Description
This pipeline can be used to deidentify PHI information from medical texts.
The PHI information will be masked and obfuscated in the resulting text.
The pipeline can mask and obfuscate MEDICALRECORD, ORGANIZATION, PROFESSION, HEALTHPLAN, DOCTOR, USERNAME, LOCATION-OTHER, URL, DEVICE, CITY, DATE, ZIP, STATE, PATIENT, COUNTRY, STREET, PHONE, HOSPITAL, EMAIL, IDNUM, BIOID, FAX, AGE, NAME, SSN, ACCOUNT, DLN, PLATE, VIN, LICENSE entities.
This pipeline is built using the ner_deid_subentity_augmented model as well as ContextualParser, RegexMatcher, and TextMatcher.
It is augmented with ner_deid_name_multilingual_clinical model.
Predicted Entities
MEDICALRECORD, ORGANIZATION, PROFESSION, HEALTHPLAN, DOCTOR, USERNAME, LOCATION-OTHER, URL, DEVICE, CITY, DATE, ZIP, STATE, PATIENT, COUNTRY, STREET, PHONE, HOSPITAL, EMAIL, IDNUM, BIOID, FAX, AGE, NAME, SSN, ACCOUNT, DLN, PLATE, VIN, LICENSE
How to use
from sparknlp.pretrained import PretrainedPipeline
deid_pipeline = PretrainedPipeline("clinical_deidentification_subentity_nameAugmented", "en", "clinical/models")
text = """Name : Hendrickson, Ora, Record date: 2093-01-13, MR #719435.
Dr. John Green, ID: 1231511863, IP 203.120.223.13.
He is a 60-year-old male was admitted to the Day Hospital for cystectomy on 01/13/93.
Patient's VIN : 1HGBH41JXMN109286, SSN #333-44-6666, Driver's license no: A334455B.
Phone (302) 786-5227, 0295 Keats Street, San Francisco, E-MAIL: smith@gmail.com."""
result = deid_pipeline.annotate(text)
import com.johnsnowlabs.nlp.pretrained.PretrainedPipeline
val deid_pipeline = PretrainedPipeline("clinical_deidentification_subentity_nameAugmented", "en", "clinical/models")
val text = """Name : Hendrickson, Ora, Record date: 2093-01-13, MR #719435.
Dr. John Green, ID: 1231511863, IP 203.120.223.13.
He is a 60-year-old male was admitted to the Day Hospital for cystectomy on 01/13/93.
Patient's VIN : 1HGBH41JXMN109286, SSN #333-44-6666, Driver's license no: A334455B.
Phone (302) 786-5227, 0295 Keats Street, San Francisco, E-MAIL: smith@gmail.com."""
val result = deid_pipeline.annotate(text)
Results
print("
Masked with entity labels")
print("-"*30)
print("
".join(result['masked']))
print("
Masked with chars")
print("-"*30)
print("
".join(result['masked_with_chars']))
print("
Masked with fixed length chars")
print("-"*30)
print("
".join(result['masked_fixed_length_chars']))
print("
Obfuscated")
print("-"*30)
print("
".join(result['obfuscated']))
Masked with entity labels
------------------------------
Name : <PATIENT>, Record date: <DATE>, MR <MEDICALRECORD>.
Dr. <DOCTOR>, ID: <DEVICE>, IP <IPADDR>.
He is a <AGE>-year-old male was admitted to the <HOSPITAL> for cystectomy on <DATE>.
Patient's VIN : <VIN>, SSN <SSN>, Driver's license no: <DLN>.
Phone <PHONE>, <STREET>, <CITY>, E-MAIL: <EMAIL>.
Masked with chars
------------------------------
Name : [**************], Record date: [********], MR [****].
Dr. [********], ID: [********], IP [************].
He is a **-year-old male was admitted to the [**********] for cystectomy on [******].
Patient's VIN : [***************], SSN [**********], Driver's license no: [******].
Phone [************], [***************], [***********], E-MAIL: [*************].
Masked with fixed length chars
------------------------------
Name : ****, Record date: ****, MR ****.
Dr. ****, ID: ****, IP ****.
He is a ****-year-old male was admitted to the **** for cystectomy on ****.
Patient's VIN : ****, SSN ****, Driver's license no: ****.
Phone ****, ****, ****, E-MAIL: ****.
Obfuscated
------------------------------
Name : Campbell Lerner, Record date: 2093-01-22, MR 301601.
Dr. Ivar Drape, ID: O1478969, IP 004.004.004.004.
He is a 74-year-old male was admitted to the DELAWARE COUNTY MEMORIAL HOSPITAL for cystectomy on 01/22/93.
Patient's VIN : 0XNAT55DDUK025427, SSN #062-37-6283, Driver's license no: T517616W.
Phone (737) 106-2694, 1120 Pine St, Durham, E-MAIL: Joseline@hotmail.com.
Model Information
| Model Name: | clinical_deidentification_subentity_nameAugmented |
| Type: | pipeline |
| Compatibility: | Healthcare NLP 5.3.0+ |
| License: | Licensed |
| Edition: | Official |
| Language: | en |
| Size: | 1.7 GB |
Included Models
- DocumentAssembler
- SentenceDetectorDLModel
- TokenizerModel
- WordEmbeddingsModel
- MedicalNerModel
- NerConverter
- MedicalNerModel
- NerConverter
- ChunkMergeModel
- ContextualParserModel
- ContextualParserModel
- ContextualParserModel
- ContextualParserModel
- ContextualParserModel
- ContextualParserModel
- TextMatcherModel
- ContextualParserModel
- RegexMatcherModel
- ContextualParserModel
- ContextualParserModel
- ContextualParserModel
- ContextualParserModel
- ChunkMergeModel
- ChunkMergeModel
- DeIdentificationModel
- DeIdentificationModel
- DeIdentificationModel
- DeIdentificationModel
- Finisher