Bayesian and deep‐learning models applied to the early detection of ovarian cancer using multiple longitudinal biomarkers
Abstract Background Ovarian cancer is the most lethal of all gynecological cancers. Cancer Antigen 125 (CA125) is the best‐performing ovarian cancer biomarker which however is still not effective as a screening test in the general population. Recent literature reports additional biomarkers with the...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2024-04-01
|
| Series: | Cancer Medicine |
| Subjects: | |
| Online Access: | https://doi.org/10.1002/cam4.7163 |
| _version_ | 1797205638939410432 |
|---|---|
| author | Luis Abrego Alexey Zaikin Ines P. Marino Mikhail I. Krivonosov Ian Jacobs Usha Menon Aleksandra Gentry‐Maharaj Oleg Blyuss |
| author_facet | Luis Abrego Alexey Zaikin Ines P. Marino Mikhail I. Krivonosov Ian Jacobs Usha Menon Aleksandra Gentry‐Maharaj Oleg Blyuss |
| author_sort | Luis Abrego |
| collection | DOAJ |
| description | Abstract Background Ovarian cancer is the most lethal of all gynecological cancers. Cancer Antigen 125 (CA125) is the best‐performing ovarian cancer biomarker which however is still not effective as a screening test in the general population. Recent literature reports additional biomarkers with the potential to improve on CA125 for early detection when using longitudinal multimarker models. Methods Our data comprised 180 controls and 44 cases with serum samples sourced from the multimodal arm of UK Collaborative Trial of Ovarian Cancer Screening (UKCTOCS). Our models were based on Bayesian change‐point detection and recurrent neural networks. Results We obtained a significantly higher performance for CA125–HE4 model using both methodologies (AUC 0.971, sensitivity 96.7% and AUC 0.987, sensitivity 96.7%) with respect to CA125 (AUC 0.949, sensitivity 90.8% and AUC 0.953, sensitivity 92.1%) for Bayesian change‐point model (BCP) and recurrent neural networks (RNN) approaches, respectively. One year before diagnosis, the CA125–HE4 model also ranked as the best, whereas at 2 years before diagnosis no multimarker model outperformed CA125. Conclusions Our study identified and tested different combination of biomarkers using longitudinal multivariable models that outperformed CA125 alone. We showed the potential of multivariable models and candidate biomarkers to increase the detection rate of ovarian cancer. |
| first_indexed | 2024-04-24T08:54:19Z |
| format | Article |
| id | doaj.art-6c163266eef744bc80d28a96ac3a01ee |
| institution | Directory Open Access Journal |
| issn | 2045-7634 |
| language | English |
| last_indexed | 2024-04-24T08:54:19Z |
| publishDate | 2024-04-01 |
| publisher | Wiley |
| record_format | Article |
| series | Cancer Medicine |
| spelling | doaj.art-6c163266eef744bc80d28a96ac3a01ee2024-04-16T08:48:34ZengWileyCancer Medicine2045-76342024-04-01137n/an/a10.1002/cam4.7163Bayesian and deep‐learning models applied to the early detection of ovarian cancer using multiple longitudinal biomarkersLuis Abrego0Alexey Zaikin1Ines P. Marino2Mikhail I. Krivonosov3Ian Jacobs4Usha Menon5Aleksandra Gentry‐Maharaj6Oleg Blyuss7Department of Women's Cancer EGA Institute for Women's Health, University College London London UKDepartment of Women's Cancer EGA Institute for Women's Health, University College London London UKDepartment of Biology and Geology, Physics and Inorganic Chemistry Universidad Rey Juan Carlos Madrid SpainResearch Center for Trusted Artificial Intelligence Ivannikov Institute for System Programming of the Russian Academy of Sciences Moscow RussiaDepartment of Women's Cancer EGA Institute for Women's Health, University College London London UKMRC Clinical Trials Unit University College London London UKDepartment of Women's Cancer EGA Institute for Women's Health, University College London London UKDepartment of Women's Cancer EGA Institute for Women's Health, University College London London UKAbstract Background Ovarian cancer is the most lethal of all gynecological cancers. Cancer Antigen 125 (CA125) is the best‐performing ovarian cancer biomarker which however is still not effective as a screening test in the general population. Recent literature reports additional biomarkers with the potential to improve on CA125 for early detection when using longitudinal multimarker models. Methods Our data comprised 180 controls and 44 cases with serum samples sourced from the multimodal arm of UK Collaborative Trial of Ovarian Cancer Screening (UKCTOCS). Our models were based on Bayesian change‐point detection and recurrent neural networks. Results We obtained a significantly higher performance for CA125–HE4 model using both methodologies (AUC 0.971, sensitivity 96.7% and AUC 0.987, sensitivity 96.7%) with respect to CA125 (AUC 0.949, sensitivity 90.8% and AUC 0.953, sensitivity 92.1%) for Bayesian change‐point model (BCP) and recurrent neural networks (RNN) approaches, respectively. One year before diagnosis, the CA125–HE4 model also ranked as the best, whereas at 2 years before diagnosis no multimarker model outperformed CA125. Conclusions Our study identified and tested different combination of biomarkers using longitudinal multivariable models that outperformed CA125 alone. We showed the potential of multivariable models and candidate biomarkers to increase the detection rate of ovarian cancer.https://doi.org/10.1002/cam4.7163CA125change‐point detectionlongitudinal biomarkersovarian cancerrecurrent neural networks |
| spellingShingle | Luis Abrego Alexey Zaikin Ines P. Marino Mikhail I. Krivonosov Ian Jacobs Usha Menon Aleksandra Gentry‐Maharaj Oleg Blyuss Bayesian and deep‐learning models applied to the early detection of ovarian cancer using multiple longitudinal biomarkers Cancer Medicine CA125 change‐point detection longitudinal biomarkers ovarian cancer recurrent neural networks |
| title | Bayesian and deep‐learning models applied to the early detection of ovarian cancer using multiple longitudinal biomarkers |
| title_full | Bayesian and deep‐learning models applied to the early detection of ovarian cancer using multiple longitudinal biomarkers |
| title_fullStr | Bayesian and deep‐learning models applied to the early detection of ovarian cancer using multiple longitudinal biomarkers |
| title_full_unstemmed | Bayesian and deep‐learning models applied to the early detection of ovarian cancer using multiple longitudinal biomarkers |
| title_short | Bayesian and deep‐learning models applied to the early detection of ovarian cancer using multiple longitudinal biomarkers |
| title_sort | bayesian and deep learning models applied to the early detection of ovarian cancer using multiple longitudinal biomarkers |
| topic | CA125 change‐point detection longitudinal biomarkers ovarian cancer recurrent neural networks |
| url | https://doi.org/10.1002/cam4.7163 |
| work_keys_str_mv | AT luisabrego bayesiananddeeplearningmodelsappliedtotheearlydetectionofovariancancerusingmultiplelongitudinalbiomarkers AT alexeyzaikin bayesiananddeeplearningmodelsappliedtotheearlydetectionofovariancancerusingmultiplelongitudinalbiomarkers AT inespmarino bayesiananddeeplearningmodelsappliedtotheearlydetectionofovariancancerusingmultiplelongitudinalbiomarkers AT mikhailikrivonosov bayesiananddeeplearningmodelsappliedtotheearlydetectionofovariancancerusingmultiplelongitudinalbiomarkers AT ianjacobs bayesiananddeeplearningmodelsappliedtotheearlydetectionofovariancancerusingmultiplelongitudinalbiomarkers AT ushamenon bayesiananddeeplearningmodelsappliedtotheearlydetectionofovariancancerusingmultiplelongitudinalbiomarkers AT aleksandragentrymaharaj bayesiananddeeplearningmodelsappliedtotheearlydetectionofovariancancerusingmultiplelongitudinalbiomarkers AT olegblyuss bayesiananddeeplearningmodelsappliedtotheearlydetectionofovariancancerusingmultiplelongitudinalbiomarkers |