Panel: Automatic Clinical Text De-Identification: Is It Worth It, and Could It Work for Me? Hercules Dalianis Clinical Text Mining Group Department of.

Slides:



Advertisements
Similar presentations
Online Course Module 5 Patients Right to Accounting of Disclosures START Click to begin…
Advertisements

©2007 World Heart Federation … Updated October 2008 Diagnosis and Management of Acute Rheumatic Fever and Rheumatic Heart Disease.
Specifying clinical IT requirements for pathways: a national perspective Dr Mark Dancy Consultant Cardiologist National Clinical Lead CHD Collaborative.
Privacy and Information Security Training ( ) VUMC Privacy Website
HIPAA – Privacy Rule and Research USCRF Research Educational Series March 19, 2003.
1 HIPAA and Research and YOU. 2 INTRODUCTION Rule #1:Don’t Panic Rule #2:Bottom Line for Researchers: HIPAA is Manageable thru Education/Awareness and.
HIPAA Health Insurance Portability and Accountability Act.
HIPAA Training Presentation for New Employees How did we get here? HIPAA Police 1.
Which women are having a Hysterectomy and why? A plain English presentation of the methodology and findings of a database linkage study Dr Helen Stokes-Lampard.
ICT and medicine IT & C Department AP - Secretariat.
Creating and Evaluating a Consensus for Negated and Speculative Words in a Swedish Clinical Corpus Hercules Dalianis Maria Skeppstedt Stockholm University.
Journal Club Alcohol and Health: Current Evidence July–August 2005.
Information Extraction from Clinical Reports Wendy W. Chapman, PhD University of Pittsburgh Department of Biomedical Informatics.
Study: Statins increase life expectancy Detroit News, Associated Press
HIPAA What’s Said Here – Stays Here…. WHAT IS HIPAA  Health Insurance Portability and Accountability Act  Purpose is to protect clients (patients)
Health Insurance Portability and Accountability Act (HIPAA)
Security and Confidentiality Practices - Houston Dept. of Health and Human Services Jerald Harms, MPH, CART and Jeff Meyer, MD, MPH HIV/AIDS Surveillance.
Stefan Schulz, Thorsten Seddig, Susanne Hanser, Albrecht Zaiß, Philipp Daumke Checking coding completeness by mining discharge summaries.
APPLICATION : DIAGNOSTIC CODING 1 SIEMENS  Coding is the translation of diagnosis terms describing patients diagnosis or treatment into a coded number.
Extraction of Adverse Drug Effects from Clinical Records E. ARAMAKI* Ph.D., Y. MIURA **, M. TONOIKE ** Ph.D., T. OHKUMA ** Ph.D., H. MASHUICHI ** Ph.D.,K.WAKI.
Protected Health Information (PHI). Privileged Communication An exchange of information between two individuals in a confidential relationship. (Examples:
Early Detection Is Your Best Protection. Breast Cancer Statistics for Women A woman has a one in eight chance of developing breast cancer in her lifetime.
Human Research Protection Programs 1a: How to Navigate Human Subject Protection Regulations Sponsored by the American Society for Investigative Pathology.
Paula Peyrani, MD Medical/Project Director, HIV Program at the 550 Clinic Assistant Director, Research Design and Development Clinical and Translational.
Ch  ICT is used in many ways in the provision and management of healthcare services:  Hospital administration  Medical training  Maintenance.
The NHCS Pretest: Incorporating DAWN Rong Cai, Charles Day DAWN, CBHSQ, SAMHSA August 8, 2012.
Primary Care and Community Outreach Research VCOM Institutional Review Board Jim Mahaney, PhD Associate Dean for Biomedical Affairs, Virginia Campus Past.
Next ETCH Confidentiality and HIPAA Annual Review What you need to know. The Privacy Rule 1.
Confidentiality and Security Issues in ART & MTCT Clinical Monitoring Systems Meade Morgan and Xen Santas Informatics Team Surveillance and Infrastructure.
De-identifying Pathology Reports for Pathology Informatics
Health information that does not identify an individual and with respect to which there is no reasonable basis to believe that the information can be.
Information Technology for the Health Professions, Third Edition Lillian Burke and Barbara Weill Copyright ©2009 by Pearson Education, Inc. Upper Saddle.
HIPAA (health insurance portability and accountability act)
Medical Informatics Patient Administration System.
Medical Law and Ethics, Third Edition Bonnie F. Fremgen Copyright ©2009 by Pearson Education, Inc. Upper Saddle River, New Jersey All rights reserved.
BNR – Stroke: data entry and data management CAREC/PAHO Curacoa,15-16 November 2010 Gina Pitts, BNR-CVD Registrar Chronic Disease Research Centre, Jemmotts.
Building a Privacy Foundation. Setting the Standard for Privacy Health Insurance Portability and Accountability Act (HIPAA) Patient Bill of Rights Federal.
Health Insurance Portability and Accountability Act (HIPAA) CCAC.
De-identification: A Critical Success Factor in Clinical and Population Research Steven Merahn MD Dee Lang, RHIT Prepared for 2007 APIII Pittsburgh, PA.
HIPAA Pre-Clerkship Review Dr. Maryann Skrabal, Pharm.D., CDE.
HIPAA THE PRIVACY RULE. 2 HISTORY In 2000, many patients that were newly diagnosed with depression received free samples of anti- depressant medications.
Acknowledgements Contact Information Anthony Wong, MTech 1, Senthil K. Nachimuthu, MD 1, Peter J. Haug, MD 1,2 Patterns and Rules  Vital signs medoids.
Data Management and Analysis Baljit Bains and Ed Klodawski Demography Team Data Management and Analysis Group Ethnic Group Fertility Rates for London using.
HIPAA LAWS.  Under the privacy rule, the patient must give consent to use his or her Protected Health Information.  Examples in which consent must be.
Studying Health Care: Some ICD-10 Tools Hude Quan, Nicole Fehr, Leslie Roos University of Calgary and Manitoba Centre for Health Policy.
A Road Map to Research at Jefferson: HIPAA Privacy and Security Rules for Researchers Presented By: Privacy Officer/Office of Legal Counsel October 2015.
Detection of Spelling Errors in Swedish Clinical Text Nizamuddin Uddin and Hercules Dalianis Department of Computer and Systems Sciences, (DSV)
Integrated Management of Childhood Illnesses
Aged and Disabled Waiver (ADW) Health Insurance Portability and Accountability Act (HIPAA) Training 2015 October 2015.
What is HIPAA? Health Insurance Portability and Accountability Act of HIPAA is a major law primarily concentrating on the prolongation of health.
The Health Insurance Portability and Accountability Act (HIPAA) requires Plumas County to train all employees in covered departments about the County’s.
BlueCross BlueShield of Tennessee, Inc., an Independent Licensee of the BlueCross BlueShield Association. This document has been classified as public Information.
Research Directions using Text Mining on the Stockholm Electronic Patient Record Corpus Maria Skeppstedt
Best-of-Breed Hybrid Methods for Text De-identification Yang H, Garibaldi JM. Automatic detection of protected health information from clinical narratives.
Healthcare Careers II HIPAA-Overview for Healthcare Workers.
A Pilot Study of Dexmedetomidine-Propofol in Children Undergoing Magnetic Resonance Imaging
Electronic Health Records (EHR)
Workshop 11:30 – 12:10 FIRST WORKSHOP SESSION  WORKSHOP 2
Protecting “High Stakes” PHI
Taming SPSS: Large Scale and Secure Data Entry with LimeSurvey
Clinical NLP in North Germanic Languages
Evaluating Sepsis Guidelines and Patient Outcomes
CONTRACTS PRIVILEGED COMMUNICATION PRIVACY ACT
Privileged Communications
The Health Insurance Portability and Accountability Act
Lesson 1: Introduction to HIPAA
CONTRACTS PRIVILEGED COMMUNICATION PRIVACY ACT
کتابهای خریداری شده فن آوری اطلاعات سلامت 1397
TRACE INITIATIVE: Confidentiality, Data Security, and Procedures for Protocol Violation or Adverse Event.
WP 4 Translation to clinical practice
Presentation transcript:

Panel: Automatic Clinical Text De-Identification: Is It Worth It, and Could It Work for Me? Hercules Dalianis Clinical Text Mining Group Department of Computer and Systems Sciences (DSV)

Background Starting 2007 Karolinska University Hospital, Stockholm Greater Stockholm (City Council) 2 million inhabitants 1800 beds/inpatients 550 clinical units Hercules Dalianis, MEDINFO

TakeCare EPR system Swedish electronic patient record system, now owned by CompuGroup Medical Centralized, text file based Built on APL programming language Data transferred to MySQL database to make it manageable (Intelligence) Hercules Dalianis, MEDINFO

Ethical permission What type of research will be carried out How will it be carried out No social security number No personal names Safe guard of data Hercules Dalianis, MEDINFO

Encryption and safe guard Encrypted server Password protected Locked into an alarmed room Server locked to a rack No Internet connection Few people have access to this server (that have to sign security paper) => Probably safer than at the hospital Hercules Dalianis, MEDINFO

Trust, Trust and more Trust Good contacts with hospital management They decide for the whole hospital/all clinical units No psychiatric or veneric diseases, no paperless refugees Hercules Dalianis, MEDINFO

We obtained 1 million patient records from 550 clinical units from the year In several extracts that also continue Each patient have an unique social security number, from birth to dead Replaced by a serial number All patient names removed The rest including sensitive text is present Hercules Dalianis, MEDINFO Stockholm EPR Corpus

DEID work Yes, we did it also to obtain an overview of what problems may occur We followed HIPAA *) but adapted it for Swedish conditions *) Health Insurance Portability and Accountability Act Hercules Dalianis, MEDINFO

Hercules Dalianis The Stockholm EPR PHI *) corpus 100 electronic patient records (EPRs) in Swedish Five clinics: Neurology, Orthopaedia, Infection, Dental Surgery and Nutrition 20 patients from each clinic, 50% men, 50% women tokens Three annotators annotated the whole corpus *) Protected Health Information 9

Hercules Dalianis PHI-classes Account_Number, Age, Age_Over_89, Biometric_Identifier, Date_Part, Full_Date, Year, First_Name, Last_Name, Patient_First_Name, Patient_Last_Name, Relative_First_Name, Relative_Last_Name, Clinician_First_Name, Clinician_Last_Name, Location, Country, Municipality, Organization, Street_Address, Town, Health_Care_Unit, Device_Identifier_and_Serial_Number, Ethnicity, Fax_Number, Phone_Number, Relation, Uncertain

Hercules Dalianis 11

Consensus eight annotation classes Age Date_Part Full_Date First_Name Last_Name, Health_Care_Unit Location Phone_Number Hercules Dalianis 12

Annotation classes and instances Age 56 Full date710 Date part500 First name923 Last name928 Location Health care unit148 Phone number135 Sum: Hercules Dalianis 13

tokens sensitive instances ~ 1 percent sensitive information Hercules Dalianis 14

Eight annotation classes training and test using Stanford NER-CRF Hercules Dalianis 15

precision, recall F-score The 8 annotation classes and the words The rest is Black box –Window breadth –Distance between words etc Hercules Dalianis 16 Conditional Random fields à la Stanford NER

Research on Stockholm EPR Corpus DEID and Resynthesis Factuality level detection of diagnoses Negation detection Detecting the amount of hospital-acquired infections (HAI) Detection of adverse drug events Comorbidities Hercules Dalianis, MEDINFO

Conclusion Preferably to work on original data Too costly and difficult to de-identify data Not safe enough De-identification makes the data too noisy. Hercules Dalianis, MEDINFO

References Velupillai, S., H. Dalianis, M. Hassel and G. H. Nilsson Developing a standard for de-identifying electronic patient records written in Swedish: precision, recall and F-measure in a manual and computerized annotation trial. International Journal of Medical Informatics (2009), doi: /j.ijmedinf Dalianis, H. and S. Velupillai De-identifying Swedish Clinical Text - Refinement of a Gold Standard and Experiments with Conditional Random Fields, Journal of Biomedical Semantics 2010, 1:6 (12 April 2010) Hercules Dalianis, MEDINFO

Alfalahi, A., S. Brissman and H. Dalianis Pseudonymisation of person names and other PHIs in an annotated clinical Swedish corpus. In the Proceedings of the Third Workshop on Building and Evaluating Resources for Biomedical Text Mining (BioTxtM 2012) held in conjunction with LREC 2012, May 26, Istanbul, pp Hercules Dalianis, MEDINFO

Comorbidities in Comorbidity-view Which ICD-10 codes co-occur with which other ones Hercules Dalianis 21

Hercules Dalianis 22 Comorbidity View

Hercules Dalianis 23

Hercules Dalianis 24

Hercules Dalianis H - IVA D : Kvinna Anamnesis Kvinna med hjrtsvikt, förmaksflimmer, angina pectoris. Ensamstående änka. Tidigare CVL med sequelae högersidig hemipares och afasi. Tidigare vårdad för krampanfall misstänkt apoplektisk. Inkommer nu efter att ha blivit hittad på en stol och sannolikt suttit så över natten. Inkommer nu för utredning. Sonen Johan är med. Example record (Anonymized manually)

23 H - IVA D : Kvinna Bedömning Grav hjärtsvikt efter hjärtinfarkt x 2 inklusive eoisod med asystoli och HLR. EF 20-25%. Neurologisk påverkan med hösidig svaghet. Blodprov. Odlingar tas i blod och urin. Remiss skickas pulm-rtg enl dr Svenssons anteckning. Atelektaser. Pneumoni, I110. Hjärtinsufficiens, ospecificerad, I509 Hercules Dalianis 26

Hercules Dalianis 27 (English translation) 123 H - IVA D : Woman Anamnesis Woman with hert failures, atrial fibrillation, and angina pectoris. Single widow. Former CVL with sequele, rght hemiparesis and aphasia. Prior hospital care for seizures, suspected to be apoepeleptic. Arrive to hospital after being found in a chair and probably been sitting there over night. Arrive for further investigation and care. Accompanied by her son Johan.

Hercules Dalianis H - IVA D : Woman Assessment/Plan Severe heart failure after heart infarction x 2. including episode with heart arrest and acute heart arrest treatment. Ejection fracture (EF) %. Neurological symptoms with right sided hemiparesis. Blood samples. Culture for blood and urine. Referral for pulmonary x-ray according to dr Svensson’s notes. Atelectases. Pneumonia, I110. Heart failure, unspecified, I509.