An Intelligent System for Classification of Patients Suffering from Chronic Diseases

2011 ◽  
pp. 39-46
Author(s):  
Christos Bellos ◽  
Athanasios Papadopoulos ◽  
Dimitrios I. Fotiadis ◽  
Roberto Rosso
Keyword(s):  
Chronic Diseases ◽  
Intelligent System

scholarly journals Factors Associated with Frailty According to Gender of Older Adults Living Alone

Healthcare ◽  
2021 ◽  
Vol 9 (4) ◽  
pp. 475
Author(s):  
Hye-Young Jang ◽  
Ji-Hye Kim
Keyword(s):  
Older Adults ◽  
Depressive Symptoms ◽  
Nutritional Status ◽  
Chronic Diseases ◽  
Multinomial Logistic Regression ◽  
Living Alone ◽  
Factors Associated ◽  
Chi Squared ◽  
Korean Elderly

This study was conducted to identify the factors associated with frailty according to gender of older adults living alone in Korea. Data from the National Survey of the Living Conditions of Korean Elderly in 2017 were used. Participants were 2340 older adults who live alone. Frailty was determined based on the frailty criteria developed by van Kan et al. that consist of fatigue, resistance, ambulation, and illness. The collected data were analyzed using descriptive statistics, chi-squared test, t-test, Jonckheere–Terpstra test and multinomial logistic regression. Among the older men living alone, 47.7% were in the pre-frail and 5.1% were in the frail. On the other hand, 51.8% were in the pre-frail and 12.2% were in the frail among the older women living alone. The factors associated with frailty according to gender are as follows. In males, depressive symptoms, limitation in IADL, and number of medications in pre-frail; BMI, limitation in IADL, and number of chronic diseases in frail. In females, depressive symptoms, number of chronic diseases, age, and nutritional status in pre-frail; limitation in IADL, depressive symptoms, age, number of chronic diseases, number of medications, nutritional status in frail. Based on the findings of this study, it is considered necessary to approach frailty management considering gender as well as the classification of frailty.

scholarly journals Pathogenetic features of anemia of chronic diseases in patients with malignant neoplasms and rheumatic pathology

2020 ◽  
Vol 15 (4) ◽  
pp. 82-90
Author(s):  
V. T. Sakhin ◽  
M. A. Grigoriev ◽  
E. V. Kryukov ◽  
S. P. Kazakov ◽  
A. V. Sotnikov ◽  
...  
Keyword(s):  
Chronic Diseases ◽  
Transferrin Receptor ◽  
Control Group ◽  
Malignant Neoplasms ◽  
Mean Corpuscular Hemoglobin ◽  
Soluble Transferrin Receptor ◽  
Corpuscular Hemoglobin ◽  
Patients With Cancer ◽  
Tnf Α

Objective: to study the importance of cytokines, hepcidin, a soluble transferrin receptor, iron metabolism in the development of anemia of chronic diseases in patients with malignant neoplasms and rheumatic pathology, to identify the leading factors in the development of anemia for each of the studied groups and to develop a working classification of anemia of chronic diseases.Materials and methods. 63 patients with rheumatic pathology were examined. The study group included 41 (17 men/24 women, average age 53.4 ± 4 years) patients with anemia, the control group included 22 (9 men/13 women, age 49.3 ± 1.78 years) patients without anemia. The patients (n = 63) with stage II–IV malignant neoplasms were examined. The study group included 41 patients with anemia (34 men/7 women, age 67.1 ± 9.9 years), in the control group 22 patients without it (17 men/5 women, age 60.2 ± 14.9 years). The number of red blood cells, the hemoglobin level, hematocrit, mean corpuscular volume, mean corpuscular hemoglobin, mean corpuscular hemoglobin concentration, concentrations of serum iron, total iron binding capacity (TIBC), ferritin, transferrin, C-reactive protein (CRP), transferrin saturation index (TSI), and soluble transferrin receptor (sTfR), hepcidin, interleukin (IL) – 6, – 10, tumor necrosis factor-α (TNF-α) were determined. Mann – Whitney U Test was applied to check for statistically significant differences in study samples.Results. Compared with the control group, elevated concentrations of ferritin, CRP, hepcidin, sTfR and IL-6 (p <0.05) were found for patients with rheumatic pathology and anemia and no differences were found in the concentrations of iron, TIBC, TSI, transferrin. For patients with solid malignant neoplasms and anemia, lower concentrations of iron, TIBC, TSI and higher concentrations of CRP, hepcidin, sTfR, IL-6, IL-10, TNF-α (p <0.05) are shown in comparison with the control group and there were no differences in the concentrations of ferritin, transferrin (p >0.05).Conclusion. The multicomponent anemia genesis in patients with cancer and rheumatic pathology is shown. The contribution of each mechanism to the development of anemia may vary depending on the specific nosological form. In patients with cancer, functional iron deficiency, activation of IL-6, IL-10, TNF-α synthesis and an increase in hepcidin synthesis lead to the development of anemia of chronic diseases. In patients with a rheumatic profile and anemia, a more pronounced synthesis of hepcidin and an increase IL-6 concentration are indicated. A working version of the classification of anemia of chronic diseases based on the leading pathogenetic factor is proposed (with a predominant iron deficiency, with impaired regulatory mechanisms of erythropoiesis, with insufficient production of erythropoietin).

scholarly journals Soft Clustering for Enhancing the Diagnosis of Chronic Diseases over Machine Learning Algorithms

2020 ◽  
Vol 2020 ◽  
pp. 1-16 ◽  
Author(s):  
Theyazn H.H Aldhyani ◽  
Ali Saleh Alshebami ◽  
Mohammed Y. Alzahrani
Keyword(s):  
Machine Learning ◽  
Chronic Disease ◽  
Chronic Diseases ◽  
Learning Algorithms ◽  
Research Work ◽  
Machine Learning Algorithms ◽  
Upper Approximation ◽  
Healthcare Data ◽  
Ambiguous Objects

Chronic diseases represent a serious threat to public health across the world. It is estimated at about 60% of all deaths worldwide and approximately 43% of the global burden of chronic diseases. Thus, the analysis of the healthcare data has helped health officials, patients, and healthcare communities to perform early detection for those diseases. Extracting the patterns from healthcare data has helped the healthcare communities to obtain complete medical data for the purpose of diagnosis. The objective of the present research work is presented to improve the surveillance detection system for chronic diseases, which is used for the protection of people’s lives. For this purpose, the proposed system has been developed to enhance the detection of chronic disease by using machine learning algorithms. The standard data related to chronic diseases have been collected from various worldwide resources. In healthcare data, special chronic diseases include ambiguous objects of the class. Therefore, the presence of ambiguous objects shows the availability of traits involving two or more classes, which reduces the accuracy of the machine learning algorithms. The novelty of the current research work lies in the assumption that demonstrates the noncrisp Rough K-means (RKM) clustering for figuring out the ambiguity in chronic disease dataset to improve the performance of the system. The RKM algorithm has clustered data into two sets, namely, the upper approximation and lower approximation. The objects belonging to the upper approximation are favourable objects, whereas the ones belonging to the lower approximation are excluded and identified as ambiguous. These ambiguous objects have been excluded to improve the machine learning algorithms. The machine learning algorithms, namely, naïve Bayes (NB), support vector machine (SVM), K-nearest neighbors (KNN), and random forest tree, are presented and compared. The chronic disease data are obtained from the machine learning repository and Kaggle to test and evaluate the proposed model. The experimental results demonstrate that the proposed system is successfully employed for the diagnosis of chronic diseases. The proposed model achieved the best results with naive Bayes with RKM for the classification of diabetic disease (80.55%), whereas SVM with RKM for the classification of kidney disease achieved 100% and SVM with RKM for the classification of cancer disease achieved 97.53 with respect to accuracy metric. The performance measures, such as accuracy, sensitivity, specificity, precision, and F-score, are employed to evaluate the performance of the proposed system. Furthermore, evaluation and comparison of the proposed system with the existing machine learning algorithms are presented. Finally, the proposed system has enhanced the performance of machine learning algorithms.

scholarly journals Intelligent system for non-technical losses management in residential users of the electricity sector

2018 ◽  
Vol 38 (2) ◽  
pp. 52-60 ◽  
Author(s):  
Miguel Uparela Cantillo ◽  
Ruben González ◽  
Jamer Jiménez Mares ◽  
Christian Quintero Monroy
Keyword(s):  
Intelligent Systems ◽  
Intelligent System ◽  
Demand Forecasting ◽  
Electricity Sector ◽  
Caribbean Region ◽  
Self Organizing Maps ◽  
Detection Rates ◽  
Distribution Company

The identification of irregular users is an important assignment in the recovery of energy in the distribution sector. This analysis requires low error levels to minimize non-technical electrical losses in power grid. However, the detection of fraudulent users who have billing does not present a generalized methodology. This issue is complex and varies according to the case study. This paper presents a novel methodology to identify residential fraudulent users by using intelligent systems. The proposed intelligent system consists of three fundamental modules. The first module performs the classification of users with similar power consumption curves using self-organizing maps and genetic algorithms. The second module allows carrying out the monthly electricity demand forecasting through of recursive adjustment of ARIMA models. The third module performs the detection of fraudulent users through an artificial neural network for pattern recognition. For the design and validation of the proposed intelligent system, several tests were performed in each developed module. The database used for the design and evaluation of the modules was constructed with data supplied by the energy distribution company of the Colombian Caribbean Region. The results obtained by the proposed intelligent system show a better performance versus the detection rates obtained by the company.

Intelligent Bearing Diagnostics Using Wavelet Support Vector Machine

2014 ◽  
Vol 493 ◽  
pp. 337-342 ◽  
Author(s):  
Achmad Widodo ◽  
I. Haryanto ◽  
T. Prahasto
Keyword(s):  
Support Vector Machine ◽  
Input Data ◽  
Intelligent System ◽  
Feature Space ◽  
Rolling Element Bearing ◽  
Support Vector ◽  
Fault Diagnostics ◽  
Standard Data ◽  
Rolling Element

This paper deals with implementation of intelligent system for fault diagnostics of rolling element bearing. In this work, the proposed intelligent system was basically created using support vector machine (SVM) due to its excellent performance in classification task. Moreover, SVM was modified by introducing wavelet function as kernel for mapping input data into feature space. Input data were vibration signals acquired from bearings through standard data acquisition process. Statistical features were then calculated from bearing signals, and extraction of salient features was conducted using component analysis. Results of fault diagnostics are shown by observing classification of bearing conditions which gives plausible accuracy in testing of the proposed system.

Sign in / Sign up

Export Citation Format

Share Document