Related Experiment Video
Updated: Sep 12, 2025
06:19
Constructing and Visualizing Models using Mime-based Machine-learning Framework
Published on: July 22, 2025
673
Multicentre retrospective observational study for development and validation of MAC prognostic score model
Kazuaki Takeda1, Takahiro Takazono2,3, Shotaro Ide1,4
1Department of Respiratory Medicine, Nagasaki University Hospital, 1-7-1 Sakamoto, Nagasaki, 852-8501, Japan.
Scientific Reports
|August 6, 2025
Summary
A new scoring system helps predict mortality in Mycobacterium avium-intracellulare complex pulmonary disease (MAC-PD). This tool identifies patients at higher risk for respiratory infection-related death, aiding clinical decisions.
Area of Science:
- Pulmonology
- Infectious Diseases
- Epidemiology
Background:
- Global incidence and mortality of Mycobacterium avium-intracellulare complex pulmonary disease (MAC-PD) are rising.
- Effective tools for predicting outcomes in MAC-PD patients are needed.
Purpose of the Study:
- To develop and validate a prognostic scoring system for predicting respiratory infection-related mortality in patients with MAC-PD.
Main Methods:
- A multicentre retrospective cohort study involving 1,165 newly diagnosed MAC-PD patients.
- Cox proportional hazards analysis identified risk factors in a derivation group (n=932).
- A prognostic score was developed and validated in a separate group (n=233).
Main Results:
- Five independent risk factors for mortality were identified: older age (≥65 years), male sex, interstitial pneumonia, low albumin (<3.5 g/dL), and cavitary lesions.
- A scoring system was created, with higher scores indicating poorer prognosis.
- The model showed good predictive performance (AUC 0.86 in derivation, 0.81 in validation).
Conclusions:
- The developed prognostic score is a clinically useful tool for stratifying MAC-PD patients based on their risk of respiratory infection-related mortality.
- This risk stratification can aid in clinical management and treatment decisions for MAC-PD.
