Kan AI identificere tuberkulose ud fra hostelyde med bedre nøjagtighed end menneskelige klinikere ?

Tuberkulose forbliver en af de førende smitsomme dræbere på verdensplan, hvor tidlig diagnose er afgørende for behandlingens succes. Hostelyde indeholder akustiske signaturer, der er unikke for luftvejssygdomme. AI-modeller bliver udviklet til at analysere hosteoptagelser for specifikke biomarkører for tuberkuloseinfektion. Disse systemer kunne muliggøre fjern- og lavpris-screening i ressourcebegrænsede områder. Sådanne værktøjer skal gennemgå streng validering på forskellige befolkningsgrupper for at sikre pålidelighed.

Background

Tuberculosis (TB) is a leading infectious cause of death globally, with early diagnosis critical for successful treatment. Cough acoustics contain unique biomarkers that may reflect underlying pulmonary pathology, including TB-specific signatures. AI models—particularly convolutional neural networks leveraging transfer learning—have been trained on crowdsourced cough datasets to detect TB with reported sensitivities and specificities of approximately 90–95%. Such systems aim to enable remote, low-cost screening in resource-limited settings, addressing gaps where access to clinical expertise or laboratory diagnostics is constrained. However, performance heavily relies on high-quality audio recordings; real-world deployment faces challenges from ambient noise, variability in recording equipment, and overlapping respiratory conditions. Current validation remains largely dataset-dependent, and broader clinical implementation awaits real-world trials and regulatory clearance. WHO emphasizes that rigorous validation across diverse populations is essential to ensure equitable and reliable diagnostic performance.