Clinical predictors, species distribution, and machine learning-based risk stratification of invasive candidiasis and in-hospital mortality: a retrospective episode-level cohort analysis.
5 affiliations
- 1Department of Microbiology, College of Medicine and Health Sciences, National University of Science and Technology, Sohar, Oman. [email protected].
- 2Department of Microbiology, College of Medicine and Health Sciences, National University of Science and Technology, Sohar, Oman.
- 3All India Institute of Medical Sciences, Mangalagiri, Hyderabad, India.
- 4Department of Pathology and Blood Bank, Sohar Hospital, Sohar, Oman.
- 5Department of Physiology, Faculty of Medicine, Neelain University, Khartoum city, AL, Sudan. [email protected].
Abstract
Background
Invasive candidiasis carries disproportionate mortality in hospitalised patients, yet the clinical determinants distinguishing invasive from non-invasive disease remain inconsistently characterised across healthcare settings. This study aimed to identify independent predictors of invasive candidiasis and in-hospital mortality, describe species distribution and antifungal resistance patterns, and evaluate machine learning models for risk stratification.Methods
A retrospective episode-level analysis was conducted on 206 laboratory-confirmed Candida-positive microbiological episodes at a single secondary care centre. Binary logistic regression univariable and multivariable was used to identify predictors of invasive candidiasis and all-cause mortality. Four machine learning classifiers (Random Forest, Gradient Boosting, Extra Trees, Logistic Regression) were developed and internally validated using five-fold stratified cross-validation. Permutation feature importance was applied for model explainability.Results
Of 206 episodes, 37 (18.0%) were invasive. Overall, in-hospital mortality among invasive cases was 73.0%. Elderly age (≥ 65 years; aOR 53.22) and male sex (aOR 4.38) independently predicted invasive disease. Elderly age (aOR 5.12), male sex (aOR 4.96), and diabetes mellitus (aOR 2.60) were independent mortality predictors. Non-albicans species predominated among invasive isolates (73.0%), with Candida glabrata and Candida parapsilosis most over-represented. Fluconazole and caspofungin resistance were detected in 3/20 (15.0%) and 2/21 (9.5%) tested invasive isolates, respectively. The Random Forest classifier achieved AUROC values of 0.987 and 0.776 for invasive candidiasis and mortality prediction, respectively; the near-perfect invasive-candidiasis performance should be interpreted as exploratory and largely driven by marked age-based separation.Conclusion
Elderly age, male sex, and diabetes mellitus consistently predicted invasive disease and/or mortality in this episode-level cohort. Machine learning identified these routinely available variables as dominant discriminative features, but the models remain exploratory and require patient-level and external validation before clinical deployment.
Related
- Evolving Epidemiology of Invasive Candidiasis in Southwest China: A Four-year Analysis of Species Distribution, Antifungal Resistance Profiles, and Mortality Risk Factors
- Molecular Etiology and Mortality Risk Stratification of Non-SARS-CoV-2 Severe Acute Respiratory Infection in a Predominantly Pediatric Cohort: A Retrospective Study From a Tertiary Care Hospital in North India
- Survival Status and Predictors of Mortality Among Women With Breast Cancer in Southern Ethiopia: A Retrospective Cohort Study
- Hemoglobin-to-red blood cell distribution width ratio and in-hospital mortality in patients with non-traumatic subarachnoid hemorrhage: a retrospective cohort study
- The red blood cell distribution width-to-albumin ratio and 28-day mortality in patients with severe cardiogenic shock: a retrospective cohort study based on MIMIC-IV with single-center external validation
BibTeX
@article{sannathimmappa2026clinical,
title = {{Clinical predictors, species distribution, and machine learning-based risk stratification of invasive candidiasis and in-hospital mortality: a retrospective episode-level cohort analysis.}},
author = {Mohan Bilikallahalli Sannathimmappa and Vinod Nambiar and Mohammmed Al Amin Ali Alsharawy and Motassim Kamran Baig and Hussein Muqdad Mahmood and Ahmed Ali Abudlamir Al-Shamaa and Miysaa Ali Abdallah Alabri and Rayyan Mohammed Almaskri and Rajeev Aravindakshan and Salima Al-Maqbali and Shahenaz Satti and Rayaan Chowdhury},
journal = {BMC infectious diseases},
year = {2026},
month = jul,
doi = {10.1186/s12879-026-14105-9},
url = {https://europepmc.org/article/MED/42958078},
note = {CC BY-NC-ND},
}
RIS
TY - JOUR
TI - Clinical predictors, species distribution, and machine learning-based risk stratification of invasive candidiasis and in-hospital mortality: a retrospective episode-level cohort analysis.
AU - Mohan Bilikallahalli Sannathimmappa
AU - Vinod Nambiar
AU - Mohammmed Al Amin Ali Alsharawy
AU - Motassim Kamran Baig
AU - Hussein Muqdad Mahmood
AU - Ahmed Ali Abudlamir Al-Shamaa
AU - Miysaa Ali Abdallah Alabri
AU - Rayyan Mohammed Almaskri
AU - Rajeev Aravindakshan
AU - Salima Al-Maqbali
AU - Shahenaz Satti
AU - Rayaan Chowdhury
PY - 2026
DA - 2026/07/31
JO - BMC infectious diseases
DO - 10.1186/s12879-026-14105-9
UR - https://europepmc.org/article/MED/42958078
AB - Background Invasive candidiasis carries disproportionate mortality in hospitalised patients, yet the clinical determinants distinguishing invasive from non-invasive disease remain inconsistently characterised across healthcare settings. This study aimed to identify independent predictors of invasive candidiasis and in-hospital mortality, describe species distribution and antifungal resistance patterns, and evaluate machine learning models for risk stratification.Methods A retrospective episode-level analysis was conducted on 206 laboratory-confirmed Candida-positive microbiological episodes at a single secondary care centre. Binary logistic regression univariable and multivariable was used to identify predictors of invasive candidiasis and all-cause mortality. Four machine learning classifiers (Random Forest, Gradient Boosting, Extra Trees, Logistic Regression) were developed and internally validated using five-fold stratified cross-validation. Permutation feature importance was applied for model explainability.Results Of 206 episodes, 37 (18.0%) were invasive. Overall, in-hospital mortality among invasive cases was 73.0%. Elderly age (≥ 65 years; aOR 53.22) and male sex (aOR 4.38) independently predicted invasive disease. Elderly age (aOR 5.12), male sex (aOR 4.96), and diabetes mellitus (aOR 2.60) were independent mortality predictors. Non-albicans species predominated among invasive isolates (73.0%), with Candida glabrata and Candida parapsilosis most over-represented. Fluconazole and caspofungin resistance were detected in 3/20 (15.0%) and 2/21 (9.5%) tested invasive isolates, respectively. The Random Forest classifier achieved AUROC values of 0.987 and 0.776 for invasive candidiasis and mortality prediction, respectively; the near-perfect invasive-candidiasis performance should be interpreted as exploratory and largely driven by marked age-based separation.Conclusion Elderly age, male sex, and diabetes mellitus consistently predicted invasive disease and/or mortality in this episode-level cohort. Machine learning identified these routinely available variables as dominant discriminative features, but the models remain exploratory and require patient-level and external validation before clinical deployment.
SN - 1471-2334
ER -