Overview

A block diagram of the Phase 01 models is provided below. The demo notebook provides an annotated version of the source code for one of the models: the Findings vs No Findings model. Since many of the models in Phase 01 use this same format, this should provide a good example for understanding how the models during this phase of the project were trained. To view the actual source code (*.py files) used for training and classifying, please refer to the train and classify documentation.

In the table below, we provide a description of the different tasks and architectures of the models.

Model Name	Task	Architecture	Source Code Function
Findings or No Findings	Identify if the report has (i) lung or adrneal findings or (ii) no findings	Stacked BiLSTM (Tensorflow / Keras)	nmrezman.phase01.train.general.train_findings_model()
Lung or Adrenal Findings	Identify if the report has (i) lung or (ii) adrneal findings	Stacked BiLSTM (Tensorflow / Keras)	nmrezman.phase01.train.general.train_lung_adrenal_model()
Lung Recommended Procedure (i.e., Chest CT or Ambiguous Follow- up Recommended)	Identify if a report with lung has findings recommends (i) a Chest CT follow-up or (ii) some other ambiguous procedure	Stacked BiLSTM (Tensorflow / Keras)	nmrezman.phase01.train.general.train_lung_recommended_proc_model()
Comment Extraction	Identify the portion of the report that contains the findings text	XGBoost	nmrezman.phase01.train.general.train_comment_model()