Related Experiment Video
Updated: Jun 2, 2026
06:19
Constructing and Visualizing Models using Mime-based Machine-learning Framework
Published on: July 22, 2025
Development of a new predictive model for polypathological patients. The PROFUND index
M Bernabeu-Wittel1, M Ollero-Baturone, L Moreno-Gaviño
1Internal Medicine Department. Hospital Universitario Virgen del Rocío. Avda Manuel Siurot, s/n. 41013 Sevilla, Spain. maxbw@telefonica.net
European Journal of Internal Medicine
|May 17, 2011
Summary
A new prognostic index accurately predicts 1-year mortality risk in polypathological patients (PP). This tool aids clinicians in stratifying risk for this complex patient group.
Area of Science:
- Gerontology
- Internal Medicine
- Public Health
Background:
- Prognostic indexes often lack accuracy for polypathological patients (PP).
- PP represent an emergent and complex patient population.
- There is a need for reliable risk assessment tools in PP.
Purpose of the Study:
- To develop and validate a 1-year mortality predictive index specifically for polypathological patients (PP).
- To compare the accuracy of the new index with the Charlson index in PP.
Main Methods:
- A multicenter prospective cohort study involving 1,632 PP was conducted.
- Nine independent mortality predictors were identified and weighted to create a risk score.
- Index accuracy was assessed through calibration and discrimination (ROC curves) in derivation and validation cohorts.
Main Results:
- Mortality rates in derivation/validation cohorts were 35%/39.5%.
- The new index demonstrated good calibration and discrimination (AUC 0.77/0.7).
- The Charlson index showed suboptimal discrimination (AUC 0.59) in this population.
Conclusions:
- The developed prognostic index is an accurate and transportable tool for stratifying 1-year mortality risk in PP.
- This index offers improved risk assessment compared to the Charlson index for PP.
