Supervised Machine Learning for Breast Cancer Risk Factors Analysis and Survival Prediction

Childhood and adolescent overweight and obesity are one of the most serious public health challenges of the 21st century. A range of genetic, family, and environmental factors, and health behaviors are associated with childhood obesity. Developing models to predict childhood obesity requires careful examination of how these factors contribute to the emergence of childhood obesity. This paper has employed Multiple Linear Regression (MLR), Random Forest (RF), Decision Tree (DT), and K-Nearest Neighbour (KNN) models to predict the age at the onset of childhood obesity in Saudi Arabia (S.A.) and to identify the significant factors associated with it. De-identified data from Arar and Riyadh regions of S.A. were used to develop the prediction models and to compare their performance using multi-prediction accuracy measures. The average age at the onset of obesity is 10.8 years with no significant difference between boys and girls. The most common age group for onset is (5-15) years. RF model with the R2 = 0.98, the root mean square error = 0.44, and mean absolute error = 0.28 outperformed other models followed by MLR, DT, and KNN. The age at the onset of obesity was linked to several demographic, medical, and lifestyle factors including height and weight, parents’ education level and income, consanguineous marriage, family history, autism, gestational age, nutrition in the first 6 months, birth weight, sleep hours, and lack of physical activities. The results can assist in reducing the childhood obesity epidemic in Saudi Arabia by identifying and managing high-risk individuals and providing better preventive care. Furthermore, the study findings can assist in predicting and preventing childhood obesity in other populations.

show abstract

Multimodal Machine Learning for Predicting Post-Surgery Quality of Life in Colorectal Cancer Patients

Rhanoui,

Mikram,

Amazian

et al. 2024

J. Imaging

View full text Add to dashboard Cite

Colorectal cancer is a major public health issue, causing significant morbidity and mortality worldwide. Treatment for colorectal cancer often has a significant impact on patients’ quality of life, which can vary over time and across individuals. The application of artificial intelligence and machine learning techniques has great potential for optimizing patient outcomes by providing valuable insights. In this paper, we propose a multimodal machine learning framework for the prediction of quality of life indicators in colorectal cancer patients at various temporal stages, leveraging both clinical data and computed tomography scan images. Additionally, we identify key predictive factors for each quality of life indicator, thereby enabling clinicians to make more informed treatment decisions and ultimately enhance patient outcomes. Our approach integrates data from multiple sources, enhancing the performance of our predictive models. The analysis demonstrates a notable improvement in accuracy for some indicators, with results for the Wexner score increasing from 24% to 48% and for the Anorectal Ultrasound score from 88% to 96% after integrating data from different modalities. These results highlight the potential of multimodal learning to provide valuable insights and improve patient care in real-world applications.

show abstract

Supervised Machine Learning for Breast Cancer Risk Factors Analysis and Survival Prediction

Cited by 3 publications

References 30 publications

Deep Learning-Based Multi-task Approach for Neuronal Cells Classification and Segmentation

Deep Learning-Based Multi-task Approach for Neuronal Cells Classification and Segmentation

Predicting age at onset of childhood obesity using regression, Random Forest, Decision Tree, and K-Nearest Neighbour—A case study in Saudi Arabia

Multimodal Machine Learning for Predicting Post-Surgery Quality of Life in Colorectal Cancer Patients

Contact Info

Product

Resources

About