Cancer Diagnosis Text Matcher

val documentAssembler = new DocumentAssembler()
    .setInputCol("text")
    .setOutputCol("document")

val sentenceDetector = SentenceDetectorDLModel.pretrained("sentence_detector_dl_healthcare","en","clinical/models")
    .setInputCols(Array("document"))
    .setOutputCol("sentence")

val tokenizer = new Tokenizer()
    .setInputCols(Array("sentence"))
    .setOutputCol("token")

val text_matcher = TextMatcherInternalModel.pretrained("cancer_diagnosis_matcher","en","clinical/models")
    .setInputCols(Array("sentence","token"))
    .setOutputCol("cancer_dx")
    .setMergeOverlapping(true)

val mathcer_pipeline = new Pipeline()
    .setStages(Array(
    documentAssembler,
    sentenceDetector,
    tokenizer,
    text_matcher))

val data = Seq("""A 65-year-old woman had a history of debulking surgery, bilateral oophorectomy with omentectomy,
 total anterior hysterectomy with radical pelvic lymph nodes dissection due to ovarian carcinoma (mucinous-type carcinoma, stage Ic) 1 year ago.
 The patient's medical compliance was poor and failed to complete her chemotherapy (cyclophosphamide 750 mg/m2, carboplatin 300 mg/m2). Recently, she noted a palpable right breast mass, 15 cm in size which nearly occupied the whole right breast in 2 months. Core needle biopsy revealed metaplastic carcinoma. Neoadjuvant chemotherapy with the regimens of Taxotere (75 mg/m2), Epirubicin (75 mg/m2), and Cyclophosphamide (500 mg/m2) was given for 6 cycles with poor response, followed by a modified radical mastectomy (MRM) with dissection of axillary lymph nodes and skin grafting. Postoperatively, radiotherapy was done with 5000 cGy in 25 fractions. The histopathologic examination revealed a metaplastic carcinoma with squamous differentiation associated with adenomyoepithelioma. Immunohistochemistry study showed that the tumor cells are positive for epithelial markers-cytokeratin (AE1/AE3) stain, and myoepithelial markers, including cytokeratin 5/6 (CK 5/6), p63, and S100 stains.
 Expressions of hormone receptors, including ER, PR, and Her-2/Neu, were all negative.""") .toDF("text")

val result = mathcer_pipeline.fit(data).transform(data)