๐Ÿง‘๐Ÿผโ€๐Ÿ’ป Research - August 15, 2025

Machine learning based analysis of leucocyte cell population data by Sysmex XN series hematology analyzer for the diagnosis of bacteremia.

๐ŸŒŸ Stay Updated!
Join AI Health Hub to receive the latest insights in health and AI.

โšก Quick Summary

This study explores the use of machine learning to analyze leucocyte cell population data from the Sysmex XN-series hematology analyzer for the early diagnosis of bacteremia. The findings indicate that the fluorescent light distribution of the neutrophil area (NE-WY) is a promising biomarker, achieving an AUC of 0.768 with a sensitivity of 73.6% and specificity of 67.9%.

๐Ÿ” Key Details

  • ๐Ÿ“Š Dataset: 533 adult patients with clinically suspected bacteremia
  • ๐Ÿงฉ Features used: Fluorescent light distribution of the neutrophil area (NE-WY)
  • โš™๏ธ Technology: Machine learning algorithms, including decision trees and support vector machines
  • ๐Ÿ† Performance: NE-WY AUC 0.768, sensitivity 73.6%, specificity 67.9%

๐Ÿ”‘ Key Takeaways

  • ๐Ÿ“Š NE-WY shows significant potential for detecting bacteremia.
  • ๐Ÿ’ก Machine learning enhances the predictive capabilities of traditional hematology data.
  • ๐Ÿ‘ฉโ€๐Ÿ”ฌ Study involved 533 patients, with 106 confirmed cases of bacteremia.
  • ๐Ÿ† The first branch of the decision tree was based on NE-WY, indicating its importance.
  • ๐Ÿค– Support vector machines did not outperform NE-WY alone in this study.
  • ๐ŸŒ Conducted at a hospital setting, emphasizing real-world applicability.
  • ๐Ÿ” Propensity score matching was utilized to ensure robust comparisons between groups.
  • ๐Ÿ”ฎ Future research is encouraged to further explore the combination of CPD and machine learning.

๐Ÿ“š Background

Bacteremia is a serious condition that can lead to severe complications if not diagnosed and treated promptly. Traditional diagnostic methods often rely on blood cultures, which can take time and may not always yield results. The advent of cell population data (CPD) from advanced hematology analyzers like the Sysmex XN-series offers a new avenue for early detection, potentially improving patient outcomes through quicker intervention.

๐Ÿ—’๏ธ Study

This study was conducted to evaluate the effectiveness of NE-WY as a diagnostic tool for bacteremia. Researchers enrolled 533 adult patients suspected of having bacteremia and performed propensity score matching to compare those with confirmed bacteremia (n=106) against those without (n=427). The focus was on analyzing the fluorescent light distribution of neutrophils, a key indicator in the diagnosis process.

๐Ÿ“ˆ Results

The analysis revealed that NE-WY exhibited the largest difference between bacteremia and non-bacteremia cases, achieving an AUC of 0.768. The sensitivity and specificity were recorded at 73.6% and 67.9%, respectively, with a cutoff value of 686.5. Notably, the decision tree analysis identified NE-WY as the primary predictor, underscoring its significance in the diagnostic process.

๐ŸŒ Impact and Implications

The findings from this study could significantly impact clinical practices surrounding the diagnosis of bacteremia. By integrating machine learning with CPD analysis, healthcare providers may achieve faster and more accurate diagnoses, ultimately leading to improved patient care. This innovative approach could pave the way for further research and development in the realm of hematology and infectious disease diagnostics.

๐Ÿ”ฎ Conclusion

This study highlights the transformative potential of combining machine learning with traditional hematology data for the early detection of bacteremia. The promising results associated with NE-WY suggest that further exploration in this area could lead to significant advancements in diagnostic methodologies. Continued research is essential to validate these findings and explore their application in broader clinical settings.

๐Ÿ’ฌ Your comments

What are your thoughts on the integration of machine learning in hematology diagnostics? We would love to hear your insights! ๐Ÿ’ฌ Leave your comments below or connect with us on social media:

Machine learning based analysis of leucocyte cell population data by Sysmex XN series hematology analyzer for the diagnosis of bacteremia.

Abstract

In clinical practice, early recognition of bacteremia leads to prognostic improvement. Recently, cell population data (CPD) from the Sysmex XN-series hematology analyzer has attracted attention as a new method for the early diagnosis of bacteremia, but its usefulness in clinical practice remains unclear. We focused on the fluorescent light distribution of the neutrophil area (NE-WY) and used machine learning to determine whether predictions could be improved. Among adult patients with clinically suspected bacteremia at our hospital, 533 who did not meet the exclusion criteria were enrolled. Propensity score matching was performed for bacteremia (nโ€‰=โ€‰106) and non-bacteremia (nโ€‰=โ€‰427) cases. NE-WY showed the largest difference between the two groups (AUC, 0.768; sensitivity, 73.6%; specificity, 67.9%; cutoff value, 686.5(no unit)). In machine learning, the first branch of the decision tree was NE-WY, and the cutoff value was set at 689.5(no unit). Support vector machines were used to examine multiple variables, but there were no significant differences relative to NE-WY alone. This is the first report to demonstrate that NE-WY is useful for detecting bacteremia by analyzing CPD using machine learning. The combination of CPD and machine learning is expected to produce new results.

Author: [‘Horie S’, ‘Yamashita M’, ‘Matsumura K’, ‘Uejima Y’, ‘Kaneda M’, ‘Nagaoka K’, ‘Tamura K’, ‘Harada K’, ‘Yamamoto Y’, ‘Kitajima I’, ‘Imai C’, ‘Niimi H’]

Journal: Sci Rep

Citation: Horie S, et al. Machine learning based analysis of leucocyte cell population data by Sysmex XN series hematology analyzer for the diagnosis of bacteremia. Machine learning based analysis of leucocyte cell population data by Sysmex XN series hematology analyzer for the diagnosis of bacteremia. 2025; 15:29078. doi: 10.1038/s41598-025-14554-3

Share on facebook
Facebook
Share on twitter
Twitter
Share on linkedin
LinkedIn
Share on whatsapp
WhatsApp

Leave a Reply

This site uses Akismet to reduce spam. Learn how your comment data is processed.