Surveillance for hepatocellular carcinoma: development and validation of an algorithm to classify tests in
Peter Richardson1, Louise Henderson, Jessica A Davila
1Section of Health Services Research, Houston Center for Quality of Care & Utilization Studies, The Houston Veterans Affairs Medical Center and Baylor College of Medicine, Houston, TX, USA.
Insights
Algorithms can identify alpha-fetoprotein (AFP) tests for hepatocellular carcinoma (HCC) surveillance in administrative data. However, determining the intent of abdominal ultrasounds (US) for HCC surveillance remains challenging.
Area of Science:
- Health Informatics
- Medical Data Analysis
- Cancer Surveillance
Background:
- Administrative data often lacks clarity on the purpose of specific medical tests.
- Identifying the use of alpha-fetoprotein (AFP) and abdominal ultrasound (US) for cancer surveillance is crucial for accurate health outcome analysis.
Purpose of the Study:
- To develop and evaluate algorithms for identifying AFP and US tests used for hepatocellular carcinoma (HCC) surveillance within administrative data.
- To assess the feasibility of distinguishing surveillance testing from other uses of these diagnostic tools.
Main Methods:
- Utilized a Veterans Affairs (VA) database containing 300 AFP and 301 US tests.
- Employed logistic regression models to examine predictors of surveillance intent within administrative files (diagnoses, labs).
- Developed classification procedures using single and multiple imputation methods to determine HCC surveillance status.
Main Results:
- Predictors for AFP surveillance included absence of alcoholism, abdominal pain, ascites, diabetes, and high AST levels.
- Predictors for US surveillance included prior AFP testing, HIV status, and absence of abdominal pain, ascites, or drug dependence.
- Single imputation demonstrated robustness for AFP classification, while both methods showed moderate robustness for US classification.
Conclusions:
- Predictive algorithms derived from administrative data can effectively identify AFP tests used for HCC surveillance.
- The intent behind abdominal ultrasound (US) testing for HCC surveillance is more challenging to ascertain using administrative data alone.
Background:
The purpose of alpha-fetoprotein (AFP) and abdominal ultrasound (US) cannot be discerned in administrative data.
Aim:
We developed an algorithm to identify AFP and US used as surveillance tests for hepatocellular carcinoma (HCC).
Methods:
We evaluated 300 AFP and 301 US tests from a VA database. Surveillance predictors in the administrative files (diagnoses, labs) were examined in logistic regression models. We calculated model-based probabilities of HCC surveillance status, and developed classification procedures using single and multiple imputation methods.
Results:
The predictors of surveillance intent for AFP were absence of alcoholism, abdominal pain, ascites, diabetes and high AST levels. For US, the predictors of surveillance were prior AFP testing and HIV status and absence of abdominal pain, ascites, or drug dependence. For AFP classification, single imputation compared favorably with multiple imputation, both showing robustness in discrimination and calibration. For US both approaches were less robust in discrimination and calibration which was more moderate in multiple imputation than single imputation.
Conclusions:
Predictive algorithms in administrative files can be used to identify AFP performed for HCC surveillance, however, the intent of US is more difficult to identify.
