Healthcare NLP v5.3.2 Release Notes

few_shot_assertion_classifier = FewShotAssertionClassifierModel().pretrained("assertion_fewshotclassifier", "en", "clinical/models")\
    .setInputCols(["sentence", "ner_chunk"])\
    .setOutputCol("assertion_fewshot")

texts = [
    ["Includes hypertension and chronic obstructive pulmonary disease."],
    ["Her former vascular no arteriovenous malformations are identified; there is no evidence of recurrence of her former vascular malformation."],
    ["He is an elderly gentleman in no acute distress. He is sitting up in bed eating his breakfast."],
    ["Trachea is midline. No jugular venous pressure distention is noted. No adenopathy in the cervical, supraclavicular, or axillary areas."],
    ["Soft and not tender. There may be some fullness in the left upper quadrant, although I do not appreciate a true spleen with inspiration."]
]

light_deidentification = LightDeIdentification() \
    .setInputCols(["ner_chunk", "sentence"]) \
    .setOutputCol("obfuscated") \
    .setMode("obfuscate") \
    .setObfuscateDate(True) \
    .setDateFormats(["MM/dd/yyyy"]) \
    .setDays(5) \
    .setObfuscateRefSource('custom') \
    .setAgeRanges([1, 4, 12, 20, 40, 60, 80])\
    .setCustomFakers({"Doctor": ["John", "Mark"],
                      "Patient": ["John", "Mark"],
                      "Hospital": ["Medical Center"],
                      "Street" : ["Main Road"],
                      "MEDICALRECORD": ["XYZ", "ABC"],
                      }) \
    .setLanguage("en") \
    .setSeed(10) \
    .setDateEntities(["DATE"]) \

light_deidentification2 = LightDeIdentification() \
    .setInputCols(["ner_chunk", "sentence"]) \
    .setOutputCol("masked") \
    .setMode("mask") \
    .setMaskingPolicy("masked") \
    .setObfuscateDate(True) \
    .setDateFormats(["yyyy"]) \
    .setUnnormalizedDateMode("skip") \
    .setAgeRanges([1, 4, 12, 20, 40, 60, 80])\
    .setSelectiveObfuscationModes({"OBFUSCATE": ["DATE", "STREET", "DOCTOR", "Patient"],
                                    "mask_same_length_chars": ["MEDICALRECORD"],
                                    "mask_entity_labels": ["HOSPITAL"],
                                    }) \

text ='''
Record date : 2093-01-13 ,M.D David Hale.
Name: Hendrickson, Ora MR # 7194334 Date: 01/13/93.
Patient: Oliveira, 25 years-old.
Cocke County Baptist Hospital, 0295 Keats Street
'''

rxnorm_resolver = SentenceEntityResolverModel.pretrained("biolordresolve_rxnorm_augmented", "en", "clinical/models")\
    .setInputCols(["embeddings"]) \
    .setOutputCol("rxnorm_code")\
    .setDistanceFunction("EUCLIDEAN")


text= "The patient was prescribed Albuterol inhaler, two puffs every 4 hours as needed for asthma. She was seen by the endocrinology service and was discharged on avandia 4 mg at night , Coumadin 5 mg with meals , and metformin 1000 mg two times a day and Lisinopril 10 mg daily"

clinical_ner = MedicalNerModel.pretrained("ner_clinical_large", "en", "clinical/models") \
    .setInputCols(["sentence", "token", "embeddings"]) \
    .setOutputCol("ner_clinical")

multi_chunk2doc = MultiChunk2Doc() \
    .setInputCols(["ner_chunk"]) \
    .setOutputCol("multi_chunk_doc") \
    .setCaseSensitive(False) \
    .setPrefix("< ") \
    .setSeparator(", ") \
    .setSuffix(" >")\
    .setWhiteList(["Problem"])

text = """She was on metformin, glipizide, and dapagliflozin for T2DM and atorvastatin and gemfibrozil for HTG. She had been on dapagliflozin for six months at the time of presentation.
Physical examination on presentation was significant for dry oral mucosa; significantly, her abdominal examination was benign with no tenderness, guarding, or rigidity."""

ner_model = MedicalNerModel.pretrained("ner_sdoh_core", "en", "clinical/models")\
    .setInputCols(["sentence", "token", "embeddings"])\
    .setOutputCol("ner")

sample_texts = [["""Smith is 55 years old, living in New York, a divorced Mexcian American woman with financial problems. She speaks Spanish and Portuguese. She lives in an apartment. She has been struggling with diabetes for the past 10 years and has recently been experiencing frequent hospitalizations due to uncontrolled blood sugar levels. Smith works as a cleaning assistant and cannot access health insurance or paid sick leave. She has a son, a student at college. Pt with likely long-standing depression. She is aware she needs rehab. Pt reports having her catholic faith as a means of support as well.  She has a long history of etoh abuse, beginning in her teens. She reports she has been a daily drinker for 30 years, most recently drinking beer daily. She smokes a pack of cigarettes a day. She had DUI in April and was due to court this week."""]]

from sparknlp.pretrained import PretrainedPipeline

ner_profiling_pipeline = PretrainedPipeline("ner_profiling_deidentification", 'en', 'clinical/models')

result = ner_profiling_pipeline.annotate("""Record date : 2093-01-13 , David Hale , M.D . , Name : Hendrickson Ora , MR # 7194334 Date : 01/13/93 . PCP : Oliveira , 25 years-old , Record date : 2079-11-09 . Cocke County Baptist Hospital , 0295 Keats Street , Phone 55-555-5555 .""")

clinical_re_Model = RelationExtractionModel()\
    .pretrained("re_clinical", "en", 'clinical/models')\
    .setInputCols(["embeddings", "pos_tags", "ner_chunk", "dependencies"])\
    .setOutputCol("relations")\
    .setRelationPairs(["problem-test", #"test-problem",
                       "treatment-problem",#"treatment-problem",
                       ])\
    .setMaxSyntacticDistance(4)\
    .setDirectionSensitive(True)

text ="""A 28-year-old female with a history of gestational diabetes mellitus diagnosed eight years prior to presentation and subsequent type two diabetes mellitus ( T2DM ),
one prior episode of HTG-induced pancreatitis three years prior to presentation,  associated with an acute hepatitis , and obesity with a body mass index ( BMI ) of 33.5 kg/m2 ,
presented with a one-week history of polyuria , polydipsia , poor appetite , and vomiting . Two weeks prior to presentation , she was treated with a five-day course of amoxicillin for a respiratory tract infection .
She was on metformin , glipizide , and dapagliflozin for T2DM and atorvastatin and gemfibrozil for HTG . She had been on dapagliflozin for six months at the time of presentation.
Physical examination on presentation was significant for dry oral mucosa ; significantly , her abdominal examination was benign with no tenderness , guarding , or rigidity .
Pertinent laboratory findings on admission were : serum glucose 111 mg/dl , bicarbonate 18 mmol/l , anion gap 20 , creatinine 0.4 mg/dL , triglycerides 508 mg/dL , total cholesterol 122 mg/dL , glycated hemoglobin ( HbA1c ) 10% , and venous pH 7.27 .
Serum lipase was normal at 43 U/L . Serum acetone levels could not be assessed as blood samples kept hemolyzing due to significant lipemia .
The patient was initially admitted for starvation ketosis , as she reported poor oral intake for three days prior to admission .
However , serum chemistry obtained six hours after presentation revealed her glucose was 186 mg/dL , the anion gap was still elevated at 21 , serum bicarbonate was 16 mmol/L , triglyceride level peaked at 2050 mg/dL , and lipase was 52 U/L .
The β-hydroxybutyrate level was obtained and found to be elevated at 5.29 mmol/L - the original sample was centrifuged and the chylomicron layer removed prior to analysis due to interference from turbidity caused by lipemia again .
The patient was treated with an insulin drip for euDKA and HTG with a reduction in the anion gap to 13 and triglycerides to 1400 mg/dL , within 24 hours .
Her euDKA was thought to be precipitated by her respiratory tract infection in the setting of SGLT2 inhibitor use .
The patient was seen by the endocrinology service and she was discharged on 40 units of insulin glargine at night , 12 units of insulin lispro with meals , and metformin 1000 mg two times a day .
It was determined that all SGLT2 inhibitors should be discontinued indefinitely .
She had close follow-up with endocrinology post discharge .
"""

clinical_re_Model = RelationExtractionModel()\
    .pretrained("re_clinical", "en", 'clinical/models')\
    .setInputCols(["embeddings", "pos_tags", "ner_chunk", "dependencies"])\
    .setOutputCol("relations")\
    .setRelationPairs(["problem-test", #"test-problem",
                       "problem-treatment",#"treatment-problem",
                       ])\
    .setFilterByTokenDistance(2)\
    .setDirectionSensitive(False)

text ="""A 28-year-old female with a history of gestational diabetes mellitus diagnosed eight years prior to presentation and subsequent type two diabetes mellitus ( T2DM ),
one prior episode of HTG-induced pancreatitis three years prior to presentation,  associated with an acute hepatitis , and obesity with a body mass index ( BMI ) of 33.5 kg/m2 ,
presented with a one-week history of polyuria , polydipsia , poor appetite , and vomiting . Two weeks prior to presentation , she was treated with a five-day course of amoxicillin for a respiratory tract infection .
She was on metformin , glipizide , and dapagliflozin for T2DM and atorvastatin and gemfibrozil for HTG . She had been on dapagliflozin for six months at the time of presentation.
Physical examination on presentation was significant for dry oral mucosa ; significantly , her abdominal examination was benign with no tenderness , guarding , or rigidity .
Pertinent laboratory findings on admission were : serum glucose 111 mg/dl , bicarbonate 18 mmol/l , anion gap 20 , creatinine 0.4 mg/dL , triglycerides 508 mg/dL , total cholesterol 122 mg/dL , glycated hemoglobin ( HbA1c ) 10% , and venous pH 7.27 .
Serum lipase was normal at 43 U/L . Serum acetone levels could not be assessed as blood samples kept hemolyzing due to significant lipemia .
The patient was initially admitted for starvation ketosis , as she reported poor oral intake for three days prior to admission .
However , serum chemistry obtained six hours after presentation revealed her glucose was 186 mg/dL , the anion gap was still elevated at 21 , serum bicarbonate was 16 mmol/L , triglyceride level peaked at 2050 mg/dL , and lipase was 52 U/L .
The β-hydroxybutyrate level was obtained and found to be elevated at 5.29 mmol/L - the original sample was centrifuged and the chylomicron layer removed prior to analysis due to interference from turbidity caused by lipemia again .
The patient was treated with an insulin drip for euDKA and HTG with a reduction in the anion gap to 13 and triglycerides to 1400 mg/dL , within 24 hours .
Her euDKA was thought to be precipitated by her respiratory tract infection in the setting of SGLT2 inhibitor use .
The patient was seen by the endocrinology service and she was discharged on 40 units of insulin glargine at night , 12 units of insulin lispro with meals , and metformin 1000 mg two times a day .
It was determined that all SGLT2 inhibitors should be discontinued indefinitely .
She had close follow-up with endocrinology post discharge .
"""

from sparknlp.pretrained import PretrainedPipeline

oncology_pipeline = PretrainedPipeline("oncology_biomarker_pipeline", "en", "clinical/models")

text = ["""Immunohistochemistry was negative for thyroid transcription factor-1 and napsin A. The test was positive for ER and PR, and negative for HER2."""]

results = oncology_pipeline.fullAnnotate(text)


column_maps = {
    "document_identifier": "XYZ-123",
    "document_text": "document",
    "entities": [
        {
            "ner_chunk_column_name": "assertion_chunk",
            "assertion_column_name": "assertion_oncology_wip",
            "resolver_column_name": None
        },
        {
            "ner_chunk_column_name": "merged_chunk",
            "assertion_column_name": None,
            "resolver_column_name": None
        }
    ],
    "relations": ["re_oncology_wip", "re_oncology_granular_wip"],
    "summary": None, 
    "deidentification": [
        {
            "original": None,
            "obfuscated": None,
            "masked": None,
        }
    ]
}

from sparknlp_jsl.pipeline_output_parser import PipelineOutputParser
pipeline_parser = PipelineOutputParser(column_maps)
pipeline_parser.__dict__

parsed_result = pipeline_parser.run(results)

{'result': [{'document_identifier': 'XXXX',
   'document_text': 'Immunohistochemistry was negative for thyroid transcription factor-1 and napsin A. The test was positive for ER and PR, and negative for HER2.',
   'entities': [
    [{'chunk_id': '0',
      'begin': 0,
      'end': 19,
      'chunk': 'Immunohistochemistry',
      'label': 'Pathology_Test',
      'assertion': 'Past',
      'term_code': None},
      {'chunk_id': '1',
      'begin': 38,
      'end': 67,
      'chunk': 'thyroid transcription factor-1',
      'label': 'Biomarker',
      'assertion': 'Present',
      'term_code': None},
      ...],
    [{'chunk_id': '0',
      'begin': 0,
      'end': 19,
      'chunk': 'Immunohistochemistry',
      'label': 'Pathology_Test',
      'assertion': None,
      'term_code': None},
     {'chunk_id': '1',
      'begin': 25,
      'end': 32,
      'chunk': 'negative',
      'label': 'Biomarker_Result',
      'assertion': None,
      'term_code': None},
      ...]
    ],
   'relations': [
    [{'relation': 'O',
      'entity1': 'Pathology_Test',
      'entity1_begin': '0',
      'entity1_end': '19',
      'chunk1': 'Immunohistochemistry',
      'entity2': 'Biomarker_Result',
      'entity2_begin': '25',
      'entity2_end': '32',
      'chunk2': 'negative',
      'confidence': '0.97084755'},
      ...],
    [...
     {'relation': 'is_finding_of',
      'entity1': 'Biomarker_Result',
      'entity1_begin': '25',
      'entity1_end': '32',
      'chunk1': 'negative',
      'entity2': 'Biomarker',
      'entity2_begin': '38',
      'entity2_end': '67',
      'chunk2': 'thyroid transcription factor-1',
      'confidence': '0.9239829'},
      ...]
    ],
   'summary': [],
   'deidentification': [{'original': [], 'obfuscated': [], 'masked': []}]}]}