The Use of Electrical Impedance Tomography (EIT) in Pulmonary Diseases

The study titled "The Use of Electrical Impedance Tomography (EIT) in Pulmonary Diseases" investigates the impact of using EIT as a non-invasive method to monitor the distribution of pulmonary ventilation and its relationship to standard spirometry in patients with various lung diseases. The main aim of this study is to investigate new approaches to the assessment of lung status and diagnosis of lung diseases. Unlike spirometry, which has long been a well-known and important diagnostic tool in pulmonary medicine, and which provides valuable information about the volume and flow of inspired and expired air, EIT provides spatial information about the distribution of ventilation in real time and without the need for active patient cooperation. Research and practice have shown that spirometry is problematic in specific groups of patients, such as patients with tracheostomy or facial palsy. The technology should also enable detection of the disease in its early stages, when treatment is most effective. 300 participants in the experimental group and 100 participants in the control group will receive spirometry and electrical impedance tomography independent examination. The primary endpoint of the study is to investigate the potential of EIT in respiratory medicine, specifically identifying the relationship between EIT and traditional spirometry. This effort is motivated by the need for novel noninvasive methods for the diagnosis and monitoring of respiratory diseases, especially in patients unable to undergo conventional spirometry, or in case of interventions requiring real-time feedback. The purpose of the research project in relation to these objectives is to bring new possibilities in the field of diagnosis and monitoring of lung diseases through EIT, which could lead to significant improvements in patient care. Demographic and anthropometric data, including age, sex, body height, body weight, body mass index (BMI), chest circumference, and smoking history will be collected in all participants. These parameters will be used as covariates in the analysis to assess their impact on EIT-derived indicators and to improve normalization of EIT signals. Additionally, the study aims to develop and validate a machine learning model, particularly a deep neural network, capable of predicting standard spirometric parameters (e.g., FEV1, FVC, PEF) based solely on EIT signals. This could allow for an accurate assessment of dynamic pulmonary volumes in cooperating patients who are unable to undergo conventional spirometry (e.g. patients with tracheostomy).