Predicting intra-abdominal candidiasis in elderly septic patients using machine learning based on lymphocyte subtyping: a prospective cohort study

Jiahui Zhang; Guoyu Zhao; Xianli Lei; Na Cui

doi:10.3389/fphar.2024.1486346

Predicting intra-abdominal candidiasis in elderly septic patients using machine learning based on lymphocyte subtyping: a prospective cohort study

Front Pharmacol. 2024 Dec 12:15:1486346. doi: 10.3389/fphar.2024.1486346. eCollection 2024.

Authors

Jiahui Zhang¹, Guoyu Zhao¹, Xianli Lei¹, Na Cui¹

Affiliation

¹ Department 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.

Abstract

Objective: Intra-abdominal candidiasis (IAC) is difficult to predict in elderly septic patients with intra-abdominal infection (IAI). This study aimed to develop and validate a nomogram based on lymphocyte subtyping and clinical factors for the early and rapid prediction of IAC in elderly septic patients.

Methods: A prospective cohort study of 284 consecutive elderly patients diagnosed with sepsis and IAI was performed. We assessed the clinical characteristics and parameters of lymphocyte subtyping at the onset of IAI. A machine-learning random forest model was used to select important variables, and multivariate logistic regression was used to analyze the factors influencing IAC. A nomogram model was constructed, and the discrimination, calibration, and clinical effectiveness of the model were verified.

Results: According to the results of the random forest and multivariate analyses, gastrointestinal perforation, renal replacement therapy (RRT), T-cell count, CD28+CD8+ T-cell count and CD38+CD8+ T-cell count were independent predictors of IAC. Using the above parameters to establish a nomogram, the area under the curve (AUC) values of the nomogram in the training and testing cohorts were 0.840 (95% CI 0.778-0.902) and 0.783 (95% CI 0.682-0.883), respectively. The AUC in the training cohort was greater than the Candida score [0.840 (95% CI 0.778-0.902) vs. 0.539 (95% CI 0.464-0.615), p< 0.001]. The calibration curve showed good predictive values and observed values of the nomogram; the DCA results showed that the nomogram had high clinical value.

Conclusion: We established a nomogram based on the T-cell count, CD28+CD8+ T-cell count, CD38+CD8+ T-cell count and clinical risk factors that can help clinical physicians quickly rule out IAC or identify elderly patients at greater risk for IAC at the onset of infection.

Clinical trial registration: [chictr.org.cn], identifier [ChiCTR2300069020].

Keywords: elderly; intra-abdominal candidiasis; lymphocyte subtyping; machine learning; nomogram; risk stratification; sepsis.

Grants and funding

The author(s) declare that financial support was received for the research, authorship, and/or publication of this article. The work was supported by National Key R&D Program of China 2022YFC2009803 from Ministry of Science and Technology of the People’s Republic of China, National High Level Hospital Clinical Research Funding (No. 2022-PUMCH-A-217, No. 2022-PUMCH-B-126), National Key R&D Program of China 2022YFC2009801 from Ministry of Science and Technology of the People’s Republic of China, National Natural Science Foundation of China (No. 82072226), and CAMS Innovation Fund for Medical Sciences (CIFMS) 2023-I2M-2-002 from Chinese Academy of Medical Sciences to NC and JZ.