Prognostic value of lymphocyte counts in bronchoalveolar lavage fluid in patients with acute respiratory failure: a retrospective cohort study

An improved Yolov5s based on transformer backbone network for detection and classification of bronchoalveolar lavage cells

Biological tissue information of the lung, such as cells and proteins, can be obtained from bronchoalveolar lavage fluid (BALF), through which it can be used as a complement to lung biopsy pathology. BALF cells can be confused with each other due to the similarity of their characteristics and differences in the way sections are handled or viewed. This poses a great challenge for cell detection. In this paper, An Improved Yolov5s Based on Transformer Backbone Network for Detection and Classification of BALF Cells is proposed, focusing on the detection of four types of cells in BALF: macrophages, lymphocytes, neutrophils and eosinophils. The network is mainly based on the Yolov5s network and uses Swin Transformer V2 technology in the backbone network to improve cell detection accuracy by obtaining global information; the C3Ghost module (a variant of the Convolutional Neural Network architecture) is used in the neck network to reduce the number of parameters during feature channel fusion and to improve feature expression performance. In addition, embedding intersection over union Loss (EIoU_Loss) was used as a bounding box regression loss function to speed up the bounding box regression rate, resulting in higher accuracy of the algorithm. The experiments showed that our model could achieve mAP of 81.29% and Recall of 80.47%. Compared to the original Yolov5s, the mAP has improved by 3.3% and Recall by 3.67%. We also compared it with Yolov7 and the newly launched Yolov8s. mAP improved by 0.02% and 2.36% over Yolov7 and Yolov8s respectively, while the FPS of our model was higher than both of them, achieving a balance of efficiency and accuracy, further demonstrating the superiority of our model.

Prognostic implication of bronchoalveolar lavage fluid analysis in patients with Pneumocystis jirovecii pneumonia without human immunodeficiency virus infection

Background

The prognostic value of bronchoalveolar lavage (BAL) fluid analysis in non-human immunodeficiency virus (HIV)-infected patients with Pneumocystis jirovecii pneumonia (PJP) has not been well elucidated. We aimed to investigate the prognostic implication of BAL fluid analysis in non-HIV patients with PJP.

Methods

The data of 178 non-HIV patients diagnosed with PJP based on the results of the polymerase chain reaction assay of BAL fluid specimens between April 2018 and December 2020 were retrospectively reviewed. The clinical characteristics, laboratory findings, and BAL fluid analysis results of patients who died within 90 days after hospital admission were compared.

Results

Twenty patients (11.2%) died within 90 days from admission. The neutrophil count in BAL fluid was significantly higher (median 22.0%, interquartile range [IQR] 2.0–46.0% vs. median 6.0%, IQR 2.0–18.0%, P = 0.044), while the lymphocyte count was significantly lower (median 24.0%, IQR 7.0–37.0% vs. median 41.0%, IQR 22.5–60.5%, P = 0.001) in the non-survivor group compared with that in the survivor group. In the multivariate analysis, the C-reactive protein level (odds ratio [OR] 1.093, 95% confidence interval [CI] 1.020–1.170, P = 0.011) and a BAL fluid lymphocyte count of ≤ 30% (OR 3.353, 95% CI 1.101–10.216, P = 0.033) were independently associated with mortality after adjusting for albumin and lactate dehydrogenase levels.

Conclusion

A low lymphocyte count in BAL fluid may be a predictor of mortality in non-HIV patients with PJP.

Supplementary Information

The online version contains supplementary material available at 10.1186/s12890-022-02041-8.

Association between lymphocyte count in bronchoalveolar lavage fluid and mortality

This is a comment on the paper by Dr. Hirasawa et al. on the predictive value of lymphocyte counts in bronchoalveolar lavage fluid in patients with acute respiratory failure.

High neutrophils and low lymphocytes percentages in bronchoalveolar lavage fluid are prognostic factors of higher in-hospital mortality in diffuse alveolar hemorrhage

BACKGROUND

Diffuse alveolar hemorrhage (DAH) is a syndrome resulting from bleeding in the microcirculation of the lung, with a poor prognosis. The study aim was to identify prognostic factors of DAH, especially bronchoalveolar lavage fluids (BALF) cell pattern.

METHODS

We conducted a single-center retrospective cohort study of patients diagnosed as having DAH and hospitalized at our hospital between October 2008 and July 2020. We performed univariate logistic regressions to identify variables associated with in-hospital death.

RESULTS

Sixty-eight patients were included in our analysis. In-hospital mortality was 26.5%. Variables associated with in-hospital death were neutrophils percentage in BALF ≥ 44.5% [Odds Ratio (OR) 16.0, 95% confidence interval (CI) 4.33-58.9)], lymphocytes percentage in BALF < 14% (OR 7.44, 95% CI 2.11-26.2), idiopathic DAH (OR 0.31, 95% CI 0.10-0.95), oxygen flow ≥ 4L/min (OR 3.90, 95% CI 1.20-12.6), and estimated glomerular filtration rate < 60 mL/min (OR 5.00, 95%CI 1.29-19.4).

CONCLUSIONS

High neutrophils and low lymphocytes percentages in BALF were associated with poor prognosis.