Wyniki wyszukiwania - BazTech

1

A novel deep learning-based approach for prediction of neonatal respiratory disorders from chest X-ray images

Erdogan Yildirim Ayse, Canayaz Murat

Biocybernetics and Biomedical Engineering

|

2023

|

Vol. 43, no. 4

635--655

EN

In recent years, many diseases can be diagnosed in a short time with the use of deep learning models in the field of medicine. Most of the studies in this area focus on adult or pediatric patients. However, deep learning studies for the diagnosis of diseases in neonatal are not sufficient. Also, since it is known that respiratory disorders such as pneumonia have a large place among the causes of neonatal death, early and accurate diagnosis of respiratory diseases in neonates is crucial. For this reason, our study aims to detect the presence of respiratory disorders through the developed deep-learning approach using chest X-ray images of patients hospitalized in the Neonatal Intensive Care Unit. Accordingly, the enhanced version of C+EffxNet, the new hybrid deep learning model, is designed to predict respiratory disorders in neonates. In this version, the features selected by PCA are combined as 100, 200, and 300, then the binary classification process was carried out. In the study, the accuracy and kappa value were obtained as 0.965, and 0.904, respectively before feature merging, while these values were obtained as 0.977, and 0.935 after feature merging. This method, which was developed for the diagnosis of respiratory disorders in neonates, was also subsequently applied to a chest X-ray dataset that is frequently used in the literature for the diagnosis of pediatric pneumonia. For this data set, while the accuracy was 0.992, the kappa value was 0.982. The results obtained confirm the success of the proposed method for both datasets.

2

Comparative Analysis of Classifiers for the Assessment of Respiratory Disorders Using Speech Parameters

Shrivastava Poonam, Tripathi Neeta, Singh Bikesh Kumar, Dewangan Bhupesh Kumar

Archives of Acoustics

|

2023

|

Vol. 48, No. 1

13--24

EN

Non-invasive techniques for the assessment of respiratory disorders have gained increased importance in recent years due to the complexity of conventional methods. In the assessment of respiratory disorders, machine learning may play a very essential role. Respiratory disorders lead to variation in the production of speech as both go hand in hand. Thus, speech analysis can be a useful means for the pre-diagnosis of respiratory disorders. This article aims to develop a machine learning approach to differentiate healthy speech from speech corresponding to different respiratory disorders (affected). Thus, in the present work, a set of 15 relevant and efficient features were extracted from acquired data, and classification was done using different classifiers for healthy and affected speech. To assess the performance of different classifiers, accuracy, specificity (Sp), sensitivity (Se), and area under the receiver operating characteristic curve (AUC) was used by applying both multi-fold cross-validation methods (5-fold and 10-fold) and the holdout method. Out of the studied classifiers, decision tree, support vector machine (SVM), and k-nearest neighbor (KNN) were found more appropriate in providing correct assessment clinically while considering 15 features as well as three significant features (Se > 89%, Sp > 89%, AUC> 82%, and accuracy > 99%). The conclusion was that the proposed classifiers may provide an aid in the simple assessment of respiratory disorders utilising speech parameters with high efficiency. In the future, the proposed approach can be evaluated for the detection of specific respiratory disorders such as asthma, COPD, etc.

3

Coal Dust Exposure Characteristic and Impact on Respiratory Impairment from Coal Unloading Station in Palembang, South Sumatra, Indonesia

Wahyudi Arie, Zulkifli Hilda, Arita Susila, Sitorus Rico Januar

Journal of Ecological Engineering

|

2022

|

Vol. 23, nr 7

113--120

EN

Coal hauling, loading, and transportation activities impacted the emergence of coal dust which is harmful to health. The coal dust exposed from coal unloading stations and coal waterway transportation has escaped attention. This study aimed to determine the characteristics of coal dust, the influence of climate parameters on the spread of coal dust, and its impact on the health of children under five in the exposed area. The coal dust characteristics and concentrations of PM PM2.5 and PM10 were analyzed from ten points spread across three mining companies (A, B, and C). The effect of climate parameters on PM2.5 and PM10 was tested statistically. The results of the chemical analysis revealed that coal dust was dominated by the high content of Si, Al, S, and Fe. The concentration of PM2.5 and PM10 is affected by wind speed. PM2.5 and PM10 can exceed the annual threshold value, which has caused a high incidence of respiratory problems in two sub-districts, namely Makrayu and Gandus.

4

Respiratory Disorders - Measuring Method and Equipment

Nitkiewicz S., Barański R., Kukwa A., Zając A.

Metrology and Measurement Systems

|

2018

|

Vol. 25, nr 1

187--202

EN

Respiratory disorders can occur from birth and accompany us throughout life. Very relevant and timely diagnosis of dysfunction is very important. Many currently performed examinations are not sufficient and do not give a full view of the cause of the disorder. In this paper the authors give several methods and pieces of equipment to do so. Furthermore, the proposed solution enables precise quantification of individual breaths, as well as their entire series. In addition to the above mentioned equipment, the authors present an example of software that works with the adopted solution. The considerations are illustrated with an example, along with calculations made using the authors’ software.

5

Model for predicting peak expiratory flow rate of Nigerian workers in a cement factory in Itori, Ogun State, Nigeria

Ismaila S. O., Akanbi O. G., Olaoniye W.

International Journal of Occupational Safety and Ergonomics

|

2015

|

Vol. 21, No. 4

547--550

EN

The main aim of the study was to propose a model for predicting the peak expiratory flow rate (PEFR) of Nigerian workers in a cement factory. Sixty randomly selected non-smoker and healthy workers (30 in production sections, 30 in the administrative section of the factory) participated in the study. Their physical characteristics and PEFR were measured. Multiple correlations using SPSS version 16.0 were performed on the data. The values of PEFR, using the obtained model, were compared with the measured values using a two-tailed t test. There were positive correlations among age, height and PEFR. A prediction equation for PEFR based on age, height, weight and years of exposure (experience) was obtained with R2 = .843 (p < 0.001). The developed model will be useful for the management in determining PEFR of workers in the cement industry for possible medical attention.

6

Analiza wpływu wybranych czynników na entropię wieloskalową rytmu pracy serca w populacji badanych pochodzącej z laboratorium snu

Radliński J., Baran Z., Tomalak W.

Pomiary Automatyka Kontrola

|

2012

|

R. 58, nr 4

365-368

PL

Celem pracy jest wstępna analiza wpływu czynników: fizjologicznego - wieku oraz chorobowych - zaburzeń oddychania, na entropię wieloskalową (Multiscale Entropy) rytmu pracy serca. W pracy dokonano analizy wpływu wieku na dwóch szerokich grupach badanych: osobach zdrowych (wiek od 1,5 do 63 lat) oraz grupie w wąskim przedziale wiekowym (40-50 lat) o różnym zakresie występowania zaburzeń oddychania w czasie snu (wskaźnik liczby zaburzeń oddychania RDI - Respiratory Disturbance Index 0,5 - 111 1/h). Wykazano wpływ wieku na wartość entropii (zmniejszanie), szczególnie w grupie osób dorosłych, oraz wpływ zaburzeń oddychania i zjawisk im towarzyszących (wybudzenia).

EN

High costs and complication of standard polysomnography (PSG) lead to attempts to develop cheaper and less complicated methods. The analysis of heart rate complexity using non-linear dynamics methods seems to be promising, however the dynamics of heart rate is biased by several physiological factors. The aim of that study was to check the influence of a physiological factor - age and of respiratory disorders during sleep on heart rate variability analysed by multiscale entropy (MSE). The two groups were selected from archived measurements from the Sleep Laboratory of Institute for TBC and Lung Diseases Rabka Branch: a healthy group and a group of semi-constant age but without limitations to those disorders (Table 1). In both groups the full night diagnostics PSG according to the American Academy of Sleep Medicine (AASM) rules was performed. The R-R intervals were detected in the recorded ECG signal (250Hz), and the multiscale entropy (Goldberg's MSE) was calculated. We found high correlation between the entropy and age (Figs. 1, 2, 3) in adults, however in the children group (age<15) there was no such relation. Similar results were found in analysis of the influence of respiratory disorders on the RR time series entropy (Figs. 4, 5, 6, 7). The results lead to a conclusion that heart rate complexity described with use of the MSE analysis is strongly biased by age. MSE could also detect changes in RR time series associated with respiratory disorders during sleep. The further investigations should be performed to