The Evidence Based Medical Compliance Cluster EBMC 2 BPM European Round Table Meeting Eindhoven 5 November 2012 UnivProf Dr Stefanie Rinderle Ma University of Vienna Faculty of Computer Science ID: 289932
Download Presentation The PPT/PDF document "Guideline Compliance for Skin Cancer Tre..." is the property of its rightful owner. Permission is granted to download and print the materials on this web site for personal, non-commercial use only, and to display it on your personal computer provided you do not modify the materials and that you retain all copyright notices contained in the materials. By downloading content from our website, you accept the terms of this agreement.
Slide1
Guideline Compliance for Skin Cancer Treatment Processes: The Evidence-Based Medical Compliance Cluster (EBMC2)
BPM European Round Table Meeting, Eindhoven, 5 November 2012
Univ.-Prof. Dr. Stefanie Rinderle-MaUniversity of ViennaFaculty of Computer ScienceResearch Group Workflow Systems and Technologystefanie.rinderle-ma@univie.ac.at
Dr. Stefanie WeberDepartment of DermatologyDivision of General DermatologyMedical University of Viennastefanie.weber@meduniwien.ac.at Slide2
Outline
1 Introduction EBMC
22 Data Sources3 First Results4 Summary©Stefanie Rinderle-Ma, University of Vienna 20122Slide3Slide4
EBMC2: Evidence-Based Medicine Compliance Cluster Interdisciplinary cluster consisting of
participants from different groups within University of ViennaMedical University of Vienna / General Hospital of Vienna
Funded by University of Vienna and Medical University of Viennahttp://ebmc2.univie.ac.at/Combining the knowledge of all participating members and their domainsProcess oriented view of treatment and follow-upTreatment of melanoma patients as first use case4
©Stefanie
Rinderle
-Ma, University
of
Vienna 2012
4Slide5
Pilot Project: Skin CancerSkin cancer constitutes a global major health problemI
ncidence of skin cancer is worldwide
increasing Clinically validated, evidence-based guidelines are availableSlide6
Non-Melanoma Skin Cancer (NMSC)NMSC is worldwide the most common cancer among Caucasian
populations2 major forms: BCC, SCCMost NMSC occur on skin that is regularly exposed to sunlight or other ultraviolet radiationOther risk factors:
sun burnslight-colored or freckled skin exposure to arsenic (BCC)family historygenetics (e.g. Goltz-Gorlin syndrome, XP)Slide7
NMSC – BCC
P. Altmeyer Enzyklopädie der Dermatologie, Venerologie, Allergologie, Umweltmedizin; SpringerSlide8
NMSC – SCC
P. Altmeyer Enzyklopädie der Dermatologie, Venerologie, Allergologie, Umweltmedizin; SpringerSlide9
Malignant Melanoma (MM)Accounting for about 5% of all skin cancer cases, MM is the most dangerous form of skin malignancy causing 90% of
of skin cancer mortality Stages: AJCC I - IV (American Joint Committee on Cancer)Early detection is crucial
Risk factors:ultraviolet radiation (UV-A & UV-B)sun burns in early childhoodlight-colored or freckled skin family historymultiple neviSlide10
Malignant Melanoma
P. Altmeyer Enzyklopädie der Dermatologie, Venerologie, Allergologie, Umweltmedizin; SpringerSlide11
Stang, A., E. Pukkala, et al. (2006). "Time trend analysis of the skin melanoma incidence of Finland from 1953 through 2003 including 16,414 cases."
Int J Cancer
119(2): 380-4.
1953 - 2002Male: 1,5 to 12,8
Female: 1,8 to 10,4Slide12
Incidence
MortalitySlide13
Age std. Incidence Rates Melanoma
Garbe, C. and U. Leiter (2009). "Melanoma epidemiology and trends."
Clin Dermatol 27(1): 3-9.
Annual increase in incidence 3% - 7%Slide14
Aims of EBMC2 1) Development of methodology for the process analysis of medical treatment processes
to identify existing treatment and follow-up processes and compare these processes with existing guidelines (conformance analysis)to investigate cancer
incidence and prevalence in Austriato evaluate the association of melanoma with other tumor entitiesto explore and develop specific processes for early cancer detection (e.g., by identifying incidence patterns of high-risk patient collectives)to determinate effective and cost-saving follow-up strategies conditional on a variety of treatment protocolsSlide15
Aims of EBMC22) Definition
of a data structure that allows formal integration of data sources with different structures and content (e.g. PTDoc application
)Slide16
EBMC
2: Evidence-Based Medicine Compliance Cluster First step
: Formal modeling based on textual guidelines, e.g., European Guideline 1Insights:Different aspects: process structure, time, dataQuite rough / general compromise of
different partiesConsequence: variability of real-world processes
16
1
Garbe
, C., Peris, K., Hauschild, A.,
Saiag
, P., Middleton, M., Spatz, A., Grob, J
.,
Malvehy
, J., Newton-Bishop, J.,
Stratigos
, A.,
Pehamberger
, H.,
Eggermont
, A
.: Diagnosis and treatment of melanoma: European consensus-based interdisciplinary guideline. European Journal of Cancer 46(2), 270{283 (2010)Slide17
Compliance analysis
S4MDB
ACR
GAP-DRG
Process
Mining
Data Integration
Process
ComplianceSlide18
Life-Cycle Support
for
ComplianceSource: ©L.T.
Ly, Presentation@CoopIS 2011Compliance MonitoringSlide19
Outline
1 Introduction EBMC
22 Data Sources3 First Results4 Summary ©Stefanie Rinderle-Ma, University of Vienna 201219Slide20
Stage IV Melanoma DatabaseDepartment of Dermatology, General Hospital of ViennaBasic medical information on melanoma and treatment in patients with stage IV melanomaInformation about follow-up treatments in stage IV patients
Major objectives arethe progress of patients with melanoma,the median survival rate and the influence of different treatment options on survival
cf. Michael Binder, Wolfgang Dorda, Georg Duftschmid, Reinhold Dunkl, Karl Anton Fröschl, Walter Gall, Wilfried Grossmann, Kaan Harmankaya, Milan Hronsky, Stefanie Rinderle-Ma, Christoph Rinner, Stefanie Weber: On Analyzing Process
Compliance in Skin Cancer Treatment: An Experience Report from the Evidence-Based Medical Compliance Cluster (EBMC2). 398-413Slide21
Austrian Social Security Institution Data (GAP-DRG)Hospitalization dataPatient treatments received from general practitionersAdministered medications dispensed at pharmaciesSick certificates
Major objectives areaccounting andbilling
cf. Michael Binder, Wolfgang Dorda, Georg Duftschmid, Reinhold Dunkl, Karl Anton Fröschl, Walter Gall, Wilfried Grossmann, Kaan Harmankaya, Milan Hronsky, Stefanie Rinderle-Ma, Christoph Rinner, Stefanie Weber: On Analyzing Process Compliance in Skin Cancer Treatment: An Experience Report
from the Evidence-Based Medical Compliance Cluster (EBMC2). 398-413Slide22
New data sources: Austrian Cancer Register Database (Statistik Austria)Cancer registry of Austrian citizensData sources: cancer report forms (paper based)
Reporting units: hospitals, pathology institutesReporting mandatoryMajor objectives areIncidence, prevalence, morbidity and mortality
Geographical distributionSlide23
Japanese Cancer Register DatabaseSimilar to Austrian cancer registrySlide24
Data Source Integration and AssessmentTime-related data for process miningRouting data for decision point analysisStage IV Melanoma DatabaseFew time-related dataMany routing data
Austrian Social Security Institution Data (GAP-DRG)Many time-related dataFew routing data
cf. Michael Binder, Wolfgang Dorda, Georg Duftschmid, Reinhold Dunkl, Karl Anton Fröschl, Walter Gall, Wilfried Grossmann, Kaan Harmankaya, Milan Hronsky, Stefanie Rinderle-Ma, Christoph Rinner, Stefanie Weber: On Analyzing Process Compliance in Skin
Cancer Treatment: An Experience Report from the Evidence-Based Medical Compliance Cluster (EBMC2). 398-413Slide25
Outline
1 Introduction EBMC
22 Data Sources3 First Results4 Summary ©Stefanie Rinderle-Ma, University of Vienna 201225Slide26
Meta Data Enrichment of the Stage IV Melanoma DatabaseData did not meet requirements for process analysis due to lack of temporal referencesExtension and data recollectionAdding meta data to compensate missing structural informationMissing temporal information
Imprecise temporal informationRestating the Data ModelDevelopment of a generic and process-oriented data structure to integrate different data sources
cf. Michael Binder, Wolfgang Dorda, Georg Duftschmid, Reinhold Dunkl, Karl Anton Fröschl, Walter Gall, Wilfried Grossmann, Kaan Harmankaya, Milan Hronsky, Stefanie Rinderle-Ma, Christoph Rinner, Stefanie Weber: On Analyzing Process Compliance in Skin
Cancer Treatment: An Experience Report from the Evidence-Based Medical Compliance Cluster (EBMC2). 398-413Slide27
Source : R.
Dunkl@CAiSE
2012Import and recollectionSlide28
Source: EBMC2 Intermediate
report
(2012)recollectionSlide29
Source: EBMC2 Intermediate
report
(2012)Slide30
Mapping to MXML
Source: EBMC2 Intermediate
report (2012)Slide31
10
patients from Stage IV Melanoma Database
Extending and adding data through recollection
Using the restated data model for integrationMining a process model with the heuristic miner from the Process Mining Framework ProMEvaluation with domain experts to verify its compliance with medical reality
cf. Michael Binder, Wolfgang Dorda, Georg Duftschmid, Reinhold
Dunkl
, Karl Anton Fröschl, Walter
Gall
, Wilfried Grossmann,
Kaan
Harmankaya
, Milan
Hronsky
, Stefanie
Rinderle
-Ma, Christoph
Rinner
, Stefanie Weber: On
Analyzing Process Compliance in Skin Cancer Treatment: An Experience Report from the Evidence-Based Medical Compliance Cluster (EBMC2). 398-413Slide32
Data
errorsImprecise temporal
informationcf. Michael Binder, Wolfgang Dorda, Georg Duftschmid, Reinhold Dunkl, Karl Anton Fröschl, Walter Gall, Wilfried Grossmann, Kaan Harmankaya
, Milan Hronsky, Stefanie Rinderle-Ma, Christoph Rinner, Stefanie Weber: On Analyzing Process Compliance in Skin Cancer Treatment: An Experience Report from the Evidence-Based Medical Compliance Cluster (EBMC2). 398-413Slide33
cf. Michael Binder, Wolfgang
Dorda
, Georg Duftschmid, Reinhold Dunkl, Karl Anton Fröschl, Walter Gall, Wilfried Grossmann, Kaan Harmankaya, Milan Hronsky, Stefanie Rinderle-Ma, Christoph Rinner, Stefanie Weber: On Analyzing Process Compliance in Skin Cancer Treatment: An Experience Report from the Evidence-Based Medical Compliance Cluster (EBMC2). 398-413Slide34
Outline
1 Introduction EBMC
22 Data Sources3 First Results4 Summary©Stefanie Rinderle-Ma, University of Vienna 2012Slide35
Development of methodology for process analysis of medical treatment processesDevelopment of application (PTDoc) for formal integration of data from different sources with varying data structure
International cooperations – experiences in collecting “good” dataImproving data quality for process miningSkin cancer as pilot project – applications in other chronic diseases desirableSlide36
Conclusion:Process mining promises to be a useful tool for auditing existing data on treatment processes. This might help to facilitate that medical experts can easily follow the treatment of a patient using the offered process oriented visualizations.