Utility of a Clinically Guided Data-Driven Approach for Predicting Breast Cancer Complications: An Application Using
Daniel Pichardo1, Russ Michael1, Michele Mercer1
1Blue Health Intelligence, Chicago, IL.
JCO Clinical Cancer Informatics
|November 23, 2022
Summary
Predictive models can identify short-term adverse events (AEs) in breast cancer (BCa) survivors. Machine learning models like gradient boosted trees (GBT) show strong performance in predicting BCa treatment-related AEs.
Area of Science:
- Oncology
- Biostatistics
- Health Informatics
Background:
- Increasing numbers of breast cancer (BCa) survivors face treatment-related side effects.
- Descriptive studies are common, but predictive approaches for adverse events (AEs) are needed for proactive strategies.
- Focus on short-term AEs in BCa survivors is crucial for managing quality of life.
Purpose of the Study:
- To evaluate the performance of predictive models for disease- or treatment-related adverse events (AEs) in women diagnosed with breast cancer (BCa).
- To compare different machine learning models in predicting short-term AEs within six months of cancer-directed treatment.
- To establish a foundation for proactive management of treatment complications in BCa patients.
Main Methods:
- Utilized administrative claims data from the Blue Health Intelligence National Data Repository.
- Included female individuals aged 18+ diagnosed with BCa and receiving cancer-directed treatment (Jan 2014 - Aug 2019).
- Developed and compared logistic regression, Lasso regression, gradient boosted tree (GBT), and random forest (RF) models using area under the receiver operating characteristic curve (AUC) and other metrics.
Main Results:
- Compared to logistic regression (AUC 0.82), Lasso (0.89), GBT (0.91), and RF (0.90) models demonstrated superior predictive performance.
- GBT, Lasso, and RF models achieved high sensitivity (0.96) for predicting AEs.
- Positive predictive values were consistently high (0.96) across GBT, Lasso, and RF models, indicating reliability.
Conclusions:
- Machine learning models, particularly GBT, show significant potential for accurately predicting short-term treatment-related adverse events in breast cancer patients.
- Big data methods combined with clinical frameworks can reliably forecast AEs, enabling proactive patient care.
- These predictive capabilities can inform clinical decision-making and improve outcomes for breast cancer survivors.
More Related Videos
Related Concept Videos
01:21Cancer Survival Analysis
415
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...
415
01:24Kaplan-Meier Approach
225
The Kaplan-Meier estimator is a non-parametric method used to estimate the survival function from time-to-event data. In medical research, it is frequently employed to measure the proportion of patients surviving for a certain period after treatment. This estimator is fundamental in analyzing time-to-event data, making it indispensable in clinical trials, epidemiological studies, and reliability engineering. By estimating survival probabilities, researchers can evaluate treatment effectiveness,...
225
01:23Types of Biopharmaceutical Studies: Controlled and Non-Controlled Approaches
157
Biopharmaceutical studies constitute a vital field aiming to enhance drug delivery methods and refine therapeutic approaches, drawing upon diverse interdisciplinary knowledge. In research methodologies, the choice between controlled and non-controlled studies significantly influences the study's reliability and accuracy.
Non-controlled studies, commonly employed for initial exploration, lack a control group, rendering them susceptible to biases and external influences. In contrast,...
Non-controlled studies, commonly employed for initial exploration, lack a control group, rendering them susceptible to biases and external influences. In contrast,...
157
01:25Statistical Methods for Analyzing Epidemiological Data
480
Epidemiological data primarily involves information on specific populations' occurrence, distribution, and determinants of health and diseases. This data is crucial for understanding disease patterns and impacts, aiding public health decision-making and disease prevention strategies. The analysis of epidemiological data employs various statistical methods to interpret health-related data effectively. Here are some commonly used methods:
480
01:12Analysis of Population Pharmacokinetic Data
347
Analysis of population pharmacokinetic data involves studying the behavior of drugs within diverse populations to understand their pharmacokinetic parameters. Traditional pharmacokinetic methods typically involve collecting samples from a few individuals and estimating these parameters. While these methods are commonly used, they have limitations in capturing the variability in drug response among individuals or heterogeneous populations. Population pharmacokinetics is employed to address these...
347
02:50Combination Therapies and Personalized Medicine
5.0K
Combining two or more treatment methods increases the life span of cancer patients while reducing damage to vital organs or tissue from the overuse of a single treatment. Combination therapy also targets different cancer-inducing pathways, thus reducing the chances of developing resistance to treatment.
The combination of the drug acetazolamide and sulforaphane is a good example of combination therapy to treat cancer. The cells in the interior of a large tumor often die due to the hypoxic and...
The combination of the drug acetazolamide and sulforaphane is a good example of combination therapy to treat cancer. The cells in the interior of a large tumor often die due to the hypoxic and...
5.0K