Clinical note scanner
Processing and applying rule-based algorithms on Electronic Health Records data making use of Natural Language Processing methods. The aim was to identify specific variables that could be used to estimate a patient’s risk on certain diseases. For example blood pressure or smoking status. One challenge in this is that the system should be able to recognize negation (no smoker vs. smoker). This abstractly means that context in these clinical notes are relevant. Results were visualized making use of the Dash library.