AI Article Synopsis
- Predictive models using average cases may fall short for unique patients, as they rely on a general population cohort.
- Building more personalized models by focusing on sub-cohorts of similar patients could enhance accuracy, utilizing secondary data like diagnoses and treatments over primary measurements.
- The study proposes a classification approach where similar patient classes are created based on secondary data, with a predictive model applied to classify new patients, successfully employing five easily obtainable measurements from initial hospital admission.
Article Abstract
Predictive models optimized for average cases might work not perfect for cases deviating from average because they are based on a cohort of all patients. Models could be more personalized if they were built on a sub-cohort of patients similar to a current one and to train models on data collected from those similar patients. In this paper, we consider patient similarity as a classification task. We suppose that data such as diagnoses and treatment obtained by physicians (secondary data) are more relevant for similarity than tests and measurements (primary data). We defined several classes based on diagnoses and outcomes and apply a predictive model for classification. We used five commonly used and easy to obtain measurements as predictors for the model. All measurements were collected during the first 24 hours after admission. We have shown that classes of similar patients can be defined on the basis of a previous patient's secondary data and new patients can be classified into these classes.
Download full-text PDF |
Source |
|---|
Publication Analysis
Top Keywords
Similar Publications
Want AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!