Harmouche R, et al. - Combining densitometry with machine learning, researchers created a new objective computed tomography (CT) analysis tool for detecting high attenuation changes in visually normal appearing lung (Norm_HA) that may precede the development of emphysema and pulmonary fibrosis. They placed 34528 training points in chest CT scans from 297 COPDGene participants to train the classification tool. Using the tool, classification of lung tissue was then done in 9038 participants as normal, emphysema, fibrotic/interstitial, or Norm_HA. Outcomes revealed higher C-reactive protein and intercellular adhesion molecule 1 in correlation to a higher percentage of lung occupied by Norm_HA. In analyses adjusted for multiple covariates, including high and low attenuation area, those in the highest quartile of Norm_HA vs those in the lowest quartile had a 6.50 absolute percent lower percent predicted lower forced expiratory volume in one second, an 8.48 absolute percent lower percent predicted forced expiratory volume, a 10.78 meter shorter six-minute walk distance and a 56% higher risk of death. Individuals without visually defined interstitial lung abnormalities also presented these findings. This study suggests the possible presence of a new class of visually normal appearing tissue on CT that may represent a unique tissue class associated with adverse outcomes, independent of emphysema and fibrosis.