Computer-aided detection thresholds for digital chest radiography interpretation in tuberculosis diagnostic algorithms.
Fiona VanobberghenAlfred Kipyegon KeterBart K M JacobsTracy R GlassLutgarde LynenIrwin LawKeelin MurphyBram van GinnekenIrene AyakakaAlastair van HeerdenLlang MaamaKlaus ReitherPublished in: ERJ open research (2024)
This is the first study to evaluate CAD4TB in a community screening context employing a range of approaches to account for unknown tuberculosis status. The assumption that those not tested are negative - regardless of testing eligibility status - was robust. As threshold determination must be context specific, our analytically straightforward approach should be adopted to leverage prevalence surveys for CAD threshold determination in other settings with a comparable proportion of eligible but not tested participants.
Keyphrases
- mycobacterium tuberculosis
- coronary artery disease
- solid phase extraction
- pulmonary tuberculosis
- machine learning
- molecularly imprinted
- hiv aids
- healthcare
- mental health
- deep learning
- cross sectional
- loop mediated isothermal amplification
- computed tomography
- emergency department
- adverse drug
- hepatitis c virus
- sensitive detection
- tandem mass spectrometry