Sparse feature selection for classification and prediction of metastasis in endometrial cancer
Abstract Background Metastasis via pelvic and/or para-aortic lymph nodes is a major risk factor for endometrial cancer. Lymph-node resection ameliorates risk but is associated with significant co-morbidities. Incidence in patients with stage I disease is 4–22% but no mechanism exists to accurately p...
| Main Authors: | , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2017-03-01
|
| Series: | BMC Genomics |
| Subjects: | |
| Online Access: | http://link.springer.com/article/10.1186/s12864-017-3604-y |
| _version_ | 1818029877659435008 |
|---|---|
| author | Mehmet Eren Ahsen Todd P. Boren Nitin K. Singh Burook Misganaw David G. Mutch Kathleen N. Moore Floor J. Backes Carolyn K. McCourt Jayanthi S. Lea David S. Miller Michael A. White Mathukumalli Vidyasagar |
| author_facet | Mehmet Eren Ahsen Todd P. Boren Nitin K. Singh Burook Misganaw David G. Mutch Kathleen N. Moore Floor J. Backes Carolyn K. McCourt Jayanthi S. Lea David S. Miller Michael A. White Mathukumalli Vidyasagar |
| author_sort | Mehmet Eren Ahsen |
| collection | DOAJ |
| description | Abstract Background Metastasis via pelvic and/or para-aortic lymph nodes is a major risk factor for endometrial cancer. Lymph-node resection ameliorates risk but is associated with significant co-morbidities. Incidence in patients with stage I disease is 4–22% but no mechanism exists to accurately predict it. Therefore, national guidelines for primary staging surgery include pelvic and para-aortic lymph node dissection for all patients whose tumor exceeds 2cm in diameter. We sought to identify a robust molecular signature that can accurately classify risk of lymph node metastasis in endometrial cancer patients. 86 tumors matched for age and race, and evenly distributed between lymph node-positive and lymph node-negative cases, were selected as a training cohort. Genomic micro-RNA expression was profiled for each sample to serve as the predictive feature matrix. An independent set of 28 tumor samples was collected and similarly characterized to serve as a test cohort. Results A feature selection algorithm was designed for applications where the number of samples is far smaller than the number of measured features per sample. A predictive miRNA expression signature was developed using this algorithm, which was then used to predict the metastatic status of the independent test cohort. A weighted classifier, using 18 micro-RNAs, achieved 100% accuracy on the training cohort. When applied to the testing cohort, the classifier correctly predicted 90% of node-positive cases, and 80% of node-negative cases (FDR = 6.25%). Conclusion Results indicate that the evaluation of the quantitative sparse-feature classifier proposed here in clinical trials may lead to significant improvement in the prediction of lymphatic metastases in endometrial cancer patients. |
| first_indexed | 2024-12-10T05:26:40Z |
| format | Article |
| id | doaj.art-5685153e23b84181b171b36625789c9b |
| institution | Directory Open Access Journal |
| issn | 1471-2164 |
| language | English |
| last_indexed | 2024-12-10T05:26:40Z |
| publishDate | 2017-03-01 |
| publisher | BMC |
| record_format | Article |
| series | BMC Genomics |
| spelling | doaj.art-5685153e23b84181b171b36625789c9b2022-12-22T02:00:41ZengBMCBMC Genomics1471-21642017-03-0118S311210.1186/s12864-017-3604-ySparse feature selection for classification and prediction of metastasis in endometrial cancerMehmet Eren Ahsen0Todd P. Boren1Nitin K. Singh2Burook Misganaw3David G. Mutch4Kathleen N. Moore5Floor J. Backes6Carolyn K. McCourt7Jayanthi S. Lea8David S. Miller9Michael A. White10Mathukumalli Vidyasagar11IBM ResearchThe University of Tennessee, College of MedicineApple R&DHarvard UniversityThe Washington University School of MedicineThe University of OklohomaThe Ohio State UniversityWomen and Infants Hospital, Brown UniversityUniversity of Texas Southwestern Medical CenterUniversity of Texas Southwestern Medical CenterUniversity of Texas Southwestern Medical CenterThe University of Texas at DallasAbstract Background Metastasis via pelvic and/or para-aortic lymph nodes is a major risk factor for endometrial cancer. Lymph-node resection ameliorates risk but is associated with significant co-morbidities. Incidence in patients with stage I disease is 4–22% but no mechanism exists to accurately predict it. Therefore, national guidelines for primary staging surgery include pelvic and para-aortic lymph node dissection for all patients whose tumor exceeds 2cm in diameter. We sought to identify a robust molecular signature that can accurately classify risk of lymph node metastasis in endometrial cancer patients. 86 tumors matched for age and race, and evenly distributed between lymph node-positive and lymph node-negative cases, were selected as a training cohort. Genomic micro-RNA expression was profiled for each sample to serve as the predictive feature matrix. An independent set of 28 tumor samples was collected and similarly characterized to serve as a test cohort. Results A feature selection algorithm was designed for applications where the number of samples is far smaller than the number of measured features per sample. A predictive miRNA expression signature was developed using this algorithm, which was then used to predict the metastatic status of the independent test cohort. A weighted classifier, using 18 micro-RNAs, achieved 100% accuracy on the training cohort. When applied to the testing cohort, the classifier correctly predicted 90% of node-positive cases, and 80% of node-negative cases (FDR = 6.25%). Conclusion Results indicate that the evaluation of the quantitative sparse-feature classifier proposed here in clinical trials may lead to significant improvement in the prediction of lymphatic metastases in endometrial cancer patients.http://link.springer.com/article/10.1186/s12864-017-3604-yEndometrial cancerLymph node metastasisSparse classificationMachine learning |
| spellingShingle | Mehmet Eren Ahsen Todd P. Boren Nitin K. Singh Burook Misganaw David G. Mutch Kathleen N. Moore Floor J. Backes Carolyn K. McCourt Jayanthi S. Lea David S. Miller Michael A. White Mathukumalli Vidyasagar Sparse feature selection for classification and prediction of metastasis in endometrial cancer BMC Genomics Endometrial cancer Lymph node metastasis Sparse classification Machine learning |
| title | Sparse feature selection for classification and prediction of metastasis in endometrial cancer |
| title_full | Sparse feature selection for classification and prediction of metastasis in endometrial cancer |
| title_fullStr | Sparse feature selection for classification and prediction of metastasis in endometrial cancer |
| title_full_unstemmed | Sparse feature selection for classification and prediction of metastasis in endometrial cancer |
| title_short | Sparse feature selection for classification and prediction of metastasis in endometrial cancer |
| title_sort | sparse feature selection for classification and prediction of metastasis in endometrial cancer |
| topic | Endometrial cancer Lymph node metastasis Sparse classification Machine learning |
| url | http://link.springer.com/article/10.1186/s12864-017-3604-y |
| work_keys_str_mv | AT mehmeterenahsen sparsefeatureselectionforclassificationandpredictionofmetastasisinendometrialcancer AT toddpboren sparsefeatureselectionforclassificationandpredictionofmetastasisinendometrialcancer AT nitinksingh sparsefeatureselectionforclassificationandpredictionofmetastasisinendometrialcancer AT burookmisganaw sparsefeatureselectionforclassificationandpredictionofmetastasisinendometrialcancer AT davidgmutch sparsefeatureselectionforclassificationandpredictionofmetastasisinendometrialcancer AT kathleennmoore sparsefeatureselectionforclassificationandpredictionofmetastasisinendometrialcancer AT floorjbackes sparsefeatureselectionforclassificationandpredictionofmetastasisinendometrialcancer AT carolynkmccourt sparsefeatureselectionforclassificationandpredictionofmetastasisinendometrialcancer AT jayanthislea sparsefeatureselectionforclassificationandpredictionofmetastasisinendometrialcancer AT davidsmiller sparsefeatureselectionforclassificationandpredictionofmetastasisinendometrialcancer AT michaelawhite sparsefeatureselectionforclassificationandpredictionofmetastasisinendometrialcancer AT mathukumallividyasagar sparsefeatureselectionforclassificationandpredictionofmetastasisinendometrialcancer |