CANCER LINQ Peter Paul Yu, MD, FACP, FASCO Washington State Medical - PowerPoint PPT Presentation

CANCER LINQ Peter Paul Yu, MD, FACP, FASCO Washington State Medical Oncology Society March 27, 2015

SITUATION LEARNING IS SLOW, LIMITED AND OFTEN NOT RELEVANT

Today, most information is lost

1.7 MM people diagnosed with cancer in the US Only 3 % enroll in 3% clinical trials.

Clinical trial patients tend to be … younger … healthier … and less diverse … less diverse … … than most of the patients we care for every day. 1. Lewis JH, et al. Participation of patients 65 years of age or older in cancer clinical trials. J Clin Oncol . 2003;21:1383-1389. http://jco.ascopubs.org/content/21/7/1383.full.pdf. 2. Mitchell AP, et al. Clinical trial subjects compared to "real world" patients: generalizability of renal cell carcinoma trials. J Clin Oncol. 2014;32(suppl):6510. 3. Taking action to diversify clinical cancer research. National Cancer Institute Web site. http://www.cancer.gov/ncicancerbulletin/051810/page7. Accessed July 23, 2014.

Information overload In 2013, Medline added 734,052 citations Assume just 1% of that new literature is relevant to a doctor's practice If a doctor reads 2 articles per night … . … .they would still be 10+ years behind Credit: Dan Masys

From one cancer to many … 1986 2014 One disease 7 molecular drivers … and more to be discovered

97% 1.7 MM of patient data locked away in unconnected files people diagnosed with and servers cancer in the US

will unlock a universe of practical insights to improve the care of every patient with cancer.

Data into Learning Knowledge Data Learning Base

The future of cancer care relies on big data and health IT The ability to mine large repositories of data in order to: – Evaluate treatment quality using large populations of similar patients – Identify long-term patient outcomes – Validate treatments/outcomes – Test treatment/outcome hypotheses 12

In a clinical trial … Insights Hypothesis development Study Clinical Data design intervention collection & analysis **Adap/ve** Data$ Hypothesis* Insights$ Tes/ng* *****clinical*trial******* collec)on$&$ genera/on* design* analysis$ With Big Data …

Improved Clinical Population Imp mproved$ Da Data$ a$ Real-world quality of decision health he healthc althcar are$ aggr ag greg ega(o a(on n patients care support outcomes oper op era(on ons

What is CancerLinQ?

CancerLinQ • A rich data repository • Not a registry for predefined questions • Allows data exploration of the real world • Generates new insights into warranted variation • Accelerates best practices, guideline development and CDS.

Example: ESA Usage in 8,300 Breast Cancer Cases Percentage of Cycles Median Hb level

Data Sources • 12-15 Vanguard Practices: cancer centers, hospital systems and community practices • CancerLinQ will extract information from EMR and Practice Management Systems • The entire medical record will be captured • Both structured fields and unstructured data (such as physician notes)

We want all the data associated with oncology patients … Clinical data • Demographics, clinical notes, procedures, practice/provider information, eRX/drug administration, ROS/physical exams, allergies, history of present illness Practice management data • Scheduling, billing, inventory , payer information Other data • Labs, pathology, tests, measurements, immunizations, encounters, medical equipment We do not have a defined set of fields, a specific data extract, or an implementation guide— we work with each data source to extract and load. 20

We Have Laid Out Our Principles That Underpin CancerLinQ • Stewardship – Robust standards; ethical procedures; adapting to changes in legal and ethical standards • Protection – Prevent harm; minimize risk; strong data security • Transparency and Accountability – Ethical duty to respect all participants in the system

CancerLinQ data requirements Data are the fuel that drives CancerLinQ Our focus is on ensuring minimal impact to sources of data Institute fully automated processes, including process monitoring No data entry requirements for participating data sources Data provided from the practices to CancerLinQ are fully identifiable and will contain PHI and PII CancerLinQ will de-identify the data as part of its standard processing CancerLinQ will generate reports or redacted data sets necessary to address 
 specific questions raised by interested users 22

CancerLinQ will be governed by a robust and multifaceted data stewardship program Board-appointed 
 oversight committees Compliance policies 
 and procedures Routine data 
 quality assessments Robust data request 
 management process

Regulatory Compliance We have extensively studied the relationship of CancerLinQ to the Common Rule and to HIPAA. Our findings were carefully laid out in a JCO paper in August of this year.

Regulatory Underpinnings of CLQ • There is a sound legal basis for CancerLinQ • All patient identifiable data in CLQ will be maintained and used in compliance with HIPAA • New England IRB has determined that CLQ participation is not human subjects research • Patients will be informed about CLQ and the system will accommodate patient opt-out 25

HIPAA • Practices can disclose patient identifiable health information (“PHI”) to CLQ without patient authorization – for quality improvement and other health care operations – under a HIPAA “Business Associate Agreement” • This is done in ASCO’s QOPI program and many other registries and quality initiatives 26

HIPAA • CLQ can use or disclose PHI only for the health care operations agreed to in advance by the oncology practices – quality improvement and reporting – benchmarking – clinical decision support – clinical trials indexing – creating limited data sets and de-identified information 27

Protecting personal health information • Physicians and practices will be able to access PHI from their patients only • Learning, trend-analysis, research, and guideline development will be done on redacted data sets

Data Ingestion How will we bring data into CancerLinQ? • Extract → Read data from source and push data into DB1 in CLQ • Transform → Standardize, normalize, and ontologize/ conceptualize the raw practice data • Load Extraction Storage Transformation Data Load → Load transformed data into DB2 Integration Gateway Clinical Data Practice Canonical Management Raw Data Format Processed Data Data (as received) Payor Data 29 Data Source DB1 DB2

Use Case: Quality Improvement • Physicians and practice managers can look at reports of adherence to quality performance measures • Reports will be ‘near real- time’ and not involve manual chart abstraction • Trends will be longitudinal, control charts mapping non- random variation

CancerLinQ measures analysis—Preliminary design My favorites (1) 88.3 87.3 Pain assessed, 2 most Pathology report % % recent visits All measurements (143) Colon (23) Central-line catheter — Antiemetic therapy associated blood stream administered for infection rate fro ICU and 91.5 1.42 moderately emetogenic Breast (32) % % high-risk nursery (HRN) chemotherapy risk patients Lung (12) Prostate (67) Fertility preservations KRAS gene mutation 91.4 72.6 % % discussed testing Non-patient related (9) Antiemetic therapy administered for 84.3 90 % % moderately emetogenic Chemotherapy plan chemotherapy risk GCSF administered to Trastuzumab not received — 92.0 0 % % patients who received her-2/neu negative chemotherapy for metastatic breast cancer

Use Case: Clinical Decision Support • Personalized diagnostic and treatment guidance based on the best available evidence • Prompts to improve quality, such as oncology drug related interactions • Iterative machine learning driven CDS development

Types of CDS Information Management Info Button, Up ToDate Situational Awareness Alerts, Dashboards Patient Decision Making Logic-based guidance

Outcomes Shared Decision Making Clinical Decision Support Systems Patient Data Healthcare Systems CPGs KB Systems KB Biology KB

Integrating Guidelines & Measures into CancerLinQ Measure Data QOPI/eQOPI Guidelines Measures CancerLinQ Outcome Data CDS = Clinical Decision Support

CancerLinQ Platform Powered by SAP HANA Practice Management Inpatient EHRs Ambulatory EHRs Biobank Lifestyle Systems

HANA Healthcare Platform SAP HANA Health Platform Extended Rules Engine App Services Procedural App Logic (Web Server) Analytics Applications DB-oriented Logic R Integration Predictive Unstructured Text Mining Decision Tables SQL Scripts EHR Fin ‘Omics Biometric Clinical Financial

Leading Organizations Trust SAP’s Industry Expertise Health Insurance Health Insurance Life Sciences &Suppliers Life Sciences &Suppliers D D i i s s c c r r e e t t e e M M a a n n u u f f a a c c t t u u r r i i n n g g 26

SAP Snapshot #1 Enterprise Software $22.2B+ SAP revenue worldwide 261,000 customers in 190 countries 68,000+ employees worldwide 74% World’s transaction revenue 86% Fortune 500 market share 25