Utilizing the open-source programming language Python to create interactive Quality Assurance dashboards for diagnostic and screening performance in Cytology.

Introduction: Effective feedback on cytology performance relies on navigating complex laboratory information system data, which is prone to errors and lacks flexibility. As a comprehensive solution, we used the Python programming language to create a dashboard application for screening and diagnostic quality metrics.

Materials And Methods: Data from the 5-year period (2018-2022) were accessed. Versatile open-source Python libraries (user developed program code packages) were used from the first step of LIS data cleaning through the creation of the application. To evaluate performance, we selected 3 gynecologic metrics: the ASC/LSIL ratio, the ASC-US/ASC-H ratio, and the proportion of cytologic abnormalities in comparison to the total number of cases (abnormal rate). We also evaluated the referral rate of cytologists/cytotechnologists (CTs) and the ratio of thyroid AUS interpretations by cytopathologists (CPs). These were formed into colored graphs that showcase individual results in established, color-coded laboratory "goal," "borderline," and "attention" zones based on published reference benchmarks. A representation of the results distribution for the entire laboratory was also developed.

Results: We successfully created a web-based test application that presents interactive dashboards with different interfaces for the CT, CP, and laboratory management (https://drkvcsstvn-dashboards.hf.space/app). The user can choose to view the desired quality metric, year, and the anonymized CT or CP, with an additional automatically generated written report of results.

Conclusions: Python programming proved to be an effective toolkit to ensure high-level data processing in a modular and reproducible way to create a personalized, laboratory specific cytology dashboard.