Developing and Validation of a Multimodal-Based Machine Learning Model for Diagnosis of Usual Interstitial Pneumonia:
Hongyi Wang1, Anqi Liu2, Yifei Ni2
1China-Japan Friendship Hospital (Institute of Clinical Medical Sciences), Chinese Academy of Medical Sciences & Peking Union Medical College, Beijing, China; National Center for Respiratory Medicine; State Key Laboratory of Respiratory Health and Multimorbidity; National Clinical Research Center for Respiratory Diseases; Institute of Respiratory Medicine, Chinese Academy of Medical Sciences; Department of Pulmonary and Critical Care Medicine, Center of Respiratory Medicine, China-Japan Friendship Hospital, Beijing, China.
Background:
Usual interstitial pneumonia (UIP) indicates a poor prognosis, and there is significant heterogeneity in the diagnosis of UIP, necessitating an auxiliary diagnostic tool.
Research Question:
Can a machine learning (ML) classifier using radiomics features and clinical data accurately identify UIP from patients with interstitial lung disease (ILD)?
Study Design And Methods:
This data from a prospective cohort includes 5,321 sets of high-resolution CT (HRCT) images from 2,901 patients with ILD (male, 63.5%; mean age ± SD, 61.7 ± 10.8 years) across 3 medical centers. Multimodal data, including whole-lung radiomics features on HRCT scan, demographics, smoking status, pulmonary function, and comorbidity data, were extracted. An XGBoost and logistic regression were used to design a nomogram predicting UIP or not. The area under the receiver operating characteristic curve (AUC) and Cox regression for all-cause mortality were used to assess the diagnostic performance and prognostic value of models, respectively.
Results:
A total of 5,213 HRCT images were divided into the training group (n = 3,639), the internal testing group (n = 785), and the external validation group (n = 789). UIP prevalence was 43.7% across the whole data set, with 42.7% and 41.3% for the internal validation set and external validation set, respectively. The radiomics-based classifier had an AUC of 0.790 in the internal testing set and 0.786 for the external validation data set. Integrating multimodal data improved AUCs to 0.802 and 0.794, respectively. The performance of the integration model was comparable with a pulmonologist with > 10 years of experience in ILD. Within 522 patients deceased during a median follow-up period of 3.37 years, the multimodal-based ML model-predicted UIP pattern was associated with high all-cause mortality risk (hazard ratio, 2.52; P < .001).
Interpretation:
The classifier combining radiomics and clinical features showed strong diagnostic performance across varied UIP prevalence. This multimodal-based ML model could serve as an adjunct in the diagnosis of UIP.
Clinical Trial Registration:
ClinicalTrials.gov; No.: NCT04370158; URL: www.
Clinicaltrials:
gov.
Related Concept Videos
01:27Chronic Obstructive Pulmonary Disease-IV: Assessement and Diagnostic Studies
Medical History
01:29Pulmonary Embolism II: Diagnostic Studies and Interprofessional Care
01:20Chronic Obstructive Pulmonary Disease-I: Introduction
01:22Chronic Obstructive Pulmonary Disease
Smoking is a primary risk factor for COPD, with over 80% of patients having a history of it. Patients typically experience progressive dyspnea or labored breathing, frequent coughing, and recurrent pulmonary infections. Many eventually succumb to respiratory failure, characterized by...
01:20COPD: Pathogenesis and Clinical Features
The primary cause for the onset of COPD is cigarette smoking and exposure to air pollution. These hazardous factors initiate a chain reaction within the lungs, resulting in chronic inflammation, damage to the airways, and a...
01:20Chronic Obstructive Pulmonary Disease-II: Pathophysiology
Chronic Inflammation