A Hybrid Deep Learning-Based Feature Selection Approach for Supporting Early Detection of Long-Term Behavioral Outcomes in Survivors of Cancer: Cross-Sectional Study
Contact us if these videos are not relevant.
Contact us if these videos are not relevant.
View abstract on PubMed
Summary
This summary is machine-generated.A new deep learning feature selection algorithm improves prediction of negative behavioral outcomes in cancer survivors. This method enhances machine learning models, aiding early detection and preventive care for long-term patient well-being.
Area Of Science
- Computational oncology
- Machine learning in healthcare
- Behavioral science in survivorship
Background
- Cancer survivors increasingly face negative long-term behavioral outcomes from treatments.
- Existing computational methods struggle to predict these outcomes, hindering preventive care.
Purpose Of The Study
- To develop an advanced feature selection algorithm using deep learning.
- To enhance machine learning classifier performance for predicting adverse behavioral outcomes in cancer survivors.
Main Methods
- A hybrid, 2-stage deep learning feature selection approach was devised.
- The algorithm integrates clinical, treatment, and socioenvironmental factors.
- A case study involved 102 acute lymphoblastic leukemia survivors, with results visualized using radial charts.
Main Results
- The novel approach outperformed traditional methods in predicting key behavioral outcomes.
- Higher F1, precision, and recall scores were achieved compared to existing feature selection techniques.
- Significant clinical and socioenvironmental risk factors for behavioral problems in young survivors were identified.
Conclusions
- The developed feature selection algorithm shows potential for improving adverse outcome prediction in cancer survivors.
- This advancement can aid clinicians in early detection and personalized treatment strategies.
Keywords:
behavioral outcome predictions behavioral outcomes behavioral study cancer clinical domain–guided framework computational biology computational study data driven deep learning deep learning models feature selection hybrid leukemia machine learning neural network oncology patients with cancer prediction predictive modeling survivors of cancer
Contact us if these videos are not relevant.
Contact us if these videos are not relevant.
Related Concept Videos
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...
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...