Machine Learning-Based Prediction of Recurrence Risk in Allergic Bronchopulmonary Aspergillosis and Its Clinical Decision-Making Value: A Multicenter Study With External Validation
试验速览
- 阶段
- 不适用
- 状态
- 招募中
- 发起方
- 入组人数
- 200
- 试验地点
- 1
- 主要终点
- The occurrence of ABPA exacerbation within one year of enrollment.
研究概览
简要总结
This multicenter bidirectional cohort study aims to develop and externally validate a machine learning model for predicting the risk of acute exacerbation within 1 year in patients with allergic bronchopulmonary aspergillosis (ABPA) during the stable phase, and further to evaluate the model's practical value in risk stratification and clinical decision-making.
All patients diagnosed with ABPA according to the ISHAM 2024 criteria will be assigned to either the acute exacerbation group or the non-exacerbation group based on whether they experience an acute exacerbation within 1 year. Enrolled participants will be randomly divided into a training set and an internal validation set. During the feature selection phase, univariate analysis, collinearity diagnostics, feature importance ranking derived from nine machine learning algorithms, and expert consensus are comprehensively applied, ultimately leading to the development of 12 independent machine learning models.
Model performance is assessed using the receiver operating characteristic (ROC) curve and its area under the curve (AUC), sensitivity, specificity, F1-score, calibration curve, and decision curve analysis. In addition, external validation further enhances the credibility of the model. To improve clinical interpretability, the SHAP method is employed to quantify the contribution of each feature, and an interactive nomogram is constructed to facilitate clinical application.
All participants will be followed up for 12 months, during which regular clinical and laboratory evaluations will be performed.
研究设计
- 研究类型
- Observational
- 观察模型
- Cohort
- 时间视角
- Other
入排标准
- 年龄范围
- 18 Years 至 —（Adult, Older Adult）
- 性别
- All
- 接受健康志愿者
- 否
入选标准
- •Aged between 18 and 80 years old.
- •Consistent with the diagnostic consensus criteria for ABPA proposed by the ISHAM-ABPA Working Group.
- •Patients in stable phase of ABPA: newly diagnosed treatment-naive patients or those with prior ABPA exacerbation who achieved at least 50% improvement in symptoms assessed by Likert scale or visual analogue scale (VAS) following initial therapy, accompanied by marked radiological improvement (≥50% reduction in pulmonary opacities) or a minimum 20% decline in serum total IgE level.
排除标准
- •Concurrent malignant tumors or severe organ dysfunction involving the heart, brain, kidney and other vital organs.
- •Complicated with severe underlying diseases, including active pulmonary tuberculosis, lung cancer, chronic heart failure (NYHA class Ⅳ), chronic kidney disease stage 5 (CKD 5), decompensated liver cirrhosis, etc.
- •Immunocompromised status, such as human immunodeficiency virus (HIV) infection, long-term oral administration of glucocorticoids or immunosuppressive agents.
- •Pregnant or breastfeeding women.
- •Patients with missing core clinical data or incomplete medical records.
结局指标
主要结局
The occurrence of ABPA exacerbation within one year of enrollment.
时间窗: 1 year
An ABPA exacerbation was defined based on the official ISHAM 2024 criteria: patients with established ABPA presenting with sustained clinical worsening for over 14 days or radiological deterioration, accompanied by a ≥50% elevation in serum total IgE compared to the stable baseline level, after ruling out alternative causes of disease flare.
次要结局
- forced vital capacity (FVC)(1 year)
- Time to first acute exacerbation(1 year)
- Total serum IgE(1 year)
- FEV1 (% predicted)(1 year)
- Changes in chest CT features including scores for bronchiectasis severity(1 year)
- Aspergillus-specific IgE(1 year)
- Aspergillus-specific IgG(1 year)
- FEV1/FVC ratio(1 year)
- diffusing capacity for carbon monoxide (DLCO)(1 year)
- extent of bronchiectasis of chest CT(1 year)
- mucus plugging on chest CT(1 year)
- high-attenuation (HAM) on chest CT(1 year)
研究者
Qian Qi
Prof.
Qianfoshan Hospital