Table 1.

Domain-specific lexicon

Type		Terms
Cancer identification	Noncancers	“adenoma,” “hematoma,” “adenomas,” “cystadenoma,” “hamartoma,” “hematomas,” “glaucoma,” “hemangioma,” “lipoma,” “hemartoma,” “coma,” “diploma,” “aroma”
	Cancer acronyms	“ALL,” “ALCL,” “AMKL,” “ANLL,” “CTCL,” “CLL,” “AML,” “CML,” “HCC,” “HCL,” “LMM,” “TCC,” “T-PLL,” “PLL,” “SCC,” “SMLC,” “SCLC”
	Unique cancers	“hodgkin,” “leukemia,” “neoplasm,” “tumor”
Modifiers	Descriptors	“acute,” “acute lymphoblastic,” “acute myelogenous,” “adrenocortical,” “aids-related,” “anal,” “basal cell,” “bile duct,” “bladder,” “bone,” “brain,” “brain stem,” “breast,” “bronchial,” “central nervous system,” “cerebellar,” “cervical,” “chronic lymphocytic,” “chronic myelogenous,” “colon,” “colorectal,” “cutaneous t-cell,” “endocrine,” “endometrial,” “esophageal,” “eye,” “gallbladder,” “gastric,” “gastrointestinal,” “gastrointestinal carcinoid,” “germ cell,” “hairy cell,” “head,” “hepatocellular,” “hodgkin,” “hodgkin's,” “hypopharyngeal,” “hypothalamic,” “intraocular,” “kaposi,” “kidney,” “laryngeal,” “lip,” “liver,” “lung,” “lymphoblastic,” “lymphocytic,” “malignant,” “melanoma”, “metastatic,” “merkel cell,” “mouth,” “myelogenous,” “myeloid,” “nasal cavity,” “nasopharyngeal,” “neck,” “non-hodgkin,” “non-small cell,” “oral,” “ovarian,” “pancreas,” “pancreatic,” “paranasal,” “parathyroid,” “penile,” “pharyngeal,” “pituitary,” “plasma cell,” “pleuropulmonary,” “prostate,” “rectal,” “renal,” “renal cell,” “salivary gland,” “sinus,” “skin,” “small cell,” “small intestine” “soft tissue,” “spinal cord,” “squamous cell,” “stomach,” “stromal,” “t-cell,” “t-cell prolymphocytic,” “testicular,” “throat,” “thymic,” “thymus,” “thymoma,” “thyroid,” “transitional cell,” “unknown,” “unknown primary site,” “uterine,” “vaginal,” “vulvar,” “wilms”
	Nouns with cancer serving as an adjective	“conference,” “marker,” “markers,” “registry”
Kinship terms	First-degree relatives (FDR)	“mother,” “father,” “sister,” “sisters,” “brother,” “brothers,” “half brother,” “half sister,” “son,” “sons,” “daughter,” “daughters,” “half-brother,” “half-sister,” “step brother,” “step sister,” “step-brother,” “step-sister,” “mom,” “dad,” (step- and half-siblings intentionally included)
	Non-FDRs	“uncle,” “aunt,” “cousin,” “grandfather,” “grandmother,” “grandpa,” “grandma”
	Nonrelatives	“husband,” “wife,” “spouse”
Section headings	Family history sections	“family history,” “family history:”, “familyhistory,” “family history,” “family history\r,” “FH:”
	Nonsubjective headings	“Physical Exam,” “Physical Exam:”, “Physicalexam,” “Physicalexam:”, “PHYSICAL EXAMINATION,” “PHYSICAL EXAMINATION:”, “PHYSICALEXAMINATION,” “PHYSICALEXAMINATION:”, “Assessment,” “ASSESSMENT,” “ASSESSMENT:”, “ASSESSMENT/PLAN,” “ASSESSMENT/PLAN,” “ASSESSMENT/PLAN:”, “ASSESSMENT AND PLAN,” “ASSESSMENT AND PLAN:”, “ASSESSMENT PLAN,” “ASSESSMENT-PLAN,” “ASSESSMENT-PLAN:”, “IMPRESSION,” “IMPRESSION:”
Negation phrases	Negation	“negative,” “negative for,” “denies,” “denies any history of,” “denies any family history of,” “negative history of,” “no family history of,” “no,” “unremarkable,” “unremarkable for,” “no history of,” “no history of other,” “no hx of,” “no family history of,” “no family hx of,” “without a history of,” “without of hx of,” “without”