Spatiotemporal Electrical Impedance Tomography for Speech Respiratory Assessment in Cleft Palate: an Interpretable Machine Learning Study

Yang WU; Xiao-Jing ZHANG; Hao YU; Cheng-Hui JIANG; Bo SUN; Jia-Feng YAO

Return

Spatiotemporal Electrical Impedance Tomography for Speech Respiratory Assessment in Cleft Palate: an Interpretable Machine Learning Study

VernacularTitle:基于时空电阻抗成像的腭裂言语呼吸功能评估：可解释性机器学习研究
Author: Yang WU ¹ ; Xiao-Jing ZHANG ² ; Hao YU ³ ; Cheng-Hui JIANG ⁴ ; Bo SUN ⁵ ; Jia-Feng YAO ⁶
Author Information

1. College of Mechanical and Electronic Engineering, Nanjing Forestry University, Nanjing 210037, China
2. Department of Stomatology, Taizhou Hospital of Traditional Chinese Medicine, Taizhou 225300, China
3. School of Engineering, The University of Edinburgh, Edinburgh EH9 3FB, UK
4. Jiangsu Engineering Research Center of Oral Translational Medicine, Jiangsu Key Laboratory of Oral Diseases, Department of Oral and Maxillofacial Surgery, The Affiliated Stomatological Hospital of Nanjing Medical University, Nanjing 210029, China
5. School of Mechanical and Precision Instrument Engineering, Xi’an University of Technology, Xi’an 710048, China
6. College of Physics and Optoelectronic Engineering, Jinan University, Guangzhou 510632, China
Publication Type:Journal Article
Keywords: electrical impedance tomography; cleft palate; speech respiratory function; spatiotemporal features; machine learning; explainable analysis
From: Progress in Biochemistry and Biophysics 2026;53(2):485-500
CountryChina
Language:Chinese
Abstract: ObjectiveCleft palate (CP) is a common congenital deformity often associated with velopharyngeal insufficiency (VPI), which disrupts the physiological coupling between respiration and speech. Conventional clinical assessments, such as nasometry and spirometry, provide limited static data and fail to visualize the dynamic spatiotemporal distribution of lung ventilation during phonation. This study introduces spatiotemporal electrical impedance tomography (ST-EIT) to evaluate speech-respiratory functional features in CP patients compared to normal controls (NC). The aim is to characterize multi-domain respiratory patterns and to validate an interpretable machine learning framework for providing objective, quantitative evidence for clinical assessment. MethodsSeventy-five participants were enrolled in this study, comprising 37 patients with surgically repaired CP and 38 healthy volunteers matched for age, gender, and body mass index (BMI). All subjects performed standardized sustained phonation tasks while undergoing synchronous monitoring with a 16-electrode EIT system and a pneumotachograph. A comprehensive feature engineering pipeline was developed to extract physiological parameters across 3 complementary domains. (1) Temporal domain: including inspiratory/expiratory phase duration (tPhase), time constants (Tau), and inspiratory-to-expiratory time ratios (TI/TE); (2) airflow domain: comprising mean flow, peak flow, and instantaneous flow at 25%, 50%, and 75% of tidal volume; and (3) spatial domain: quantifying global and regional tidal impedance variation (TIV), global inhomogeneity (GI), and center of ventilation (CoV). Extreme Gradient Boosting (XGBoost) classifiers were trained using 5 distinct data sources (Spirometry, Nasometry, Inspiratory-EIT, Expiratory-EIT, and fused ST-EIT). Model performance was rigorously evaluated via stratified 5-fold cross-validation, and Shapley additive explanations (SHAP) were employed to quantify global and local feature contributions. ResultsThe CP group exhibited a distinct respiratory phenotype compared to controls. In the temporal domain, CP patients showed significantly shorter inspiratory (1.60 s vs.1.85 s, P<0.001) and expiratory phase durations (2.45 s vs. 3.95 s, P<0.001), indicating a rapid, shallow breathing rhythm. In the airflow domain, while inspiratory flows were comparable, the CP group demonstrated significantly elevated mean and peak flows during the expiratory phase (P<0.001), reflecting compensatory respiratory effort. Spatially, CP patients presented significant ventilation redistribution, characterized by higher regional TIV in the right-anterior (ROI1) and left-posterior (ROI4) quadrants, but lower TIV in the left-anterior (ROI2) quadrant. In terms of diagnostic accuracy, the multi-modal ST-EIT model achieved the highest performance (AUC: 0.915±0.012, Accuracy: 0.843±0.019, F1-score: 0.872±0.017), substantially outperforming models based on spirometry (AUC: 0.721) or nasometry (AUC: 0.625) alone. Interpretability analysis revealed that spatial domain features were the most critical, contributing 53.4% to the model’s decision-making, followed by temporal (25.0%) and airflow (21.6%) features. ConclusionST-EIT successfully captures the temporal, airflow, and spatial deviations in CP speech respiration that are undetectable by conventional methods—specifically, rapid phase transitions, hyperdynamic expiratory airflow, and regional ventilation heterogeneity. This study validates ST-EIT as a robust, non-invasive, and radiation-free tool for characterizing speech-respiratory dysfunction, offering high clinical value for bedside screening, rehabilitation planning, and longitudinal monitoring of patients with cleft palate.