The use of a neural network to detect upper airway obstruction caused by goiter

Effect of Thyroidectomy on Tracheal Remodeling and Airway Physiology in Apparently Asymptomatic Patients with Goiter: A Prospective Study

BACKGROUND

Tracheal airflow limitation is frequently reported in patients with goiter but is severely underestimated, and studies on how goiter and its treatment affect trachea are scarce. Moreover, the choice of the optimal treatment for individual patient with asymptomatic goiter is not straightforward. Therefore, in this study we aim to investigate the effect of goiter and subsequent thyroidectomy on tracheal anatomy and change in airflow in asymptomatic patient with goiter.

METHODS

Seventy patients undergoing total/hemithyroidectomy (TT/HT) from Feb 2020 to Feb 2021 satisfying inclusion criteria were enrolled in the study. Neck radiograph (NR) and forced spirometry (FS) were performed preoperatively and on postoperative day 10 and 6 weeks and 3 months.

RESULTS

Out of 70 patients, 84.3% patients were female, and mean duration and weight of goiter were 54.7 months and 72.21 gm, respectively. Of 70 patients, 57 were of benign pathology. Significant improvement in tracheal compression with moderate improvement in deviation was observed after surgery. Preoperative spirometry showed significant reduction in almost all parameters. After surgery, a weak improvement was observed at postoperative day 10 and 6 weeks; however, significant improvement in FEV1, PEFR, FEV1/FEV0.5, and FEF50%/FIF50% was observed at postoperative 3 months. Patient with right sided and those with ≥ 8 mm deviation were associated with poorer pulmonary function. Weak correlation was observed between neck NR and spirometry parameters. Weight of the thyroid gland significantly correlated with ratio of MVV/FEV1.

CONCLUSION

Patients with asymptomatic goiter can have significant abnormal changes in airflow as evidenced by FS and NR. Thyroidectomy is followed by gradual restoration of tracheal deviation and compression with significant improvement in pulmonary airflow.

Airway Management in a Patient with Retrosternal Goiter: A Context-Sensitive Airway Management Strategy

Retrosternal extension of the goiter can cause compression of the trachea, esophagus and major blood vessels. Airway management is indeed a challenge in patients with airway obstructive signs and symptoms and it is based on the severity of the patient's clinical symptoms, availability of airway equipments, familiarity and expertise. We encountered a patient with retrosternal goiter with tracheal compression, presented for surgery required pediatric Fiber-Optic Bronchoscope (FOB) for securing the airway. A 45 year female patient presented with a swelling in front of the neck for 6 months. Recently, she developed intermittent stridor which was aggravated by lying supine. In computed tomography, there was a retrosternal extension of thyroid gland into superior mediastinum causing tracheal compression and narrowing (80%). Awake fiber-optic intubation with paediatric FOB was used to secure the airway before induction of anaesthesia. Paediatric FOB can be useful to secure airway in patients with tracheal compression and narrowing.

Deep Learning for Automatic Upper Airway Obstruction Detection by Analysis of Flow-Volume Curve

BACKGROUND

Due to the similar symptoms of upper airway obstruction to asthma, misdiagnosis is common. Spirometry is a cost-effective screening test for upper airway obstruction and its characteristic patterns involving fixed, variable intrathoracic and extrathoracic lesions. We aimed to develop a deep learning model to detect upper airway obstruction patterns and compared its performance with that of lung function clinicians.

METHODS

Spirometry records were reviewed to detect the possible condition of airway stenosis. Then they were confirmed by the gold standard (e.g., computed tomography, endoscopy, or clinic diagnosis of upper airway obstruction). Images and indices derived from flow-volume curves were used for training and testing the model. Clinicians determined cases using spirometry records from the test set. The deep learning model evaluated the same data.

RESULTS

Of 45,831 patients' spirometry records, 564 subjects with curves suggesting upper airway obstruction, after verified by the gold standard, 351 patients were confirmed. These cases and another 200 cases without airway stenosis were used as the training and testing sets. 432 clinicians evaluated 20 cases of each of the three patterns and 20 no airway stenosis cases (n = 80). They assigned an accuracy of 41.2% (±15.4) (interquartile range: 27.5-52.5%), with poor agreements (κ = 0.12). For the same cases, the model generated a correct detection of 81.3% (p < 0.0001).

CONCLUSIONS

Deep learning could detect upper airway obstruction patterns from other classic patterns of ventilatory defects with high accuracy, whereas clinicians presented marked errors and variabilities. The model may serve as a support tool to enhance clinicians' correct diagnosis of upper airway obstruction using spirometry.

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

BACKGROUND

Small plateau (SP) on the flow-volume curve was found in parts of patients with suspected asthma or upper airway abnormalities, but it lacks clear scientific proof. Therefore, we aimed to characterize its clinical features.

METHODS

We involved patients by reviewing the bronchoprovocation test (BPT) and bronchodilator test (BDT) completed between October 2017 and October 2020 to assess the characteristics of the sign. Patients who underwent laryngoscopy were assigned to perform spirometry to analyze the relationship of the sign and upper airway abnormalities. SP-Network was developed to recognition of the sign using flow-volume curves.

RESULTS

Of 13,661 BPTs and 8,168 BDTs completed, we labeled 2,123 (15.5%) and 219 (2.7%) patients with the sign, respectively. Among them, there were 1,782 (83.9%) with the negative-BPT and 194 (88.6%) with the negative-BDT. Patients with SP sign had higher median FVC and FEV₁% predicted (both P < .0001). Of 48 patients (16 with and 32 without the sign) who performed laryngoscopy and spirometry, the rate of laryngoscopy-diagnosis upper airway abnormalities in patients with the sign (63%) was higher than those without the sign (31%) (P = 0.038). SP-Network achieved an accuracy of 95.2% in the task of automatic recognition of the sign.

CONCLUSIONS

SP sign is featured on the flow-volume curve and recognized by the SP-Network model. Patients with the sign are less likely to have airway hyperresponsiveness, automatic visualizing of this sign is helpful for primary care centers where BPT cannot available.

Artificial intelligence, machine learning and the pediatric airway

Artificial intelligence and machine learning are rapidly expanding fields with increasing relevance in anesthesia and, in particular, airway management. The ability of artificial intelligence and machine learning algorithms to recognize patterns from large volumes of complex data makes them attractive for use in pediatric anesthesia airway management. The purpose of this review is to introduce artificial intelligence, machine learning, and deep learning to the pediatric anesthesiologist. Current evidence and developments in artificial intelligence, machine learning, and deep learning relevant to pediatric airway management are presented. We critically assess the current evidence on the use of artificial intelligence and machine learning in the assessment, diagnosis, monitoring, procedure assistance, and predicting outcomes during pediatric airway management. Further, we discuss the limitations of these technologies and offer areas for focused research that may bring pediatric airway management anesthesiology into the era of artificial intelligence and machine learning.

Acute airway obstruction due to benign multinodular goitre

Benign multinodular goitre is a common illness. When accompanied by obstructive symptoms, such as dyspnoea, it carries an indication for surgery. Benign multinodular goitres rarely cause acute airway obstruction. We report the case of a 88-year-old woman who presented with acute shortness of breath and stridor. A chest CT revealed marked enlargement of the thyroid gland, with an extensive intrathoracic component. She was proposed for total thyroidectomy. Her intraoperative course was unremarkable, but the patient passed away in postoperative period from ventricular fibrillation. Recognition of these cases is important, as they constitute a preventable cause of mortality if timely diagnosed and treated.

High-accuracy detection of airway obstruction in asthma using machine learning algorithms and forced oscillation measurements

BACKGROUND AND OBJECTIVES

The main pathologic feature of asthma is episodic airway obstruction. This is usually detected by spirometry and body plethysmography. These tests, however, require a high degree of collaboration and maximal effort on the part of the patient. There is agreement in the literature that there is a demand of research into new technologies to improve non-invasive testing of lung function. The purpose of this study was to develop automatic classifiers to simplify the clinical use and to increase the accuracy of the forced oscillation technique (FOT) in the diagnosis of airway obstruction in patients with asthma.

METHODS

The data consisted of FOT parameters obtained from 75 volunteers (39 with obstruction and 36 without). Different supervised machine learning (ML) techniques were investigated, including k-nearest neighbors (KNN), random forest (RF), AdaBoost with decision trees (ADAB) and feature-based dissimilarity space classifier (FDSC).

RESULTS

The first part of this study showed that the best FOT parameter was the resonance frequency (AUC = 0.81), which indicates moderate accuracy (0.70-0.90). In the second part of this study, the use of the cited ML techniques was investigated. All the classifiers improved the diagnostic accuracy. Notably, ADAB and KNN were very close to achieving high accuracy (AUC = 0.88 and 0.89, respectively). Experiments including the cross products of the FOT parameters showed that all the classifiers improved the diagnosis accuracy and KNN was able to reach a higher accuracy range (AUC = 0.91).

CONCLUSIONS

Machine learning classifiers can help in the diagnosis of airway obstruction in asthma patients, and they can assist clinicians in airway obstruction identification.

Machine learning algorithms and forced oscillation measurements applied to the automatic identification of chronic obstructive pulmonary disease

The purpose of this study is to develop a clinical decision support system based on machine learning (ML) algorithms to help the diagnostic of chronic obstructive pulmonary disease (COPD) using forced oscillation (FO) measurements. To this end, the performances of classification algorithms based on Linear Bayes Normal Classifier, K nearest neighbor (KNN), decision trees, artificial neural networks (ANN) and support vector machines (SVM) were compared in order to the search for the best classifier. Four feature selection methods were also used in order to identify a reduced set of the most relevant parameters. The available dataset consists of 7 possible input features (FO parameters) of 150 measurements made in 50 volunteers (COPD, n = 25; healthy, n = 25). The performance of the classifiers and reduced data sets were evaluated by the determination of sensitivity (Se), specificity (Sp) and area under the ROC curve (AUC). Among the studied classifiers, KNN, SVM and ANN classifiers were the most adequate, reaching values that allow a very accurate clinical diagnosis (Se > 87%, Sp > 94%, and AUC > 0.95). The use of the analysis of correlation as a ranking index of the FOT parameters, allowed us to simplify the analysis of the FOT parameters, while still maintaining a high degree of accuracy. In conclusion, the results of this study indicate that the proposed classifiers may contribute to easy the diagnostic of COPD by using forced oscillation measurements.

Prevalence of upper airway obstruction in patients with apparently asymptomatic euthyroid multi nodular goitre

AIMS

To study the prevalence of upper airway obstruction (UAO) in "apparently asymptomatic" patients with euthyroid multinodular goitre (MNG) and find correlation between clinical features, UAO on pulmonary function test (PFT) and tracheal narrowing on computerised tomography (CT).

MATERIALS AND METHODS

Consecutive patients with apparently asymptomatic euthyroid MNG attending thyroid clinic in a tertiary centre underwent clinical examination to elicit features of UAO, PFT, and CT of neck and chest.

STATISTICAL ANALYSIS USED

Statistical analysis was done with SPSS version 11.5 using paired t-test, Chi square test, and Fisher's exact test. P value of <0.05 was considered to be significant.

RESULTS

Fifty-six patients (52 females and four males) were studied. The prevalence of UAO (PFT) and significant tracheal narrowing (CT) was 14.3%. and 9.3%, respectively. Clinical features failed to predict UAO or significant tracheal narrowing. Tracheal narrowing (CT) did not correlate with UAO (PFT). Volume of goitre significantly correlated with degree of tracheal narrowing.

CONCLUSIONS

Clinical features do not predict UAO on PFT or tracheal narrowing on CT in apparently asymptomatic patients with euthyroid MNG.

Automatic identification of Chronic Obstructive Pulmonary Disease Based on forced oscillation measurements and artificial neural networks

The purpose of this study is to develop an automatic classifier based on Artificial Neural Networks (ANNs) to help the diagnostic of Chronic Obstructive Pulmonary Disease (COPD) using forced oscillation measurements (FOT). The classifier inputs are the parameters provided by the FOT and the output is the indication if the parameters indicate COPD or not. The available dataset consists of 7 possible input features (FOT parameters) of 90 measurements made in 30 volunteers. Two feature selection methods (the analysis of the linear correlation and forward search) were used in order to identify a reduced set of the most relevant parameters. Two different training strategies for the ANNs were used and the performance of resulting networks were evaluated by the determination of accuracy, sensitivity (Se), specificity (Sp) and AUC. The ANN classifiers presented high accuracy (Se > 0.9, Se > 0.9 and AUC > 0.9) both in the complete and the reduce sets of FOT parameters. This indicates that ANNs classifiers may contribute to easy the diagnostic of COPD using forced oscillation measurements.

Using a generalized neural network to identify airway obstructions in anesthetized patients postoperatively based on photoplethysmography

Photoplethysmography has been recently studied asa non-invasive indicator of circulatory and respiratory function. In this study, photoplethysmographic (PPG) data were recorded from patients under the influence of anesthesia, but not intubated. Both time and frequency domain features were extracted from the PPG and used as inputs to a neural network classifier. This classifier considers inter-subject variability so that it generalizes well to a large population. This classifier provided 86.1%accuracy to classify segments as being times of 'obstructed' vs.'normal' airways status.

The cuff-leak test is a simple tool to verify severe laryngeal edema in patients undergoing long-term mechanical ventilation

OBJECTIVE

The cuff-leak test has been proposed as a simple tool to clinically predict stridor or respiratory distress secondary to laryngeal edema following extubation. However, the true incidence of laryngeal edema in patients on long-term mechanical ventilation is uncertain. The relationship between upper airway obstruction (detected by video bronchoscopy) and the cuff-leak test value for patients with prolonged translaryngeal intubation during percutaneous dilatational tracheostomy (PDT) was investigated.

DESIGN

Prospective, clinical investigation.

SETTING

Intensive care unit of a university hospital.

PATIENTS

Ninety-five patients with prolonged translaryngeal intubation requiring PDT were enrolled during a 12-month period.

INTERVENTIONS

Cuff-leak test, PDT, video bronchoscopy.

MEASUREMENTS AND MAIN RESULTS

The average duration of translaryngeal intubation was 28.1 +/- 17.6 days. The incidence of severe laryngeal edema was 36.8% (35/95). We chose 140 mL as the threshold cuff-leak volume below which edema is indicated. The rate of cuff-leak test positivity was 38.9% (37/95). The sensitivity and the specificity of the test were 88.6% and 90.0%, respectively. The positive and negative predictive values were 83.8% and 93.1%, respectively. Patients who developed severe laryngeal edema had a smaller leak volume than those who did not, expressed in absolute values (53.9 +/- 56.2 vs. 287.9 +/- 120.0 mL; p < .001) or in relative values (10.1 +/- 10.2 vs. 55.3 +/- 22.7%, p < .001). The occurrence of severe laryngeal edema was not associated with age, gender, body weight, respiratory failure due to pneumonia, duration of translaryngeal intubation, endotracheal tube diameter, Acute Physiology and Chronic Health Evaluation II score, or history of self-extubation.

CONCLUSIONS

A reduced cuff-leak volume measured before PDT may signal the presence of severe laryngeal edema in patients on long-term mechanical ventilation.

Estimating respiratory system compliance during mechanical ventilation using artificial neural networks

In this study we evaluated whether a technology based on artificial neural networks (ANN) could estimate the static compliance (C(RS)) of the respiratory system, even in the absence of an end-inspiratory pause, during continuous mechanical ventilation. A porcine model of acute lung injury was used to provide recordings of different respiratory mechanics conditions. Each recording consisted of 10 or more consecutive breaths in volume-controlled mechanical ventilation, followed by a breath having an end-inspiratory pause used to calculate C(RS) according to the interrupter technique (IT). The volume-pressure loop of the breath immediately preceding the one with pause was given to the ANN for the training, together with the C(RS) separately calculated by the IT. The prospective phase consisted of giving only the loops to the trained ANN and comparing the results yielded by it to the compliance separately calculated by the investigators. Determination of measurement agreement between ANN and IT methods showed an error of -0.67 +/- 1.52 mL/cm H(2)O (bias +/- SD). We could conclude that ANN, during volume-controlled mechanical ventilation, can extract C(RS) without needing to stop inspiratory flow.

IMPLICATIONS

We studied the application of artificial neural networks (ANN) to the estimation of respiratory compliance during mechanical ventilation. The study was performed on an animal model of acute lung injury, testing the performance of ANN in both healthy and diseased conditions of the lung.

Prediction of the progression of thyroid-associated ophthalmopathy at first ophthalmologic examination: use of a neural network

In the present work we analyzed patients with thyroid-associated ophthalmopathy (TAO) at various clinical stages of disease progression and implemented a model of neural analysis for disease classification and prediction of progression. We studied 246 patients (group 1), seen only once because they had absent, minimal, or inactive TAO and 152 patients (group 2), seen two or more times because of active and/or progressive TAO. The ophthalmologic assessment included: (1) lid fissure measurement; (2) Hertel; (3) color vision; (4) cover test and Hess screen; (5) visual acuity; (6) tonometry; (7) fundus examination; (8) visual field; (9) orbital computed tomography (CT) scan or ultrasound. A back propagation model of neural network was based on the relative variations of 13 clinical eye signs (input variables) for classification and prediction of disease progression (output variable). Approximately 300 eyes (20%) were randomly selected as a test group. Correlation between expected and calculated patients' classification was highly significant (p < 0.00001). Concordance between clinical assessment and the neural network prediction was obtained in 78 of 117 eyes (67%). We have developed a neural model that allows classification of TAO and preliminary prediction of disease progression at the first clinical examination. The results are validating the classification into the two groups on which our initial assumption was based.

Assessment of respiratory system mechanics by artificial neural networks: an exploratory study

We evaluated 1) the performance of an artificial neural network (ANN)-based technology in assessing the respiratory system resistance (Rrs) and compliance (Crs) in a porcine model of acute lung injury and 2) the possibility of using, for ANN training, signals coming from an electrical analog (EA) of the lung. Two differently experienced ANNs were compared. One ANN (ANN(BIO)) was trained on tracings recorded at different time points after the administration of oleic acid in 10 anesthetized and paralyzed pigs during constant-flow mechanical ventilation. A second ANN (ANN(MOD)) was trained on EA simulations. Both ANNs were evaluated prospectively on data coming from four different pigs. Linear regression between ANN output and manually computed mechanics showed a regression coefficient (R) of 0.98 for both ANNs in assessing Crs. On Rrs, ANN(BIO) showed a performance expressed by R = 0.40 and ANN(MOD) by R = 0.61. These results suggest that ANNs can learn to assess the respiratory system mechanics during mechanical ventilation but that the assessment of resistance and compliance by ANNs may require different approaches.