Personalized Care Pathways using BPM and AI techniques


Published on

Slides of my talk in European BPM Round Table. The video here:

Published in: Health & Medicine
  • Be the first to comment

No Downloads
Total views
On SlideShare
From Embeds
Number of Embeds
Embeds 0
No embeds

No notes for slide

Personalized Care Pathways using BPM and AI techniques

  1. 1. Business Process Management Artificial Intelligence Healthcare Personalized Care Pathways using BPM and AI techniques Arturo González-Ferrer, PhD Department of Information Systems1 European BPM round table, Nov 5th 2012
  2. 2. Summary Formalization of Guideline Knowledge  How can BPMN help Enabling Clinical Workflow & Therapy Planning  Care Pathways  How can AI planning/scheduling help?  Mix Physician-view, Patient-view, Organizational-view  Personalized Care Pathways: Cognocare Knowledge-to-Data mapping  MobiGuide project2 BPM round table, Eindhoven, Nov 5th,
  3. 3. Guideline Knowledge Modeling + Computer-interpretable Guidelines (CIGs) are formalisms developed in the last decade: - PROforma, - Asbru, - GLIF, - SAGE - GLARE, - EON,…3 BPM round table, Eindhoven, Nov 5th,
  4. 4. What BPMN can provide for modeling? • BPMN able to represent roles/participants • Temporal Perspective • time points, • absolute, periodic, relative • intervals/durations • maximum, minimum, estimated • temporal constraints • As Soon As Possible (ASAP) • As Late As Possible (ALAP) • Start No Earlier Than (SNET) • Finish No Earlier Than (FNET) • Start No Later Than (SNLT) • Finish No Later Than (FNLT) • temporal dependencies • Start-to-Finish (SF), Start-to-Start (SS) • Finish-to-Start (FS), Finish-to-Finish (FF) Denis Gagné and André Trudel,“Time-BPMN”, First Workshop on BPMN, 2009“At enactment time, the temporal perspective of the workflow specification leads to the ability to precisely schedule a processand its resources” 4 BPM round table, Eindhoven, Nov 5th,
  5. 5. Enabling Organizational Workflow &Therapy Planning Physicians:  Managers:  Did the patient take medication?  Are we running out of resources?  Who did what? Who is in charge of what?  Dont forget the lab test!  How many nurses do we need next week?  Am I following evidence during treatment?  Do we have a peak of patients at any moment?  How many times did I change dosages/plan?  It is safe to reassign resources?  Provide recommendations compatible with CPOE  Are we following evidence GL? Patients:  Show insurance companies that we did according  Allow them a personalized care to Clinical Guidelines  Remind them next steps  Record their recommendations/actions (PHR)  Personalized CPs adapted to patient’s insurance coverage “Hardly any of the existing Clinical Decision Support Systems (CDSS) appear to be aimed at supporting extended clinical workflows, management of information and decision-making in plans that unfold over time” J. Fox et al. Delivering clinical decision support services: there is nothing as practical as a good theory. Journal of Biomedical Informatics, 43(5), 2010 5 BPM round table, Eindhoven, Nov 5th,
  6. 6. Care Pathways Aim to model a timed process of patient-focused care, by specifying key events, clinical exams and assessments to produce the best prescribed outcomes, within the limits of the resources available, for an appropriate episode of careFigure extracted from R. Lenz, M. Reichert “IT support for healthcareprocesses – premises, challenges, perspectives”, Data & KnowledgeEngineering 61, 20076 BPM round table, Eindhoven, Nov 5th,
  7. 7. How can HTN AI planning help? HTN: Hierarchical Task Network Declarative in nature, but able to also express control flow patterns Able to express knowledge-based heuristics It is based in first-order logic, but very useful for domains based on expert knowledge7 BPM round table, Eindhoven, Nov 5th,
  8. 8. Integrating technologies CIGs  Model the physician view of care process  Their interpretation can provide single-step decision support BPMN  Model the organization view of care process  It can represent knowledge about roles, resources that are not included in CIG Artificial Intelligence P&S  Can use the knowledge provided by CIGs and BPM models  Provide a treatment plan considering physician, patient, and organizational views  Can model heuristics to drive the search of the goal plan 8 BPM round table, Eindhoven, Nov 5th,
  9. 9. Deliberative ReactiveAI Planning approaches BPM Continual Fully deliberative approach  A plan or process is designed hoping that everything is going to happen as expected and everything is fully predictable Fully reactive approach  The outcome of some tasks may not be predicted Building processes with conditional branches  The branch to be executed depends on the satisfaction of certain conditions (e.g. BPM) Continual planning Dwight D. Eisenhower  Dynamically building a simple process, perhaps In preparing for battle I the most likely to be successful until the end or until an intermediate milestone, try to execute have always found that it, discard it when it fails, and quickly re-build a plans are useless, but new one planning is indispensable 9 BPM round table, Eindhoven, Nov 5th,
  10. 10. Knowledge Engineering: BPM/CIG to HTN P&S Gonzalez-Ferrer, A. et al., From business process models to hierarchical task network planning domains” 28(2), June 2013, The Knowledge Engineering Review, Cambridge Journals  JABBAH : González-Ferrer A et al., Automated generation of patient- tailored electronic care pathways by translating computer- interpretable guidelines into hierarchical task networks, 2012, Artificial Intelligence in Medicine, Elsevier 10 BPM round table, Eindhoven, Nov 5th,
  11. 11. 11
  12. 12. Powered by
  13. 13. Cognocare is based on IActive’s award-wining technology “How Knowledge Workers Get Things Done: Real-World Adaptive Case Management”, 2012 Award-winning Artificial Intelligence engine Global Awards for Excellence in International Conference on Adaptive Case Management. Gold Planning & Scheduling. Award for Winner of the Healthcare category. Excellence in Knowledge Workflow Management Coalition Engineering. 2012, USA. ICAPS 2009. Tesalónica, Greece. Spain National Informatics Congress. International Conference on Best Application Using Artificial Planning & Scheduling. Award for Intelligence. Best Application. CEDI 2005, Spain. ICAPS 2006. United Kingdom.13 BPM round table, Eindhoven, Nov 5th,
  14. 14. The Cancer Problem High incidence, prevalence and cost High complexityEvidence-based medicine is not personalized Constant change of patient conditions 14 BPM round table, Eindhoven, Nov 5th,
  15. 15. What do physicians need? To design personalized I 0 treatments efficiently To conform to I 0 evidence-based medicine To keep up with the I 0 latest practice guidelines To react to patient’s I 0 changing conditions At the point of care!15 BPM round table, Eindhoven, Nov 5th,
  16. 16. Physicians may modify the details of the treatment Alerts about scheduled lab tests Detailed explanations about dosages Next scheduled test Log of every decision made Tentative forecast of the treatment (subject to lab tests)
  17. 17. Estimation of ResourcesDifficulties - Integration with EMRs - Integration of the provided output with CPOEs 17 BPM round table, Eindhoven, Nov 5th,
  18. 18. Knowledge-Data: The good & evil simile to enable this bridge we need someone smart18 BPM round table, Eindhoven, Nov 5th,
  19. 19. Knowledge Engineering Turning the process of constructing Knowledge Based Systems from an Art into an Engineering Discipline, using better methodological approaches Studer et. al, Knowledge Engineering: Principles and Methods,199819 BPM round table, Eindhoven, Nov 5th,
  20. 20. Knowledge-Data Mapping + Clinical concept data representation of(pregnancy) is clear to this concept can bedoctors, and to all of us very different How to evaluate if a patient is pregnant?20 BPM round table, Eindhoven, Nov 5th,
  21. 21. MobiGuide ( MobiGuide project develops an intelligent system for patients with chronic illnesses, such ascardiac arrhythmias, diabetes, and high blood pressure. The patients wear sensors that can monitorbio-signals (e.g., heart rate, blood pressure); the signals are transmitted to their Smartphone. TheMobiGuide decision-support tools analyse the data, alert the patient about actions that should betaken, ask the patient questions (in the case that additional information is needed) and makerecommendations regarding lifestyle changes or contacting care providers. All recommendationsregarding therapy are transmitted to the patients care providers. EMR1 PHR CIG EMR2 Knowledge-Data mapping CIG BAN KB recommendations CDSS 21 BPM round table, Eindhoven, Nov 5th,
  22. 22. my namesake Arthur used to say: ‘There is no worse death than the end of hope’ Thanks! contact me at: arturogf@gmail.com22 BPM round table, Eindhoven, Nov 5th,