Abstract: A system develops classifiers that can aid medical professionals by diagnosing whether or not a patient has a medical condition like pneumothorax. The system breaks the task into multiple steps, using YOLOv4 to extract relevant regions of the video and a 3D sparse coding model to represent video features. Given the difficulty in acquiring positive training videos, the inventors trained a small-data classifier with a maximum of 15 positive and 32 negative examples. To counteract this limitation, the inventors leveraged subject matter expert (SME) knowledge to limit the hypothesis space, thus reducing the cost of data collection. The inventors present results using two lung ultrasound datasets and demonstrate that the inventors' model is capable of achieving performance on par with SMEs in pneumothorax identification.