Development of a Predictive Model of Occult Cancer After a Venous Thromboembolism Event Using Machine Learning: The CLOVER Study
<i>Background and Objectives</i>: Venous thromboembolism (VTE) can be the first manifestation of an underlying cancer. This study aimed to develop a predictive model to assess the risk of occult cancer between 30 days and 24 months after a venous thrombotic event using machine learning (...
Saved in:
| Main Authors: | , , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-12-01
|
| Series: | Medicina |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1648-9144/61/1/18 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832587996261515264 |
|---|---|
| author | Anabel Franco-Moreno Elena Madroñal-Cerezo Cristina Lucía de Ancos-Aracil Ana Isabel Farfán-Sedano Nuria Muñoz-Rivas José Bascuñana Morejón-Girón José Manuel Ruiz-Giardín Federico Álvarez-Rodríguez Jesús Prada-Alonso Yvonne Gala-García Miguel Ángel Casado-Suela Ana Bustamante-Fermosel Nuria Alfaro-Fernández Juan Torres-Macho |
| author_facet | Anabel Franco-Moreno Elena Madroñal-Cerezo Cristina Lucía de Ancos-Aracil Ana Isabel Farfán-Sedano Nuria Muñoz-Rivas José Bascuñana Morejón-Girón José Manuel Ruiz-Giardín Federico Álvarez-Rodríguez Jesús Prada-Alonso Yvonne Gala-García Miguel Ángel Casado-Suela Ana Bustamante-Fermosel Nuria Alfaro-Fernández Juan Torres-Macho |
| author_sort | Anabel Franco-Moreno |
| collection | DOAJ |
| description | <i>Background and Objectives</i>: Venous thromboembolism (VTE) can be the first manifestation of an underlying cancer. This study aimed to develop a predictive model to assess the risk of occult cancer between 30 days and 24 months after a venous thrombotic event using machine learning (ML). <i>Materials and Methods</i>: We designed a case–control study nested in a cohort of patients with VTE included in a prospective registry from two Spanish hospitals between 2005 and 2021. Both clinically and ML-driven feature selection were performed to identify predictors for occult cancer. XGBoost, LightGBM, and CatBoost algorithms were used to train different prediction models, which were subsequently validated in a hold-out dataset. <i>Results</i>: A total of 815 patients with VTE were included (51.5% male and median age of 59). During follow-up, 56 patients (6.9%) were diagnosed with cancer. One hundred and twenty-one variables were explored for the predictive analysis. CatBoost obtained better performance metrics among the ML models analyzed. The final CatBoost model included, among the top 15 variables to predict hidden malignancy, age, gender, systolic blood pressure, heart rate, weight, chronic lung disease, D-dimer, alanine aminotransferase, hemoglobin, serum creatinine, cholesterol, platelets, triglycerides, leukocyte count and previous VTE. The model had an ROC-AUC of 0.86 (95% CI, 0.83–0.87) in the test set. Sensitivity, specificity, and negative and positive predictive values were 62%, 94%, 93% and 75%, respectively. <i>Conclusions</i>: This is the first risk score developed for identifying patients with VTE who are at increased risk of occult cancer using ML tools, obtaining a remarkably high diagnostic accuracy. This study’s limitations include potential information bias from electronic health records and a small cancer sample size. In addition, variability in detection protocols and evolving clinical practices may affect model accuracy. Our score needs external validation. |
| format | Article |
| id | doaj-art-68485b073d1e465caede3a7eea38b9ac |
| institution | Kabale University |
| issn | 1010-660X 1648-9144 |
| language | English |
| publishDate | 2024-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Medicina |
| spelling | doaj-art-68485b073d1e465caede3a7eea38b9ac2025-01-24T13:40:16ZengMDPI AGMedicina1010-660X1648-91442024-12-016111810.3390/medicina61010018Development of a Predictive Model of Occult Cancer After a Venous Thromboembolism Event Using Machine Learning: The CLOVER StudyAnabel Franco-Moreno0Elena Madroñal-Cerezo1Cristina Lucía de Ancos-Aracil2Ana Isabel Farfán-Sedano3Nuria Muñoz-Rivas4José Bascuñana Morejón-Girón5José Manuel Ruiz-Giardín6Federico Álvarez-Rodríguez7Jesús Prada-Alonso8Yvonne Gala-García9Miguel Ángel Casado-Suela10Ana Bustamante-Fermosel11Nuria Alfaro-Fernández12Juan Torres-Macho13Department of Internal Medicine, Hospital Universitario Infanta Leonor–Virgen de la Torre, 28031 Madrid, SpainDepartment of Internal Medicine, Hospital Universitario de Fuenlabrada, 28942 Madrid, SpainDepartment of Internal Medicine, Hospital Universitario de Fuenlabrada, 28942 Madrid, SpainDepartment of Internal Medicine, Clínica Universidad de Navarra-Hospital, 31008 Pamplona, SpainDepartment of Internal Medicine, Hospital Universitario Infanta Leonor–Virgen de la Torre, 28031 Madrid, SpainDepartment of Internal Medicine, Hospital Universitario 12 de Octubre, 28041 Madrid, SpainDepartment of Internal Medicine, Hospital Universitario de Fuenlabrada, 28942 Madrid, SpainDepartment of Anatomical Pathology, Hospital Universitario Infanta Leonor–Virgen de la Torre, 28031 Madrid, SpainHorus-ML, Alcalá Street 268, 28027 Madrid, SpainHorus-ML, Alcalá Street 268, 28027 Madrid, SpainDepartment of Internal Medicine, Hospital Universitario Infanta Leonor–Virgen de la Torre, 28031 Madrid, SpainDepartment of Internal Medicine, Hospital Universitario Infanta Leonor–Virgen de la Torre, 28031 Madrid, SpainDepartment of Internal Medicine, Hospital Universitario Infanta Leonor–Virgen de la Torre, 28031 Madrid, SpainDepartment of Internal Medicine, Hospital Universitario Infanta Leonor–Virgen de la Torre, 28031 Madrid, Spain<i>Background and Objectives</i>: Venous thromboembolism (VTE) can be the first manifestation of an underlying cancer. This study aimed to develop a predictive model to assess the risk of occult cancer between 30 days and 24 months after a venous thrombotic event using machine learning (ML). <i>Materials and Methods</i>: We designed a case–control study nested in a cohort of patients with VTE included in a prospective registry from two Spanish hospitals between 2005 and 2021. Both clinically and ML-driven feature selection were performed to identify predictors for occult cancer. XGBoost, LightGBM, and CatBoost algorithms were used to train different prediction models, which were subsequently validated in a hold-out dataset. <i>Results</i>: A total of 815 patients with VTE were included (51.5% male and median age of 59). During follow-up, 56 patients (6.9%) were diagnosed with cancer. One hundred and twenty-one variables were explored for the predictive analysis. CatBoost obtained better performance metrics among the ML models analyzed. The final CatBoost model included, among the top 15 variables to predict hidden malignancy, age, gender, systolic blood pressure, heart rate, weight, chronic lung disease, D-dimer, alanine aminotransferase, hemoglobin, serum creatinine, cholesterol, platelets, triglycerides, leukocyte count and previous VTE. The model had an ROC-AUC of 0.86 (95% CI, 0.83–0.87) in the test set. Sensitivity, specificity, and negative and positive predictive values were 62%, 94%, 93% and 75%, respectively. <i>Conclusions</i>: This is the first risk score developed for identifying patients with VTE who are at increased risk of occult cancer using ML tools, obtaining a remarkably high diagnostic accuracy. This study’s limitations include potential information bias from electronic health records and a small cancer sample size. In addition, variability in detection protocols and evolving clinical practices may affect model accuracy. Our score needs external validation.https://www.mdpi.com/1648-9144/61/1/18early detection of cancermachine learningoccult malignancypredictive modelvenous thromboembolism |
| spellingShingle | Anabel Franco-Moreno Elena Madroñal-Cerezo Cristina Lucía de Ancos-Aracil Ana Isabel Farfán-Sedano Nuria Muñoz-Rivas José Bascuñana Morejón-Girón José Manuel Ruiz-Giardín Federico Álvarez-Rodríguez Jesús Prada-Alonso Yvonne Gala-García Miguel Ángel Casado-Suela Ana Bustamante-Fermosel Nuria Alfaro-Fernández Juan Torres-Macho Development of a Predictive Model of Occult Cancer After a Venous Thromboembolism Event Using Machine Learning: The CLOVER Study Medicina early detection of cancer machine learning occult malignancy predictive model venous thromboembolism |
| title | Development of a Predictive Model of Occult Cancer After a Venous Thromboembolism Event Using Machine Learning: The CLOVER Study |
| title_full | Development of a Predictive Model of Occult Cancer After a Venous Thromboembolism Event Using Machine Learning: The CLOVER Study |
| title_fullStr | Development of a Predictive Model of Occult Cancer After a Venous Thromboembolism Event Using Machine Learning: The CLOVER Study |
| title_full_unstemmed | Development of a Predictive Model of Occult Cancer After a Venous Thromboembolism Event Using Machine Learning: The CLOVER Study |
| title_short | Development of a Predictive Model of Occult Cancer After a Venous Thromboembolism Event Using Machine Learning: The CLOVER Study |
| title_sort | development of a predictive model of occult cancer after a venous thromboembolism event using machine learning the clover study |
| topic | early detection of cancer machine learning occult malignancy predictive model venous thromboembolism |
| url | https://www.mdpi.com/1648-9144/61/1/18 |
| work_keys_str_mv | AT anabelfrancomoreno developmentofapredictivemodelofoccultcancerafteravenousthromboembolismeventusingmachinelearningthecloverstudy AT elenamadronalcerezo developmentofapredictivemodelofoccultcancerafteravenousthromboembolismeventusingmachinelearningthecloverstudy AT cristinaluciadeancosaracil developmentofapredictivemodelofoccultcancerafteravenousthromboembolismeventusingmachinelearningthecloverstudy AT anaisabelfarfansedano developmentofapredictivemodelofoccultcancerafteravenousthromboembolismeventusingmachinelearningthecloverstudy AT nuriamunozrivas developmentofapredictivemodelofoccultcancerafteravenousthromboembolismeventusingmachinelearningthecloverstudy AT josebascunanamorejongiron developmentofapredictivemodelofoccultcancerafteravenousthromboembolismeventusingmachinelearningthecloverstudy AT josemanuelruizgiardin developmentofapredictivemodelofoccultcancerafteravenousthromboembolismeventusingmachinelearningthecloverstudy AT federicoalvarezrodriguez developmentofapredictivemodelofoccultcancerafteravenousthromboembolismeventusingmachinelearningthecloverstudy AT jesuspradaalonso developmentofapredictivemodelofoccultcancerafteravenousthromboembolismeventusingmachinelearningthecloverstudy AT yvonnegalagarcia developmentofapredictivemodelofoccultcancerafteravenousthromboembolismeventusingmachinelearningthecloverstudy AT miguelangelcasadosuela developmentofapredictivemodelofoccultcancerafteravenousthromboembolismeventusingmachinelearningthecloverstudy AT anabustamantefermosel developmentofapredictivemodelofoccultcancerafteravenousthromboembolismeventusingmachinelearningthecloverstudy AT nuriaalfarofernandez developmentofapredictivemodelofoccultcancerafteravenousthromboembolismeventusingmachinelearningthecloverstudy AT juantorresmacho developmentofapredictivemodelofoccultcancerafteravenousthromboembolismeventusingmachinelearningthecloverstudy |