Patient Identification and Tumor Identification Management: Quality Program in a Cancer Multicentric Clinical Data Warehouse

Abstract

Background: The Regional Basis of Solid Tumor (RBST), a clinical data warehouse, centralizes information related to cancer patient care in 5 health establishments in 2 French departments.

Purpose: To develop algorithms matching heterogeneous data to "real" patients and "real" tumors with respect to patient identification (PI) and tumor identification (TI).

Methods: A graph database programed in java Neo4j was used to build the RBST with data from ~20 000 patients. The PI algorithm using the Levenshtein distance was based on the regulatory criteria identifying a patient. A TI algorithm was built on 6 characteristics: tumor location and laterality, date of diagnosis, histology, primary and metastatic status. Given the heterogeneous nature and semantics of the collected data, the creation of repositories (organ, synonym, and histology repositories) was required. The TI algorithm used the Dice coefficient to match tumors.

Results: Patients matched if there was complete agreement of the given name, surname, sex, and date/month/year of birth. These parameters were assigned weights of 28%, 28%, 21%, and 23% (with 18% for year, 2.5% for month, and 2.5% for day), respectively. The algorithm had a sensitivity of 99.69% (95% confidence interval [CI] [98.89%, 99.96%]) and a specificity of 100% (95% CI [99.72%, 100%]). The TI algorithm used repositories, weights were assigned to the diagnosis date and associated organ (37.5% and 37.5%, respectively), laterality (16%) histology (5%), and metastatic status (4%). This algorithm had a sensitivity of 71% (95% CI [62.68%, 78.25%]) and a specificity of 100% (95% CI [94.31%, 100%]).

Conclusion: The RBST encompasses 2 quality controls: PI and TI. It facilitates the implementation of transversal structuring and assessments of the performance of the provided care.

Keywords: Clinical data warehouse; patient identification; quality program; tumor identification.

Figure 1.

Description of the RBST. The graph database programed in JAVA is composed of 2 modules: RBST-Evaluation, which permits the recording and visualization of patient care and follow-up data, and RBST-Research, corresponding to de-identified data allowing the development of translational research and clinical projects following the implementation of a complex queries tool. Abbreviations: API, application programing interface; ETL, extract, transform, and load; NLP, natural language processing.

Figure 2.

PI and TI algorithm flowcharts: (A) Patient identification and (B) tumor identification.

Figure 3.

Manual patient identification interface. Trust file with a list of patients whose data required reconciliation (A). In the example framed in red (5/5/2/0/0), the RBST administrator flagged 5 cases, with the mistakes shown in red (B), 5 cases with a suggested match (B), 2 cases with an automatic match (C), 0 manual matches realized, and 0 duplicates. Only the name and surname were changed to hide identity.

Figure 4.

Manual tumor identification interface. A list of patients with tumors requiring reconciliation (A) is shown on the left. In this example, encircled in red (4/3/1), the patient had 4 tumors: 3 were directly proposed for reconciliation after treatment by the 3 tumor identification steps (B) and the fourth tumor was not reconciled automatically and had to be reconciled manually (C). The organ repository used to select the organ where the tumor was located (D) is shown on the right. Only the name and surname were changed to hide identity.