Clinical analysis of the "small plateau" sign on the flow-volume curve followed by deep learning automated recognition

Influence of Achalasia on the Spirometry Flow-Volume Curve and Peak Expiratory Flow

BACKGROUND

Achalasia is an esophageal motor disorder characterized by aperistalsis and the failure of the relaxation of the lower esophageal sphincter. We want to find out whether external compression or recurrent micro-aspiration of undigested food has a functional effect on the airway.

METHODS

The aim of this research was to analyze the influence of achalasia on the peak expiratory flow and flow-volume curve. All of the 110 patients performed spirometry.

RESULTS

The mean diameter of the esophagus was 5.4 ± 2.1 cm, and nine of the patients had mega-esophagus. Seven patients had a plateau in the inspiratory part of the flow-volume curve, which coincides with the patients who had mega-esophagus. The rest of the patients had a plateau in the expiration part of the curve. The existence of a plateau in the diameter of the esophagus of more than 5 cm was significant (p 0.003). Statistical significance between the existence of a plateau and a lowered PEF (PEF < 80) has been proven (p 0.001). Also, a statistical significance between the subtype and diameter of more than 4 cm has been proved. There was no significant improvement in the PEF values after operation. In total, 20.9% of patients had a spirometry abnormality finding. The frequency of the improvement in the spirometry values after surgery did not differ significantly by achalasia subtype. The improvement in FEV1 was statistically significant compared to the FVC values.

CONCLUSIONS

Awareness of the influence of achalasia on the pulmonary parameters is important because low values of PEF with a plateau on the spirometry loop can lead to misdiagnosis. The recognition of various patterns of the spirometry loop may help in identifying airway obstruction caused by another non-pulmonary disease such as achalasia.

Body mass index affects spirometry indices in patients with chronic obstructive pulmonary disease and asthma

Background: Body mass index (BMI) is known to affect the outcomes of spirometry indices. However, its association with spirometry indices in COPD and asthma is less studied. We aimed to explore the impact of BMI on these patients. Methods: Patients with COPD or asthma who completed bronchodilator tests (BDTs) between 2017 and 2021 were reviewed. Spirometry indices were compared among patients with COPD or asthma that were subclassified as underweight (BMI< 18.5 kg/m2), normal weight (≥18.5 to < 25), overweight (≥ 25 to < 30), and obesity (≥ 30). Results. Results: Analysis was conducted on 3891 COPD patients (age:66.5 ± 7.8 years) and 1208 asthma patients (age:59.7 ± 7.5 years). COPD patients classified as underweight demonstrated significantly lower values of pre-and post FEV1 (L, %), pre-and post FVC (L, %), and pre- and post-FEV1/FVC (all p < 0.05). In contrast, COPD patients who were overweight or obese exhibited higher values for pre-and post FEV1 (L, %), and pre and post FEV1/FVC (all p < 0.05). Within the cohort of asthma patients, those underweight had lower pre-and post FEV1 (L, %), pre and post FVC (L, %), pre and post FEV1/FVC %. Obese asthma patients displayed higher pre and post FEV1/FVC (all p < 0.05). Conclusion: Significant BMI category differences in spirometry indices can be seen in patients with COPD or asthma. Both underweight and obesity could affect the diagnosis and severity of these diseases. Recognizing these effects is essential to better management and diagnosis of these patients.

Deep Learning-Based Analytic Models Based on Flow-Volume Curves for Identifying Ventilatory Patterns

Introduction

Spirometry, a pulmonary function test, is being increasingly applied across healthcare tiers, particularly in primary care settings. According to the guidelines set by the American Thoracic Society (ATS) and the European Respiratory Society (ERS), identifying normal, obstructive, restrictive, and mixed ventilatory patterns requires spirometry and lung volume assessments. The aim of the present study was to explore the accuracy of deep learning-based analytic models based on flow–volume curves in identifying the ventilatory patterns. Further, the performance of the best model was compared with that of physicians working in lung function laboratories.

Methods

The gold standard for identifying ventilatory patterns was the rules of ATS/ERS guidelines. One physician chosen from each hospital evaluated the ventilatory patterns according to the international guidelines. Ten deep learning models (ResNet18, ResNet34, ResNet18_vd, ResNet34_vd, ResNet50_vd, ResNet50_vc, SE_ResNet18_vd, VGG11, VGG13, and VGG16) were developed to identify patterns from the flow–volume curves. The patterns obtained by the best-performing model were cross-checked with those obtained by the physicians.

Results

A total of 18,909 subjects were used to develop the models. The ratio of the training, validation, and test sets of the models was 7:2:1. On the test set, the best-performing model VGG13 exhibited an accuracy of 95.6%. Ninety physicians independently interpreted 100 other cases. The average accuracy achieved by the physicians was 76.9 ± 18.4% (interquartile range: 70.5–88.5%) with a moderate agreement (κ = 0.46), physicians from primary care settings achieved a lower accuracy (56.2%), while the VGG13 model accurately identified the ventilatory pattern in 92.0% of the 100 cases (P &lt; 0.0001).

Conclusions

The VGG13 model identified ventilatory patterns with a high accuracy using the flow–volume curves without requiring any other parameter. The model can assist physicians, particularly those in primary care settings, in minimizing errors and variations in ventilatory patterns.