Skip to main content

Entityschema

Schema package for clinical entity extraction from NHS medical documents.

Structure

📁 entityschema
├── examples/            # Training examples showing document input and structured output
├── schema.py            # Pydantic model for specifying expected output structure
├── prompt_builder.py    # Prompt builder for data generation and inference
├── prompt_datagen.txt   # Prompt template with example (for training data generation)
├── prompt_main.txt      # Prompt template without example (for inference/deployment)
└── py.typed             # Type checking marker

Usage

from entityschema.prompt_builder import PromptBuilder

# Initialize builder
builder = PromptBuilder()

# Build data generation prompt (with example)
datagen_prompt = builder.build_datagen_prompt()

# Build main/inference prompt (without example)
main_prompt = builder.build_main_prompt()

Schema

Schema overview

Type Values
EntityType gastroenteritis, c_difficile_enterocolitis, amoebic_infection, amoebic_liver_disease, pulmonary_tuberculosis, extrapulmonary_tuberculosis, miliary_tuberculosis, meningitis, meningococcal_meningitis, streptococcal_meningitis, viral_meningitis, encephalitis, viral_encephalitis, brain_abscess, spinal_abscess, liver_abscess, perianal_abscess, discitis, osteomyelitis, sepsis, meningococcal_septicaemia, streptococcal_septicaemia, staph_aureus_septicaemia, gram_negative_septicaemia, catheter_or_line_related_septicaemia, toxic_shock_syndrome, upper_respiratory_tract_infection, sinusitis, pharyngitis_or_tonsillitis, epiglottitis, oropharyngeal_abscess, ludwigs_angina, influenza, lower_respiratory_tract_infection, pneumonia, community_acquired_pneumonia, hospital_acquired_pneumonia, aspiration_pneumonia, viral_pneumonia, lung_abscess, legionnaires_disease, cellulitis, cutaneous_abscess, surgical_wound_infection, necrotising_fasciitis, neurosyphilis, lyme_disease, herpes_simplex_infection, eczema_herpeticum, herpes_zoster_infection, acute_hepatitis_a, acute_hepatitis_b, acute_hepatitis_c, acute_hepatitis_e, chronic_hepatitis_b, chronic_hepatitis_c, symptomatic_hiv_disease, cytomegaloviral_disease, infectious_mononucleosis, candidiasis, candidal_septicaemia, aspergillosis, invasive_pulmonary_aspergillosis, pulmonary_aspergilloma, pneumocystis_pneumonia, malaria, toxoplasmosis, giardiasis, cryptosporidiosis, scabies, pertussis, varicella, measles, croup, bronchiolitis, sars_infection, covid_19_infection, post_covid_19_syndrome, resistance_to_beta_lactam_antibiotics, resistance_to_other_antibiotics, pyrexia_of_unknown_origin, primary_cancer_lung, primary_cancer_breast, primary_cancer_colorectal, primary_cancer_prostate, primary_cancer_skin, primary_cancer_pancreas, primary_cancer_liver_or_biliary, primary_cancer_gi_upper, primary_cancer_kidney_or_bladder, primary_cancer_gynaecological, primary_cancer_testicular, primary_cancer_brain_or_cns, primary_cancer_head_and_neck, primary_cancer_haematological, primary_cancer_hodgkin_lymphoma, primary_cancer_non_hodgkin_lymphoma, primary_cancer_acute_leukaemia, primary_cancer_chronic_leukaemia, primary_cancer_myeloma, cancer_unknown_primary, kaposi_sarcoma, cancer_metastases, benign_neoplasm, early_stage_neoplasm_in_situ, chemotherapy, radiotherapy, anaemia, iron_deficiency_anaemia, pernicious_anaemia, anaemia_of_chronic_disease, haemolytic_anaemia, aplastic_anaemia, sickle_cell_trait, sickle_cell_disease, vaso_occlusive_crisis, thalassaemia, haemophilia, thrombophilia, von_willebrand_disease, thrombocytopenia, immune_thrombocytopenia, heparin_induced_thrombocytopenia, disseminated_intravascular_coagulation, thrombotic_thrombocytopenic_purpura, haemolytic_uraemic_syndrome, antiphospholipid_syndrome, neutropenia, febrile_neutropenia, agranulocytosis, polycythaemia_vera, myelodysplastic_syndrome, myelofibrosis, monoclonal_gammopathy_of_undetermined_significance, common_variable_immunodeficiency, tumour_lysis_syndrome, cytokine_release_syndrome, amyloidosis, anaphylaxis, allergic_reaction_to_drug, hypothyroidism, myxoedema_coma, hyperthyroidism, graves_disease, thyroid_storm, thyroiditis, hashimotos_thyroiditis, sick_euthyroid_syndrome, diabetes_mellitus, type_1_diabetes_mellitus, type_2_diabetes_mellitus, diabetic_ketoacidosis, hyperglycaemia, hyperosmolar_hyperglycaemic_state, diabetic_nephropathy, diabetic_retinopathy, diabetic_peripheral_neuropathy, diabetic_autonomic_neuropathy, diabetic_ulcers, hypoglycaemia, hypoglycaemic_coma, hypoparathyroidism, hyperparathyroidism, acromegaly, hyperprolactinaemia, syndrome_of_inappropriate_adh, hypopituitarism, diabetes_insipidus, cushings_syndrome, hyperaldosteronism, adrenocortical_insufficiency, addisonian_crisis, polycystic_ovarian_syndrome, primary_ovarian_failure, testicular_hypofunction, carcinoid_syndrome, malnutrition, refeeding_syndrome, wernicke_encephalopathy, vitamin_d_deficiency, iron_deficiency, obesity, obesity_hypoventilation, hyperlipidaemia, hypernatraemia, hyponatraemia, hyperkalaemia, hypokalaemia, hypercalcaemia, hypocalcaemia, volume_depletion, fluid_overload, lactic_acidosis, phaeochromocytoma, alcohol_use_disorder, alcohol_withdrawal, delirium_tremens, opioid_use_disorder, opioid_withdrawal, iv_drug_use_disorder, cocaine_use_disorder, cannabis_use_disorder, psychotic_episode, schizophrenia, schizoaffective_disorder, manic_episode, bipolar_affective_disorder, depression, low_mood, suicidal_ideation, anxiety_disorder, post_traumatic_stress_disorder, attention_deficit_hyperactivity_disorder, anorexia_nervosa, bulimia_nervosa, personality_disorder, learning_disability, insomnia, dementia, vascular_dementia, frontotemporal_dementia, lewy_body_dementia, mild_cognitive_impairment, delirium, huntingtons_disease, hereditary_ataxia, motor_neuron_disease, paraneoplastic_neurological_syndrome, parkinsons_disease, secondary_parkinsonism, neuroleptic_malignant_syndrome, serotonin_syndrome, essential_tremor, alzheimers_disease, early_onset_alzheimers_disease, multiple_sclerosis, central_pontine_myelinolysis, epilepsy, status_epilepticus, migraine, cluster_headache_syndrome, trigeminal_neuralgia, bells_palsy, subarachnoid_haemorrhage, cerebral_aneurysm_nonruptured, intracerebral_haemorrhage, ischaemic_stroke, transient_ischaemic_attack, cerebral_venous_sinus_thrombosis, nerve_root_or_plexus_disorder, guillain_barre_syndrome, chronic_inflammatory_demyelinating_polyneuropathy, peripheral_neuropathy, myasthenia_gravis, lambert_eaton_syndrome, muscular_dystrophy, myopathy, critical_illness_myopathy, cerebral_palsy, hemiplegia, paraplegia_or_tetraplegia, locked_in_syndrome, hydrocephalus, normal_pressure_hydrocephalus, raised_intracranial_pressure, hypoxic_anoxic_brain_injury, idiopathic_intracranial_hypertension, encephalopathy, posterior_reversible_encephalopathy_syndrome, compression_of_brain, cerebral_oedema, extradural_haemorrhage, subdural_haemorrhage, spinal_cord_compression, cauda_equina_syndrome, conjunctivitis, disorders_of_sclera, keratitis, uveitis, retinal_detachment, cataract, retinal_vascular_occlusions, retinal_haemorrhage, glaucoma, optic_neuritis, papilloedema, visual_disturbance, blindness, otitis_media, otitis_externa, mastoiditis, vestibular_disorders, hearing_loss, macular_degeneration, dental_condition, rheumatic_fever, essential_hypertension, hypertensive_cardiomyopathy, hypertensive_renal_disease, malignant_hypertension, hypertensive_encephalopathy, secondary_hypertension, angina_pectoris, stable_angina, unstable_angina, acute_myocardial_infarction, silent_myocardial_infarction, non_st_elevation_myocardial_infarction, st_elevation_myocardial_infarction, chronic_ischaemic_heart_disease, coronary_artery_stent_in_situ, dresslers_syndrome, aneurysm_of_heart, pulmonary_embolism, massive_pulmonary_embolism, cor_pulmonale, primary_pulmonary_hypertension, secondary_pulmonary_hypertension, pericarditis, restrictive_pericarditis, pericardial_effusion, cardiac_tamponade, infective_endocarditis, mitral_valve_prolapse, mitral_regurgitation, mitral_stenosis, aortic_regurgitation, aortic_stenosis, tricuspid_regurgitation, tricuspid_stenosis, pulmonary_regurgitation, pulmonary_stenosis, myocarditis, cardiomyopathy, dilated_cardiomyopathy, hypertrophic_cardiomyopathy, takotsubo_cardiomyopathy, sick_sinus_syndrome, heart_block, first_degree_heart_block, second_degree_heart_block, complete_heart_block, trifascicular_block, tachyarrhythmia, supraventricular_tachycardia, wolff_parkinson_white_syndrome, atrial_fibrillation, paroxysmal_atrial_fibrillation, atrial_flutter, ventricular_ectopics, ventricular_tachycardia, ventricular_fibrillation, cardiac_arrest, cardiac_arrest_with_rosc, long_qt_syndrome, brugada_syndrome, pacemaker_in_situ, replacement_heart_valve_in_situ, implantable_cardioverter_defibrillator_in_situ, heart_failure, left_ventricular_failure, right_ventricular_failure, heart_failure_preserved_ef, cardiomegaly, atherosclerosis, carotid_artery_stenosis, renal_artery_stenosis, peripheral_artery_disease, acute_limb_ischaemia, gangrene, mesenteric_ischaemia, ischaemic_colitis, aortic_dissection, aortic_aneurysm, aortic_aneurysm_rupture, hereditary_haemorrhagic_telangiectasia, venous_thromboembolism, deep_vein_thrombosis, peripheral_venous_insufficiency, lymphoedema, hypertension, hypotension, orthostatic_hypotension, drug_induced_hypotension, postural_orthostatic_tachycardia_syndrome, copd, emphysema, copd_infective_exacerbation, copd_non_infective_exacerbation, asthma, status_asthmaticus, bronchiectasis, bronchiectasis_infective_exacerbation, cystic_fibrosis, cystic_fibrosis_infective_exacerbation, occupational_lung_disease, acute_respiratory_distress_syndrome, pulmonary_oedema, pulmonary_haemorrhage, idiopathic_pulmonary_fibrosis, interstitial_lung_disease, pneumothorax, tension_pneumothorax, surgical_emphysema, bronchopleural_fistula, pleural_effusion, haemothorax, empyema, type_1_respiratory_failure, type_2_respiratory_failure, respiratory_arrest, sarcoidosis, obstructive_sleep_apnoea, long_term_oxygen_therapy, gastro_oesophageal_reflux_disease, oesophagitis, barretts_oesophagus, mallory_weiss_tear, hiatus_hernia, gastritis_or_duodenitis, upper_gi_ulcer, gastric_ulcer, duodenal_ulcer, perforated_upper_gi_ulcer, upper_gi_bleed, haematemesis, melaena, lower_gi_bleed, rectal_bleeding, acute_appendicitis, inguinal_or_femoral_hernia, umbilical_hernia, ventral_hernia, crohns_disease, ulcerative_colitis, colitis, proctitis, volvulus, intestinal_obstruction, ileus, acute_diverticulitis, diverticular_disease, irritable_bowel_syndrome, megacolon, bowel_perforation, peritonitis, haemorrhoids, anal_fissure, rectal_prolapse, gilberts_syndrome, fatty_liver, non_alcoholic_fatty_liver, alcoholic_fatty_liver, alcoholic_liver_disease, alcoholic_hepatitis, non_alcoholic_steatohepatitis, autoimmune_hepatitis, acute_liver_failure, subacute_liver_failure, hepatic_fibrosis, hepatic_cirrhosis, chronic_liver_failure, portal_hypertension, hepatic_encephalopathy, hepatorenal_syndrome, portal_vein_thrombosis, budd_chiari_syndrome, variceal_disease, oesophageal_varices, gastric_varices, acute_variceal_bleed, spontaneous_bacterial_peritonitis, primary_biliary_cholangitis, primary_sclerosing_cholangitis, alpha_1_antitrypsin_deficiency, wilsons_disease, haemochromatosis, cholelithiasis, cholecystitis, cholangitis, acute_pancreatitis, chronic_pancreatitis, pancreatic_pseudocyst, achalasia, gastroparesis, intestinal_malabsorption, coeliac_disease, impetigo, pemphigus, pemphigoid, atopic_dermatitis, psoriasis, urticaria, erythema_multiforme, stevens_johnson_syndrome, dress_syndrome, toxic_epidermal_necrolysis, erythema_nodosum, pyoderma_gangrenosum, hidradenitis_suppurativa, skin_ulceration, pressure_ulcer, venous_ulcer, arterial_ulcer, septic_arthritis, prosthetic_joint_infection, reactive_arthropathy, rheumatoid_arthritis, psoriatic_or_enteropathic_arthropathy, juvenile_arthritis, gout, pseudogout, osteoarthritis, vasculitis, polyarteritis_nodosa, granulomatosis_with_polyangiitis, takayasu_arteritis, giant_cell_arteritis, polymyalgia_rheumatica, microscopic_polyangiitis, polymyositis, dermatomyositis, systemic_lupus_erythematosus, systemic_sclerosis, sjogrens_syndrome, behcets_disease, raynauds_phenomenon, hypermobility_syndrome, scoliosis, ankylosing_spondylitis, spondylosis, spinal_stenosis, cervical_disc_disorder, sciatica, fibromyalgia, osteoporosis, pathological_fracture, rickets, adult_osteomalacia, osteonecrosis, pagets_disease_of_bone, chronic_pain_syndrome, nephrotic_syndrome, nephritic_syndrome, microscopic_haematuria, macroscopic_haematuria, glomerulonephritis, minimal_change_disease, membranoproliferative_glomerulonephritis, iga_nephropathy, focal_segmental_glomerulosclerosis, anti_gbm_disease, autosomal_dominant_polycystic_kidney_disease, renal_tubular_acidosis, acute_tubular_necrosis, rhabdomyolysis, tubulointerstitial_nephritis, acute_kidney_injury, acute_renal_replacement_therapy, chronic_kidney_disease, ckd_stage_3, ckd_stage_4, ckd_stage_5, arteriovenous_fistula_in_situ, long_term_haemodialysis, peritoneal_dialysis, contrast_induced_nephropathy, urolithiasis, renal_colic, hydronephrosis, hydroureter, nephrogenic_diabetes_insipidus, renal_ischaemia_or_infarction, urinary_tract_infection, cystitis, pyelonephritis, urosepsis, benign_prostatic_hyperplasia, prostatitis, testicular_torsion, female_pelvic_inflammatory_disease, endometriosis, fibroids, ovarian_torsion, dysmenorrhoea, menorrhagia, uterine_prolapse, pregnant, ectopic_pregnancy, pregnancy_with_abortive_outcome, pregnancy_successful_delivery, pregnancy_pre_existing_hypertension, gestational_hypertension, pre_eclampsia, hellp_syndrome, eclampsia, hyperemesis_gravidarum, pregnancy_pre_existing_diabetes, gestational_diabetes, tuberous_sclerosis, fetal_alcohol_syndrome, marfan_syndrome, down_syndrome, edwards_syndrome, patau_syndrome, turner_syndrome, klinefelter_syndrome, fragile_x_syndrome, congenital_heart_disease, ehlers_danlos_syndrome, tachycardia, bradycardia, palpitations, diaphoresis, night_sweats, cyanosis, pallor, flushing, tachypnoea, dyspnoea, exertional_dyspnoea, orthopnoea, cough, purulent_sputum, epistaxis, haemoptysis, stridor, wheezing, hypoxia, vertigo, dizziness, presyncope, syncope_or_any_collapse, pyrexia, febrile_convulsion, rigors, seizure, lymphadenopathy, peripheral_oedema, polydipsia, chest_pain, pleuritic_pain, abdominal_pain, abdominal_distension_or_bloating, guarding_or_peritonism, upper_abdominal_pain, lower_abdominal_pain, flank_pain, lower_back_pain, thoracic_back_pain, chronic_back_pain, arthralgia, myalgia, headache, meningism, pain, neuropathic_pain, severe_pain, calf_pain_or_swelling, claudication, vomiting, nausea, heartburn, dysphagia, constipation, diarrhoea, faecal_incontinence, jaundice, ascites, absent_bowel_sounds, absent_flatus, change_in_bowel_habit, skin_numbness, hyperaesthesia, pruritus, tremor, rigidity, muscle_cramp_or_spasm, fasciculation, ataxia, ataxic_gait, paralytic_gait, difficulty_in_walking, immobility, frailty, recurrent_falls, loss_of_appetite, abnormal_weight_loss, poor_oral_intake, cachexia, dysuria, urinary_incontinence, urinary_retention, anuria, oliguria, polyuria, confusion_or_disorientation, drowsiness, stupor_difficult_to_rouse, avpu_alert, avpu_voice_response, avpu_pain_response, avpu_unresponsive, auditory_hallucinations, visual_hallucinations, agitation, anger, physical_violence, poor_personal_hygiene, cognitive_decline, speech_disturbance, dysphasia_or_aphasia, dysarthria, anosmia_or_parosmia, joint_effusion, non_specific_malaise, fatigue, general_weakness, muscle_wasting, hypothermia, warm_well_perfused, periarrest_state, acute_fall, thoracic_trauma, abdominal_trauma, intracranial_trauma, concussion, fracture_of_skull_or_facial_bones, fracture_of_cervical_spine, fracture_of_thoracic_spine, fracture_of_rib, flail_chest, fracture_of_lumbar_spine, fracture_of_shoulder_or_humerus, fracture_of_forearm_wrist_or_hand, fracture_of_pelvis, fracture_of_hip_or_neck_of_femur, fracture_of_femoral_shaft, fracture_of_lower_leg_ankle_or_foot, compartment_syndrome, intentional_self_harm, intentional_self_overdose, neglect, physical_abuse_or_assault, burn_or_scald_injury, drowning_or_submersion_injury, medication_side_effect, acute_toxicity_from_medication, acute_toxicity_from_paracetamol, acute_alcohol_intoxication, acute_opioid_intoxication, acute_toxicity_from_cocaine, acute_toxicity_from_benzodiazepines, acute_toxicity_from_antidepressants, carbon_monoxide_poisoning, fabry_disease, gaucher_disease, pompe_disease, mucopolysaccharidosis, porphyria, glycogen_storage_disease, mitochondrial_disease, tracheostomy_in_situ, tracheostomy_malfunction, cvc_or_picc_line_in_situ, oxygen_therapy, high_flow_oxygen_therapy, bi_level_positive_pressure_ventilation, continuous_positive_airway_pressure, invasive_ventilation, peg_or_pej_in_situ, stoma_in_situ, blood_transfusion, transplanted_kidney, transplanted_liver, transplanted_heart, transplanted_stem_cells, transplant_failure_or_rejection, extracorporeal_membrane_oxygenation, multiple_organ_dysfunction_or_failure, graft_versus_host_disease, systemic_inflammatory_response_syndrome, circulatory_failure, cardiogenic_shock, hypovolaemic_shock, distributive_shock, massive_haemorrhage, palliative_care, end_of_life_care, emergency_surgery, emergency_laparotomy, major_open_surgery, minimally_invasive_surgery, upper_gi_endoscopic_therapy, lower_gi_endoscopic_therapy, ureteroscopic_or_cystoscopic_therapy, bronchoscopic_therapy, percutaneous_drain, vascular_interventional_procedure, organ_transplantation, coronary_artery_bypass_graft, percutaneous_coronary_intervention, cardiac_electrophysiology_procedure, transcatheter_valve_procedure, cancer_tumour_resection_or_debulking, major_upper_gi_surgery, major_lower_gi_surgery, major_hpb_surgery, major_thoracic_surgery, major_vascular_surgery, major_neurosurgery, major_cardiac_surgery, major_orthopaedic_surgery, major_urologic_surgery, major_gynaecological_surgery, surgical_or_procedural_complication, social_care_package, residential_or_care_home, temporary_accommodation, no_fixed_abode, living_alone_at_home, living_with_others_at_home, zimmer_or_walker_dependency, wheelchair_dependency, assisted_transfer_bed_to_chair_dependency, bedbound, unemployed, active_smoker, ex_smoker, never_smoked, medically_fit_for_discharge, discharge_pending_social, discharge_pending_placement, discharge_pending_transfer
Assertion positive, negated, hypothetical, ambiguous
Subject patient, family_history, mother_or_child_or_foetus, other, ambiguous
Relevance active, recent, historical, planned, ambiguous

License

This project uses a proprietary license issued by Guy's and St Thomas' NHS Foundation Trust, enabling free (non-commercial) use by NHS organisations. See LICENSE files for details.

Metadata

Release files for londonaicentre-entityschema 1.2.0

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for londonaicentre-entityschema 1.2.0
File Size Uploaded
londonaicentre_entityschema-1.2.0.tar.gz 49.0 kB Details

Built distribution (wheel)

Table of built distributions (wheels) for londonaicentre-entityschema 1.2.0
File Interpreter ABI Platform
londonaicentre_entityschema-1.2.0-py3-none-any.whl Python 3 none any Details

Total release size: 93.3 kB

Release files / londonaicentre_entityschema-1.2.0.tar.gz

Download URL londonaicentre_entityschema-1.2.0.tar.gz
Size 49.0 kB
Tags Source
SHA-256 checksum
How to use checksums
e55bf64522fa35a79e781bbe743baa0fb329278f2594b522c9951310e868166e
BLAKE2b-256 checksum
How to use checksums
c22244faf48677737f706f21f49f86ff2d08e2b9ee93f9363f2964c2b07f4f8b
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via uv/0.11.21 {"installer":{"name":"uv","version":"0.11.21","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"Amazon Linux","version":"2023","id":null,"libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":true}

Release files / londonaicentre_entityschema-1.2.0-py3-none-any.whl

Download URL londonaicentre_entityschema-1.2.0-py3-none-any.whl
Size 44.2 kB
Tags Python 3
SHA-256 checksum
How to use checksums
dca4024a16e914fa6b7736bf1f47a69a271014492c81e0808132ebffb82d7d1b
BLAKE2b-256 checksum
How to use checksums
6456f9ebedba87f2cfccf3eb3c06c8d36b5b14e157347640e9b5c2044fefb35f
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via uv/0.11.21 {"installer":{"name":"uv","version":"0.11.21","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"Amazon Linux","version":"2023","id":null,"libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":true}

Release history Release notifications | RSS feed

This release

1.2.0 This release

2 release files

1.1.0

2 release files

1.0.0

2 release files

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page