Chronic obstructive and inflammatory lung diseases share overlapping clinical manifestations and spirometric features, complicating differential diagnosis and monitoring. In this study, we performed an integrative real-time proton-transfer-reaction time-of-flight mass spectrometry (PTR-TOF-MS) breathomics analysis to assess whether exhaled volatile organic compound (VOC) profiles enable multiclass discrimination among bronchial asthma (BA), chronic obstructive pulmonary disease (COPD), cystic fibrosis (CF), and lymphangioleiomyomatosis (LAM), with healthy individuals as controls. Breath VOC data from 843 subjects were analyzed using a stratified 70/30 train/test split. An ensemble feature selection strategy based on gradient boosting (XGBoost with SMOTE within cross-validation) identified stable VOC panels (top 25% selection probability), yielding 29 VOCs and 31 features including clinical covariates. On the independent test set, the VOC-only model achieved a macro-averaged one-vs-one (OvO) AUC of 0.866 (95% CI 0.829–0.903), while the combined model improved to 0.888 (95% CI 0.853–0.919), indicating modest value of clinical variables. Pairwise analysis demonstrated highest discrimination for CF (AUC up to 0.988), whereas BA and LAM showed lower sensitivity (<0.60), likely reflecting heterogeneity and limited sample size. Given differences in age, sex, BMI, and smoking status across cohorts, confounding effects were assessed, confirming that VOC signatures retain independent diagnostic information. Disease-specific VOC interaction networks revealed distinct remodeling patterns, with central metabolites not captured by univariate analysis. Overall, PTR-TOF-MS breathomics demonstrates proof-of-concept multiclass discrimination across chronic lung diseases.

Background/Objectives: To evaluate the Risk Factor-Weighted Clinical Likelihood (RF-CL) model for the diagnosis of chronic coronary syndrome (CCS) in men and women. Methods: The study included 222 patients (100 men and 122 women; mean age 64.76 ± 10.3 years) with suspected CCS. Diagnostic evaluation was performed in accordance with the 2024 clinical practice guidelines for stable coronary artery disease developed by the Russian Society of Cardiology. The clinical probability of obstructive coronary artery disease (CAD) was calculated for all patients using the RF-CL model. Results: Application of the RF-CL model demonstrated higher probabilities in men than in women (17% [11–27] vs. 6% [4,5,6,7,8,9,10], p < 0.001). Moderate CCS probability (RF-CL > 15–50%) was observed in 64% of men and 9.8% of women (p < 0.001); low probability (RF-CL > 5–15%) in 30% and 60.7% (p < 0.001); very low (RF-CL ≤ 5%) in 6% and 29.5% (p < 0.001). The prevalence of typical angina (21% vs. 17.2%, p = 0.47), atypical angina (31% vs. 26.2%, p = 0.43), and non-anginal chest pain (31% vs. 26.2%, p = 0.43) did not differ. Dyspnea was less frequent in men (44% vs. 59.8%, p = 0.02). Only 35 (15.8%) patients had indications for invasive coronary angiography (ICA), and significant stenosis (≥70%) was found in 17 patients. According to the ROC analysis, the cutoff value of RF-CL for predicting a positive stress test was 19.5% in men (AUC 0.723; p = 0.002), 6.5% in women (AUC 0.479; p = 0.852), and 15% in the overall cohort (AUC 0.737; p < 0.0001). Conclusions: Men with moderate and women with low probability of obstructive CAD are predominantly encountered in clinical practice when the RF-CL model is applied. Our observations have shown that ICA is indicated in relatively few patients and suggest potential overuse of exercise testing regardless of the clinicians’ adherence to the traditional Diamond–Forrester model or the RF-CL algorithm in suspected CCS.