Related Experiment Video
Updated: Jun 11, 2026
A Contemporary Warming/Restraining Device for Efficient Tail Vein Injections in a Murine Fungal Sepsis Model
Published on: November 6, 2020
Predicting intra-abdominal candidiasis in elderly septic patients using machine learning based on lymphocyte
Jiahui Zhang1, Guoyu Zhao1, Xianli Lei1
1Department of Critical Care Medicine, State Key Laboratory of Complex Severe and Rare Diseases, Peking Union Medical College Hospital, Chinese Academy of Medical Science and Peking Union Medical College, Beijing, China.
This study developed a nomogram using lymphocyte subtyping and clinical factors to predict intra-abdominal candidiasis (IAC) in elderly septic patients. The nomogram aids in early identification of high-risk individuals, improving patient outcomes.
Area of Science:
- Infectious Diseases
- Immunology
- Geriatrics
Background:
- Intra-abdominal candidiasis (IAC) is challenging to predict in elderly patients with intra-abdominal infection (IAI).
- Early and accurate prediction is crucial for timely intervention and improved patient outcomes.
Purpose of the Study:
- To develop and validate a predictive nomogram for early and rapid identification of IAC in elderly septic patients.
- To utilize lymphocyte subtyping and clinical factors for enhanced diagnostic accuracy.
Main Methods:
- A prospective cohort study involving 284 elderly patients with sepsis and IAI.
- Machine-learning (random forest) for variable selection and multivariate logistic regression for factor analysis.
- Construction and validation of a nomogram model, assessing discrimination, calibration, and clinical utility.
Main Results:
- Gastrointestinal perforation, renal replacement therapy (RRT), T-cell count, CD28+CD8+ T-cell count, and CD38+CD8+ T-cell count were identified as independent predictors of IAC.
- The nomogram demonstrated strong predictive performance with AUC values of 0.840 (training) and 0.783 (testing), outperforming the Candida score.
- The nomogram exhibited good calibration and high clinical value, as indicated by decision curve analysis (DCA).
Conclusions:
- A validated nomogram integrating T-cell counts and clinical factors can effectively predict IAC in elderly septic patients.
- This tool assists clinicians in rapidly ruling out IAC or identifying at-risk individuals at the onset of infection.
- The nomogram offers a valuable adjunct for managing elderly patients with IAI and suspected candidiasis.
