Xiaoqun Xu,1,* Xiao Liu,2,* Chao Yang,2,* Long Cai,1 Libin Liu,1 Tielong Chen,3 Houyong Zhu,3 Hui Wei1 

1Centre of Laboratory Medicine, Hangzhou Red Cross Hospital, Hangzhou, Zhejiang, People’s Republic of China; 2The Fourth School of Clinical Medicine, Zhejiang Chinese Medical University, Hangzhou, Zhejiang, People’s Republic of China; 3Department of Cardiology, Hangzhou TCM Hospital Affiliated to Zhejiang Chinese Medical University, Hangzhou, Zhejiang, People’s Republic of China

*These authors contributed equally to this work

Correspondence: Hui Wei, Hangzhou Red Cross Hospital, No. 208 East Huancheng Road, Hangzhou, 310003, People’s Republic of China, Email weihui-hzred@qq.com Houyong Zhu, Department of Cardiology, Hangzhou TCM Hospital Affiliated to Zhejiang Chinese Medical University, No. 453 Stadium Road, Hangzhou, 310007, People’s Republic of China, Email houyongzhu@foxmail.com

Background and Aims: Tuberculous pericarditis (TBP) is a severe, life-threatening complication, yet its diagnosis is highly challenging due to the lack of sufficient diagnostic tools. The aim of this study was to develop and validate a diagnostic prediction model suitable for primary healthcare institutions to predict the risk of TBP.
Methods: We collected detailed medical histories, imaging examination results, laboratory test data, and clinical characteristics of patients and used the Least Absolute Shrinkage and Selection Operator (LASSO) technique combined with logistic regression analysis to construct a predictive model. The diagnostic efficacy of the model was assessed using the Receiver Operating Characteristic (ROC) curve, calibration curve, and Decision Curve Analysis (DCA).
Results: A total of 304 patients were included in the study, with a median age of 64 years, of which 144 were diagnosed with tuberculous pericarditis. Patients were randomly assigned to the training and validation sets in a 7:3 ratio. LASSO logistic regression analysis revealed that weight loss (P=0.011), body mass index (BMI) (P=0.061), history of tuberculosis (P=0.022), history of dust exposure (P=0.03), moderate to severe kidney disease (P=0.005), erythrocyte sedimentation rate (ESR) (P=0.084), and B-type natriuretic peptide (BNP) (P< 0.001) are independent risk factors for TBP. Based on these factors, we constructed a nomogram with an Area Under the Receiver Operating Characteristic Curve (AUC) of 0.757 in both the training and validation sets, indicating high discriminative ability of the model. Calibration curve analysis showed good consistency of the model. DCA results indicated that the model has significant clinical application value when the threshold probability is set between 1– 100% (training set) and 30– 100% (validation set).
Conclusion: We successfully developed a nomogram model for predicting tuberculous pericarditis, which can assist clinicians in improving diagnostic accuracy and reducing misdiagnoses and missed diagnoses in primary healthcare settings.
Plain Language Summary: Imagine you have a tool that helps doctors figure out if someone has a serious heart issue called tuberculous pericarditis, which is tough to detect. Our team collected data from 304 patients, looking at everything from their medical history to lab results. We used a smart method to pinpoint key risk factors like weight loss, body mass index, past tuberculosis, exposure to dust, moderate or severe kidney disease, a measure of inflammation called erythrocyte sedimentation rate, and a heart failure marker known as B-type natriuretic peptide. From there, we crafted a simple scoring tool that predicts the likelihood of having this heart problem. When we put our tool to the test, it did a great job, especially when we set the risk level just right. This means we have developed a helpful guide for doctors, especially in places with limited resources, to diagnose this condition more accurately and avoid mistakes. In simple terms, our research has led to a better way to spot a dangerous heart condition that can be tricky to find. This not only helps patients get the right treatment but also raises awareness about the importance of medical research and its impact on public health.

Keywords: tuberculous pericarditis, diagnostic prediction model, primary healthcare, LASSO logistic regression