Prediction of clinical deterioration within one year in chronic obstructive pulmonary disease using the systemic coagulation-inflammation index: a retrospective study employing multiple machine learning method

• Published in: PeerJ (San Francisco, CA) Vol. 13; p. e18989
• Main Authors: Hou, Ling, Min, Ming, Hou, Rui, Tan, Wei, Zhang, Minghua, Liu, Qianfei
• Format: Journal Article
• Language: English
• Published: United States PeerJ. Ltd 25.02.2025; PeerJ, Inc; PeerJ Inc
• Subjects: Aged; Blood clotting; Blood Coagulation; C-reactive protein; Cardiac arrhythmia; Cardiovascular disease; Cell number; Chronic illnesses; Chronic obstructive pulmonary disease; Clinical deterioration; Coagulation; Comorbidity; Coronary vessels; Development and progression; Diabetes; Disease Progression; Erythrocytes; Female; Health aspects; Hematology; Hemoglobin; Hospitalization; Hospitals; Humans; Hypertension; Inflammation; Inflammation - blood; Learning algorithms; Lung diseases; Lung diseases, Obstructive; Lymphocytes; Machine Learning; Male; Medical research; Medicine, Experimental; Methods; Middle Aged; Mortality; Patients; Physiological aspects; Predictor; Procalcitonin; Prognosis; Pulmonary Disease, Chronic Obstructive - blood; Pulmonary Disease, Chronic Obstructive - diagnosis; Pulmonary Disease, Chronic Obstructive - physiopathology; Python; Regression analysis; Respiratory failure; Retrospective Studies; Statistical analysis; Support vector machines; Systemic coagulation-inflammation index; Variables; Vein & artery diseases; China; Chronic obstructive pulmonary disease; Predictor; Clinical deterioration; Machine learning; Systemic coagulation-inflammation index
• ISSN: 2167-8359; 2167-8359
• DOI: 10.7717/peerj.18989

Inflammatory response and the coagulation system are pivotal in the pathogenesis of clinical deterioration in chronic obstructive pulmonary disease (COPD), prompting us to hypothesize that the systemic coagulation-inflammation (SCI) index is associated with clinical deterioration in COPD. A cohort of 957 COPD patients (mean age: 68.4 ± 7.8 years; 74.4% male) from January 2018 to December 2021 was analyzed. Six machine learning models (XGBoost, logistic regression, Random Forest, elastic net (ENT), support vector machine (SVM), and K-nearest neighbors (KNN)) were evaluated using accuracy, precision, recall, F1-score, and the area under the receiver operating characteristic curve (AUC-ROC). Our study encompassed 957 patients, out of which 171 were classified in the clinical deterioration of COPD (cd-COPD) cohort. Significant disparities in age, comorbidities like respiratory failure, C-reactive protein, lymphocyte count, red blood cell distribution width (RDW), SCI, procalcitonin (PCT), and D-dimer were depicted between the cd-COPD and non-cd-COPD groups. Concerning machine learning and model comparison, the SVM model showcased consistent performance and strong generalization capabilities on both the training and testing sets compared to the other five machine learning (ML) models. The SCI index, as the most influential predictor, demonstrated a median of 93.08 in cd-COPD compared to 81.67 in non-cd-COPD patients. The SCI is markedly elevated in cd-COPD patients compared to COPD patients, and SVM demonstrates reliable performance in cd-COPD prediction.