Test performance metrics for breast, cervical, colon, and lung cancer screening: a systematic review

Abstract

Background Multiple quality metrics have been recommended to ensure consistent, high-quality execution of screening tests for breast, cervical, colorectal and lung cancers. However, minimal data exist evaluating the evidence base supporting these recommendations and the consistency of definitions and concepts included within and between cancer types. Methods We performed a systematic review for each cancer type using MEDLINE, Embase and CINAHL from 2010 to April 2020, to identify guidelines from screening programs or professional organizations containing quality metrics for tests used in breast, cervical, colorectal and lung cancer screening. We abstracted metrics’ definitions, target performance levels, and related supporting evidence for test completeness, adequacy (sufficient visualization or collection), accuracy, and safety. Results We identified 11 relevant guidelines with 20 suggested quality metrics for breast cancer, 5 guidelines with 9 metrics for cervical cancer, 13 guidelines with 18 metrics for colorectal cancer, and 3 guidelines with 7 metrics for lung cancer. These included 54 metrics related to adequacy (6), test completeness (3), accuracy (33), and safety (12). Target performance levels were defined for 30 metrics (56%). Ten (19%) were supported by evidence, all from breast and colorectal cancer, with no evidence cited to support metrics from cervical and lung cancer screening. Conclusions Considerably more guideline-recommended test performance metrics exist for breast and colorectal cancer screening than cervical or lung cancer. The domains covered are inconsistent among cancers and few targets are supported by evidence. Clearer evidence-based domains and targets are needed for test performance metrics. Registration PROSPERO 2020 CRD42020179139

Cervical Cancer Classification From Pap Smear Images Using Deep Convolutional Neural Network Models

“…The existing literature does not yet provide a target accuracy for classifying images related to cervical cancer screening. In [ 34 ], the authors concluded that guidelines from screening programs and professional organizations lack cited evidence supporting the performance metrics for cervical cancer tests. For example, the United Kingdom’s Office for Health Improvement & Disparities [ 35 ] set a performance threshold of a sensitivity greater than 90% for all abnormalities and a sensitivity greater than 95% for high-grade abnormalities, based on the accuracy of the initial cytology examination as determined by rapid review.…”