scholarly journals Artificial intelligence in the respiratory sounds analysis and computer diagnostics of bronchial asthma

Author(s):  
Anton Gelman ◽  
Vladimir Sokolovsky ◽  
Evgeny G. Furman ◽  
Nataliya Kalinina ◽  
Gregory Furman

Using a database containing audio files of respiratory sound records of asthmatic patients and healthy patients, a method of computer-aided diagnostics based on the machine learning technique creation of neural networks, has been developed. The database contains 952 records of respiratory sounds of asthma patients at different stages of the disease, aged from several months to 47 years, and 167 records of volunteers. Records were carried out with a quiet breathing at four points: in the oral cavity, above the trachea, on the chest, the second intercostal space on the right side, and at a point on the back. The developed method of computer-aided diagnostics allows diagnosing bronchial asthma with high reliability: sensitivity of 89.3%, specificity of 86%, accuracy of about 88% and Youden index of 0.753. The program learned once makes it possible to diagnose bronchial asthma with high reliability regardless of patient's gender and age, a stage of disease, as well as the point of sound recording. The developed method can be used as an additional screening method for the diagnostics of bronchial asthma and serve as the basis for development of computer control methods, including remote control (telemedicine) of patients condition and the effectiveness of the applied drugs in real time.

2021 ◽  
Vol 80 (Suppl 1) ◽  
pp. 353.1-353
Author(s):  
E. Van Delft ◽  
D. Lopes Barreto ◽  
A. Van der Helm - van Mil ◽  
C. Alves ◽  
J. Hazes ◽  
...  

Background:The Rotterdam Early Arthritis Cohort (REACH) rule [1] and Clinical Arthritis RulE (CARE) [2] are both evidence-based and easy-to-use methods developed to identify the presence of inflammatory arthritis (IA) in patients suspected by their general practitioner (GP). However, the clinical utility of both models in daily clinical practice in an independent primary care setting has not yet been established. While developed for recognizing IA, we believe that it is also important that the broader spectrum of inflammatory rheumatic diseases (IRDs) is correctly classified from primary care, to facilitate appropriate referral towards outpatient rheumatology clinics.Objectives:The primary objective was to determine the diagnostic performance and clinical utility of the REACH and CARE referral rules in identifying IA in an independent population of unselected suspected patients from primary care. Secondly we will assess the diagnostic performance and clinical utility of both models in identifying IRDs.Methods:This prospective observational diagnostic study consisted of adults newly suspected by their GP for the need of referral to the rheumatology outpatient clinic of the Maasstad Hospital in Rotterdam. Primary outcome was IA, consisting of rheumatoid arthritis, axial spondylitis and psoriatic arthritis. Secondary outcome was IRD, defined as IA plus arthritis in systemic disorders such as systemic lupus erythematosus, systemic sclerosis and morbus sjögren. Rheumatologist diagnosis was used as gold standard. To evaluate the clinical performance of the REACH and CARE referral rules in this population, diagnostic accuracy measures were investigated using the Youden index (J) [3]. Moreover, a net benefit approach [4] was used to determine clinical utility of both rules when compared to usual care.Results:This study consisted of 250 patients (22.8% male) with a mean age of 50.8 years (SD 13.9 years). In total 42 (17%) patients were diagnosed with IA and 55 (22%) with an IRD. Figure 1 presents the diagnostic performance in IA (Figure 1A) and in IRD (Figure 1B). For the primary outcome, the REACH model shows an AUC of 0.72 (95% CI 0.64-0.80) and the optimal cut-off point is indicated (J). The CARE model shows an AUC of 0.82 (95% CI 0.75-0.88) and at J there is a somewhat higher sensitivity and specificity. When taking the broader spectrum of IRDs as outcome, the AUC was 0.66 (95% CI 0.58-0.74) for the REACH and 0.76 (95% CI 0.69-0.83) for the CARE model. The net benefit analysis with either IA or IRD as outcome showed that the CARE was of the highest clinical value when compared to usual care.Conclusion:Both the REACH and CARE model showed a good diagnostic performance for detecting IA in an independent population of unselected suspected patients from primary care. Although not specifically developed to recognize the entire spectrum of IRDs, the CARE shows a good performance in doing so. When evaluating clinical utility, we see that both rules have a net benefit in recognizing IA as well as IRDs compared to usual care, however the CARE shows superiority over the REACH. By using the CARE, over half of all suspected patients can be withheld from expensive outpatient rheumatology care, implied by the high specificity of 70%. These results support the idea that incorporating these easy-to-use methods into primary care could lead to providing patients the right care at the right place and improving value based health care.References:[1]ten Brinck RM, van Dijk BT, van Steenbergen HW, le Cessie S, Numans ME. Development and validation of a clinical rule for recognition of early inflammatory arthritis. BMJ Open; 2018: 8[2]Alves, C. Improving early referral of inflammatory arthritis. In Early detection of patients at risk for rheumatoid arthritis – a challenge for primary and secondary care; 2015: 27-38 Ridderkerk, the Netherlands.[3]Fluss R, Faraggi D, Reiser B. Estimation of the Youden Index and its associated cutoff point. Biom J; 2005: 47(4): 458-472[4]Vickers AJ, Elkin EB. Decision curve analysis: a novel method for evaluating prediction models. Med Decis Making; 2006: 26(6): 565-574Disclosure of Interests:None declared


2020 ◽  
Vol 11 ◽  
pp. 215145932096938
Author(s):  
Yuki Suzuki ◽  
Toshihiko Kasashima ◽  
Kazutoshi Hontani ◽  
Yasuhiro Yamamoto ◽  
Kanako Ito ◽  
...  

Introduction: The ongoing outbreak of novel coronavirus disease 2019 (COVID-19) is a worldwide problem. Although diagnosing COVID-19 in fracture patients is important for selecting treatment, diagnosing early asymptomatic COVID-19 is difficult. We describe herein a rare case of femoral intertrochanteric fracture concomitant with early asymptomatic novel COVID-19. Case presentation: An 87-year-old Japanese woman was transferred to our emergency room with a right hip pain after she fell. She had no fever, fatigue, or respiratory symptoms on admission and within the 14 days before presenting to our hospital, and no specific shadow was detected in chest X-ray. However, chest computed tomography (CT) was performed considering COVID-19 pandemic, and showed ground-glass opacities with consolidation in the dorsal segment of the right lower lung field. Then, qualitative real-time reverse-transcriptase-polymerase-chain-reaction (RT-PCR) was carried out and turned out to be positive. She was diagnosed right femoral intertrochanteric fracture with concomitant COVID-19 infection. Conservative treatment was applied to the fracture due to infection. After admission, fever and oxygen demand occurred but she recovered from COVID-19. Throughout the treatment period, no cross-infection from the patient was identified in our hospital. Conclusion: This case highlights the importance of considering chest CT as an effective screening method for infection on hospital admission in COVID-19-affected areas, especially in trauma patients with early asymptomatic novel COVID-19.


1935 ◽  
Vol 31 (1) ◽  
pp. 142-142
Author(s):  
К. Leriche ◽  
К. Fontain

Injection of 10 сс 1% Novocain in the right cervical ganglion stellatum gives excellent therapeutic effects in cases of angina pectoris, bronchial asthma and various algias in the upper limbs.


Author(s):  
Ismail Hakki Akgün

Objective: Tocreate an easy-to-use structure-based screening workflow using KNIME and open source software to prepare and screen virtual libraries in order to discover novel bioactive or drug molecules. Materials and Methods: In the preparation of the workflow we mentioned in the article KNIME version 4, AutoDock Vina, Pymol were used. KNIME plugins used in this study are RDKit KNIME Integration, ChemAxon/Infocom Marvin Extensions Feature, KNIME Python Integration, Lhasa Metabolism Feature, KNIME Ploty and KNIME JavaScript View. We have used Python3 and libraries in the python scripts through Anaconda installation. Results: A workflow that can work with a single click after making required adjustments which uses docking as structure-based screening method was created and tested. Conclusion: With the workflow we have created, it will be possible for researchers especially those who are working in the field of computer-aided drug design/development to create personalized molecule libraries, perform virtual screening, reporting the results in a short time with the least effort.


2021 ◽  
Vol 33 (3) ◽  
pp. 217
Author(s):  
Maria Efrinta Ginting ◽  
Rosiliwati Wihardja ◽  
Dyah Nindita Carolina

Introduction: Bronchial asthma patients use inhalation drugs as therapy to achieve a controlled asthma state. Inhaled corticosteroids and β2 agonists are the medication that is being used in this case. Prolonged use of inhalation drugs will affect the health of periodontal tissue. The effect of these drugs can reduce the periodontal defense mechanism and increase the risk of periodontal disease. This study aims to determine the periodontal clinical features of bronchial asthma patients using inhalation drugs. Method: This research was a descriptive study. The sample of the study were 22 females and 8 males bronchial asthma patients at the Community Lung Health Center of Bandung (Balai Besar Kesehatan Paru Masyarakat Bandung/BBKPM Bandung) who had been using inhalation drugs for at least one year. The periodontal clinical feature was assessed by employing a Community Periodontal Index (CPI) modified with probing the gingival sulcus to assess the presence of gingival bleeding, periodontal pocket, and loss of clinical attachment where then a periodontal status was obtained. The periodontal status data were then processed using the periodontitis case definitions from the Centers for Disease Control and Prevention/American Academy of Periodontology (CDC/AAP) to determine periodontal disease in asthmatics patients. Results: Clinical features of gingival bleeding were found in 26 asthmatic patients (86.7%), periodontal pockets in 18 asthmatic patients (60%), and loss of clinical attachment in 27 asthmatic patients (90%). Based on the CDC/AAP case definition, 23 asthmatic patients (76.7%) had periodontitis. Bronchial asthma patients who used inhalation drugs had a risk of periodontitis.Conclusion: Bronchial asthma patients who used inhalation drugs for at least one year had gingival bleeding and loss of clinical attachment and periodontal pocket.


2017 ◽  
Vol 29 (8) ◽  
pp. 1368-1377 ◽  
Author(s):  
Buyun Xu ◽  
Joan Liu-Shuang ◽  
Bruno Rossion ◽  
James Tanaka

A growing body of literature suggests that human individuals differ in their ability to process face identity. These findings mainly stem from explicit behavioral tasks, such as the Cambridge Face Memory Test (CFMT). However, it remains an open question whether such individual differences can be found in the absence of an explicit face identity task and when faces have to be individualized at a single glance. In the current study, we tested 49 participants with a recently developed fast periodic visual stimulation (FPVS) paradigm [Liu-Shuang, J., Norcia, A. M., & Rossion, B. An objective index of individual face discrimination in the right occipitotemporal cortex by means of fast periodic oddball stimulation. Neuropsychologia, 52, 57–72, 2014] in EEG to rapidly, objectively, and implicitly quantify face identity processing. In the FPVS paradigm, one face identity (A) was presented at the frequency of 6 Hz, allowing only one gaze fixation, with different face identities (B, C, D) presented every fifth face (1.2 Hz; i.e., AAAABAAAACAAAAD…). Results showed a face individuation response at 1.2 Hz and its harmonics, peaking over occipitotemporal locations. The magnitude of this response showed high reliability across different recording sequences and was significant in all but two participants, with the magnitude and lateralization differing widely across participants. There was a modest but significant correlation between the individuation response amplitude and the performance of the behavioral CFMT task, despite the fact that CFMT and FPVS measured different aspects of face identity processing. Taken together, the current study highlights the FPVS approach as a promising means for studying individual differences in face identity processing.


2021 ◽  
Vol 19 (8) ◽  
pp. 119-124
Author(s):  
Hayder Abdul-Amir Makki Al-Hindy ◽  
Ali Jihad Hemid Al-Athari ◽  
Mazin J. Mousa ◽  
Safa Jihad Hameed ◽  
Suhad Hafidh Obeed

Background: Bronchial asthma (BrA), recognized lately as an umbrella, covers various subtypes rather than only one disease. Asthma is a chronic inflammation of the airways, in which cytokines could play a crucial role in its pathogenesis. Hence, labors to progress noninvasive markers for asthma had centered through this era. Presently, the fractional exhaled nitric oxide (FeNO), serum C-reactive protein (CRP), and interleukin levels are emerging analytical biomarkers in this field. FeNO is a noninvasive and practical tool even in mild asthma. This study aimed to evaluate the utility of serum IL-1β and CRP together with fractional exhaled nitric oxide in the diagnosis of adult bronchial asthma. Method: The study was a case control, including 150-patients and 100-healthy controls. FeNO tests, measurements of plasma levels IL-1β and HS-CRP had undertaken for all the participants. The statistical data had examined by SPSS (V/27) for Windows. Descriptive data of the variables had compatibly used. A significance lower than or identical to 0.05 had intended. ROC curve examination of FeNO tests, IL-1β, and HS-CRP, to predict asthma from healthy control had applied. Results: there was a significant difference in the FeNo test, HS-CRP levels, and BMI, while no significant difference in all other variables between the groups. The FeNo results correlate positively, though not significantly, with the levels of IL-1β in asthmatic patients (> 0.05). There was a nonsignificant negative correlation between the FeNo results with the level of HSCRP. The accuracy, sensitivity, and specificity of the IL-1β to distinguish asthma were 68.6% and 58% at 95% CI [0.41-0.745], respectively, which was not significant (p>0.05). However, ROC analysis of HS-CRP revealed predictability for asthma patients (p-0.000), with higher accuracy, sensitivity, and specificity: 89.9%, and 68.1% at 95% CI [0.820-0.979], respectively. The FeNo tests revealed highly significant (0.000), high sensitivity, and specific (91% for both) with high 95% CI [0.938-1.000] predictability for asthma. Conclusion: The utility of circulating HS-CRP is more valuable than IL-1β when combined with fractional exhaled nitric oxide in the diagnosis of asthma. Novel biomarkers could improve the precision of this field.


2019 ◽  
Vol 5 (1) ◽  
pp. 38-41
Author(s):  
Md Haroon Ur Rashid ◽  
Md Rezaul Karim Chowdhury ◽  
Md Anwarul Hoque Faraji ◽  
Shamimur Rahman

Background: Asthma is one of the most common chronic diseases worldwide and has been increasing in prevalence over the last few decades. Magnesium (Mg++) has been shown to relax bronchial smooth muscle and influence the function of respiratory muscles. Hypomagnesemia has been associated with diminished respiratory muscle power. Objective: The purpose of the present study was to assess the serum Mg++ level in bronchial asthma patients during stable state and during exacerbation (Acute severe asthma). Methodology: This comparative cross-sectional study was conducted in the OPD and IPD of Department of Pulmonology at Enam Medical College and Hospital, Savar, Dhaka, Bangladesh and this study was carried out from January 2017 to December 2017 for a period of one year. Subjects were enrolled from Enam Medical College and Hospital. Patients diagnosed as bronchial asthma were taken as group A and healthy individuals were as a group B. The asthmatic patients were divided into groups those having chronic stable bronchial asthma and those having acute severe asthma. Results: Serum Mg++ level was significantly (p=0.000) lower in asthmatic patients 1.59±0.24 as compared with healthy controls (2.05±0.34) and significantly lower (p=0.006) in asthmatic patients during exacerbation (1.49±0.27) when compared to stable asthmatics (1.69±0.15). Asthmatic on ≥3 drugs has significantly (p=0.000) lower serum Mg++ 1.43±0.23 than those on <3 drugs (1.65±0.22). Conclusions: Serum Mg++ level was significantly lower in asthmatic patients during exacerbations compared with stable asthmatics. Journal of National Institute of Neurosciences Bangladesh, 2019;5(1): 38-41


Author(s):  
Jessica Thomson ◽  
Christoph M Rüegger ◽  
Elizabeth J Perkins ◽  
Prue M Pereira-Fantini ◽  
Olivia Farrell ◽  
...  

ObjectivesTo determine the regional ventilation characteristics during non-invasive ventilation (NIV) in stable preterm infants. The secondary aim was to explore the relationship between indicators of ventilation homogeneity and other clinical measures of respiratory status.DesignProspective observational study.SettingTwo tertiary neonatal intensive care units.PatientsForty stable preterm infants born <30 weeks of gestation receiving either continuous positive airway pressure (n=32) or high-flow nasal cannulae (n=8) at least 24 hours after extubation at time of study.InterventionsContinuous electrical impedance tomography imaging of regional ventilation during 60 min of quiet breathing on clinician-determined non-invasive settings.Main outcome measuresGravity-dependent and right–left centre of ventilation (CoV), percentage of whole lung tidal volume (VT) by lung region and percentage of lung unventilated were determined for 120 artefact-free breaths/infant (4770 breaths included). Oxygen saturation, heart and respiratory rates were also measured.ResultsVentilation was greater in the right lung (mean 69.1 (SD 14.9)%) total VT and the gravity-non-dependent (ND) lung; ideal–actual CoV 1.4 (4.5)%. The central third of the lung received the most VT, followed by the non-dependent and dependent regions (p<0.0001 repeated-measure analysis of variance). Ventilation inhomogeneity was associated with worse peripheral capillary oxygen saturation (SpO2)/fraction of inspired oxygen (FiO2) (p=0.031, r2 0.12; linear regression). In those infants that later developed bronchopulmonary dysplasia (n=25), SpO2/FiO2 was worse and non-dependent ventilation inhomogeneity was greater than in those that did not (both p<0.05, t-test Welch correction).ConclusionsThere is high breath-by-breath variability in regional ventilation patterns during NIV in preterm infants. Ventilation favoured the ND lung, with ventilation inhomogeneity associated with worse oxygenation.


2013 ◽  
Vol 468 ◽  
pp. 141-144
Author(s):  
Su Hua Chen ◽  
Yong Guang Liu ◽  
Xu Fang

Smart home system mainly consists of home networking, wireless local area network and external network, and with the advantages of low cost and high reliability, Zigbee wireless technology is the right choice for smart home system and the main part of home networking. The design of smart home system based on Zigbee is proposed, the Zigbeethe design process of the systemintelligent socket and data communication rule are elaborated. The system has been applied in smart community of Shaoxing Electric Power Bureau, which has good performances, high availability and reliability, better market prospects.


Sign in / Sign up

Export Citation Format

Share Document