For accurate diagnosis of interstitial lung disease (ILD), a consensus of radiologic, pathological, and clinical findings is vital. Management of ILD also requires thorough follow-up with computed tomography (CT) studies and lung function tests to assess disease progression, severity, and response to treatment. However, accurate classification of ILD subtypes can be challenging, especially for those not accustomed to reading chest CTs regularly. Dynamic models to predict patient survival rates based on longitudinal data are challenging to create due to disease complexity, variation, and irregular visit intervals. Here, we utilize RadImageNet pretrained models to diagnose five types of ILD with multimodal data and a transformer model to determine a patient's 3-year survival rate. When clinical history and associated CT scans are available, the proposed deep learning system can help clinicians diagnose and classify ILD patients and, importantly, dynamically predict disease progression and prognosis.

The idea that multiple traumatic brain injury (TBI) can have a cumulative detrimental effect on functioning is widely accepted. Most research supporting this idea comes from athlete samples, and it is not known whether remote history of previous TBI affects functioning after subsequent TBI in community-based samples. This study investigates whether a previous history of TBI with loss of consciousness (LOC) is associated with worse health and functioning in a sample of individuals who require emergency department care for current TBI. Twenty-three percent of the 586 individuals with current TBI in the Transforming Research and Clinical Knowledge in Traumatic Brain Injury study reported having sustained a previous TBI with LOC. Individuals with previous TBI were more likely to be unemployed (χ(2)=17.86; p=0.000), report a variety of chronic medical and psychiatric conditions (4.75≤χ(2)≥24.16; p<0.05), and report substance use (16.35≤χ(2)≥27.57; p<0.01) before the acute injury, compared to those with no previous TBI history. Those with a previous TBI had less-severe acute injuries, but experienced worse outcomes at 6-month follow-up. Results of a series of regression analyses controlling for demographics and acute injury severity indicated that individuals with previous TBI reported more mood symptoms, more postconcussive symptoms, lower life satisfaction, and had slower processing speed and poorer verbal learning, compared to those with no previous TBI history. These findings suggest that history of TBI with LOC may have important implications for health and psychological functioning after TBI in community-based samples.