A novel machine learning prediction model for metastasis in breast cancer
Abstract Background Breast cancer (BC) metastasis is the common cause of high mortality. Conventional prognostic criteria cannot accurately predict the BC metastasis risk. The machine learning technologies can overcome the disadvantage of conventional models. Aim We developed a model to predict BC m...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2024-03-01
|
| Series: | Cancer Reports |
| Subjects: | |
| Online Access: | https://doi.org/10.1002/cnr2.2006 |
| _version_ | 1797236883567149056 |
|---|---|
| author | Huan Li Ren‐Bin Liu Chen‐meng Long Yuan Teng Yu Liu |
| author_facet | Huan Li Ren‐Bin Liu Chen‐meng Long Yuan Teng Yu Liu |
| author_sort | Huan Li |
| collection | DOAJ |
| description | Abstract Background Breast cancer (BC) metastasis is the common cause of high mortality. Conventional prognostic criteria cannot accurately predict the BC metastasis risk. The machine learning technologies can overcome the disadvantage of conventional models. Aim We developed a model to predict BC metastasis using the random survival forest (RSF) method. Methods Based on demographic data and routine clinical data, we used RSF‐recursive feature elimination to identify the predictive variables and developed a model to predict metastasis using RSF method. The area under the receiver operating characteristic curve (AUROC) and Kaplan–Meier survival (KM) analyses were plotted to validate the predictive effect when C‐index was plotted to assess the discrimination and Brier scores was plotted to assess the calibration of the predictive model. Results We developed a metastasis prediction model comprising three variables (pathological stage, aspartate aminotransferase, and neutrophil count) selected by RSF‐recursive feature elimination. The model was reliable and stable when assessed by the AUROC (0.932 in training set and 0.905 in validation set) and KM survival analyses (p < .0001). The C‐indexes (0.959) and Brier score (0.097) also validated the good predictive ability of this model. Conclusions This model relies on routine data and examination indicators in real‐time clinical practice and exhibits an accurate prediction performance without increasing the cost for patients. Using this model, clinicians can facilitate risk communication and provide precise and efficient individualized therapy to patients with breast cancer. |
| first_indexed | 2024-04-24T17:10:56Z |
| format | Article |
| id | doaj.art-c286b876a571489cbc6cb249294df985 |
| institution | Directory Open Access Journal |
| issn | 2573-8348 |
| language | English |
| last_indexed | 2024-04-24T17:10:56Z |
| publishDate | 2024-03-01 |
| publisher | Wiley |
| record_format | Article |
| series | Cancer Reports |
| spelling | doaj.art-c286b876a571489cbc6cb249294df9852024-03-28T12:30:35ZengWileyCancer Reports2573-83482024-03-0173n/an/a10.1002/cnr2.2006A novel machine learning prediction model for metastasis in breast cancerHuan Li0Ren‐Bin Liu1Chen‐meng Long2Yuan Teng3Yu Liu4Department of Thyroid and Breast Surgery Third Affiliated Hospital of Sun Yat‐sen University Guangzhou ChinaDepartment of Thyroid and Breast Surgery Third Affiliated Hospital of Sun Yat‐sen University Guangzhou ChinaDepartment of Breast Surgery Liuzhou Women and Children's Medical Center Liuzhou ChinaDepartment of Breast Surgery Guangzhou Women and Children's Medical Center Guangzhou ChinaDepartment of Thyroid and Breast Surgery Third Affiliated Hospital of Sun Yat‐sen University Guangzhou ChinaAbstract Background Breast cancer (BC) metastasis is the common cause of high mortality. Conventional prognostic criteria cannot accurately predict the BC metastasis risk. The machine learning technologies can overcome the disadvantage of conventional models. Aim We developed a model to predict BC metastasis using the random survival forest (RSF) method. Methods Based on demographic data and routine clinical data, we used RSF‐recursive feature elimination to identify the predictive variables and developed a model to predict metastasis using RSF method. The area under the receiver operating characteristic curve (AUROC) and Kaplan–Meier survival (KM) analyses were plotted to validate the predictive effect when C‐index was plotted to assess the discrimination and Brier scores was plotted to assess the calibration of the predictive model. Results We developed a metastasis prediction model comprising three variables (pathological stage, aspartate aminotransferase, and neutrophil count) selected by RSF‐recursive feature elimination. The model was reliable and stable when assessed by the AUROC (0.932 in training set and 0.905 in validation set) and KM survival analyses (p < .0001). The C‐indexes (0.959) and Brier score (0.097) also validated the good predictive ability of this model. Conclusions This model relies on routine data and examination indicators in real‐time clinical practice and exhibits an accurate prediction performance without increasing the cost for patients. Using this model, clinicians can facilitate risk communication and provide precise and efficient individualized therapy to patients with breast cancer.https://doi.org/10.1002/cnr2.2006breast cancermetastasispredictive modelrandom survival forestrecursive feature elimination |
| spellingShingle | Huan Li Ren‐Bin Liu Chen‐meng Long Yuan Teng Yu Liu A novel machine learning prediction model for metastasis in breast cancer Cancer Reports breast cancer metastasis predictive model random survival forest recursive feature elimination |
| title | A novel machine learning prediction model for metastasis in breast cancer |
| title_full | A novel machine learning prediction model for metastasis in breast cancer |
| title_fullStr | A novel machine learning prediction model for metastasis in breast cancer |
| title_full_unstemmed | A novel machine learning prediction model for metastasis in breast cancer |
| title_short | A novel machine learning prediction model for metastasis in breast cancer |
| title_sort | novel machine learning prediction model for metastasis in breast cancer |
| topic | breast cancer metastasis predictive model random survival forest recursive feature elimination |
| url | https://doi.org/10.1002/cnr2.2006 |
| work_keys_str_mv | AT huanli anovelmachinelearningpredictionmodelformetastasisinbreastcancer AT renbinliu anovelmachinelearningpredictionmodelformetastasisinbreastcancer AT chenmenglong anovelmachinelearningpredictionmodelformetastasisinbreastcancer AT yuanteng anovelmachinelearningpredictionmodelformetastasisinbreastcancer AT yuliu anovelmachinelearningpredictionmodelformetastasisinbreastcancer AT huanli novelmachinelearningpredictionmodelformetastasisinbreastcancer AT renbinliu novelmachinelearningpredictionmodelformetastasisinbreastcancer AT chenmenglong novelmachinelearningpredictionmodelformetastasisinbreastcancer AT yuanteng novelmachinelearningpredictionmodelformetastasisinbreastcancer AT yuliu novelmachinelearningpredictionmodelformetastasisinbreastcancer |