Related Experiment Video
Updated: May 2, 2026
12:18
A Machine Learning Approach to Design an Efficient Selective Screening of Mild Cognitive Impairment
Published on: January 11, 2020
7.0K
A modified real AdaBoost algorithm to discover intensive care unit subgroups with a poor outcome.
Antonie Koetsier1, Nicolette F de Keizer1, Ameen Abu-Hanna1
1Academic Medical Center, Amsterdam, the Netherlands.
AMIA ... Annual Symposium Proceedings. AMIA Symposium
|February 20, 2014
Summary
Researchers identified specific patient subgroups within Intensive Care Units (ICUs) that experience poorer outcomes. This finding highlights areas for potential quality improvement in critical care, using a novel data analysis method.
Area of Science:
- Critical Care Medicine
- Health Services Research
- Data Science in Healthcare
Background:
- Intensive Care Unit (ICU) patient populations are diverse, leading to variations in care quality.
- Identifying specific patient subgroups with poor outcomes is crucial for targeted quality improvement initiatives.
Purpose of the Study:
- To investigate if poor Intensive Care Unit (ICU) outcomes can be attributed to excess deaths within specific patient subgroups.
- To develop and apply a novel algorithm for discovering these high-risk subgroups.
Main Methods:
- A modified adaptive decision tree boosting algorithm was applied to data from 80 Dutch ICUs.
- Candidate subgroups were identified and validated by comparing case-mix adjusted outcomes against top-performing ICUs.
Main Results:
- The algorithm identified 122 genuine subgroups across 59 ICUs, with a median of three defining variables (e.g., Glasgow Coma Scale, age).
- Of 29 ICUs with overall poor outcomes, the algorithm identified the source of excess deaths in 22.
Conclusions:
- A new adaptive decision tree boosting method effectively discovers patient subgroups with potentially improvable outcomes in ICUs.
- This approach offers a data-driven strategy for enhancing critical care quality by focusing on specific patient segments.
Related Concept Videos
01:20Comparing the Survival Analysis of Two or More Groups
712
Survival analysis is a cornerstone of medical research, used to evaluate the time until an event of interest occurs, such as death, disease recurrence, or recovery. Unlike standard statistical methods, survival analysis is particularly adept at handling censored data—instances where the event has not occurred for some participants by the end of the study or remains unobserved. To address these unique challenges, specialized techniques like the Kaplan-Meier estimator, log-rank test, and...
712
01:17Classification of Illness
9.4K
The meaning of illness is individualized to each person who experiences an alteration in health. In contrast, disease is a medical term indicating a pathological change in the structure and function of the body or mind. It is a condition that has specific symptoms and boundaries.
An illness is a response to a disease in which the person's level of functioning is changed compared with a previous level. The general classification of illness includes acute and chronic.
Acute illness is severe...
An illness is a response to a disease in which the person's level of functioning is changed compared with a previous level. The general classification of illness includes acute and chronic.
Acute illness is severe...
9.4K
01:21Cancer Survival Analysis
863
Cancer survival analysis focuses on quantifying and interpreting the time from a key starting point, such as diagnosis or the initiation of treatment, to a specific endpoint, such as remission or death. This analysis provides critical insights into treatment effectiveness and factors that influence patient outcomes, helping to shape clinical decisions and guide prognostic evaluations. A cornerstone of oncology research, survival analysis tackles the challenges of skewed, non-normally...
863
01:02Quantifying and Rejecting Outliers: The Grubbs Test
4.0K
Sometimes, a data set can have a recorded numerical observation that greatly deviates from the rest of the data. Assuming that the data is normally distributed, a statistical method called the Grubbs test can be used to determine whether the observation is truly an outlier. To perform a two-tailed Grubbs test, first, calculate the absolute difference between the outlier and the mean. Then, calculate the ratio between this difference and the standard deviation of the sample. This...
4.0K