  
Vol 2020 ◽  
pp. 1-11 ◽  
Author(s):  
Chu He ◽  
Zishan Shi ◽  
Peizhang Fang ◽  
Dehui Xiong ◽  
Bokun He ◽  
...  
Keyword(s):  
Prior Information ◽  
Semantic Segmentation ◽  
Bayesian Framework ◽  
Excellent Performance ◽  
Transform Method ◽  
Data Set ◽  
Distance Map ◽  
Constraint Network ◽  
Average Accuracy ◽  
Complex Boundaries

In recent years, methods based on neural network have achieved excellent performance for image segmentation. However, segmentation around the edge area is still unsatisfactory when dealing with complex boundaries. This paper proposes an edge prior semantic segmentation architecture based on Bayesian framework. The entire framework is composed of three network structures, a likelihood network and an edge prior network at the front, followed by a constraint network. The likelihood network produces a rough segmentation result, which is later optimized by edge prior information, including the edge map and the edge distance. For the constraint network, the modified domain transform method is proposed, in which the diffusion direction is revised through the newly defined distance map and some added constraint conditions. Experiments about the proposed approach and several contrastive methods show that our proposed method had good performance and outperformed FCN in terms of average accuracy for 0.0209 on ESAR data set.

Sign in / Sign up

Export Citation Format

Share Document