AI-powered Somatic Cancer Cell Analysis for Early Detection of Metastasis: The 62 principal Cancer Types
Background: Early detection of metastasis is critical in improving survival outcomes in cancer patients, with artificial intelligence offering advanced tools for predictive analytics. Objective: To emphasize the importance of early metastasis detection in improving cancer patient outcomes, and to h...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Universitas Padjadjaran
2025-04-01
|
| Series: | International Journal of Integrated Health Sciences |
| Subjects: | |
| Online Access: | https://journal.fk.unpad.ac.id/index.php/ijihs/article/view/4061 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | Background: Early detection of metastasis is critical in improving survival outcomes in cancer patients, with artificial intelligence offering advanced tools for predictive analytics.
Objective: To emphasize the importance of early metastasis detection in improving cancer patient outcomes, and to highlight that recent advancements in AI-powered somatic cancer cell analysis may enhance early detection and personalize treatment strategies.
Methods: This study leveraged a comprehensive survival and artificial intelligence (AI) powered analysis to identify key genomic and clinical factors influencing cancer prognosis, with a focus on early metastatic detection. The AI algorithms explored the possibility of detecting tumors with a high spread risk. The study underscored the critical role of AI-powered analysis in the early detection of metastasis and the personalization of treatment strategies in cancer care.
Results: By leveraging advanced AI algorithms, key predictors of cancer prognosis such as fraction genome alteration, primary tumor site, and smoking history, all of which significantly influence metastasis outcomes, were identified. Furthermore, the models demonstrated exceptional predictive accuracy, with XGBoost and Support Vector Machines achieving an accuracy of 0.95.
Conclusion: Integrating AI capabilities into clinical workflows holds the promise of significantly enhancing early detection and treatment of metastatic cancer, thereby improving patient outcomes and optimizing therapeutic interventions. |
|---|---|
| ISSN: | 2302-1381 2338-4506 |