Table 1_Confronting the “lethal duo” in the ICU: early identification of Aspergillus–Mucor

Hongqiang Xie's retrospective study of 93 critically ill patients (75 with Aspergillus infection, 18 with co-infection) admitted between 2017 and 2025. The research compares clinical characteristics, inflammatory markers, and immunophenotypes to develop a predictive nomogram. The dataset, last updated in April 2026, is a 23.5 KB document describing the study and its results.

Use Cases

• Training a classification model to predict fungal co-infection risk based on the identified clinical-immuno-inflammatory signature.
• Benchmarking feature selection methods for clinical data, referencing the multi-algorithm strategy (LASSO, Ridge, Random Forest) used in the study.
• Developing decision-support tools for early antifungal therapy initiation based on the nomogram's predictors (NK cell count, CRP, corticosteroid history, Gram-positive co-infection).

Strengths

• The predictive nomogram demonstrated robust discrimination with an AUC of 0.878 and good calibration.
• Study includes 93 patient records with a defined time range from 2017 to 2025.
• Analysis incorporates multiple machine learning algorithms for variable selection and includes internal validation.

Limitations

• Row count and column-level documentation are absent; field semantics must be inferred after download.
• Data is from a single-center retrospective study, which may limit generalizability.
• The dataset is very small at 23.5 KB, indicating limited raw data scope.

Provenance

Source

Hongqiang Xie via figshare.

Collection Method

Single-center, retrospective observational study.

Time Range

2017 to 2025.

Freshness

Last updated 2026-04-22 05:35:30; freshness should be verified.

Geography

null