dlituiev commited on
Commit
d996c61
1 Parent(s): de3d77f

Update spaCy pipeline

Browse files
.gitattributes CHANGED
@@ -25,3 +25,10 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
25
  *.zip filter=lfs diff=lfs merge=lfs -text
26
  *.zstandard filter=lfs diff=lfs merge=lfs -text
27
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
 
25
  *.zip filter=lfs diff=lfs merge=lfs -text
26
  *.zstandard filter=lfs diff=lfs merge=lfs -text
27
  *tfevents* filter=lfs diff=lfs merge=lfs -text
28
+ *.whl filter=lfs diff=lfs merge=lfs -text
29
+ *.npz filter=lfs diff=lfs merge=lfs -text
30
+ *strings.json filter=lfs diff=lfs merge=lfs -text
31
+ vectors filter=lfs diff=lfs merge=lfs -text
32
+ model filter=lfs diff=lfs merge=lfs -text
33
+ ner/moves filter=lfs diff=lfs merge=lfs -text
34
+ tokenizer filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ tags:
3
+ - spacy
4
+ - token-classification
5
+ language:
6
+ - en
7
+ model-index:
8
+ - name: en_sdoh_roberta_cui
9
+ results:
10
+ - task:
11
+ name: NER
12
+ type: token-classification
13
+ metrics:
14
+ - name: NER Precision
15
+ type: precision
16
+ value: 0.8016997167
17
+ - name: NER Recall
18
+ type: recall
19
+ value: 0.7526595745
20
+ - name: NER F Score
21
+ type: f_score
22
+ value: 0.7764060357
23
+ ---
24
+ CNN based Social determinants of health NER with a fine-grained window context bag-of-words classifier and a standard ontology extension interface (SNOMED_CT and CUI)
25
+
26
+ | Feature | Description |
27
+ | --- | --- |
28
+ | **Name** | `en_sdoh_roberta_cui` |
29
+ | **Version** | `0.0.0` |
30
+ | **spaCy** | `>=3.2.1,<3.3.0` |
31
+ | **Default Pipeline** | `transformer`, `ner`, `sdoh_cui` |
32
+ | **Components** | `transformer`, `ner`, `sdoh_cui` |
33
+ | **Vectors** | 0 keys, 0 unique vectors (0 dimensions) |
34
+ | **Sources** | n/a |
35
+ | **License** | n/a |
36
+ | **Author** | [Dima Lituiev]() |
37
+
38
+ ### Label Scheme
39
+
40
+ <details>
41
+
42
+ <summary>View label scheme (52 labels for 1 components)</summary>
43
+
44
+ | Component | Labels |
45
+ | --- | --- |
46
+ | **`ner`** | `Anxiety: GAD`, `Anxiety: Generalized Anxiety Disorder`, `Anxiety: Level of anxiety`, `Anxiety: NA`, `Anxiety: Signs and symptoms of anxiety`, `Anxiety: family hx: Anxiety state`, `Anxiety: hx of anxiety state`, `Depression: Family hx: Depression`, `Depression: Major depressive disorder`, `Depression: NA`, `Depression: PHQ`, `Depression: Symptoms of depression`, `Depression: hx of Depression`, `Financial_strain: Financial problem`, `Financial_strain: Financially secure`, `Financial_strain: NA`, `Financial_strain: Unable to afford medication`, `Food: Able to obtain food`, `Food: Fruit and vegetable intake`, `Food: NA`, `Housing: Homeless`, `Housing: Housing unsuited to needs`, `Housing: Marginally housed`, `Housing: NA`, `Housing: Stably housed`, `Housing: Subsidized housing`, `Housing: lives in facility`, `Insurance_status: Inadequate healthcare resources`, `Insurance_status: NA`, `Marital_or_partnership_status: Divorced`, `Marital_or_partnership_status: Engaged to be married`, `Marital_or_partnership_status: Married`, `Marital_or_partnership_status: NA`, `Marital_or_partnership_status: Partner`, `Marital_or_partnership_status: Partner relationship problem`, `Marital_or_partnership_status: Separated`, `Marital_or_partnership_status: Single person`, `Marital_or_partnership_status: Widowed`, `Social_isolation: At risk for loneliness`, `Social_isolation: Has social support`, `Social_isolation: Lives alone`, `Social_isolation: Lives with`, `Social_isolation: NA`, `Social_isolation: Personal relationship breakdown`, `Social_isolation: Social Isolation`, `Transportation: Has access to a car`, `Transportation: Has access to public transport vehicle`, `Transportation: NA`, `Transportation: Transportation problems`, `pain_and_disability: NA`, `pain_and_disability: Pain intensity rating scale, current`, `pain_and_disability: Pain intensity rating scale, worst` |
47
+
48
+ </details>
49
+
50
+ ### Accuracy
51
+
52
+ | Type | Score |
53
+ | --- | --- |
54
+ | `ENTS_F` | 77.64 |
55
+ | `ENTS_P` | 80.17 |
56
+ | `ENTS_R` | 75.27 |
57
+ | `TRANSFORMER_LOSS` | 37708138.10 |
58
+ | `NER_LOSS` | 1444086.80 |
config.cfg ADDED
@@ -0,0 +1,148 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [paths]
2
+ train = "./data/spacy-level-2/sdoh-cocoa-skippy-no-empty-2022-01-11-fold-2-train.spacy"
3
+ dev = "./data/spacy-level-2/sdoh-cocoa-skippy-no-empty-2022-01-11-fold-2-val.spacy"
4
+ vectors = null
5
+ init_tok2vec = null
6
+
7
+ [system]
8
+ gpu_allocator = "pytorch"
9
+ seed = 1
10
+
11
+ [nlp]
12
+ lang = "en"
13
+ pipeline = ["transformer","ner","sdoh_cui"]
14
+ batch_size = 16
15
+ disabled = []
16
+ before_creation = null
17
+ after_creation = null
18
+ after_pipeline_creation = null
19
+ tokenizer = {"@tokenizers":"spacy.Tokenizer.v1"}
20
+
21
+ [components]
22
+
23
+ [components.ner]
24
+ factory = "ner"
25
+ incorrect_spans_key = null
26
+ moves = null
27
+ scorer = {"@scorers":"spacy.ner_scorer.v1"}
28
+ update_with_oracle_cut_size = 100
29
+
30
+ [components.ner.model]
31
+ @architectures = "spacy.TransitionBasedParser.v2"
32
+ state_type = "ner"
33
+ extra_state_tokens = false
34
+ hidden_width = 64
35
+ maxout_pieces = 2
36
+ use_upper = false
37
+ nO = null
38
+
39
+ [components.ner.model.tok2vec]
40
+ @architectures = "spacy-transformers.TransformerListener.v1"
41
+ grad_factor = 1.0
42
+ pooling = {"@layers":"reduce_mean.v1"}
43
+ upstream = "*"
44
+
45
+ [components.sdoh_cui]
46
+ factory = "sdoh_cui"
47
+
48
+ [components.transformer]
49
+ factory = "transformer"
50
+ max_batch_items = 4096
51
+ set_extra_annotations = {"@annotation_setters":"spacy-transformers.null_annotation_setter.v1"}
52
+
53
+ [components.transformer.model]
54
+ @architectures = "spacy-transformers.TransformerModel.v3"
55
+ name = "roberta-base"
56
+ mixed_precision = true
57
+
58
+ [components.transformer.model.get_spans]
59
+ @span_getters = "spacy-transformers.strided_spans.v1"
60
+ window = 128
61
+ stride = 96
62
+
63
+ [components.transformer.model.grad_scaler_config]
64
+
65
+ [components.transformer.model.tokenizer_config]
66
+ use_fast = true
67
+
68
+ [components.transformer.model.transformer_config]
69
+
70
+ [corpora]
71
+
72
+ [corpora.dev]
73
+ @readers = "spacy.Corpus.v1"
74
+ path = ${paths.dev}
75
+ max_length = 0
76
+ gold_preproc = false
77
+ limit = 0
78
+ augmenter = null
79
+
80
+ [corpora.train]
81
+ @readers = "spacy.Corpus.v1"
82
+ path = ${paths.train}
83
+ max_length = 0
84
+ gold_preproc = false
85
+ limit = 0
86
+ augmenter = null
87
+
88
+ [training]
89
+ seed = ${system.seed}
90
+ accumulate_gradient = 3
91
+ dev_corpus = "corpora.dev"
92
+ train_corpus = "corpora.train"
93
+ gpu_allocator = ${system.gpu_allocator}
94
+ dropout = 0.1
95
+ patience = 1600
96
+ max_epochs = 0
97
+ max_steps = 20000
98
+ eval_frequency = 200
99
+ frozen_components = []
100
+ annotating_components = []
101
+ before_to_disk = null
102
+
103
+ [training.batcher]
104
+ @batchers = "spacy.batch_by_padded.v1"
105
+ discard_oversize = true
106
+ size = 2000
107
+ buffer = 256
108
+ get_length = null
109
+
110
+ [training.logger]
111
+ @loggers = "spacy.ConsoleLogger.v1"
112
+ progress_bar = false
113
+
114
+ [training.optimizer]
115
+ @optimizers = "Adam.v1"
116
+ beta1 = 0.9
117
+ beta2 = 0.999
118
+ L2_is_weight_decay = true
119
+ L2 = 0.01
120
+ grad_clip = 1.0
121
+ use_averages = false
122
+ eps = 0.00000001
123
+
124
+ [training.optimizer.learn_rate]
125
+ @schedules = "warmup_linear.v1"
126
+ warmup_steps = 250
127
+ total_steps = 20000
128
+ initial_rate = 0.00005
129
+
130
+ [training.score_weights]
131
+ ents_f = 1.0
132
+ ents_p = 0.0
133
+ ents_r = 0.0
134
+ ents_per_type = null
135
+
136
+ [pretraining]
137
+
138
+ [initialize]
139
+ vectors = ${paths.vectors}
140
+ init_tok2vec = ${paths.init_tok2vec}
141
+ vocab_data = null
142
+ lookups = null
143
+ before_init = null
144
+ after_init = null
145
+
146
+ [initialize.components]
147
+
148
+ [initialize.tokenizer]
en_sdoh_roberta_cui-any-py3-none-any.whl ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2dd2bf2b6c4275f2c80e5f6c2f106aea044edb56ab574ebae0b5c94fa4ef219a
3
+ size 441082126
meta.json ADDED
@@ -0,0 +1,317 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "lang":"en",
3
+ "name":"sdoh_roberta_cui",
4
+ "version":"0.0.0",
5
+ "description":"CNN based Social determinants of health NER with a fine-grained window context bag-of-words classifier and a standard ontology extension interface (SNOMED_CT and CUI)",
6
+ "author":"Dima Lituiev",
7
+ "email":"d.lituiev@gmail.com",
8
+ "url":"",
9
+ "license":"",
10
+ "spacy_version":">=3.2.1,<3.3.0",
11
+ "spacy_git_version":"800737b41",
12
+ "vectors":{
13
+ "width":0,
14
+ "vectors":0,
15
+ "keys":0,
16
+ "name":null
17
+ },
18
+ "labels":{
19
+ "transformer":[
20
+
21
+ ],
22
+ "ner":[
23
+ "Anxiety: GAD",
24
+ "Anxiety: Generalized Anxiety Disorder",
25
+ "Anxiety: Level of anxiety",
26
+ "Anxiety: NA",
27
+ "Anxiety: Signs and symptoms of anxiety",
28
+ "Anxiety: family hx: Anxiety state",
29
+ "Anxiety: hx of anxiety state",
30
+ "Depression: Family hx: Depression",
31
+ "Depression: Major depressive disorder",
32
+ "Depression: NA",
33
+ "Depression: PHQ",
34
+ "Depression: Symptoms of depression",
35
+ "Depression: hx of Depression",
36
+ "Financial_strain: Financial problem",
37
+ "Financial_strain: Financially secure",
38
+ "Financial_strain: NA",
39
+ "Financial_strain: Unable to afford medication",
40
+ "Food: Able to obtain food",
41
+ "Food: Fruit and vegetable intake",
42
+ "Food: NA",
43
+ "Housing: Homeless",
44
+ "Housing: Housing unsuited to needs",
45
+ "Housing: Marginally housed",
46
+ "Housing: NA",
47
+ "Housing: Stably housed",
48
+ "Housing: Subsidized housing",
49
+ "Housing: lives in facility",
50
+ "Insurance_status: Inadequate healthcare resources",
51
+ "Insurance_status: NA",
52
+ "Marital_or_partnership_status: Divorced",
53
+ "Marital_or_partnership_status: Engaged to be married",
54
+ "Marital_or_partnership_status: Married",
55
+ "Marital_or_partnership_status: NA",
56
+ "Marital_or_partnership_status: Partner",
57
+ "Marital_or_partnership_status: Partner relationship problem",
58
+ "Marital_or_partnership_status: Separated",
59
+ "Marital_or_partnership_status: Single person",
60
+ "Marital_or_partnership_status: Widowed",
61
+ "Social_isolation: At risk for loneliness",
62
+ "Social_isolation: Has social support",
63
+ "Social_isolation: Lives alone",
64
+ "Social_isolation: Lives with",
65
+ "Social_isolation: NA",
66
+ "Social_isolation: Personal relationship breakdown",
67
+ "Social_isolation: Social Isolation",
68
+ "Transportation: Has access to a car",
69
+ "Transportation: Has access to public transport vehicle",
70
+ "Transportation: NA",
71
+ "Transportation: Transportation problems",
72
+ "pain_and_disability: NA",
73
+ "pain_and_disability: Pain intensity rating scale, current",
74
+ "pain_and_disability: Pain intensity rating scale, worst"
75
+ ]
76
+ },
77
+ "pipeline":[
78
+ "transformer",
79
+ "ner",
80
+ "sdoh_cui"
81
+ ],
82
+ "components":[
83
+ "transformer",
84
+ "ner",
85
+ "sdoh_cui"
86
+ ],
87
+ "disabled":[
88
+
89
+ ],
90
+ "performance":{
91
+ "ents_f":0.7764060357,
92
+ "ents_p":0.8016997167,
93
+ "ents_r":0.7526595745,
94
+ "ents_per_type":{
95
+ "Marital_or_partnership_status: Divorced":{
96
+ "p":0.92,
97
+ "r":0.7666666667,
98
+ "f":0.8363636364
99
+ },
100
+ "Marital_or_partnership_status: Single person":{
101
+ "p":0.9850746269,
102
+ "r":1.0,
103
+ "f":0.992481203
104
+ },
105
+ "Social_isolation: Lives alone":{
106
+ "p":0.875,
107
+ "r":0.7777777778,
108
+ "f":0.8235294118
109
+ },
110
+ "Social_isolation: Has social support":{
111
+ "p":0.5740740741,
112
+ "r":0.4246575342,
113
+ "f":0.4881889764
114
+ },
115
+ "Housing: Stably housed":{
116
+ "p":0.6612903226,
117
+ "r":0.6949152542,
118
+ "f":0.6776859504
119
+ },
120
+ "pain_and_disability: NA":{
121
+ "p":0.8622754491,
122
+ "r":0.9536423841,
123
+ "f":0.9056603774
124
+ },
125
+ "pain_and_disability: Pain intensity rating scale, current":{
126
+ "p":1.0,
127
+ "r":0.7586206897,
128
+ "f":0.862745098
129
+ },
130
+ "pain_and_disability: Pain intensity rating scale, worst":{
131
+ "p":0.7586206897,
132
+ "r":0.6285714286,
133
+ "f":0.6875
134
+ },
135
+ "Marital_or_partnership_status: Married":{
136
+ "p":0.9136690647,
137
+ "r":0.9007092199,
138
+ "f":0.9071428571
139
+ },
140
+ "Anxiety: hx of anxiety state":{
141
+ "p":0.8305084746,
142
+ "r":0.8305084746,
143
+ "f":0.8305084746
144
+ },
145
+ "Depression: hx of Depression":{
146
+ "p":0.8591549296,
147
+ "r":0.7721518987,
148
+ "f":0.8133333333
149
+ },
150
+ "Marital_or_partnership_status: Partner":{
151
+ "p":0.95,
152
+ "r":0.9047619048,
153
+ "f":0.9268292683
154
+ },
155
+ "Social_isolation: Lives with":{
156
+ "p":0.8409090909,
157
+ "r":0.880952381,
158
+ "f":0.8604651163
159
+ },
160
+ "Depression: Major depressive disorder":{
161
+ "p":0.4,
162
+ "r":0.2,
163
+ "f":0.2666666667
164
+ },
165
+ "Depression: Symptoms of depression":{
166
+ "p":0.6447368421,
167
+ "r":0.7903225806,
168
+ "f":0.7101449275
169
+ },
170
+ "Anxiety: Signs and symptoms of anxiety":{
171
+ "p":0.72,
172
+ "r":0.8571428571,
173
+ "f":0.7826086957
174
+ },
175
+ "Depression: NA":{
176
+ "p":0.0,
177
+ "r":0.0,
178
+ "f":0.0
179
+ },
180
+ "Marital_or_partnership_status: Separated":{
181
+ "p":0.0,
182
+ "r":0.0,
183
+ "f":0.0
184
+ },
185
+ "Anxiety: NA":{
186
+ "p":0.6666666667,
187
+ "r":0.9333333333,
188
+ "f":0.7777777778
189
+ },
190
+ "Social_isolation: NA":{
191
+ "p":0.0,
192
+ "r":0.0,
193
+ "f":0.0
194
+ },
195
+ "Anxiety: family hx: Anxiety state":{
196
+ "p":1.0,
197
+ "r":1.0,
198
+ "f":1.0
199
+ },
200
+ "Depression: Family hx: Depression":{
201
+ "p":0.875,
202
+ "r":0.7777777778,
203
+ "f":0.8235294118
204
+ },
205
+ "Marital_or_partnership_status: Widowed":{
206
+ "p":0.7428571429,
207
+ "r":0.7222222222,
208
+ "f":0.7323943662
209
+ },
210
+ "Food: Provision of food":{
211
+ "p":0.0,
212
+ "r":0.0,
213
+ "f":0.0
214
+ },
215
+ "Anxiety: Generalized Anxiety Disorder":{
216
+ "p":0.2,
217
+ "r":0.25,
218
+ "f":0.2222222222
219
+ },
220
+ "Financial_strain: NA":{
221
+ "p":0.0,
222
+ "r":0.0,
223
+ "f":0.0
224
+ },
225
+ "Insurance_status: Inadequate healthcare resources":{
226
+ "p":0.0,
227
+ "r":0.0,
228
+ "f":0.0
229
+ },
230
+ "Insurance_status: NA":{
231
+ "p":0.0,
232
+ "r":0.0,
233
+ "f":0.0
234
+ },
235
+ "Marital_or_partnership_status: NA":{
236
+ "p":0.0,
237
+ "r":0.0,
238
+ "f":0.0
239
+ },
240
+ "Transportation: Has access to a car":{
241
+ "p":0.5,
242
+ "r":0.2222222222,
243
+ "f":0.3076923077
244
+ },
245
+ "Anxiety: GAD-7":{
246
+ "p":0.0,
247
+ "r":0.0,
248
+ "f":0.0
249
+ },
250
+ "Depression: PHQ-9":{
251
+ "p":0.0,
252
+ "r":0.0,
253
+ "f":0.0
254
+ },
255
+ "Financial_strain: Financial problem":{
256
+ "p":0.0,
257
+ "r":0.0,
258
+ "f":0.0
259
+ },
260
+ "Housing: Housing unsuited to needs":{
261
+ "p":0.0,
262
+ "r":0.0,
263
+ "f":0.0
264
+ },
265
+ "Housing: Subsidized housing":{
266
+ "p":0.0,
267
+ "r":0.0,
268
+ "f":0.0
269
+ },
270
+ "Social_isolation: At risk for loneliness":{
271
+ "p":0.0,
272
+ "r":0.0,
273
+ "f":0.0
274
+ },
275
+ "Marital_or_partnership_status: Engaged to be married":{
276
+ "p":1.0,
277
+ "r":0.5,
278
+ "f":0.6666666667
279
+ },
280
+ "Financial_strain: Unable to afford medication":{
281
+ "p":0.0,
282
+ "r":0.0,
283
+ "f":0.0
284
+ },
285
+ "Transportation: Has access to public transport vehicle":{
286
+ "p":0.0,
287
+ "r":0.0,
288
+ "f":0.0
289
+ },
290
+ "Housing: lives in facility":{
291
+ "p":0.0,
292
+ "r":0.0,
293
+ "f":0.0
294
+ },
295
+ "Transportation: Transportation problems":{
296
+ "p":1.0,
297
+ "r":1.0,
298
+ "f":1.0
299
+ },
300
+ "Social_isolation: Social Isolation":{
301
+ "p":0.0,
302
+ "r":0.0,
303
+ "f":0.0
304
+ },
305
+ "Housing: NA":{
306
+ "p":0.0,
307
+ "r":0.0,
308
+ "f":0.0
309
+ }
310
+ },
311
+ "transformer_loss":377081.381025166,
312
+ "ner_loss":14440.8680006622
313
+ },
314
+ "requirements":[
315
+ "spacy-transformers>=1.1.4,<1.2.0"
316
+ ]
317
+ }
ner/cfg ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "moves":null,
3
+ "update_with_oracle_cut_size":100,
4
+ "multitasks":[
5
+
6
+ ],
7
+ "min_action_freq":1,
8
+ "learn_tokens":false,
9
+ "beam_width":1,
10
+ "beam_density":0.0,
11
+ "beam_update_prob":0.0,
12
+ "incorrect_spans_key":null
13
+ }
ner/model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ed474050bf0cafe37e52d67a9129383968da4f0be2bca8620be8b87ec98e58a5
3
+ size 527025
ner/moves ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:66b702df2ca0fd0417c10846eb7a2a1cb40d55c24a14bad0af4353a05fceae2c
3
+ size 8096
sdoh_cui/mapping-ontology-to-umls.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"Anxiety: Level of anxiety": {"SNOMED_CT": 286644009, "CUI": "C0564474", "canonical_text": "Level of anxiety (finding)"}, "Anxiety: Signs and symptoms of anxiety": {"SNOMED_CT": 79823003, "CUI": "C0233481", "canonical_text": "Worry"}, "Anxiety: Anxiety": {"SNOMED_CT": 48694002, "CUI": "C0003467", "canonical_text": "Anxiety (finding)"}, "Anxiety: Generalized Anxiety Disorder": {"SNOMED_CT": 21897009, "CUI": "C0270549", "canonical_text": "Generalized Anxiety Disorder (disorder)"}, "Anxiety: family hx: Anxiety state": {"SNOMED_CT": 160332003, "CUI": "C0455385", "canonical_text": "Family history: Anxiety state (situation)"}, "Anxiety: hx of anxiety state": {"SNOMED_CT": 161470009, "CUI": "C0455504", "canonical_text": "History of anxiety state (situation)"}, "Anxiety: Assessment of anxiety": {"SNOMED_CT": 710841007, "CUI": "C4039089", "canonical_text": "Assessment of anxiety (procedure)"}, "Anxiety: GAD-7": {"SNOMED_CT": 445455005, "CUI": "C2919162", "canonical_text": "Generalized anxiety disorder 7 item score (observable entity)"}, "Depression: Major depressive disorder ": {"SNOMED_CT": 370143000, "CUI": "C1269683", "canonical_text": "Major depressive disorder (disorder)"}, "Depression: Family hx: Depression": {"SNOMED_CT": 160329001, "CUI": "C0455383", "canonical_text": "Family history: Depression (situation)"}, "Depression: Depressed mood": {"SNOMED_CT": 366979004, "CUI": "C0344315", "canonical_text": "Depressed mood (finding)"}, "Depression: Mixed anxiety and depressive disorder": {"SNOMED_CT": 231504006, "CUI": "C0338908", "canonical_text": "Mixed anxiety and depressive disorder (disorder)"}, "Depression: hx of Depression": {"SNOMED_CT": 161469008, "CUI": "C0455503", "canonical_text": "History of depression (situation)"}, "Depression: PHQ-9": {"SNOMED_CT": 715252007, "CUI": "C4275234", "canonical_text": "Depression screening using Patient Health Questionnaire Nine Item score (procedure)"}, "pain_and_disability: Oswestry disability index": {"SNOMED_CT": 273675001, "CUI": "C0451360", "canonical_text": "Oswestry disability index (assessment scale)"}, "pain_and_disability: Pain intensity rating scale, current": {"SNOMED_CT": 425401001, "CUI": "C1960637", "canonical_text": "Pain intensity rating scale, current"}, "pain_and_disability: Pain intensity rating scale, worst": {"SNOMED_CT": 425401001, "CUI": "C1960637", "canonical_text": "Pain intensity rating scale, worst"}, "Housing: Housed": {"SNOMED_CT": 414418009, "CUI": "C0020056", "canonical_text": "Housed (stably housed)"}, "Housing: Homeless": {"SNOMED_CT": 32911000, "CUI": "C0237154", "canonical_text": "Homeless"}, "Housing: Lives in sheltered housing": {"SNOMED_CT": 160729004, "CUI": "C0425211", "canonical_text": "Lives in sheltered housing"}, "Housing: Marginally housed": {"SNOMED_CT": 105532006, "CUI": "C0425229", "canonical_text": "Overcrowded in house (finding)"}, "Housing: Housing case management": {"SNOMED_CT": 410341008, "CUI": "C1444479", "canonical_text": "Housing case management"}, "Housing: Housing unsuited to needs": {"SNOMED_CT": 160721001, "CUI": "C0578892", "canonical_text": "Housing unsuited to needs (finding)"}, "Housing: House in good repair": {"SNOMED_CT": 224262000, "CUI": "C0557253", "canonical_text": "House in good repair"}, "Housing: Housing education, guidance, and counseling": {"SNOMED_CT": 410297008, "CUI": "C1626900", "canonical_text": "Housing education, guidance, and counseling"}, "Housing: Home safety education": {"SNOMED_CT": 49919000, "CUI": "C0204944", "canonical_text": "Home safety education"}, "Housing: Lives in facility": {"SNOMED_CT": 11762561000119100, "CUI": "C4510636", "canonical_text": "Assisted living facility patient (finding)"}, "Housing: Housing surveillance": {"SNOMED_CT": 410392000, "CUI": "C1444530", "canonical_text": "Housing surveillance"}, "Transportation: Has access to a car": {"SNOMED_CT": 160687009, "CUI": "C0425253", "canonical_text": "Has access to a car"}, "Transportation: Has access to public transport vehicle": {"SNOMED_CT": 413288008, "CUI": "C1446359", "canonical_text": "Has access to public transport vehicle"}, "Transportation: Transportation problems": {"SNOMED_CT": 266934004, "CUI": "C0425259", "canonical_text": "Transport problems"}, "Transportation: Transportation case management": {"SNOMED_CT": 410365006, "CUI": "C1444503", "canonical_text": "Transportation case management"}, "Utilities: Telephone in house": {"SNOMED_CT": 160941000, "CUI": "C0425076", "canonical_text": "Telephone in house"}, "Utilities: No cooling in house": {"SNOMED_CT": 423798004, "CUI": "C1827351", "canonical_text": "Lack of cooling in house"}, "Utilities: No heat in house": {"SNOMED_CT": 105535008, "CUI": "C0425225", "canonical_text": "Lack of heat in house"}, "Utilities: No electricity in house": {"SNOMED_CT": 105536009, "CUI": "C0686993", "canonical_text": "Living in housing without electricity"}, "Utilities: Provision of adequate water supply": {"SNOMED_CT": 710924006, "CUI": "C4039114", "canonical_text": "Provision of adequate water supply"}, "Utilities: Provision of telephone": {"SNOMED_CT": 312635000, "CUI": "C0729989", "canonical_text": "Provision of telephone"}, "Utilities: Provision of wireless": {"SNOMED_CT": 243747004, "CUI": "C0419279", "canonical_text": "Provision of wireless"}, "Utilities: No telephone in home environment": {"SNOMED_CT": 5501000175107, "CUI": "C4082100", "canonical_text": "Lack of telephone in home environment"}, "Utilities: Inadequate sanitation": {"SNOMED_CT": 160707003, "CUI": "C0425226", "canonical_text": "Inadequate sanitation"}, "Utilities: No running water in house": {"SNOMED_CT": 5491000175103, "CUI": "C4081856", "canonical_text": "Lack of running water in house"}, "Financial_strain: Unable to afford blood pressure monitor": {"SNOMED_CT": 5521000175101, "CUI": "C4081857", "canonical_text": "Unable to afford blood pressure monitor"}, "Financial_strain: Unable to afford glucose monitoring device": {"SNOMED_CT": 5371000175108, "CUI": "C4081660", "canonical_text": "Unable to afford glucose monitoring device"}, "Financial_strain: Unable to afford weight scale": {"SNOMED_CT": 5731000175109, "CUI": "C4081858", "canonical_text": "Unable to afford weight scale"}, "Financial_strain: Financially secure": {"SNOMED_CT": 224165005, "CUI": "C0557160", "canonical_text": "Financially secure"}, "Financial_strain: Financial problem": {"SNOMED_CT": 160932005, "CUI": "C0549106", "canonical_text": "Financial problem (financial insecurity)"}, "Financial_strain: Low Income": {"SNOMED_CT": 424860001, "CUI": "C1331016", "canonical_text": "Low Income"}, "Financial_strain: Management of financial circumstance": {"SNOMED_CT": 710962009, "CUI": "C3165504", "canonical_text": "Management of financial circumstance"}, "Financial_strain: Unable to afford visit copayment": {"SNOMED_CT": 5311000175103, "CUI": "C4081884", "canonical_text": "Unable to afford visit copayment"}, "Financial_strain: Unable to afford medication": {"SNOMED_CT": 454061000124102, "CUI": "C4520569", "canonical_text": "Unable to afford medication"}, "Social_isolation: At risk for loneliness": {"SNOMED_CT": 129698004, "CUI": "C1268628", "canonical_text": "At risk for loneliness"}, "Social_isolation: Receives as much social support as wanted": {"SNOMED_CT": 445091000124106, "CUI": "C3853122", "canonical_text": "Receives as much social support as wanted (has social support)"}, "Social_isolation: Social Isolation": {"SNOMED_CT": 422650009, "CUI": "C0037421", "canonical_text": "Social Isolation"}, "Social_isolation: Lives alone": {"SNOMED_CT": 105529008, "CUI": "C0439044", "canonical_text": "Lives alone (finding)"}, "Social_isolation: Lives with": {"SNOMED_CT": 224130005, "CUI": "C0595998", "canonical_text": "Household composition"}, "Social_isolation: Personal relationship breakdown": {"SNOMED_CT": 105414008, "CUI": "C0524322", "canonical_text": "Personal relationship breakdown"}, "Social_isolation: Support system case management": {"SNOMED_CT": 410364005, "CUI": "C1444502", "canonical_text": "Support system case management"}, "Insurance_status: Able to access healthcare services": {"SNOMED_CT": 460821000124100, "CUI": "C4759353", "canonical_text": "Able to access healthcare services (finding)"}, "Insurance_status: No access to services": {"SNOMED_CT": 413332002, "CUI": "C1446402", "canonical_text": "No access to services"}, "Insurance_status: Inadequate healthcare resources": {"SNOMED_CT": 423593006, "CUI": "C1828339", "canonical_text": "Inadequate healthcare resources"}, "Insurance_status: Education about insurance coverage": {"SNOMED_CT": 453771000124109, "CUI": "C4316347", "canonical_text": "Education about insurance coverage"}, "Food: Able to obtain food": {"SNOMED_CT": 286441005, "CUI": "C0564281", "canonical_text": "Food security (Able to obtain food)"}, "Food: Food Insecurity": {"SNOMED_CT": 733423003, "CUI": "C3494174", "canonical_text": "Food Insecurity"}, "Food: Provision of food": {"SNOMED_CT": 710925007, "CUI": "C4039510", "canonical_text": "Provision of food"}, "Food: Fruit and vegetable intake": {"SNOMED_CT": 391129005, "CUI": "C1271941", "canonical_text": "Fruit and vegetable intake (observable entity)"}, "Marital_or_partnership_status: Separated": {"SNOMED_CT": 13184001, "CUI": "C4721417", "canonical_text": "Separated (finding)"}, "Marital_or_partnership_status: Divorce": {"SNOMED_CT": 63234004, "CUI": "C0086170", "canonical_text": "Divorce"}, "Marital_or_partnership_status: Common law partnership": {"SNOMED_CT": 14012001, "CUI": "C0009448", "canonical_text": "Common law partnership (finding)"}, "Marital_or_partnership_status: Engaged to be married": {"SNOMED_CT": 54986009, "CUI": "C0425152", "canonical_text": "Engaged to be married (finding)"}, "Marital_or_partnership_status: Married": {"SNOMED_CT": 87915002, "CUI": "C0555047", "canonical_text": "Married (finding)"}, "Marital_or_partnership_status: Single person": {"SNOMED_CT": 125681006, "CUI": "C0037179", "canonical_text": "Single person (finding)"}, "Marital_or_partnership_status: Partner relationship problem": {"SNOMED_CT": 1041000119100, "CUI": "C0236858", "canonical_text": "Partner relationship problem (finding)"}, "Marital_or_partnership_status: Marital status of parents": {"SNOMED_CT": 302172001, "CUI": "C0578882", "canonical_text": "Marital status of parents (situation)"}, "Misc: Mental state, behavior and/or psychosocial function finding": {"SNOMED_CT": 384821006, "CUI": "C1272788", "canonical_text": "Mental state, behavior and/or psychosocial function finding (finding)"}, "Misc: Social factor": {"SNOMED_CT": 61072005, "CUI": "C0337460", "canonical_text": "Social factor (finding)"}}
tokenizer ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c6fa5031a14a4f7ea4f3de4287ff1ccb8b11999f4835c2b3fe032f2fb6b60b07
3
+ size 77777
transformer/cfg ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "max_batch_items":4096
3
+ }
transformer/model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a9351170cd48fd05935b6e3c984e7cde6e3d5670316c24e1444afefcd90fa061
3
+ size 501274140
vocab/key2row ADDED
@@ -0,0 +1 @@
 
 
1
+
vocab/lookups.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:76be8b528d0075f7aae98d6fa57a6d3c83ae480a8469e668d7b0af968995ac71
3
+ size 1
vocab/strings.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9f9a31f9f1e9deed865e7d8d10e13867e328fd2e2d4306ef7faeb055bdcadfb2
3
+ size 476334
vocab/vectors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:14772b683e726436d5948ad3fff2b43d036ef2ebbe3458aafed6004e05a40706
3
+ size 128
vocab/vectors.cfg ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "mode":"default"
3
+ }