A Machine-Learning Model for Lung Age Forecasting by Analyzing Exhalations

Abstract

Spirometers are important devices for following up patients with respiratory diseases. These are mainly located only at hospitals, with all the disadvantages that this can entail. This limits their use and consequently, the supervision of patients. Research efforts focus on providing digital alternatives to spirometers. Although less accurate, the authors claim they are cheaper and usable by many more people worldwide at any given time and place. In order to further popularize the use of spirometers even more, we are interested in also providing user-friendly lung-capacity metrics instead of the traditional-spirometry ones. The main objective, which is also the main contribution of this research, is to obtain a person's lung age by analyzing the properties of their exhalation by means of a machine-learning method. To perform this study, 188 samples of blowing sounds were used. These were taken from 91 males (48.4%) and 97 females (51.6%) aged between 17 and 67. A total of 42 spirometer and frequency-like features, including gender, were used. Traditional machine-learning algorithms used in voice recognition applied to the most significant features were used. We found that the best classification algorithm was the Quadratic Linear Discriminant algorithm when no distinction was made between gender. By splitting the corpus into age groups of 5 consecutive years, accuracy, sensitivity and specificity of, respectively, 94.69%, 94.45% and 99.45% were found. Features in the audio of users' expiration that allowed them to be classified by their corresponding lung age group of 5 years were successfully detected. Our methodology can become a reliable tool for use with mobile devices to detect lung abnormalities or diseases.

Keywords: exhalation; lung capacity forecasting; machine learning.

Figure 1

Data collection process. The participant opens the app, moves the phone to the indicated distance (20 cm), takes a deep breath and exhales.

Figure 2

Example of different flows rates in a spirometry test.

Figure 3

Original data corpus distribution among range-ages without using SMOTE.

Figure 4

Original data corpus distribution among range-ages using SMOTE.

Figure 5

Comparison of the metrics of the best algorithm separated by age ranges using the Quadratic Discriminant Analysis algorithm.