Predicting forced vital capacity (FVC) using support vector regression (SVR).
Physiol Meas. 2019 Jan 30;:
Authors: Wang C, Chen X, Zhao R, He Z, Zhao Z, Zhan Q, Yang T, Fang Z
Objectives: Spirometry, as the golden approach in the diagnosis of chronic obstructive pulmonary disease (COPD), has strict end-of-test (EOT) criteria (e.g., complete exhalation), which cannot be met by patients with compromised health situations. Thus, significant parameters measured by spirometry such as FVC has limited accuracies. In order to address this issue, the present study was aimed to develop models based on support vector regression to predict values of FVC under the condition that the EOT criteria were not fully met. Approach: The prediction models for the quantification of FVC were developed based on SVR. 354 subjects conducted conventional spirometry (CS) and the resulting data of forced expiratory volumes in one second (FEV1), peak expiratory flow(PEF), age and gender were used as input features and the resulting values of the FVC were used as the target feature in the prediction models. After that, three prediction models (Mixed Model, Normal Model and Abnormal Model) were established according to the criterion in the diagnosis of COPD that a postbronchodilator FEV1/FVC lower than 0.70. Then 35 subjects were recruited to be tested with both CS and low-degree-of EOT criteria spirometry (LDCS), which did not fully met the EOT criteria of CS. In LDCS, subjects were allowed to terminate the procedures based on their own wills at any time after the technicians assumed that both acceptable values of FEV1 and PEF were obtained. Quantified values of FVC derived from both CS and LDCS were compared to validate the performances of the developed prediction models. Main results: The FVC prediction performance of the Normal Model and Abnormal Model were better than that of the Mixed Model. The RMSE are lower than 0.35L and the accuracy are higher to 95%. One tailed t test results demonstrate that the absolute differences of the measured and predicted values are not significantly different from 0.15L for both Abnormal Model and Normal Model. Significance: Our study shows the possibility of predicting FVC with acceptable precision in cases of the EOT criteria of spirometry were not fully met, which can be beneficial for patients who cannot or did not make full exhalation in spirometry.
PMID: 30699391 [PubMed – as supplied by publisher]