External Validation of the CLOVER Score for Detecting Occult Cancer in Venous Thromboembolism Patients (CLOVER)

External Validation of a Predictive Model for Occult Cancer Risk in Patients With Venous Thromboembolism Developed Using Machine Learning

This study aims to externally validate the CLOVER score, a machine learning-based predictive model designed to identify patients with venous thromboembolism (VTE) who are at increased risk of having an occult cancer. The study includes a retrospective cohort of patients with acute symptomatic VTE diagnosed between 2000 and 2022, and a prospective cohort of consecutively recruited patients from December 2025 to December 2027. The CLOVER model will be applied to all participants, and its ability to discriminate between patients with and without occult cancer will be evaluated. The study also assesses clinicians' satisfaction with the web-based tool (CLOVER-Web) developed to facilitate the use of the score in clinical practice.

Study Overview

• Status: Recruiting
• Conditions: Venous Thromboembolism (VTE); Occult Cancer

Detailed Description

This study aims to externally validate the CLOVER score, a machine learning-based predictive model designed to identify patients with venous thromboembolism (VTE) who are at increased risk of having an occult cancer. The study combines a retrospective and a prospective cohort.

Retrospective cohort:

Patients aged ≥18 years with objectively confirmed symptomatic deep vein thrombosis (DVT) and/or pulmonary embolism (PE) diagnosed between January 1, 2000, and August 31, 2022, in participating hospitals across Spain will be included. Patients from centers involved in the model derivation (Hospital Universitario Infanta Leonor and Hospital Universitario de Fuenlabrada) will be excluded. Cases are defined as patients with a histologically confirmed cancer diagnosis occurring between 1 and 24 months after the index VTE event. Controls are defined as patients without a cancer diagnosis during the same period. All variables required for the CLOVER model (age, D-dimer, systolic blood pressure, ALT, hemoglobin, creatinine, total cholesterol, platelet count, triglycerides, leukocyte count, weight, chronic lung disease, heart rate, sex, and previous VTE recurrence) will be extracted from electronic health records using a standardized data collection form. The CLOVER model will be applied to each patient to assess its discrimination for cancer prediction in the retrospective cohort.

Prospective cohort:

From December 1, 2025, to December 31, 2027, consecutive adult patients with objectively confirmed symptomatic VTE will be recruited in participating hospitals. All patients will undergo a standard clinical evaluation including medical history, physical examination, basic laboratory testing (complete blood count and biochemistry), chest X-ray, and age- and sex-appropriate cancer screening tests according to clinical practice guidelines. The CLOVER score will be calculated at the time of VTE diagnosis using a dedicated web-based tool (CLOVER-Web). Patients will be classified as "low risk" or "high risk" based on the optimal F1-score threshold (0.487), corresponding to a sensitivity of 51%, specificity of 95%, PPV of 46%, and NPV of 96%. All participants will be followed for at least two years to determine whether an occult cancer is diagnosed. Further diagnostic testing for suspected cancer will be performed at the discretion of the treating physician, regardless of CLOVER result.

Model performance and bias assessment:

The external validation will evaluate model discrimination using sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), and the area under the ROC curve (AUC). Additional analyses will assess potential prediction bias across demographic and clinical subgroups (e.g., age, sex, comorbidities). Model calibration and temporal performance will also be reviewed, with predefined procedures for identifying deviations from expected behavior. Weekly reports during the prospective phase will alert investigators to performance drift or potential implementation issues in the web-based tool.

Clinician satisfaction:

A secondary objective is to evaluate clinician satisfaction with the CLOVER-Web tool. An online questionnaire specifically designed for this study will be administered to participating clinicians to assess usability, clarity, and clinical utility.

Ethical considerations:

The study follows the Declaration of Helsinki and Spanish regulations on biomedical research and data protection. Retrospective data collection will request exemption from informed consent due to the use of anonymized clinical information. Prospective participants will provide written or electronic informed consent. All data will be pseudonymized and stored securely.

• Study Type: Observational
• Enrollment (Estimated): 500

Contacts and Locations

• Study Contact: Name: Anabel Franco Moreno, MD, PhD; Phone Number: +34686102661; Email: afranco278@hotmail.com
• Study Contact Backup: Name: Anabel Franco Moreno; Phone Number: MD, PhD; Email: afranco278@hotmail.com

Study Locations

• Spain
  • Balea, Spain
    • Recruiting
    • Hospital Universitario Son Llatzer
    • Contact: Elena Cisneros de la Fuente, MD; Email: ecisneros@hsll.es
  • Madrid, Spain
    • Recruiting
    • Hospital Universitario 12 de Octubre
    • Contact: Jose Bascuñana Morejon de Giron, MD, PhD; Email: josebascumor@gmail.com
  • Madrid, Spain
    • Recruiting
    • Hospital Universitario de Fuenlabrada
    • Contact: Cristina De Ancos Aracil, MD; Email: drcancos@gmail.com
  • Barcelona
    • Barcelona, Barcelona, Spain
      • Recruiting
      • Hospital Clinic
      • Contact: JESUS AIBAR, MD, PhD; Phone Number: 932 27 54 00; Email: JAIBAR@clinic.cat
  • Madrid
    • Madrid, Madrid, Spain, 28051
      • Recruiting
      • Hospital Universitario Infanta Leonor
      • Contact: Anabel Franco Moreno, MD, PhD; Phone Number: 686102661; Email: afranco278@hotmail.com
    • Madrid, Madrid, Spain, 28051
      • Recruiting
      • Hospital Universitario La Paz
      • Contact: Teresa Sancho, MD; Phone Number: 917 27 70 00; Email: tsbueso@gmail.com
    • Madrid, Madrid, Spain, 28051
      • Recruiting
      • Hospital Universitario Príncipe de Asturias
      • Contact: f garcia sanchez, MD; Phone Number: 91 887 81 00; Email: fgarciasanchez@salud.madrid.org
    • Madrid, Madrid, Spain, 28051
      • Recruiting
      • Hospital Universitatio del Sureste
      • Contact: Ana Mancebo Plaza, MD; Phone Number: 918 39 40 00 686102661; Email: abmancebop@gmail.com
    • Madrid, Madrid, Spain
      • Recruiting
      • Hospital Universitario de Móstoles
      • Contact: Andrea Pérez, MD; Phone Number: 916 64 86 00; Email: a.perezrodr@gmail.com
  • Murcia
    • Murcia, Murcia, Spain
      • Recruiting
      • Hospital Clínico Universitario Virgen de la Arrixaca
      • Contact: Leticia Guirado Torrecillas, MD; Phone Number: 968 36 95 00; Email: leticia.guiradotorrecillas@gmail.com
    • Murcia, Murcia, Spain
      • Recruiting
      • Hospital Universitario Morales Meseguer
      • Contact: Javier Pagán, MD, PhD; Phone Number: 968 36 09 00; Email: pagan02468@gmail.com
  • Principality of Asturias
    • Avilés, Principality of Asturias, Spain
      • Recruiting
      • Hospital San Agustín
      • Contact: José Ferreiro Celeiro, MD; Phone Number: 985 12 30 00; Email: jcaussie@hotmail.com

Participation Criteria

Eligibility Criteria

• Ages Eligible for Study: Adult; Older Adult
• Accepts Healthy Volunteers: No

• Sampling Method: Non-Probability Sample

Study Population

Adults (≥18 years) with objectively confirmed symptomatic venous thromboembolism (deep vein thrombosis or pulmonary embolism) who are consecutively recruited in participating hospitals in Spain. All participants undergo routine clinical evaluation, laboratory testing, and age- and sex-appropriate cancer screening according to standard practice. The population represents real-world patients with new-onset VTE without known or suspected cancer at baseline.

Description

Inclusion Criteria:

• Age ≥18 years.
• Objectively confirmed acute symptomatic venous thromboembolism (deep vein thrombosis and/or pulmonary embolism).
• Ability to provide written or electronic informed consent.

Exclusion Criteria:

• Suspicion of cancer during the initial diagnostic evaluation for VTE.
• Participation in another interventional study that may interfere with outcomes.
• Inability or refusal to provide informed consent.

Study Plan

How is the study designed?

Number of groups / cohorts

1

Cohorts and Interventions

Group / Cohort

Prospective VTE Cohort; Adults with objectively confirmed symptomatic venous thromboembolism (deep vein thrombosis and/or pulmonary embolism) consecutively enrolled from December 2025 to December 2027 in participating hospitals. All participants will undergo routine clinical evaluation, laboratory testing, and cancer screening according to standard practice. The CLOVER score will be calculated at baseline using the web-based tool (CLOVER-Web).

What is the study measuring?

Primary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Detection of occult cancer within 24 months	Proportion of participants with a histologically confirmed diagnosis of occult cancer identified between 1 and 24 months after the index venous thromboembolism (VTE) event. Occult cancer is defined as a new cancer diagnosis not clinically evident at the time of VTE diagnosis	24 months

Collaborators and Investigators

• Sponsor: Infanta Leonor University Hospital
• Collaborators: Fundación para la Investigación e Innovación Biomédica del Hospital Universitario Infanta Leonor
• Investigators: Principal Investigator: Anabel Franco-Moreno, MD, PhD, Hospital Universitario Infanta Leonor; Principal Investigator: Franco-Moreno, MD, PhD, Hospital Universitario Infanta Leonor

Publications and helpful links

General Publications

• Franco-Moreno A, Madronal-Cerezo E, de Ancos-Aracil CL, Farfan-Sedano AI, Munoz-Rivas N, Bascunana Morejon-Giron J, Ruiz-Giardin JM, Alvarez-Rodriguez F, Prada-Alonso J, Gala-Garcia Y, Casado-Suela MA, Bustamante-Fermosel A, Alfaro-Fernandez N, Torres-Macho J; CLOVER Research Group. Development of a Predictive Model of Occult Cancer After a Venous Thromboembolism Event Using Machine Learning: The CLOVER Study. Medicina (Kaunas). 2024 Dec 27;61(1):18. doi: 10.3390/medicina61010018.

Study record dates

Study Major Dates

• Study Start (Actual): December 1, 2025
• Primary Completion (Estimated): December 31, 2028
• Study Completion (Estimated): December 31, 2028

Study Registration Dates

• First Submitted: December 8, 2025
• First Submitted That Met QC Criteria: December 20, 2025
• First Posted (Actual): December 30, 2025

Study Record Updates

• Last Update Posted (Actual): December 30, 2025
• Last Update Submitted That Met QC Criteria: December 20, 2025
• Last Verified: December 1, 2025

More Information

Terms related to this study

• Keywords: External validation; Venous thromboembolism; Prediction model; Machine learning; Occult Cancer; CLOVER score
• Additional Relevant MeSH Terms: Vascular Diseases; Cardiovascular Diseases; Embolism and Thrombosis; Thromboembolism; Venous Thromboembolism
• Other Study ID Numbers: CLOVER_validation

Plan for Individual participant data (IPD)

• Plan to Share Individual Participant Data (IPD)?: YES
• IPD Plan Description: De-identified individual participant data (IPD) will be shared, including baseline characteristics, clinical variables, imaging results, and outcomes related to occult cancer detection. Data will be made available to qualified investigators upon reasonable request and after signing a data sharing agreement ensuring confidentiality and appropriate use. IPD will be available beginning 12 months after study completion and will remain accessible for 5 years. Access to IPD will be granted to qualified researchers with a methodologically sound research proposal. Requests must be submitted to the study's coordinating center and will be evaluated by the principal investigators. A data use agreement will be required before any data transfer. Data will be hosted on the HORUS-ML secure research platform (restricted access).
• IPD Sharing Time Frame: IPD will be available beginning 12 months after the completion of the study and will remain accessible for a period of 5 years. Supporting documentation will be provided during the same availability window.
• IPD Sharing Access Criteria: IPD will be available to qualified researchers who submit a methodologically sound research proposal. All requests must be evaluated and approved by the principal investigators. Access will require signing a data use agreement ensuring confidentiality and appropriate use. Data will be shared through the secure HORUS-ML platform.
• IPD Sharing Supporting Information Type: STUDY_PROTOCOL; SAP; ICF

Drug and device information, study documents

• Studies a U.S. FDA-regulated drug product: No
• Studies a U.S. FDA-regulated device product: No