HDR UK Gateway
HDR Gateway logo

Bookmarks

Anosmia

Description

Application to extract and classify mentions related to anosmia.

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

The output includes-

Examples of positive mentions:

“Loss of enjoyment of food due to anosmia”,

“COVID symptoms such as anosmia”

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

“Nil anosmia”,

“Anosmia related to people other than the patient”,

“Mentions of medications for it”,

“Don’t come to the practice if you have any covid symptoms such as anosmia”

Search term(case insensitive): Anosmia*

Results/Insights

Cohen's k = 83% (100 Random Documents). Instance level, (testing done on 100 random documents):Precision (specificity / accuracy) = 83% Recall (sensitivity / coverage) = 93%