EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Comparative evaluation of the aggregate index of systemic inflammation (AISI) and its modified version for early detection of central line-associated bloodstream infection: a pilot study using machine learning techniques

Gargee Anand, Ketan Priyadarshi, Bandana Kumari, Jutang Babat Ain Tiewsoh, Rijhul Lahariya

GMS Hygiene and Infection Control · 30.06.2026 · 21 (Doc52) · Doc52

DOI: 10.3205/dgkh000661 ↗

Kurz gefasst

Fachartikel in der Zeitschrift GMS Hygiene and Infection Control, erschienen am 30.06.2026. Verfasst von Gargee Anand und 4 weiteren Autor:innen. Beteiligte Einrichtung: Department of Microbiology, All India Institute of Medical Sciences, Patna, Bihar, India. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Central line-associated bloodstream infections (CLABSI) are a common and serious problem in critically ill patients; their early detecting is challenging. This study evaluated the predictive ability of the aggregate index of systemic inflammation (AISI) and its modified form for early identification of CLABSI within two calendar days following central line insertion, using a machine learning approach.

Method

We conducted an analysis of patients who received central line insertion. Inflammatory indices were calculated using laboratory parameters obtained on second day post-insertion. Four machine learning algorithms were applied to evaluate their predictive performance for early CLABSI detection.

Results

Among 234 patients who met the inclusion criteria, 39 were confirmed CLABSI cases. We found both indices significantly elevated in the CLABSI group. Modified AISI demonstrated the strongest performance using XGBoost, with the highest area under the ROC curve (0.99), 97% sensitivity and 98% specificity, indicating its potential as the better early screening marker for CLABSI than AISI.

Conclusion

Both AISI and modified AISI demonstrated strong predictive value for early CLABSI detection, being both accessible and cost-effective. Modified AISI outperformed AISI in predictive performance. These findings support the need for the prospective validation of the modified AISI before clinical implementation.

Schlagwörter

Stichwörter der Autor:innen

AISICLABSIaggregate index of systemic inflammationcentral line-associated bloodstream infectionearly predictionmachine learning

Autor:innen und Institutionen

  • Department of Microbiology, All India Institute of Medical Sciences, Patna, Bihar, India.
  • Department of Microbiology, All India Institute of Medical Sciences, Deoghar, Jharkhand, India.
  • Department of Biochemistry, All India Institute of Medical Sciences, Patna, Bihar, India.
  • All India Institute of Medical Sciences, Patna, Bihar, India.

Zitieren

APA

Anand, G., Priyadarshi, K., Kumari, B., Tiewsoh, J. B. A., & Lahariya, R. (2026). Comparative evaluation of the aggregate index of systemic inflammation (AISI) and its modified version for early detection of central line-associated bloodstream infection: a pilot study using machine learning techniques. GMS Hygiene and Infection Control, 21(Doc52), Doc52. https://doi.org/10.3205/dgkh000661

Vancouver

Anand G, Priyadarshi K, Kumari B, Tiewsoh JBA, Lahariya R. Comparative evaluation of the aggregate index of systemic inflammation (AISI) and its modified version for early detection of central line-associated bloodstream infection: a pilot study using machine learning techniques. GMS Hygiene and Infection Control. 2026;21(Doc52):Doc52. doi:10.3205/dgkh000661

BibTeX
@article{Anand2026,
  author = {Anand, Gargee and Priyadarshi, Ketan and Kumari, Bandana and Tiewsoh, Jutang Babat Ain and Lahariya, Rijhul},
  title = {Comparative evaluation of the aggregate index of systemic inflammation (AISI) and its modified version for early detection of central line-associated bloodstream infection: a pilot study using machine learning techniques},
  journal = {GMS Hygiene and Infection Control},
  year = {2026},
  volume = {21},
  number = {Doc52},
  pages = {Doc52},
  doi = {10.3205/dgkh000661}
}
Kostenlos starten →