Scholarlink

Purpose <p>To identify predictors and risk factors for <i>Pneumocystis jirovecii</i> pneumonia (PJP) in non-HIV immunocompromised patients.</p> Methods <p>Retrospective analysis of 301 non-HIV patients with <i>P. jirovecii</i> in bronchoalveolar lavage fluid (BALF) using metagenomic next-generation sequencing (mNGS) identified PJP (<i>n</i> = 161) and <i>P. jirovecii</i> colonization (PJC, <i>n</i> = 140) groups, evaluated XGBoost for prediction, applied SHAP for insights, and assessed 28-day mortality risks. We assessed five machine learning algorithms, selecting XGBoost as the final predictive model, and applied SHapley Additive exPlanations (SHAP) analysis for interpretability. We assessed 28-day mortality risks. and performed subgroup survival analyses.</p> Results <p>The XGBoost model achieved an area under the curve (AUC) of 0.9000 in distinguishing PJP from PJC. Key predictors included serum (1–3)-β-D-glucan (BDG) levels, log-transformed reads for <i>P. jirovecii</i>, CD4<sup>+</sup> T cell count, and respiratory support. Significant risk factors for 28-day mortality in PJP patients included the use of decreased PaO<sub>2</sub>/FiO<sub>2</sub> ratios (final OR: 0.98, <i>P</i> &lt; 0.001), lower platelet counts (final OR: 0.98, <i>P</i> = 0.057), lower CD3<sup>+</sup> (final OR: 0.99, <i>P</i> = 0.034), as was a lower CD4<sup>+</sup> T cell count (final OR: 0.98, <i>P</i> = 0.023). Patients with immune-mediated diseases had the worst survival rates. Corticosteroids failed to improve survival, regardless of patients having good or poor oxygenation status. Co-infections, particularly those with multiple pathogens, were associated with the most adverse outcomes.</p> Conclusion <p>The study underscores mNGS for <i>P. jirovecii</i> detection, XGBoost’s effectiveness in PJP differentiation, and the importance of identifying predictors and mortality risks in clinical management, noting worse outcomes in immune-mediated disease patients and co-infections, with corticosteroids not improving survival.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Machine learning model for differentiating Pneumocystis jirovecii pneumonia from colonization and analyzing mortality risk in non-HIV patients using BALF metagenomic sequencing

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年10月1日

查看全文
  • Yuhui Chen,
  • Yiwei Bai,
  • Meng Li,
  • Xinai Gan,
  • Yutong Wang,
  • Yongzhao Zhou,
  • Ting Niu

摘要

Purpose

To identify predictors and risk factors for Pneumocystis jirovecii pneumonia (PJP) in non-HIV immunocompromised patients.

Methods

Retrospective analysis of 301 non-HIV patients with P. jirovecii in bronchoalveolar lavage fluid (BALF) using metagenomic next-generation sequencing (mNGS) identified PJP (n = 161) and P. jirovecii colonization (PJC, n = 140) groups, evaluated XGBoost for prediction, applied SHAP for insights, and assessed 28-day mortality risks. We assessed five machine learning algorithms, selecting XGBoost as the final predictive model, and applied SHapley Additive exPlanations (SHAP) analysis for interpretability. We assessed 28-day mortality risks. and performed subgroup survival analyses.

Results

The XGBoost model achieved an area under the curve (AUC) of 0.9000 in distinguishing PJP from PJC. Key predictors included serum (1–3)-β-D-glucan (BDG) levels, log-transformed reads for P. jirovecii, CD4+ T cell count, and respiratory support. Significant risk factors for 28-day mortality in PJP patients included the use of decreased PaO2/FiO2 ratios (final OR: 0.98, P < 0.001), lower platelet counts (final OR: 0.98, P = 0.057), lower CD3+ (final OR: 0.99, P = 0.034), as was a lower CD4+ T cell count (final OR: 0.98, P = 0.023). Patients with immune-mediated diseases had the worst survival rates. Corticosteroids failed to improve survival, regardless of patients having good or poor oxygenation status. Co-infections, particularly those with multiple pathogens, were associated with the most adverse outcomes.

Conclusion

The study underscores mNGS for P. jirovecii detection, XGBoost’s effectiveness in PJP differentiation, and the importance of identifying predictors and mortality risks in clinical management, noting worse outcomes in immune-mediated disease patients and co-infections, with corticosteroids not improving survival.