Developing Information Developing Information Systems for Cancer Systems for Cancer Research Research Christopher Flowers, MD, MSc Christopher Flowers, MD, MSc Assistant Professor Assistant Professor Medical Director, Oncology Data Center Medical Director, Oncology Data Center Bone Marrow and Stem Cell Transplant Center Bone Marrow and Stem Cell Transplant Center Winship Cancer Institute Winship Cancer Institute Emory University Emory University
52
Embed
Developing Information Systems for Cancer Research
Developing Information Systems for Cancer Research. Christopher Flowers, MD, MSc Assistant Professor Medical Director, Oncology Data Center Bone Marrow and Stem Cell Transplant Center Winship Cancer Institute Emory University. Health Care Data Integration Medical Intelligence Applications. - PowerPoint PPT Presentation
Welcome message from author
This document is posted to help you gain knowledge. Please leave a comment to let me know what you think about it! Share it to your friends and learn new things together.
Transcript
Developing Information Systems for Developing Information Systems for Cancer ResearchCancer Research
Christopher Flowers, MD, MScChristopher Flowers, MD, MScAssistant ProfessorAssistant Professor
Medical Director, Oncology Data CenterMedical Director, Oncology Data CenterBone Marrow and Stem Cell Transplant CenterBone Marrow and Stem Cell Transplant Center
Winship Cancer InstituteWinship Cancer InstituteEmory UniversityEmory University
Health Care Data Integration
Medical Intelligence Applications
PatientDemographics
GSI DB
INTEGRATEDHEALTH CARE
DATA
Pharmacy
Financial /Billing System
Lab Results
O.R. Surgery &Materials Sys.
CancerRegistry
TranscribedNotes
Tissue Bank
Any OtherLegacy, CurrentSource System
MEDICALINTELLIGENCE
CASE REPORT
TISSUE BANK
GENETIC
SYSTEMADMINISTRATION
EXTRACTTRANSFORM
& LOAD(ETL)
REGULARDATA
UPDATE& REFRESH
HEALTH CARESOURCE SYSTEMS
NUTEC SERVICESPROCESSES
GENESYS SIDATABASE
GENESYS SISOFTWAREMODULES
JDBC
ODBC
ASCII
HL7
DTS
HEALTH CARE DATA INTEGRATION & MEDICAL INTELLIGENCE
What Data are available? What Data are available? Patient Genomics Patient Genomics
– Microarrays and Gene ChipMicroarrays and Gene Chip– Analysis ResultsAnalysis Results– Quality ValuesQuality Values
Ragini Kudchadkar, MD1, Leroy Hill1, Michael S. Keehan, PhD2,Jonathan Simons, MD1, Christopher Flowers, MD1
1 Winship Cancer Institute, Department of Hematology and Oncology, Emory University School of Medicine, Atlanta, GA (http://www.winshipcancerinstitute.org)
* Emory University has a financial interest in NuTec Health Systems, which designed and built GeneSys SI. Emory may financially benefit from this interest if NuTec is successful in marketing GeneSys SI. This project may produce income for Emory’s charitable purposes and for NuTec’s commercial purposes.
Development of GeneSys SIDevelopment of GeneSys SI
● Collaborative effort between Emory’s Winship Cancer Collaborative effort between Emory’s Winship Cancer Institute and NuTec Health SystemsInstitute and NuTec Health Systems
● Web-based query tool and genomic analysis tools Web-based query tool and genomic analysis tools designed with a team of Emory oncologists and designed with a team of Emory oncologists and research investigatorsresearch investigators
● August, 2002 – 175,000 Emory patients identified by August, 2002 – 175,000 Emory patients identified by cancer diagnosis loaded into GeneSys SIcancer diagnosis loaded into GeneSys SI● New patients added by individual patient consentNew patients added by individual patient consent
● Ongoing efforts to add new sources of dataOngoing efforts to add new sources of data● Tissue BankingTissue Banking● Genomic toolsGenomic tools
GeneSys SI ModulesHealth Care Applications
APPLICATIONS USERS
Principal InvestigatorResearcherPhysician
Health Care AdministratorFinancial Administrator
Cost Controller
Principal InvestigatorResearcher
Health Care Administrator
Principal InvestigatorResearcherPhysician
Clinical Research Outcomes Research
Health Care Data Mining Personalized Medicine
Quality Assurance Materials Cost Analysis
Labor Cost Analysis
Case Report Forms Patient Surveys Exit Interviews
Patient Consenting
Genetic Research Match Clinical Outcome
Match Phenotype Personalized Medicine
GENESYS SI SOFTWARE HEALTH CARE INSTITUTION
Forms BuildingPatient Data EntryForms/Data ImportQuery Tool (GSI DB)
CASE REPORT
Microarray QuantificationMicroarray AnalysisSNiP AnalysisPublic DB Search
GENETIC
TOOLSMODULES
MEDICALINTELLIGENCE
Multi DB QueryData Mining & AnalysisMulti DB ReportingRegional MapSurvival AnalysisChart Search & ValidationLab Views & Graphics
Principal InvestigatorProcurement Administrator
Procurement Assistant
Protocol Management Tissue Harvest Request
Archived Tissue Request Procurement Operations
Protocol Reg. & Admin.Tissue RequestsTissue ArchiveTissue Bank Administration
TISSUE BANK
System AdministratorDB AdministratorSecurity Service
GeneSys SI contains information on patients who have visited Emory University Hospital, Crawford Long Hospital, or The Emory Clinic and have received an oncology diagnosis. Benign neoplasms are also included.
Database Population
Numbers
• Total patients 175,748
• Newly consented 551
• By ICD9 & ICD10
Data currently available in GeneSys SIData currently available in GeneSys SI DATA SOURCE ENTRY DATE HISTORY (YEARS)DATA SOURCE ENTRY DATE HISTORY (YEARS)
Cancer RegistryCancer RegistryEmory HositalEmory HositalCrawford Long HospitalCrawford Long Hospital
1977197719811981
27272323
Clinical TrialsClinical Trials 19811981 2121
Electronic Medical RecordElectronic Medical RecordPowerChartPowerChart 19911991 1313
Radiation OncologyRadiation OncologyThe Emory ClinicThe Emory ClinicCrawford Long HospitalCrawford Long Hospital
1994199420012001
101033
FormsFormsInformed ConsentInformed Consent
July, 2003July, 2003 1 1
GenomicsGenomics TBDTBD N/AN/A
Linked Oncology DatabaseLinked Oncology Database
Useful for:Useful for:● Retrospective clinical outcomes researchRetrospective clinical outcomes research● Clinical trials planningClinical trials planning● Cost effectiveness analysesCost effectiveness analyses● Storage of unique clinical dataStorage of unique clinical data● Linking to public genomic and proteomic databasesLinking to public genomic and proteomic databases
● PharmacogenomicsPharmacogenomics
Limitations of linked heterogeneous databasesLimitations of linked heterogeneous databases
● Reliance on patient identifiers such as SSN to linkReliance on patient identifiers such as SSN to link● data entry errors, missing data, business practicesdata entry errors, missing data, business practices
● Patchwork of different databases not intended for Patchwork of different databases not intended for research purposesresearch purposes
● Reliance upon coded outcomes (e.g. ICD-9 codes)Reliance upon coded outcomes (e.g. ICD-9 codes)● frequently assigned by personnel unfamiliar with patient, frequently assigned by personnel unfamiliar with patient,
disease, or proceduredisease, or procedure
● Multiple sources for the same dataMultiple sources for the same data● diagnosis, treatment, DOB, DOE, other demographics diagnosis, treatment, DOB, DOE, other demographics
Breitfeld et.al. J Clin Epi, 2001.Breitfeld et.al. J Clin Epi, 2001.Earle et al. Med Care, 2002.Earle et al. Med Care, 2002.Verstraeten et.al. Verstraeten et.al. Expert Rev. VaccinesExpert Rev. Vaccines, 2003., 2003.
Research ObjectivesResearch Objectives
● Develop query algorithms to identify pts with a Develop query algorithms to identify pts with a histological diagnosishistological diagnosis● Follicular lymphomaFollicular lymphoma
● Examine sensitivity and specificity of query Examine sensitivity and specificity of query algorithmsalgorithms
● Develop query strategies for identifying pts with Develop query strategies for identifying pts with other diseases of interestother diseases of interest
10 Leading Cancer Sites by Gender, US, 200510 Leading Cancer Sites by Gender, US, 2005
− Peripheral T-cell lymphoma not otherwise characterized
− Hepatosplenic gamma/delta T-cell lymphoma
− Angioimmunoblastic T-cell lymphoma
− Extranodal T-/NK-cell lymphoma, nasal type
− Enteropathy-type intestinal T-cell lymphoma
− Adult T-cell lymphoma/leukemia (HTLV1+)
− Anaplastic large cell lymphoma, primary systemic type
− Anaplastic large cell lymphoma, primary cutaneous type
− Aggressive NK-cell leukemia
Fisher et al. In: DeVita et al, eds. Cancer: Principles and Practice of Oncology. 2005:1967.Jaffe et al, eds. World Health Organization Classification of Tumours. 2001.
WHO NHL ClassificationB-cell Precursor B-cell neoplasms
− Peripheral T-cell lymphoma not otherwise characterized
− Hepatosplenic gamma/delta T-cell lymphoma
− Angioimmunoblastic T-cell lymphoma
− Extranodal T-/NK-cell lymphoma, nasal type
− Enteropathy-type intestinal T-cell lymphoma
− Adult T-cell lymphoma/leukemia (HTLV1+)
− Anaplastic large cell lymphoma, primary systemic type
− Anaplastic large cell lymphoma, primary cutaneous type
− Aggressive NK-cell leukemia
Fisher et al. In: DeVita et al, eds. Cancer: Principles and Practice of Oncology. 2005:1967.Jaffe et al, eds. World Health Organization Classification of Tumours. 2001.
MethodsMethods
● Selected disease for initial query algorithm study Selected disease for initial query algorithm study (follicular lymphoma - FL)(follicular lymphoma - FL)
● Developed and ran queries for FL using all available Developed and ran queries for FL using all available sources for diagnosissources for diagnosis● Clinic & Hospital ICD9 codes, Cancer Registry histology Clinic & Hospital ICD9 codes, Cancer Registry histology
codes, Medical record text reports: chart, pathologycodes, Medical record text reports: chart, pathology
● Verified diagnosis for each patientVerified diagnosis for each patient● pathology reportspathology reports● other chart reportsother chart reports
● For each query calculated specificity and sensitivityFor each query calculated specificity and sensitivity
GeneSys SI queries to find follicular lymphoma patientsGeneSys SI queries to find follicular lymphoma patients
QUERYQUERY SOURCESOURCE CRITERIACRITERIA
QCQC Cancer Registry NHL patients Cancer Registry NHL patients NHL between 1985-2002NHL between 1985-2002
* For sensitivity and specificity calculations, numbers of true and false negatives were based on the total population of patients unique to these queries (1520 pts; 1084 pt w/ path) and not the entire patient population in GeneSys SI.
* For sensitivity and specificity calculations, numbers of true and false negatives were based on the total population of patients unique to these queries (1520 pts; 1084 pt w/ path) and not the entire patient population in GeneSys SI.
* For sensitivity and specificity calculations, numbers of true and false negatives were based on the total population of patients unique to these queries (1520 pts; 1084 pt w/ path) and not the entire patient population in GeneSys SI.
* For sensitivity and specificity calculations, numbers of true and false negatives were based on the total population of patients unique to these queries (1520 pts; 1084 pt w/ path) and not the entire patient population in GeneSys SI.
● Examining Treatment Strategies & Outcomes for Examining Treatment Strategies & Outcomes for Fludarabine Refractory CLLFludarabine Refractory CLL
● The influence of Comorbidity on Outcome in patients The influence of Comorbidity on Outcome in patients undergoing Allogeneic Transplantationundergoing Allogeneic Transplantation Other Cancer TreatmentsOther Cancer Treatments
● Examining Treatment Strategies & Outcomes for Examining Treatment Strategies & Outcomes for Relapsed Follicular LymphomaRelapsed Follicular Lymphoma
● Management of Squamous Cell Cancer of the Anus Management of Squamous Cell Cancer of the Anus (Reducing Surgical Morbidity)(Reducing Surgical Morbidity)
● Provide utilization data for cost-effectiveness Provide utilization data for cost-effectiveness studiesstudies
● Provide resources to support observational Provide resources to support observational studies and clinical trials in studies and clinical trials in pharmacogenomicspharmacogenomics
● Resource for developing algorithms for Resource for developing algorithms for pattern recognitionpattern recognition
Clinical Trials SupportClinical Trials Support
● Screening algorithms for identifying patients Screening algorithms for identifying patients eligible for clinical trialseligible for clinical trials
● Identify populations that would permit clinical Identify populations that would permit clinical trial investigationtrial investigation
● Data resource for monitoring trial outcomesData resource for monitoring trial outcomes Regimen-related toxicityRegimen-related toxicity Treatment ResponseTreatment Response SurvivalSurvival
Data descriptors or “metadata” for cancer researchPrecisely defining the questions and answers What question are you asking, exactly? What are the possible answers, and what do they
mean?
Ongoing projects covering various domains Clinical Trials Imaging Biomarkers Genomics
caBIO Overview
Software industry design paradigms Unified Modeling Language (UML)
representations of biomedical “objects” Java 2 Enterprise Edition “n-tier” system
architecture Broad coverage of biomedicine (but not comprehensive yet): Genomics Gene expression Model systems for cancer Human clinical trialsData “on-tap” via application programming interfaces
Cancer Clinical Database Application SystemCancer Clinical Database Application SystemWeb Form Generation Web Form Generation
Web form input fields for Cancer Chemotherapy
Configurable column attributes for the Cancer Chemotherapy form