The use of innovative Technologies to improve the delivery of cancer supportive care Clifford Hudis, MD Chief, Breast Cancer Medicine Service, MSKCC Professor of Medicine, WCMC President, ASCO Milano, 4.04.2014
Success Story: Cancer Survival
$120 Billion Price Tag by 2020 Cost control + no quality monitoring/measurement = inappropriate care Payer-driven quality efforts must include improved outcomes Solution: Quality measurement, meaningful and feasible to healthcare providers Promising initiatives
Growth in QOPI Since 2006
The HIT Revolution in Cancer Care 2012: EHR/EMR Use in U.S. Oncology Practices 8% Widespread adoption of EHRs by physicians and hospitals Improved data processing and storage capacities Rapid analysis tools 14.9% 16.2% 60.8% of practices already have advanced EHRs/EMRs Has basic EHR/EMR Looking to implement EHR/EMR in next 6 months No EHR/EMR Advances in natural language processing Source: Forte, GJ, et al. American Society of Clinical Oncology National Census of Oncology Practices: Preliminary Report. JOP January 2013 vol. 9 no. 1 9-19 Accessed 13 October 2013 - http://www.asco.org/sites/www.asco.org/files/census_infographic_0.pd
Current Landscape: Big Data Is Here The Institute of Medicine (IOM) recommends establishing a learning health system in the US Insistence on evidence-based health care in the ObamaCare Accountable Care Act, the HITECH Act and by insurers Big data is now part of our day-to-day virtual and physical life 9
A system in which realtime clinical data is captured, analyzed, and used to enhance patient care and drive scientific discovery Our Vision
Clin. Pharm. Ther. Vol 91, March, 2012
Safety Example: Rofecoxib Time from FDA approval to withdrawal due to a 2-fold increase in myocardial events 61 months Time needed to see safety signal in Kaiser-type system (7-8 million patients) 30 months Time to see signal if half the country were being tracked (~150M subjects) 6 months Time to see signal if the entire country had their data recorded 8-10 weeks
ASCO s CancerLinQ
The Prototype Processing: Raw Data from Varian from Epic from Altos from Impac Transformed Data 1. Understand 2. Standardize 3. Normalize 4. Make it Available
Outcomes
Assessed Actual Practice
Outcomes Match Prospective Trial Results
Linked CDS
Benchmarks Against Quality Measures
Demonstrate value-added tools, such as the ability to measure a clinician s performance on a subset of QOPI measures in real-time Create new ways of exploring clinical data and hypotheses generation Prototype: Goals Exceeded >170,000 patients 30 practices - 4 EHRs Demonstrate ASCO s capability to develop rapid, real-time, clinical decision support based on clinical guidelines and integrate the into a demonstration Provide lessons HER system learned about the technological and logistical challenges involved in a fullscale CancerLinQ Demonstrate the implementation ability to capture and aggregate complete longitudinal patient records from any source, in any format, use the data
22
The primary purpose of CancerLinQ is to improve the QUALITY of care and to enhance outcomes Many other secondary benefits will be realized For Patients: Highest quality care with best outcomes for EVERY patient Clinical Trial Matching Safety Monitoring Evidence based education materials Real time side effect management Patient Portals to interact with providers and provide patient reported outcomes (PROs)
The primary purpose of CancerLinQ is to improve the QUALITY of care and to enhance outcomes Many other secondary benefits will be realized For Research/Public Health: Ability to mine big data for correlations that could never be identified without aggregate data Comparative Effectiveness Research Hypothesis generating exploration of data could lead to better use of current products Identifying patients available for clinical trials Identifying early signals for adverse events Identifying early signals for effectiveness in off label use Using omics to identify best treatment options