Dataset Information

Pattern recognition of forced oscillation technique measurement results using deep learning can identify asthmatic patients more accurately than setting reference ranges.

ABSTRACT: No official clinical reference values have been established for MostGraph, which measures total respiratory resistance and reactance using the forced oscillation technique, complicating result interpretation. This study aimed to establish a reference range for MostGraph measurements and examine its usefulness in discriminating participants with asthma from controls (participants without any respiratory diseases). The study also aimed to investigate the effectiveness of deep learning in discriminating between the two aforementioned groups. To establish reference ranges, the MostGraph measurements of healthy controls (n = 215) were power-transformed to distribute the data more normally. After inverse transformation, the mean ± standard deviation × 2 of the transformed values were used to establish the reference ranges. The number of measured items outside the reference ranges was evaluated to discriminate patients with asthma (n = 941) from controls. Additionally, MostGraph measurements were evaluated using deep learning. Although reference ranges were established, patients with asthma could not be discriminated from controls. However, with deep learning, we could discriminate between the two groups with 78% accuracy. Therefore, deep learning, which considers multiple measurements as a whole, was more effective in interpreting MostGraph measurement results than use of reference ranges, which considers each result individually.

SUBMITTER: Funaita C

PROVIDER: S-EPMC10703832 | biostudies-literature | 2023 Dec

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Pattern recognition of forced oscillation technique measurement results using deep learning can identify asthmatic patients more accurately than setting reference ranges.

Funaita Chiune C Furuie Wakaba W Koike Fumika F Oyama Saki S Endo Junji J Otani Yoshio Y Ichikawa Yuri Y Ito Minako M Nakamura Yoichi Y Komatuzaki Keiko K Hirata Akira A Miyazaki Yasunari Y Sumi Yuki Y

Scientific reports 20231207 1

No official clinical reference values have been established for MostGraph, which measures total respiratory resistance and reactance using the forced oscillation technique, complicating result interpretation. This study aimed to establish a reference range for MostGraph measurements and examine its usefulness in discriminating participants with asthma from controls (participants without any respiratory diseases). The study also aimed to investigate the effectiveness of deep learning in discrimin ...[more]

PMID: 38062060

Similar Datasets

Project description:IntroductionPerforming lung function test in geriatric patients has never been an easy task. With well-established evidence indicating impaired small airway function and air trapping in patients with geriatric COPD, utilizing forced oscillation technique (FOT) as a supplementary tool may aid in the assessment of lung function in this population.AimsTo study the use of FOT in the assessment of airflow limitation and air trapping in geriatric COPD patients.Study designA cross-sectional study in a public hospital in Hong Kong. ClinicalTrials.gov ID: NCT01553812.MethodsGeriatric patients who had spirometry-diagnosed COPD were recruited, with both FOT and plethysmography performed. "Resistance" and "reactance" FOT parameters were compared to plethysmography for the assessment of air trapping and airflow limitation.ResultsIn total, 158 COPD subjects with a mean age of 71.9±0.7 years and percentage of forced expiratory volume in 1 second of 53.4±1.7 L were recruited. FOT values had a good correlation (r=0.4-0.7) to spirometric data. In general, X values (reactance) were better than R values (resistance), showing a higher correlation with spirometric data in airflow limitation (r=0.07-0.49 vs 0.61-0.67), small airway (r=0.05-0.48 vs 0.56-0.65), and lung volume (r=0.12-0.29 vs 0.43-0.49). In addition, resonance frequency (Fres) and frequency dependence (FDep) could well identify the severe type (percentage of forced expiratory volume in 1 second <50%) of COPD with high sensitivity (0.76, 0.71) and specificity (0.72, 0.64) (area under the curve: 0.8 and 0.77, respectively). Moreover, X values could stratify different severities of air trapping, while R values could not.ConclusionFOT may act as a simple and accurate tool in the assessment of severity of airflow limitation, small and central airway function, and air trapping in patients with geriatric COPD who have difficulties performing conventional lung function test. Moreover, reactance parameters were better than resistance parameters in correlation with air trapping.

Project description:Background: The bronchial provocation test (BPT) performed by using the forced oscillation technique (FOT) is cooperated without forced expiratory effort. However, a comparison of the application value and safety of BPTs measured by using the FOT and the standardized dosimeter method is lacking, which limits its clinical practice. Objective: We aimed to analyze the diagnostic value and safety of the BPT as measured by the FOT in patients with asthma and in healthy subjects. Methods: This was a randomized cross-over clinical study. Airway responsiveness was measured by using the FOT and the aerosol provocation system (APS) dosimeter method in all the participants. The between-test interval was 24 hours. The diagnostic value and safety of the two tests were analyzed. Results: Asthma control status was assessed based on ACT scores, and patients with asthma (including 27 uncontrolled, 34 partially controlled, and 32 controlled) were collected, and 69 healthy subjects were recruited. Receiver operating characteristic curves revealed slightly superior screening capability of cumulative dose of methacholine causing a 20% decrease (PD20)-forced expiratory volume in the first second of expiration when measured by using the APS-dosimeter method (area under the curve [AUC] 0.981 [95% confidence interval {CI}, 0.952-1.000]) over that of cumulative dose of inhaled methacholine at the inflection point when respiratory resistance began to increase continuously (Dmin) by using the FOT (AUC 0.959 [95% CI, 0.924-0.994]). The sensitivity and specificity were 98.9% and 98.6%, respectively, with the APS-dosimeter method, and 100% and 87.0%, respectively, with the FOT. It took an average of 9.0 minutes (range, 6.0-11.0 minutes) when using the FOT and an average of 17.0 minutes (range, 14.0-25.0 minutes) when using APS-dosimeter method (p < 0.01) in all the participants. The measurement time for the FOT was reduced by 47.1% than the APS-dosimeter. The incidence rate of the adverse events with the FOT was slightly higher than that with the APS-dosimeter method (p < 0.05). Both tests were well tolerated. No serious adverse event was found. Conclusion: The FOT, characterized as being simple, safe, and time saving, could be used to assess airway hyperresponsiveness in patients with asthma and worthy of clinical application.

Project description:BackgroundThe current reference test for the detection of respiratory abnormalities in asbestos-exposed workers is spirometry. However, spirometry has several shortcomings that greatly affect the efficacy of current asbestos control programs. The forced oscillation technique (FOT) represents the current state-of-the-art technique in the assessment of lung function. This method provides a detailed analysis of respiratory resistance and reactance at different oscillatory frequencies during tidal breathing. Here, we evaluate the FOT as an alternative method to standard spirometry for the early detection and quantification of respiratory abnormalities in asbestos-exposed workers.Methodology/principal findingsSeventy-two subjects were analyzed. The control group was composed of 33 subjects with a normal spirometric exam who had no history of smoking or pulmonary disease. Thirty-nine subjects exposed to asbestos were also studied, including 32 volunteers in radiological category 0/0 and 7 volunteers with radiological categories of 0/1 or 1/1. FOT data were interpreted using classical parameters as well as integer (InOr) and fractional-order (FrOr) modeling. The diagnostic accuracy was evaluated by investigating the area under the receiver operating characteristic curve (AUC). Exposed workers presented increased obstruction (resistance p<0.001) and a reduced compliance (p<0.001), with a predominance of obstructive changes. The FOT parameter changes were correlated with the standard pulmonary function analysis methods (R = -0.52, p<0.001). Early respiratory abnormalities were identified with a high diagnostic accuracy (AUC = 0.987) using parameters obtained from the FrOr modeling. This accuracy was significantly better than those obtained with classical (p<0.001) and InOr (p<0.001) model parameters.ConclusionsThe FOT improved our knowledge about the biomechanical abnormalities in workers exposed to asbestos. Additionally, a high diagnostic accuracy in the diagnosis of early respiratory abnormalities in asbestos-exposed workers was obtained. This makes the FOT particularly useful as a screening tool in the context of asbestos control and elimination. Moreover, it can facilitate epidemiological research and the longitudinal follow-up of asbestos exposure and asbestos-related diseases.

Project description:Intravascular fluid shifts, mechanical ventilation and inhalational anesthetic drugs may contribute to intraoperative lung injury. This prospective observational study measured the changes in respiratory impedance resulting from inhalational anesthesia and mechanical ventilation in adults undergoing transurethral resection of bladder tumors. The components of respiratory impedance (resistance and reactance) were measured using the forced oscillation technique (FOT).Respiratory resistance at 5 Hz (R5) and 20 Hz (R20), respiratory reactance at 5 Hz (X5), resonant frequency (Fres) and area of low reactance (ALX) were measured before and immediately after surgery in 30 adults. In addition, preoperative vital capacity (VC), forced vital capacity (FVC) and forced expiratory volume in the first second (FEV1.0) were evaluated using spirometry. All patients were intubated with an endotracheal tube and were mechanically ventilated, with anesthesia maintained with sevoflurane. Pre- and postoperative FOT measurements were compared using Wilcoxon paired rank tests, and the relationships between FOT measurements and preoperative spirometry findings were determined by Spearman's rank correlation analysis.Twenty-six patients were included in the final analysis: postoperative FOT could not be performed in four because of postoperative restlessness or nausea. The mean duration of surgery was 47 min. All components of respiratory resistance deteriorated significantly over the course of surgery, with median increases in R5, R20, and R5-R20 of 1.67 cmH2O/L/s (p < 0.0001), 1.28 cmH2O/L/s (p < 0.0001) and 0.46 cmH2O/L/s (p = 0.0004), respectively. The components of respiratory reactance also deteriorated significantly, with X5 decreasing 1.7 cmH2O/L/s (p < 0.0001), Fres increasing 5.57 Hz (p < 0.0001) and ALX increasing 10.51 cmH2O/L/s (p < 0.0001). There were statistically significant and directly proportional relationships between pre- and postoperative X5 and %VC, %FEV1.0 and %FVC, with inverse relationships between pre- and postoperative Fres and ALX.All components measured by FOT deteriorated significantly after a relatively short period of general anesthesia and mechanical ventilation. All components of resistance increased. Of the reactance components, X5 decreased and Fres and ALX increased. Pre- and postoperative respiratory reactance correlated with parameters measured by spirometry.JMA-IIA00136 .

Project description:BackgroundA single laboratory range for all individuals may fail to take into account underlying physiologic differences based on sex and genetic factors. We hypothesized that laboratory distributions differ based on self-reported sex and ethnicity and that ranges stratified by these factors better correlate with postoperative mortality and acute kidney injury (AKI).MethodsResults from metabolic panels, complete blood counts, and coagulation panels for patients in outpatient encounters were identified from our electronic health record. Patients were grouped based on self-reported sex (2 groups) and ethnicity (6 groups). Stratified ranges were set to be the 2.5th/97.5th percentile for each sex/ethnic group. For patients undergoing procedures, each patient/laboratory result was classified as normal/abnormal using the stratified and nonstratified (traditional) ranges; overlap in the definitions was assessed between the 2 classifications by looking for the percentage of agreement in result classifications of normal/abnormal using the 2 methods. To assess which definitions of normal are most associated with adverse postoperative outcomes, the odds ratio (OR) for each outcome/laboratory result pair was assessed, and the frequency that the confidence intervals of ORs for the stratified versus nonstratified range did not overlap was examined.ResultsAmong the 300 unique combinations (race × sex × laboratory type), median proportion overlap (meaning patient was either "normal" or "abnormal" for both methodologies) was 0.86 [q1, 0.80; q3, 0.89]. All laboratory results except 6 overlapped at least 80% of the time. The frequency of overlap did not differ among the racial/ethnic groups. In cases where the ORs were different, the stratified range was better associated with both AKI and mortality (P < .001). There was no trend of bias toward any specific sex/ethnic group.ConclusionsBaseline "normal" laboratory values differ across sex and ethnic groups, and ranges stratified by these groups are better associated with postoperative AKI and mortality as compared to the standard reference ranges.

Project description:BackgroundThe number of children with obesity has increased in Saudi Arabia, which is a significant public health concern. Early diagnosis of childhood obesity and screening of the prevalence is needed using a simple in situ method. This study aims to generate statistical equations to predict body fat percentage (BF%) for Saudi children by employing machine learning technology and to establish gender and age-specific body fat reference range.MethodsData was combined from two cross-sectional studies conducted in Saudi Arabia for 1,292 boys and girls aged 8-12 years. Body fat was measured in both studies using bio-electrical impedance analysis devices. Height and weight were measured and body mass index was calculated and classified according to CDC 2,000 charts. A total of 603 girls and 374 boys were randomly selected for the learning phase, and 153 girls and 93 boys were employed in the validation set. Analyses of different machine learning methods showed that an accurate, sensitive model could be created. Two regression models were trained and fitted with the construction samples and validated. Gradient boosting algorithm was employed to achieve a better estimation and produce the equations, then the root means squared error (RMSE) equation was performed to decrease the error. Body fat reference ranges were derived for children aged 8-12 years.ResultsFor the gradient boosting models, the predicted fat percentage values were more aligned with the true value than those in regression models. Gradient boosting achieved better performance than the regression equation as it combined multiple simple models into a single composite model to take advantage of that weak classifier. The developed predictive model archived RMSE of 3.12 for girls and 2.48 boys. BF% and Fat mass index charts were presented in which cut-offs for 5th, 75th and 95th centiles are used to define 'under-fat', 'normal', 'overfat' and 'subject with obesity'.ConclusionMachine learning models could represent a significant advancement for investigators studying adiposity-related issues in children. These models and newly developed centile charts could be useful tools for the estimation and classification of BF%.

Dataset Information

Pattern recognition of forced oscillation technique measurement results using deep learning can identify asthmatic patients more accurately than setting reference ranges.

Publications

Pattern recognition of forced oscillation technique measurement results using deep learning can identify asthmatic patients more accurately than setting reference ranges.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets