Browsing by Author "Chiu, Ming-Jang"

Now showing 1 - 5 of 5

Bio-signal Analysis System Design with Support Vector Machines based on Cloud Computing Service Architecture
(2010-01-01)
Shen, Chia-Ping
;
Chen, Wei-Hsin
;
Chen, Jia-Ming
;
Hsu, Kai-Ping
;
Lin, Jeng-Wei
Today, many bio-signals such as Electroencephalography (EEG) are recorded in digital format. It is an emerging research area of analyzing these digital bio-signals to extract useful health information in biomedical engineering. In this paper, a bio-signal analyzing cloud computing architecture, called BACCA, is proposed. The system has been designed with the purpose of seamless integration into the National Taiwan University Health Information System. Based on the concept of. NET Service Oriented Architecture, the system integrates heterogeneous platforms, protocols, as well as applications. In this system, we add modern analytic functions such as approximated entropy and adaptive support vector machine (SVM). It is shown that the overall accuracy of EEG bio-signal analysis has increased to nearly 98% for different data sets, including open-source and clinical data sets.
Cognitive stimulation during hospitalization improves global cognition of older Taiwanese undergoing elective total knee and hip replacement surgery
(2012-06-01)
Cheng, Chia-Min
;
Chiu, Ming-Jang
;
Wang, Jyh-Horng
;
Liu, Hwa-Chang
;
Shyu, Yea-Ing Lotus
cheng c.-m., chiu m.-j., wang j.-h., liu h.-c., shyu y.-i.l., huang g.-h. & chen c.c.-h. (2012) Cognitive stimulation during hospitalization improves global cognition of older Taiwanese undergoing elective total knee and hip replacement surgery. Journal of Advanced Nursing68(6), 1322-1329. Abstract Aim. This article is a report on a pilot study conducted to determine the effects of cognitively stimulating activities in older patients undergoing elective hip and/or knee replacement. Background. Cognitive decline occurs in 16-35.5% of older hospitalized patients. In-hospital interventions, such as cognitively stimulating activities, might combat cognitive decline. However, evidence supporting such interventions is limited. Methods. For this randomized pilot trial, 50 older patients (90% women with a mean age of 72.8 years) were recruited in 2008 from a tertiary medical centre in Taiwan. While hospitalized, participants in the intervention group received a daily nurse-led, individual-based, cognitive-stimulation intervention. The comparison group received usual care. Cognitive function was assessed using Mini-Mental State Examination at admission, discharge and 1 month after discharge. Results. The incidence of cognitive decline (=2-point decline in cognitive score) by hospital discharge was significantly lower for the intervention group (12%) than the usual care group (44%). The intervention group also had better cognitive scores following hospitalization. Upon discharge, participants in the intervention group scored 1.28 points higher than at admission, whereas participants in the usual care declined by 0.76 points. Improvement in cognitive status persisted for the intervention group (+1.33 points) vs. usual care (-0.26 points) at 1 month after discharge. Group differences in changes were statistically significant both at discharge and 1 month afterwards. Conclusion. Our cognitive-stimulation intervention benefited global cognitive function among older patients undergoing elective hip and/or knee replacement. The benefit persisted at 1 month after discharge.
Delirium, Subsyndromal Delirium, and Cognitive Changes in Individuals Undergoing Elective Coronary Artery Bypass Graft Surgery
(2015-07-01)
Li, Hsiu-Ching
;
Chen, Yih-Sharng
;
Chiu, Ming-Jang
;
Fu, Mei-Chiung
;
Huang, Guan-Hua
Background: The course of incident delirium and subsyndromal delirium (SSD) after cardiac surgery is not well studied. Objective: The aim of this study was to evaluate the course of incident delirium and SSD, their risk factors, and impact on patients\' cognitive function after elective coronary artery bypass graft (CABG) surgery. Methods: Consecutive patients scheduled for an isolated CABG at a tertiary medical center in Taiwan were enrolled if they had no preoperative delirium symptoms. Delirium was assessed daily for 1 week after surgery using the Confusion Assessment Method. Subsyndromal delirium was defined as presenting with any core symptom below the diagnostic threshold for delirium. Cognitive function was assessed by the Mini-mental State Examination. Results: Of 38 participants, 7 had incident (first-time) delirium (18.4% incidence) and 13 had incident SSD (34.2% incidence). Whereas SSD usually lasted 1 day, delirium changed gradually to SSD to recovery and its symptomatology lasted longer. We identified 6 delirium risk factors: older age, more comorbidities, cardiac pulmonary bypass, blood transfusion, larger transfusion volume, and longer duration of intraoperative blood pressure less than 60 mm Hg. The frequencies of these risk factors for SSD were often intermediate between those of risk factors in groups with and without delirium. By hospital discharge, participants with delirium had the longest hospital stays and lowest cognitive scores, those with SSD had intermediate stays and scores, and those without delirium had the lowest stays and scores. Conclusion: Delirium and SSD after CABG are common. Greater number and severity of risk factors for delirium may predict increasingly poor outcomes, with the dose-response relationship between risk factors and outcomes for SSD intermediate between that for no symptoms and full delirium. Intervention trials are indicated, particularly for patients with a greater number and severity of predisposing and precipitating risk factors.
High-Performance Seizure Detection System Using a Wavelet-Approximate Entropy-fSVM Cascade With Clinical Validation
(2013-10-01)
Shen, Chia-Ping
;
Chen, Chih-Chuan
;
Hsieh, Sheau -Ling
;
Chen, Wei-Hsin
;
Chen, Jia-Ming
The classification of electroencephalography (EEG) signals is one of the most important methods for seizure detection. However, verification of an atypical epileptic seizure often can only be done through long-term EEG monitoring for 24 hours or longer. Hence, automatic EEG signal analysis for clinical screening is necessary for the diagnosis of epilepsy. We propose an EEG analysis system of seizure detection, based on a cascade of wavelet-approximate entropy for feature selection, Fisher scores for adaptive feature selection, and support vector machine for feature classification. Performance of the system was tested on open source data, and the overall accuracy reached 99.97%. We further tested the performance of the system on clinical EEG obtained from a clinical EEG laboratory and bedside EEG recordings. The results showed an overall accuracy of 98.73% for routine EEG, and 94.32% for bedside EEG, which verified the high performance and usefulness of such a cascade system for seizure detection. Also, the prediction model, trained by routine EEG, can be successfully generalized to bedside EEG of independent patients.
Patterns of cognitive change in elderly patients during and 6 months after hospitalisation: A prospective cohort study
(2011-03-01)
Chen, Cheryl Chia-Hui
;
Chiu, Ming-Jang
;
Chen, Sui-Pi
;
Cheng, Chia-Min
;
Huang, Guan-Hua
Background: The extent and patterns of cognitive change regularly occurring in elderly patients who experience prolonged hospitalisation have not been well examined. Objective: To describe patterns of cognitive change during and 6 months after hospitalisation and to identify prognostic factors associated with different patterns of changes. Design: A prospective cohort study. Setting: Five med-surgical units at a tertiary hospital in Taipei, Taiwan. Participants: Patients >= 65 years old without preexisting profound cognitive impairment (Mini-Mental State Examination score >= 20) and with an expected hospital length of stay >5 days were drawn from consecutive admissions. Of 351 patients, 82.9% (138 women, 153 men, mean age = 71.6 years) completed all four scheduled assessments. Methods: Cognition was measured by the Mini-Mental State Examination at 4 times: admission, discharge, and 3 and 6 months post-discharge. Possible prognostic factors at admission included demographics, comorbidities, number of medications, serum haemoglobin, length of hospital stay, and surgery. Results: Four cognitive-change patterns with a high prevalence of decline were identified by cluster analysis. The worsening then improve group (n = 47) had a deep V-shape with a mean fluctuation of 3.9 points on the Mini-Mental State Examination, and the low continuous group (n = 83) had little change. Both the start high and decline (n = 66) and start low and decline (n = 95) groups showed persistent and accelerated declines, with baseline cognitive scores of 29.1 and 25.5 points, respectively. Predictor variables at admission for different patterns of cognitive change were age, total education (years), cardiovascular comorbidities, number of medications, functional and nutritional status, depressive symptoms, surgical treatment, and haemoglobin level <12 g/dL. Conclusions: Cognitive decline during and after hospitalisation shows four heterogeneous patterns of change. Different patterns of change were predicted by age, education, cardiovascular comorbidities, number of medications, functional and nutritional status, depressive symptoms, surgical treatment, and haemoglobin level <12 g/dL, most of which are potentially modifiable factors. (C) 2010 Elsevier Ltd. All rights reserved.