Development and evaluation of a computable phenotype to identify pediatric patients with leukemia and lymphoma treated with chemotherapy using electronic health record data

Abstract

Background: Widespread implementation of electronic health records (EHR) has created new opportunities for pediatric oncology observational research. Little attention has been given to using EHR data to identify patients with pediatric hematologic malignancies.

Methods: This study used EHR-derived data in a pediatric clinical data research network, PEDSnet, to develop and evaluate a computable phenotype algorithm to identify pediatric patients with leukemia and lymphoma who received treatment with chemotherapy. To guide early development, multiple computable phenotype-defined cohorts were compared to one institution's tumor registry. The most promising algorithm was chosen for formal evaluation and consisted of at least two leukemia/lymphoma diagnoses (Systematized Nomenclature of Medicine codes) within a 90-day period, two chemotherapy exposures, and three hematology-oncology provider encounters. During evaluation, the computable phenotype was executed against EHR data from 2011 to 2016 at three large institutions. Classification accuracy was assessed by masked medical record review with phenotype-identified patients compared to a control group with at least three hematology-oncology encounters.

Results: The computable phenotype had sensitivity of 100% (confidence interval [CI] 99%, 100%), specificity of 99% (CI 99%, 100%), positive predictive value (PPV) and negative predictive value (NPV) of 100%, and C-statistic of 1 at the development institution. The computable phenotype performance was similar at the two test institutions with sensitivity of 100% (CI 99%, 100%), specificity of 99% (CI 99%, 100%), PPV of 96%, NPV of 100%, and C-statistic of 0.99.

Conclusion: The EHR-based computable phenotype is an accurate cohort identification tool for pediatric patients with leukemia and lymphoma who have been treated with chemotherapy and is ready for use in clinical studies.

Keywords: computable phenotype; epidemiology; leukemias (acute); lymphoma; pediatric oncology.

FIGURE 1

Computable phenotype algorithm HO hematology-oncology The computable phenotype used each institution’s electronic health record data contained within PEDSnet. First, the total population was screened for patients with at least three hematology-oncology encounters during the study period between 2011–2016. Next, the cohort was screened for patients with at least two leukemia or lymphoma inclusion diagnoses (Table 1) at separate encounters (outpatient / ambulatory clinic visit, inpatient consultation, inpatient admission, or emergency room visit) within a 90-day timeframe. Finally, patients were screened for at least two chemotherapy administrations from the following list: cyclophosphamide, cytarabine, daunorubicin, dasatinib, doxorubicin, etoposide, imatinib, mitoxantrone, tretinoin, vincristine. The two chemotherapy administrations must have occurred at separate encounters that were associated with a cancer diagnosis. Finally, the patient must not have had any of the non-malignant exclusion diagnoses (Table 1).

FIGURE 2.

Attrition diagram for leukemia and lymphoma computable phenotype The total number of patients in PEDSnet for each site is shown for each step in the process to create the phenotype starting with the total patient population. The attrition diagram shows many patients have a single leukemia or lymphoma diagnosis and the majority of these patients do not have multiple cancer diagnoses recorded and have never received chemotherapy. When patients were randomly selected, the same number of patients were selected from each site: 100 non-cases (300 total, 100 development site, 200 test sites), 70 primary phenotype cases (210 total, 70 development site, 140 test sites) and 30 sensitivity analysis cases (90 total, 30 development site, 60 test sites). CHOP Children’s Hospital of Philadelphia; CHCO Children’s Hospital Colorado; SCH Seattle Children’s Hospital.