Development of Interactive Nomograms for Predicting Short-Term Survival in ICU Patients with Aplastic Anemia

TL;DR

This study developed and validated interactive nomograms based on seven key predictors to accurately estimate short-term mortality risk in ICU patients with aplastic anemia, aiding personalized clinical decision-making.

Contribution

The paper introduces a novel, validated set of interactive nomograms using machine learning-selected predictors for short-term mortality in ICU aplastic anemia patients.

Findings

Logistic regression outperformed Cox regression in predictive accuracy.

Seven key predictors were identified for mortality risk.

Nomograms demonstrated high AUROC values in both internal and external validation.

Abstract

Aplastic anemia is a rare, life-threatening hematologic disorder characterized by pancytopenia and bone marrow failure. ICU admission in these patients often signals critical complications or disease progression, making early risk assessment crucial for clinical decision-making and resource allocation. In this study, we used the MIMIC-IV database to identify ICU patients diagnosed with aplastic anemia and extracted clinical features from five domains: demographics, synthetic indicators, laboratory results, comorbidities, and medications. Over 400 variables were reduced to seven key predictors through machine learning-based feature selection. Logistic regression and Cox regression models were constructed to predict 7-, 14-, and 28-day mortality, and their performance was evaluated using AUROC. External validation was conducted using the eICU Collaborative Research Database to assess model generalizability. Among 1,662 included patients, the logistic regression model demonstrated superior performance, with AUROC values of 0.8227, 0.8311, and 0.8298 for 7-, 14-, and 28-day mortality, respectively, compared to the Cox model. External validation yielded AUROCs of 0.7391, 0.7119, and 0.7093. Interactive nomograms were developed based on the logistic regression model to visually estimate individual patient risk. In conclusion, we identified a concise set of seven predictors, led by APS III, to build validated and generalizable nomograms that accurately estimate short-term mortality in ICU patients with aplastic anemia. These tools may aid clinicians in personalized risk stratification and decision-making at the point of care.