A new method to predict values for postoperative lung function and surgical risk of lung resection by quantitative breath sound measurements

Predicting Pulmonary Function From the Analysis of Voice: A Machine Learning Approach

Introduction

To self-monitor asthma symptoms, existing methods (e.g. peak flow metre, smart spirometer) require special equipment and are not always used by the patients. Voice recording has the potential to generate surrogate measures of lung function and this study aims to apply machine learning approaches to predict lung function and severity of abnormal lung function from recorded voice for asthma patients.

Methods

A threshold-based mechanism was designed to separate speech and breathing from 323 recordings. Features extracted from these were combined with biological factors to predict lung function. Three predictive models were developed using Random Forest (RF), Support Vector Machine (SVM), and linear regression algorithms: (a) regression models to predict lung function, (b) multi-class classification models to predict severity of lung function abnormality, and (c) binary classification models to predict lung function abnormality. Training and test samples were separated (70%:30%, using balanced portioning), features were normalised, 10-fold cross-validation was used and model performances were evaluated on the test samples.

Results

The RF-based regression model performed better with the lowest root mean square error of 10·86. To predict severity of lung function impairment, the SVM-based model performed best in multi-class classification (accuracy = 73.20%), whereas the RF-based model performed best in binary classification models for predicting abnormal lung function (accuracy = 85%).

Conclusion

Our machine learning approaches can predict lung function, from recorded voice files, better than published approaches. This technique could be used to develop future telehealth solutions including smartphone-based applications which have potential to aid decision making and self-monitoring in asthma.

Predicting Lung Function Following Lobectomy: A New Method to Adjust for Inherent Selection Bias

BACKGROUND

Predictions that overestimate post-lobectomy lung function are more likely than underestimates to lead to lobectomy. Studies of post-lobectomy lung function have included only surgical patients, so overestimates are overrepresented. This selection bias has led to incorrect estimates of prediction bias, which has led to inaccurate threshold values for determining lobectomy eligibility.

OBJECTIVE

The objective of this study was to demonstrate and adjust for this selection bias in order to arrive at correct estimates of prediction bias, the 95% limits of agreement, and adjusted threshold values for determining when exercise testing is warranted.

METHODS

We conducted a retrospective study of patients evaluated for lobectomy. We used multiple imputations to determine postoperative results for patients who did not have surgery because their predicted postoperative values were low. We combined these results with surgical patients to adjust for selection bias. We used the Bland-Altman method and the bivariate normal distribution to determine threshold values for surgical eligibility.

RESULTS

Lobectomy evaluation was performed in 114 patients; 79 had lobectomy while 35 were ineligible based on predicted values. Prediction bias using the Bland-Altman method changed significantly after controlling for selection bias. To achieve a postoperative FEV1 > 30% and DLCO ≥30%, a predicted FEV1 > 46% and DLCO ≥53% were required. Compared to current guidelines, using these thresholds would change management in 17% of cases.

CONCLUSION

The impact of selection bias on estimates of prediction accuracy was significant but can be corrected. Threshold values for determining surgical eligibility should be reassessed.

Prediction of postoperative lung function after major lung resection for lung cancer using volumetric computed tomography

OBJECTIVES

The study objectives were to assess the accuracy of volumetric computed tomography to predict postoperative lung function in patients with lung cancer in relation to anatomic segments counting and perfusion scintigraphy, to generate specific predictive equations for each functional parameter, and to evaluate accuracy and precision of these in a validation cohort.

METHODS

We assessed pulmonary functions preoperatively and 3 to 4 months postoperatively after lung resection for lung cancer (n = 114). Absolute and relative lung volumes (total and upper/middle/lower) were determined using volumetric software analysis for staging thoracic computed tomography scans. Predicted postoperative function was calculated by segments counting, scintigraphy, and volumetric computed tomography.

RESULTS

Volumetric computed tomography achieves a higher correlation and precision with measured postoperative lung function than segments counting or scintigraphy (correlation and intraclass correlation coefficients, 0.779-0.969 and 0.776-0.969; 0.573-0.887 and 0.552-0.882; and 0.578-0.834 and 0.532-0.815, respectively), as well as greater accuracy, determined by narrower agreement coefficients for forced vital capacity, forced expiratory volume in 1 second, lung diffusing capacity, and peak oxygen uptake. After validation in an independent cohort (n = 43), adjusted linear regression including volumetric estimation of decreased postoperative ventilation for postoperative lung function parameters explains 98% to 99% of variance.

CONCLUSIONS

Volumetric computed tomography is a reliable and accurate method to predict postoperative lung function in patients undergoing lung resection that provides better accuracy than conventional procedures. Because lung computed tomography is systematically performed in the staging of patients with suspected lung cancer, this volumetric analysis might simultaneously provide the information necessary to evaluate operability.