Application to identify instances of aggressive behaviour in patients, including verbal, physical and sexual aggression.

Development approach: Machine-learning. Classification of past or present symptom: Both. Classes produced: Positive

The output includes-

Examples of positive mentions:

“reported to be quite aggressive towards…”,

“violence and aggression, requires continued management and continues to reduce in terms of incidents etc”.

Examples of negative / irrelevant mentions (not included in the output):

“no aggression”,

“no evidence of aggression”

“aggression won’t be tolerated”.

Search term(case insensitive): aggress

Cohen's k = 85% (50 un-annotated documents - 25 events/25 attachments, search term ‘aggress*’). Instance level (testing done on 100 random documents): Precision (specificity / accuracy) = 91%

Recall (sensitivity / coverage) = 75% Patient level (testing done on 50 random documents): Precision (specificity / accuracy) = 76%