MyMedR

Displaying all 8 publications

Abstract:

Sort:

Fulltext Results of the international field trial with the Reason for Encounter Classification

Lamberts H, Meads S, Wood M

Soz Praventivmed, 1985;30(2):80-7.
PMID: 4002871

The Reason for Encounter Classification (RFEC) was designed by a WHO Working Party to classify the reasons why patients seek care at the primary care level. It is designed along two axes: Chapters and Components. Each chapter carries an alpha-code which is the first character of the basic 3-character alphanumeric code. Each chapter is subdivided into seven "components" carrying 2-digit numeric codes. The field trial was undertaken by family physicians and nurses in: Australia, Barbados, Brazil, Hungary, Malaysia, the Netherlands, Norway and the US. 90497 RFE's were analysed. Their distribution over the chapters and components characterize the content of international primary care. Listings with the most common RFE's in the participating countries reflect the cultural differences. It is concluded that the RFEC is not only feasible to classify reasons why patients seek care but also to classify the diagnosis and the process of primary care. As a result of this, the International Classification of Primary Care (ICPC) succeeds the RFEC.

Matched MeSH terms: Disease/classification*
Novel technique for reorganisation of opinion order to interval levels for solving several instances representing prioritisation in patients with multiple chronic diseases

Mohammed KI, Zaidan AA, Zaidan BB, Albahri OS, Albahri AS, Alsalem MA, et al.

Comput Methods Programs Biomed, 2020 Mar;185:105151.
PMID: 31710981 DOI: 10.1016/j.cmpb.2019.105151

CONTEXT: Telemedicine has been increasingly used in healthcare to provide services to patients remotely. However, prioritising patients with multiple chronic diseases (MCDs) in telemedicine environment is challenging because it includes decision-making (DM) with regard to the emergency degree of each chronic disease for every patient.
OBJECTIVE: This paper proposes a novel technique for reorganisation of opinion order to interval levels (TROOIL) to prioritise the patients with MCDs in real-time remote health-monitoring system.
METHODS: The proposed TROOIL technique comprises six steps for prioritisation of patients with MCDs: (1) conversion of actual data into intervals; (2) rule generation; (3) rule ordering; (4) expert rule validation; (5) data reorganisation; and (6) criteria weighting and ranking alternatives within each rule. The secondary dataset of 500 patients from the most relevant study in a remote prioritisation area was adopted. The dataset contains three diseases, namely, chronic heart disease, high blood pressure (BP) and low BP.
RESULTS: The proposed TROOIL is an effective technique for prioritising patients with MCDs. In the objective validation, remarkable differences were recognised among the groups' scores, indicating identical ranking results. In the evaluation of issues within all scenarios, the proposed framework has an advantage of 22.95% over the benchmark framework.
DISCUSSION: Patients with the most severe MCD were treated first on the basis of their highest priority levels. The treatment for patients with less severe cases was delayed more than that for other patients.
CONCLUSIONS: The proposed TROOIL technique can deal with multiple DM problems in prioritisation of patients with MCDs.

Matched MeSH terms: Chronic Disease/classification*
Optimal set of EEG features for emotional state classification and trajectory visualization in Parkinson's disease

Yuvaraj R, Murugappan M, Ibrahim NM, Sundaraj K, Omar MI, Mohamad K, et al.

Int J Psychophysiol, 2014 Dec;94(3):482-95.
PMID: 25109433 DOI: 10.1016/j.ijpsycho.2014.07.014

In addition to classic motor signs and symptoms, individuals with Parkinson's disease (PD) are characterized by emotional deficits. Ongoing brain activity can be recorded by electroencephalograph (EEG) to discover the links between emotional states and brain activity. This study utilized machine-learning algorithms to categorize emotional states in PD patients compared with healthy controls (HC) using EEG. Twenty non-demented PD patients and 20 healthy age-, gender-, and education level-matched controls viewed happiness, sadness, fear, anger, surprise, and disgust emotional stimuli while fourteen-channel EEG was being recorded. Multimodal stimulus (combination of audio and visual) was used to evoke the emotions. To classify the EEG-based emotional states and visualize the changes of emotional states over time, this paper compares four kinds of EEG features for emotional state classification and proposes an approach to track the trajectory of emotion changes with manifold learning. From the experimental results using our EEG data set, we found that (a) bispectrum feature is superior to other three kinds of features, namely power spectrum, wavelet packet and nonlinear dynamical analysis; (b) higher frequency bands (alpha, beta and gamma) play a more important role in emotion activities than lower frequency bands (delta and theta) in both groups and; (c) the trajectory of emotion changes can be visualized by reducing subject-independent features with manifold learning. This provides a promising way of implementing visualization of patient's emotional state in real time and leads to a practical system for noninvasive assessment of the emotional impairments associated with neurological disorders.

Matched MeSH terms: Parkinson Disease/classification*
Effectiveness of autogenic training in improving motor performances in Parkinson's disease

Ajimsha MS, Majeed NA, Chinnavan E, Thulasyammal RP

Complement Ther Med, 2014 Jun;22(3):419-25.
PMID: 24906579 DOI: 10.1016/j.ctim.2014.03.013

Relaxation training can be an important adjunct in reducing symptoms associated with Parkinson's disease (PD). Autogenic Training (AT) is a simple, easily administered and inexpensive technique for retraining the mind and the body to be able to relax. AT uses visual imagery and body awareness to promote a state of deep relaxation.

Matched MeSH terms: Parkinson Disease/classification
Fulltext International classification of primary care

Bentsen BG

Scand J Prim Health Care, 1986 Feb;4(1):43-50.
PMID: 3961309 DOI: 10.3109/02813438609013970

"Health for all by year 2000" was the subject of the WHO Conference at Alma-Ata in 1978. It was evident that good primary care was a requirement to reach this goal. However, knowledge about this was scanty, and the instrument, an acceptable classification for analyses of primary care, was lacking. Since 1978 a WHO Working Party on Classifications of Primary Care has been working on a Reason for Encounter Classification. A RFEC test form was produced. In 1983 a feasibility study was conducted in nine countries: Australia, Barbados, Brazil, Hungary, Malaysia, The Netherlands, Norway, the Philippines, and the USA. The results of this were changing the original proposal very much. In addition, the WONCA/WHO Classification of Health Problems in Primary Care was included in the final version. In 1984 this final version was accepted by WONCA Classification Committee. This is called ICPC = The International Classification of Primary Care. ICPC is biaxial with the chapters of organ/organ systems along the one axis, in addition of three chapters: General, Mental, and Social problems. The other axis comprises seven components: Complaints, Process and Diagnosis. An alphanumeric code is used. The feasibility study of RFEC comprised ten test sites, and 138 primary care professionals recorded a total of 100 452 reasons for encounter. The English version of the RFEC was translated into five other languages, and these versions were used during the study. ICPC is a comprehensive, simple and practicable classification which can be used in medical records and in different areas of primary care research.

Matched MeSH terms: Disease/classification*
Automated Detection of Alzheimer's Disease Using Brain MRI Images- A Study with Various Feature Extraction Techniques

Acharya UR, Fernandes SL, WeiKoh JE, Ciaccio EJ, Fabell MKM, Tanik UJ, et al.

J Med Syst, 2019 Aug 09;43(9):302.
PMID: 31396722 DOI: 10.1007/s10916-019-1428-9

The aim of this work is to develop a Computer-Aided-Brain-Diagnosis (CABD) system that can determine if a brain scan shows signs of Alzheimer's disease. The method utilizes Magnetic Resonance Imaging (MRI) for classification with several feature extraction techniques. MRI is a non-invasive procedure, widely adopted in hospitals to examine cognitive abnormalities. Images are acquired using the T2 imaging sequence. The paradigm consists of a series of quantitative techniques: filtering, feature extraction, Student's t-test based feature selection, and k-Nearest Neighbor (KNN) based classification. Additionally, a comparative analysis is done by implementing other feature extraction procedures that are described in the literature. Our findings suggest that the Shearlet Transform (ST) feature extraction technique offers improved results for Alzheimer's diagnosis as compared to alternative methods. The proposed CABD tool with the ST + KNN technique provided accuracy of 94.54%, precision of 88.33%, sensitivity of 96.30% and specificity of 93.64%. Furthermore, this tool also offered an accuracy, precision, sensitivity and specificity of 98.48%, 100%, 96.97% and 100%, respectively, with the benchmark MRI database.

Matched MeSH terms: Alzheimer Disease/classification
Fulltext Non-Hodgkin's lymphoma in an Asian population: 1968-1992 time trends and ethnic differences in Singapore

Seow A, Lee J, Sng I, Fong CM, Lee HP

Cancer, 1996 May 1;77(9):1899-904.
PMID: 8646691

BACKGROUND: Non-Hodgkin's lymphoma has increased in incidence in many countries, particularly in the West. Advances in diagnostic methods and the understanding of the disease over time pose a challenge to the interpretation of these trends. The aim of this study was to determine if the disease has increased in Singapore, a newly industrialized Asian country, and to examine the possible factors that may account for any observed changes.
METHODS: Data from the population-based Singapore Cancer Registry for the period 1968 to 1992 were reviewed to determine time trends based on sex and ethnic group. The Poisson regression model was fitted to the cross-tabulated data to obtain the adjusted incidence density ratios.
RESULTS: A total of 1988 cases of non-Hodgkin's lymphoma were included in the analysis. There was an overall increase in incidence among both Chinese and Malaysians. However, the rate of increase was greater in females (age-standardized rate from 1.8 per 100,000 in 1968-1972 to 4.5 per 100,000 in 1988-1992) than in males (3.2 per 100,000 to 5.9 per 100,000 in the same time periods). Between ethnic groups, Malay females were at higher overall risk compared with their Chinese counterparts (incidence density ratio 1.32; 95% confidence interval, 1.08-1.61). Although a substantial proportion of patients diagnosed with Hodgkin's disease between 1968 and 1972 were reclassified on review, using present criteria, as having non-Hodgkin's lymphoma, it is unlikely that this, and other recent changes in histologic interpretation, could have accounted for an increase of this magnitude.
CONCLUSIONS: Non-Hodgkin's lymphoma has increased in incidence among the Chinese and Malay populations in Singapore. The pattern of increase differs from that of the common cancer sites, and suggests the need to look for environmental and genetic factors that have not yet been elucidated.

Matched MeSH terms: Hodgkin Disease/classification
A new hybrid intelligent system for accurate detection of Parkinson's disease

Hariharan M, Polat K, Sindhu R

Comput Methods Programs Biomed, 2014 Mar;113(3):904-13.
PMID: 24485390 DOI: 10.1016/j.cmpb.2014.01.004

Elderly people are commonly affected by Parkinson's disease (PD) which is one of the most common neurodegenerative disorders due to the loss of dopamine-producing brain cells. People with PD's (PWP) may have difficulty in walking, talking or completing other simple tasks. Variety of medications is available to treat PD. Recently, researchers have found that voice signals recorded from the PWP is becoming a useful tool to differentiate them from healthy controls. Several dysphonia features, feature reduction/selection techniques and classification algorithms were proposed by researchers in the literature to detect PD. In this paper, hybrid intelligent system is proposed which includes feature pre-processing using Model-based clustering (Gaussian mixture model), feature reduction/selection using principal component analysis (PCA), linear discriminant analysis (LDA), sequential forward selection (SFS) and sequential backward selection (SBS), and classification using three supervised classifiers such as least-square support vector machine (LS-SVM), probabilistic neural network (PNN) and general regression neural network (GRNN). PD dataset was used from University of California-Irvine (UCI) machine learning database. The strength of the proposed method has been evaluated through several performance measures. The experimental results show that the combination of feature pre-processing, feature reduction/selection methods and classification gives a maximum classification accuracy of 100% for the Parkinson's dataset.

Matched MeSH terms: Parkinson Disease/classification