Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Videos

Identifying cancer relapse using SEER-Medicare data.

Craig C Earle1, Ann B Nattinger, Arnold L Potosky

  • 1Department of Adult Oncology, Dana-Farber Cancer Institute, Boston, Massachusetts 02115, USA. craig_earle@dfci.harvard.edu

Medical Care
|August 21, 2002
PubMed
Summary
This summary is machine-generated.

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Patient-reported Psychological and Prostate Cancer-specific Functional Outcomes Among Men With Low-risk Prostate Cancer Two Years After Diagnosis: The PREPARE Prospective Cohort Study.

Urology·2026
Same author

Leveraging the national cancer institute's collaborative efforts to understand the benefits and harms of cannabis use among individuals with cancer.

Journal of the National Cancer Institute·2026
Same author

Competing Risk of Death in Heart Failure or Cardiomyopathy Prediction After Breast Cancer-Reply.

JAMA oncology·2026
Same author

Correlates and Detection of Digital Health Literacy in Patients With Colorectal Carcinoma or Non-Hodgkin Lymphoma: Cross-Sectional Study.

JMIR cancer·2025
Same author

Risk Prediction Model for Development of Heart Failure or Cardiomyopathy After Breast Cancer Treatment.

JAMA oncology·2025
Same author

Comorbidity burden and risk of second primary non-breast cancer in breast cancer survivors.

Cancer epidemiology·2025
Same journal

Hepatitis C Virus Cascade of Care in Florida Emergency Departments.

Medical care·2026
Same journal

Association of Neighborhood Socioeconomic Disadvantage and Uptake of Diabetes Prevention Interventions.

Medical care·2026
Same journal

Machine Learning for Evaluating the Heterogeneous Effects of Intensive In-Hospital Rehabilitation During the Postacute Phase After Hip Fracture Surgery on Activities of Daily Living.

Medical care·2026
Same journal

Hospital-Physician Integration and Differences in the Use of Orthopedic Care Across Race and Ethnicity.

Medical care·2026
Same journal

Temporal Misalignment and Selection Bias in "Burn Pit Smoke Exposure and Sleep Apnea in US Veterans.

Medical care·2026
Same journal

The Impact of an Oncology Hospital at Home Program on Health Care Costs.

Medical care·2026
See all related articles

Linking tumor registry data with administrative data can help identify cancer relapse. Algorithms developed for acute myelogenous leukemia (AML) show high accuracy in detecting relapse from billing data.

Area of Science:

  • Oncology
  • Health Informatics
  • Cancer Epidemiology

Background:

  • Tumor registries collect diagnostic data but lack longitudinal follow-up.
  • Investigating relapsed disease requires methods to track cancer recurrence over time.
  • Linking Surveillance, Epidemiology, and End Results (SEER) and Medicare data enables inference of relapse.

Purpose of the Study:

  • To develop and validate algorithms for detecting relapsed acute myelogenous leukemia (AML) using administrative data.
  • To assess the feasibility of using SEER-Medicare data for inferring cancer relapse.
  • To evaluate the accuracy of algorithms in identifying relapse from billing data compared to medical records.

Main Methods:

  • Retrospective cohort study of patients with AML.

Related Experiment Videos

  • Development of algorithms to detect relapse based on billing data.
  • Comparison of algorithm results with medical record review for validation.

    • Main Results:

    • Eighty-nine AML patients were analyzed; 22 had relapsed disease.
    • The best algorithm achieved 86% sensitivity and 99% specificity for relapse detection.
    • Positive predictive value was 95% and negative predictive value was 96%.

    Conclusions:

    • Clinical algorithms can identify cancer relapse from SEER-Medicare data for specific cancer types.
    • Feasibility is highest for cancers with treatment for relapse and detectable billing data.
    • This approach is optimal for studies prioritizing positive predictive value and evaluating outcomes in treated relapsed patients.