Explainable machine learning of the breast cancer staging for designing smart biomarker sensors
In medical diagnostics, smart biomarker sensors are used to detect and monitor biomarker thresholds. Recent bariatric research has shown a connection between obesity and an elevated risk of breast cancer in women, with the growth of adipose tissues and malignancy as a disease caused by the secretion...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
KeAi Communications Co., Ltd.
2022-01-01
|
| Series: | Sensors International |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S266635112200047X |
| _version_ | 1828064466066997248 |
|---|---|
| author | Muhammad Idrees Ayesha Sohail |
| author_facet | Muhammad Idrees Ayesha Sohail |
| author_sort | Muhammad Idrees |
| collection | DOAJ |
| description | In medical diagnostics, smart biomarker sensors are used to detect and monitor biomarker thresholds. Recent bariatric research has shown a connection between obesity and an elevated risk of breast cancer in women, with the growth of adipose tissues and malignancy as a disease caused by the secretion of proinflammatory cytokines and adipocytokines. The current article focuses on HOMA, leptin, adiponectin, and resistin, the adipocytokines that have been identified as the primary causes of breast cancer in obese women during the last two decades. In this manuscript, the XAI tool is implemented on the breast cancer data and presents graphical interpretation. The clinical significance and molecular processes behind circulating HOMA, leptin, adiponectin, and breast cancer resistance have been explored, and XAI methods have been used to construct models for the identification of novel breast cancer biomarkers. The premise of this study is based on classifying each adipokine into two groups: low- and high-level concentrations. We examine the correlation between each group and the likelihood of developing breast cancer. The results provided useful evidence to develop accurate treatment interventions for breast cancer patients based on their biomarker levels and body mass index. |
| first_indexed | 2024-04-10T22:59:18Z |
| format | Article |
| id | doaj.art-95a4ae501d1549e49ef9abe947a25391 |
| institution | Directory Open Access Journal |
| issn | 2666-3511 |
| language | English |
| last_indexed | 2024-04-10T22:59:18Z |
| publishDate | 2022-01-01 |
| publisher | KeAi Communications Co., Ltd. |
| record_format | Article |
| series | Sensors International |
| spelling | doaj.art-95a4ae501d1549e49ef9abe947a253912023-01-14T04:27:29ZengKeAi Communications Co., Ltd.Sensors International2666-35112022-01-013100202Explainable machine learning of the breast cancer staging for designing smart biomarker sensorsMuhammad Idrees0Ayesha Sohail1Department of Mathematics and Statistics, The University of Lahore, Lahore, 54000, PakistanDepartment of Mathematics, Comsats University Islamabad, Lahore, 54000, Pakistan; Corresponding author.In medical diagnostics, smart biomarker sensors are used to detect and monitor biomarker thresholds. Recent bariatric research has shown a connection between obesity and an elevated risk of breast cancer in women, with the growth of adipose tissues and malignancy as a disease caused by the secretion of proinflammatory cytokines and adipocytokines. The current article focuses on HOMA, leptin, adiponectin, and resistin, the adipocytokines that have been identified as the primary causes of breast cancer in obese women during the last two decades. In this manuscript, the XAI tool is implemented on the breast cancer data and presents graphical interpretation. The clinical significance and molecular processes behind circulating HOMA, leptin, adiponectin, and breast cancer resistance have been explored, and XAI methods have been used to construct models for the identification of novel breast cancer biomarkers. The premise of this study is based on classifying each adipokine into two groups: low- and high-level concentrations. We examine the correlation between each group and the likelihood of developing breast cancer. The results provided useful evidence to develop accurate treatment interventions for breast cancer patients based on their biomarker levels and body mass index.http://www.sciencedirect.com/science/article/pii/S266635112200047XXAIBiomarkersSupport vector machine learningBiomedical engineering |
| spellingShingle | Muhammad Idrees Ayesha Sohail Explainable machine learning of the breast cancer staging for designing smart biomarker sensors Sensors International XAI Biomarkers Support vector machine learning Biomedical engineering |
| title | Explainable machine learning of the breast cancer staging for designing smart biomarker sensors |
| title_full | Explainable machine learning of the breast cancer staging for designing smart biomarker sensors |
| title_fullStr | Explainable machine learning of the breast cancer staging for designing smart biomarker sensors |
| title_full_unstemmed | Explainable machine learning of the breast cancer staging for designing smart biomarker sensors |
| title_short | Explainable machine learning of the breast cancer staging for designing smart biomarker sensors |
| title_sort | explainable machine learning of the breast cancer staging for designing smart biomarker sensors |
| topic | XAI Biomarkers Support vector machine learning Biomedical engineering |
| url | http://www.sciencedirect.com/science/article/pii/S266635112200047X |
| work_keys_str_mv | AT muhammadidrees explainablemachinelearningofthebreastcancerstagingfordesigningsmartbiomarkersensors AT ayeshasohail explainablemachinelearningofthebreastcancerstagingfordesigningsmartbiomarkersensors |