Design & Implementation of a Learning Health System in Australia - - PowerPoint PPT Presentation
Design & Implementation of a Learning Health System in Australia Data Dissect Pty Ltd (datadissect.com.au) Tom Cundy, Stefan Court-Kowalski, Andrew Feutrill, Hilary Boucaut, Francois Duvenage, Tim Boucaut, Peter Hewett, Sanjeev Khurana Health
Data Dissect Pty Ltd (datadissect.com.au)
Tom Cundy, Stefan Court-Kowalski, Andrew Feutrill, Hilary Boucaut, Francois Duvenage, Tim Boucaut, Peter Hewett, Sanjeev Khurana
Health Data Analytics 2019, Sydney, October 16-17 2019
www.datadissect.com.au Health technology company
Collaborative of Surgeons, Mathematician, IT Consultant, Computer Scientists, Business Manager
– Linear process – Start and end dates of study/trial – Strict inclusion/exclusion criteria – Generalisability of results not guaranteed – Expensive – Inefficient – Translation to practice not guaranteed
itself and not by-product of clinical care
researchers and clinical work force
– Isolating outcome measures or variables to investigate causes or effects
mode, where huge amounts of effort is invested to associate data with rare events, to a harvest mode in which huge amounts of data are used more efficiently to give insight.”
– Embrace multi-dimensional, multi-disciplinary data with human-computing symbiosis
1. http://www.learninghealthcareproject.org/publication/5/66/dr-paul-wallace-interview
Value = (Quality + Outcomes + Safety) Cost
Ureteric reimplantation rate (per 100,000) NSW 1.0 VIC 0.8 QLD 2.5 SA 6.5 WA 10.8 TAS
– 2007 first description – 2013 Institute of Medicine definition
improvement, yielding knowledge as a by-product of the patient-clinician interaction and focused on improving patient health and system outcomes”
– Immense and rapidly changing volume of medical information, complexity of decision making, limited capacity to evaluate decisions
1. Deans KJ, et al. Learning health systems. Semin Pediatr Surg. 2018 Dec;27(6):375-378. 2. Forrest CB, et al. Development of the Learning Health System Researcher Core Competencies. Health Serv Res. 2018 Aug;53(4):2615-2632. 3. Budrionis A , et al The Learning Healthcare System: Where are we now? A systematic review. J Biomed Inform. 2016 Dec;64:87-92. 4. Kwon S, et al. Creating a learning healthcare system in surgery: Washington State's Surgical Care and Outcomes Assessment Program (SCOAP) at 5 years. Surgery. 2012 Feb;151(2):146-52.
– Cycle begins and ends with clinician-patient interaction – Improving rather than proving – Afferent (blue) and Efferent (red) arms – Research influences practice, and practice influences research
– Patient/family engagement through self-reported outcomes – LHS researchers embedded at point-of-care – Leverages evidence about “what works” in context of own setting
1. Deans KJ, et al. Learning health systems. Semin Pediatr Surg. 2018 Dec;27(6):375-378. 2. Greene SM, et al. Implementing the learning health system: from concept to action. Ann Intern Med. 2012 Aug 7;157(3):207-10. 3. http://www.learninghealthcareproject.org
Clinical information Learning Health System Medical Record Registry or Audit
consent, etc
quality improvement
Context Data
Interpretation Visualisation
Acquisition Collation Storage Analytics
Human factors Technological factors Socio-Technological System
continuously improve system
transparent
their data collection via QoL assessments that populate platform
learning to permeate organization
– Launched 2006 – 60 out of 65 hospitals with surgical service – Surgeon designed, grassroots, voluntary, peer-based QI collaborative
– SCOAP OR Checklist – Decreased negative appendicectomy – Decreased UTI in epidural patients – Decreased anastomotic leak rate in colorectal surgery – Decreased blood transfusions (only if Hb < 7 g/dL) – Improved nutritional pre-habilitation for elective surgery – Appropriate use of neoadjuvant therapy for rectal cancer
1. Kwon S, et al. Creating a learning healthcare system in surgery: Washington State's Surgical Care and Outcomes Assessment Program (SCOAP) at 5
15
Appendicitis “Uncomplicated”
“Complicated” “Advanced”
– Fast track protocols – Identification of a subset of patients with complicated appendicitis that could be safely discharged earlier
1. Health Roundtable national audit data. https://www.healthroundtable.org/ 2. Cundy TP, et al. Fast-track surgery for uncomplicated appendicitis in children: a matched case-control study. ANZ Journal of Surgery. 2017 Apr;87(4):271-276.
– Customised user interface – Browser and smart-phone functionality – Hosted on off-site University of Adelaide server – Approval for satisfying patient privacy and data security protocols
– n = 180 consecutive patients in 9 months – Multi disciplinary teams gather data that is not currently being captured at the point of care
– Research influences practice, and practice influences research
– Rapid access quality improvement – Improved patient outcomes with reduced cost of care
www.datadissect.com.au Health technology company
Collaborative of Surgeons, Mathematician, IT Consultant, Computer Scientists, Business Manager
NSQIP Data Dissect Main use Designed to gather highly accurate clinical outcome data on patients undergoing surgery and produce benchmarking reports. An effective, affordable means of collecting info required to drive efficiency of care delivery in conditions that have already been identified as not meeting benchmarks. Mode of collection Specially trained senior nurse (1.0 FTE) will need accreditation by American college of surgeons (ACS) Point of care data entry by all treating team members; overseen by unit clinical nurse
Type of patients on whom data collected Only those having an operation Any condition – medical or surgical Limitation on data points Limited to max 80 clinical variables Unlimited variables including digital photos. Data storage Two separate databases: 1. To store identifiable data locally. Generates unique ID that is used for storing clinical data on second database. All clinical data stored anonymously on ACS database in USA. All data stored locally on uni Adelaide servers. Data kept encrypted and identifiable info visible only to authorised wch staff. (See attached doc on tech specs) Methodology Dedicated Data collector has to retrospectively collect prescribed dataset for a certain minimum number (38) cases per cycle. The case mix priority is determined by ACS. 1. A Customised Data set is collected at point of care by various members of the treating team for all relevant cases. Any number of conditions can be audited simultaneously Pricing model 25000 AUD per annum + 1.0 FTE senior nurse salary Data sharing All clinical data is shared with ACS No clinical data sharing required. However, deidentified data can be easily exported for multi centre studies