Literature DB >> 33766046

Machine learning associated with respiratory oscillometry: a computer-aided diagnosis system for the detection of respiratory abnormalities in systemic sclerosis.

Domingos S M Andrade1, Luigi Maciel Ribeiro1, Agnaldo J Lopes2, Jorge L M Amaral3, Pedro L Melo4.   

Abstract

INTRODUCTION: The use of machine learning (ML) methods would improve the diagnosis of respiratory changes in systemic sclerosis (SSc). This paper evaluates the performance of several ML algorithms associated with the respiratory oscillometry analysis to aid in the diagnostic of respiratory changes in SSc. We also find out the best configuration for this task.
METHODS: Oscillometric and spirometric exams were performed in 82 individuals, including controls (n = 30) and patients with systemic sclerosis with normal (n = 22) and abnormal (n = 30) spirometry. Multiple instance classifiers and different supervised machine learning techniques were investigated, including k-Nearest Neighbors (KNN), Random Forests (RF), AdaBoost with decision trees (ADAB), and Extreme Gradient Boosting (XGB). RESULTS AND DISCUSSION: The first experiment of this study showed that the best oscillometric parameter (BOP) was dynamic compliance, which provided moderate accuracy (AUC = 0.77) in the scenario control group versus patients with sclerosis and normal spirometry (CGvsPSNS). In the scenario control group versus patients with sclerosis and altered spirometry (CGvsPSAS), the BOP obtained high accuracy (AUC = 0.94). In the second experiment, the ML techniques were used. In CGvsPSNS, KNN achieved the best result (AUC = 0.90), significantly improving the accuracy in comparison with the BOP (p < 0.01), while in CGvsPSAS, RF obtained the best results (AUC = 0.97), also significantly improving the diagnostic accuracy (p < 0.05). In the third, fourth, fifth, and sixth experiments, different feature selection techniques allowed us to spot the best oscillometric parameters. They resulted in a small increase in diagnostic accuracy in CGvsPSNS (respectively, 0.87, 0.86, 0.82, and 0.84), while in the CGvsPSAS, the best classifier's performance remained the same (AUC = 0.97).
CONCLUSIONS: Oscillometric principles combined with machine learning algorithms provide a new method for diagnosing respiratory changes in patients with systemic sclerosis. The present study's findings provide evidence that this combination may help in the early diagnosis of respiratory changes in these patients.

Entities:  

Keywords:  Clinical decision support system; Diagnostic of respiratory diseases; Forced oscillation technique; Machine learning; Respiratory oscillometry; System identification techniques; Systemic sclerosis

Mesh:

Year:  2021        PMID: 33766046      PMCID: PMC7995797          DOI: 10.1186/s12938-021-00865-9

Source DB:  PubMed          Journal:  Biomed Eng Online        ISSN: 1475-925X            Impact factor:   2.819


  42 in total

1.  Combined 5 x 2 cv F test for comparing supervised classification learning algorithms.

Authors:  E Alpaydin
Journal:  Neural Comput       Date:  1999-11-15       Impact factor: 2.026

2.  The future of pulmonary function testing.

Authors:  Neil R MacIntyre
Journal:  Respir Care       Date:  2012-01       Impact factor: 2.258

Review 3.  Receiver Operating Characteristic (ROC) Curve Analysis for Medical Diagnostic Test Evaluation.

Authors:  Karimollah Hajian-Tilaki
Journal:  Caspian J Intern Med       Date:  2013

4.  Respiratory resistive impedance in obstructive patients: linear regression analysis vs viscoelastic modelling.

Authors:  A M Lorino; F Zerah; C Mariette; A Harf; H Lorino
Journal:  Eur Respir J       Date:  1997-01       Impact factor: 16.671

5.  Inspiratory resonant frequency of forced oscillation technique as a predictor of the composite physiologic index in interstitial lung disease.

Authors:  Masato Fujii; Toshihiro Shirai; Kazutaka Mori; Masashi Mikamo; Yuichiro Shishido; Takefumi Akita; Satoru Morita; Kazuhiro Asada; Takafumi Suda
Journal:  Respir Physiol Neurobiol       Date:  2014-12-13       Impact factor: 1.931

6.  Machine learning algorithms and forced oscillation measurements to categorise the airway obstruction severity in chronic obstructive pulmonary disease.

Authors:  Jorge L M Amaral; Agnaldo J Lopes; Alvaro C D Faria; Pedro L Melo
Journal:  Comput Methods Programs Biomed       Date:  2014-11-22       Impact factor: 5.428

Review 7.  Pulmonary physiology: future directions for lung function testing in COPD.

Authors:  Vito Brusasco; Giovanni Barisione; Emanuele Crimi
Journal:  Respirology       Date:  2014-09-25       Impact factor: 6.424

8.  Mechanical properties of lungs and chest wall during spontaneous breathing.

Authors:  J Nagels; F J Làndsér; L van der Linden; J Clément; K P Van de Woestijne
Journal:  J Appl Physiol Respir Environ Exerc Physiol       Date:  1980-09

9.  Comparison of impedance measured by the forced oscillation technique and pulmonary functions, including static lung compliance, in obstructive and interstitial lung disease.

Authors:  Naoya Takeichi; Haruna Yamazaki; Keisaku Fujimoto
Journal:  Int J Chron Obstruct Pulmon Dis       Date:  2019-05-24

10.  Oscillation mechanics of the respiratory system in never-smoking patients with silicosis: pathophysiological study and evaluation of diagnostic accuracy.

Authors:  Paula Morisco de Sá; Agnaldo José Lopes; José Manoel Jansen; Pedro Lopes de Melo
Journal:  Clinics (Sao Paulo)       Date:  2013-05       Impact factor: 2.365

View more
  3 in total

1.  Explainable machine learning methods and respiratory oscillometry for the diagnosis of respiratory abnormalities in sarcoidosis.

Authors:  Allan Danilo de Lima; Agnaldo J Lopes; Jorge Luis Machado do Amaral; Pedro Lopes de Melo
Journal:  BMC Med Inform Decis Mak       Date:  2022-10-20       Impact factor: 3.298

Review 2.  The Use and Utility of Machine Learning in Achieving Precision Medicine in Systemic Sclerosis: A Narrative Review.

Authors:  Francesco Bonomi; Silvia Peretti; Gemma Lepri; Vincenzo Venerito; Edda Russo; Cosimo Bruni; Florenzo Iannone; Sabina Tangaro; Amedeo Amedei; Serena Guiducci; Marco Matucci Cerinic; Silvia Bellando Randone
Journal:  J Pers Med       Date:  2022-07-23

3.  Deep learning models for detecting respiratory pathologies from raw lung auscultation sounds.

Authors:  Ali Mohammad Alqudah; Shoroq Qazan; Yusra M Obeidat
Journal:  Soft comput       Date:  2022-09-26       Impact factor: 3.732

  3 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.