Mode
Text Size
Log in / Sign up

Clinical prediction model differentiates NTM pulmonary disease from tuberculosis in hospitalized patientsCan a simple checklist help doctors tell two serious lung infections apart?

AI-generated summary of the cited source, checked by automated accuracy review. How we work

Key Takeaway
Consider this NTM-PD prediction model as preliminary; external validation is needed before clinical adoption.

A retrospective cross-sectional cohort study developed and internally validated a clinical prediction model to differentiate nontuberculous mycobacterial pulmonary disease (NTM-PD) from pulmonary tuberculosis (PTB). The study included 351 consecutive hospitalized patients with microbiologically confirmed diagnoses (145 NTM-PD, 206 PTB) from January 2021 to December 2023. The model identified six clinical and radiographic variables: older age, female gender, absence of diabetes mellitus, presence of bronchiectasis, presence of COPD, and presence of lung cavitation.

The model demonstrated good discrimination with an area under the receiver operating characteristic curve (AUC) of 0.846 (95% CI, 0.805–0.877). Calibration was excellent with a Hosmer-Lemeshow test p-value of 0.949. Internal validation showed an optimism-corrected concordance index of 0.830, indicating robust performance within the study cohort. Decision curve analysis suggested clinical utility across a range of threshold probabilities.

Safety and tolerability data were not reported. Key limitations include the retrospective design, single-center setting, and lack of external validation. The study was observational and cannot establish causality. While the model may help clinicians raise early suspicion for NTM-PD and optimize diagnostic pathways while awaiting culture confirmation, its generalizability remains uncertain until validated in diverse populations and settings.

When someone comes to the hospital with a serious lung infection, doctors face a critical puzzle: Is it pulmonary tuberculosis (TB), or is it a different infection called nontuberculous mycobacterial pulmonary disease (NTM-PD)? They look similar but require completely different treatments, and waiting for lab results can take weeks. Getting it wrong early can delay the right care.

Researchers looked back at the records of 351 hospitalized patients who had confirmed cases of either infection. They developed a simple checklist based on six patient characteristics: being older, being female, not having diabetes, and having certain lung conditions like bronchiectasis, COPD, or lung cavitation. When they tested this model on the same group of patients, it showed good ability to tell the two infections apart.

It's important to know this tool was built and tested using data from just one hospital. The study was retrospective, meaning it looked at past records, which can sometimes miss important details. The researchers only validated the model internally, so we don't know yet how well it would work for patients in other hospitals or communities. No safety issues were reported because this was a data analysis study, not a test of a new drug or procedure.

For now, this checklist is a promising first step. It could help doctors raise an early suspicion for NTM-PD and avoid misdiagnosing it as TB while cultures are growing in the lab. But because it hasn't been tested elsewhere, it's not ready to be a standalone decision-maker. More research is needed to see if it holds up in the real world.

What this means for you:
A six-item checklist shows promise for telling two serious lung infections apart, but needs more testing.

Study Details

Study typeCohort
EvidenceLevel 3
PublishedApr 2026
View Original Abstract ↓
The rising global incidence of nontuberculous mycobacterial pulmonary disease (NTM-PD) and its significant overlap with pulmonary tuberculosis (PTB) in symptoms and imaging pose a major diagnostic challenge, often leading to misdiagnosis and inappropriate treatment. A reliable pre-culture predictive tool is urgently needed. In this retrospective cross-sectional study, we analyzed consecutive hospitalized patients with microbiologically confirmed NTM-PD (n = 145) or PTB (n = 206) from January 2021 to December 2023. Demographic, clinical, comorbidity, laboratory, and high-resolution CT (HRCT) data were collected. Least Absolute Shrinkage and Selection Operator (LASSO) regression with 10-fold cross-validation was used for feature selection. Selected variables were incorporated into a multivariate logistic regression model to construct a final prediction model. Model performance was evaluated by area under the receiver operating characteristic curve (AUC), calibration (Hosmer-Lemeshow test, calibration plot), and internal validation via 1,000 bootstrap resamples. Clinical utility was assessed using decision curve analysis (DCA). The LASSO regression identified six independent predictors for the final model: older age, female gender, absence of diabetes mellitus, presence of bronchiectasis, presence of chronic obstructive pulmonary disease (COPD), and presence of lung cavitation on HRCT. The model demonstrated good discrimination with an AUC of 0.846 (95% CI, 0.805–0.877) and excellent calibration (Hosmer-Lemeshow test, p = 0.949). Bootstrap internal validation yielded an optimism-corrected concordance index of 0.830. DCA confirmed the model’s clinical net benefit across a wide range of threshold probabilities. We developed and internally validated a parsimonious six-variable prediction model that effectively differentiates NTM-PD from PTB. Incorporating objective feature selection (LASSO) and rigorous validation, this tool can aid clinicians in raising early suspicion for NTM-PD, optimizing diagnostic pathways, and preventing misdiagnosis while awaiting culture results.
Free Newsletter

Clinical research that matters. Delivered to your inbox.

Join thousands of clinicians and researchers. No spam, unsubscribe anytime.