-
Notifications
You must be signed in to change notification settings - Fork 105
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
Merge branch 'master' into production
- Loading branch information
Showing
76 changed files
with
3,961 additions
and
3,358 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -1,79 +1,142 @@ | ||
| # # Example of some test cases | ||
| # # They will try to cover as many possible use cases as possible | ||
| # # The idea is that the CUI corresponding to the name is expected to be | ||
| # # obtained by MedCAT | ||
| # # Only the 'filters' under 'targeting' and the 'phrases' under | ||
| # # the test case are the two required sections, the rest is optional | ||
| # | ||
| # test-case-name-1: # name of this test case | ||
| # targeting: # info regarding targets of this test case | ||
| # strategy: "ALL" # the strategy for dealing with the filters below | ||
| # # so "ALL" means the targets need to match all the below filters | ||
| # # and "ANY" means that the targets need to match at least one of the filters | ||
| # # if only one type of target it specified, this is irrelevant | ||
| # # the default value is "ALL" if not specified | ||
| # prefname-only: False # set to True if only prefered names should be checked (defaults to False) | ||
| # targfiltersets: # the filters for this specific test case | ||
| # # there has to be one type of target, but multiple can be specified | ||
| # # if multiple types are target, the strategy defined above is taken into affect | ||
| # # each type can specify one or multiple values | ||
| # # this example shows has one values | ||
| # # the next example (below) will have multiple values | ||
| # type_id: "0123" # type_id or type_ids | ||
| # cui: "01230" # the target CUI (or list of CUIS) | ||
| # name: "name0" # the target names | ||
| # # all specified names need to exist within the CDB | ||
| # phrases: "The quick brown %s jumped over the lazy cat" # the phrases to go through | ||
| # # for each phrases, '%s' is replaced | ||
| # # by each name that is to be tested | ||
| # test-case-name-2: # name of this test case | ||
| # targeting: | ||
| # filters: | ||
| # type_id: # multiple target type IDs | ||
| # - "123" | ||
| # - "223" | ||
| # cui: # multiple target CUI | ||
| # - "1234" | ||
| # - "2234" | ||
| # name: # multiple names | ||
| # - "name1" | ||
| # - "name2" | ||
| # cui_and_children: # an example with CUI and children | ||
| # cui: '111' # the CUI (or CUIs) | ||
| # depth: 2 # and the depth of children | ||
| # phrases: | ||
| # - "The %s was measured" | ||
| # - "The %s was not measured" | ||
| # | ||
| # # The following example was (rather arbitrarily) created and should work for | ||
| # # the included SNOMED models | ||
| test-case-1: | ||
| targeting: | ||
| strategy: "ALL" | ||
| filters: | ||
| type_id: "2680757" | ||
| phrases: | ||
| - "The %s was measured" | ||
| # this is an example test case | ||
| # it is based on SNOMED-CT | ||
| test-case-1: # The (somewhat) arbitrary name of the test case | ||
| targeting: # the description of the replacement targets in the phrase(s) | ||
| placeholders: # the placeholders to replace in the phrase(s) | ||
| # Note that only 1 concept will be tested for at one time. | ||
| # So if the prhase(s) has/have more than 1 placeholder, the | ||
| # rest of them will be substitued in without care for whether | ||
| # or how accurately the model is able to recognise them. | ||
| # For the concepts that are not under test at a given time | ||
| # the "first" name is used (because the implementation has | ||
| # names in a set, there is possibility for run-to-run variance | ||
| # because of different names being used). | ||
| # | ||
| # There are 2 modes for the placeholders: | ||
| # 1. any-combination: false | ||
| # In this mode, only the concepts in the same position | ||
| # in the various lists are used in conjunction to oneanother. | ||
| # Though this also means that it is expected that all of the | ||
| # placeholders have the same number of CUIs to use. | ||
| # Assuming each of the N placeholders defines M replacement | ||
| # cuis, this approach produces M*N cases. | ||
| # 2. any-combination: true | ||
| # In this mode, any combination of the replacement CUIs is | ||
| # allowed. This means that quite a few different combinations | ||
| # will be generated and used. It also means that different | ||
| # placeholders can have different number of concepts suitbale | ||
| # for them. | ||
| # Assuming eacho of the N placeholders defines M repalcement | ||
| # cuis, this approach produces N * N^M (where `^` is power) | ||
| # cases. But for a more complicated set up (i.e where different | ||
| # placeholders have a different number of swappable CUIs) | ||
| # this calculation is not as straight forward. | ||
| # | ||
| # NOTE: The above description does not take into account different | ||
| # number of names associated with different concepts. For each | ||
| # of the "primary" concepts, each possible name is attempted. | ||
| - placeholder: '[DISORDER]' # the palceholder that will be substituted in the phrase(s) | ||
| cuis: ['4473006', # Intracerebral hemorrhage | ||
| '85189001', # Acute appendicitis | ||
| '186738001', # vestibular neuritis | ||
| '186738001', # vestibular neuritis | ||
| ] | ||
| - placeholder: '[FINDING1]' | ||
| cuis: ['162300006', # unilateral headache | ||
| '21522001', # abdominal pain | ||
| '103298005', # severe vertigo | ||
| '103298005', # severe vertigo | ||
| ] | ||
| prefname-only: false # this is an optional keyword for wach placeholder | ||
| # if set to true, only the preferred name will be used for | ||
| # this concept. Otherwise, all names will be used as | ||
| # different sub-cases | ||
| - placeholder: '[FINDING2]' | ||
| cuis: ['409668002', # photophobia | ||
| '422587007', # nausea | ||
| '422587007', # nausea | ||
| '422587007', # nausea | ||
| ] | ||
| - placeholder: '[FINDING3]' | ||
| cuis: ['2228002', # scintillating scotoma | ||
| '386661006', # fever | ||
| '81756001', # horizontal nystagmus | ||
| '81756001', # horizontal nystagmus | ||
| ] | ||
| - placeholder: '[NEGFINDING]' | ||
| cuis: ['386661006', # fever | ||
| '62315008', # diarrhea | ||
| '15188001', # hearing loss | ||
| '60862001', # tinnitus | ||
| ] | ||
| any-combination: false # if set to false, same length of CUIs is expected | ||
| # for each placeholder and only a combination is used | ||
| phrases: # The list of phrases | ||
| - > | ||
| Description: [DISORDER] | ||
| CC: [FINDING1] on presentation; then developed [FINDING3] | ||
| HX: On the day of presentation, this 32 y/o RHM suddenly developed [FINDING1] and [FINDING2]. | ||
| Four hours later he experienced sudden [FINDING3] lasting two hours. | ||
| There were no other associated symptoms except for the [FINDING1] and [FINDING2]. | ||
| He denied [NEGFINDING]. | ||
| test-case-2: | ||
| targeting: | ||
| filters: | ||
| type_id: "9090192" | ||
| phrases: | ||
| - "Patient presented with %s" | ||
| - "No %s was present" | ||
| test-case-3: | ||
| targeting: | ||
| filters: | ||
| type_id: "67667581" | ||
| phrases: | ||
| - "The patient has been diagnosed with %s" | ||
| - "There are no signs of %s" | ||
| test-case-4: | ||
| targeting: | ||
| strategy: "ALL" | ||
| filters: | ||
| cui_and_children: | ||
| cui: "364075005" # 'heart rate' | ||
| depth: 4 # and children 4 deep | ||
| placeholders: | ||
| - placeholder: '[FINDING1]' | ||
| cuis: ['49727002', # cough | ||
| '29857009', # chest pain | ||
| '21522001', # abdominal pain | ||
| '57676002', # joint pain | ||
| '25064002', # headache | ||
| '271807003', # fever | ||
| '162397003', # hematuria (blood in urine) | ||
| '271757001', # fatigue | ||
| '386661006', # weight loss | ||
| '62315008', # dysuria (painful urination) | ||
| ] | ||
| - placeholder: '[FINDING2]' | ||
| cuis: ['267036007', # shortness of breath | ||
| '68962001', # palpatations | ||
| '422587007', # nausea | ||
| '182888003', # swelling | ||
| '404640003', # dizziness | ||
| '422400008', # sore throat | ||
| '267036007', # shortness of breath | ||
| '267064002', # night sweats | ||
| '162607003', # back pain | ||
| '267102003', # urinary frequency | ||
| ] | ||
| - placeholder: '[DISORDER]' | ||
| cuis: ['195967001', # asthma | ||
| '194828000', # angina pectoris | ||
| '25374005', # gastroenteritis | ||
| '69896004', # rheumatoid arthritis | ||
| '37796009', # migraine | ||
| '186747009', # influenza | ||
| '106063007', # urinary tract infection | ||
| '444814009', # chronic fatigue syndrome | ||
| '95281007', # tuberculosis | ||
| '431855005', # cystitis | ||
| ] | ||
| any-combination: false | ||
| phrases: | ||
| - "The patient's %s was 82 bps" | ||
| - > | ||
| The patient presents with [FINDING1] and [FINDING2]. These findings are suggestive of [DISORDER]. | ||
| Further diagnostic evaluation and investigations are required to confirm the diagnosis. | ||
| - > | ||
| The patient reports [FINDING1] and has also been experiencing [FINDING2]. These symptoms are consistent with a clinical presentation of [DISORDER]. | ||
| Further assessment and diagnostic tests are required to establish the underlying cause. | ||
| - > | ||
| Upon evaluation, the patient exhibits [FINDING1] along with [FINDING2]. This combination of findings raises suspicion for [DISORDER]. | ||
| Comprehensive diagnostic workup is advised to confirm the diagnosis and plan appropriate management. | ||
| - > | ||
| During the consultation, the patient described [FINDING1] and noted a recent history of [FINDING2]. These clinical features are suggestive of [DISORDER]. | ||
| Further investigation is necessary to verify the diagnosis and rule out other potential causes. | ||
| - > | ||
| The patient's symptoms include [FINDING1] and [FINDING2], which are commonly associated with [DISORDER]. | ||
| It is recommended that additional diagnostic procedures be performed to confirm this working diagnosis. | ||
| - > | ||
| The clinical presentation of [FINDING1] and [FINDING2] is indicative of [DISORDER]. | ||
| To ensure accurate diagnosis, further clinical evaluation and diagnostic tests are required. |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Oops, something went wrong.