[PPT] - Department of Information Systems 1 European BPM round table, Nov 5 PowerPoint Presentation

SLIDE 1

Personalized Care Pathways using BPM and AI techniques

Arturo González-Ferrer, PhD Department of Information Systems European BPM round table, Nov 5th 2012 1 Healthcare

Artificial Intelligence

Business Process Management

SLIDE 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 project

BPM round table, Eindhoven, Nov 5th, 2

SLIDE 3

Guideline Knowledge Modeling +

Computer-interpretable Guidelines (CIGs) are formalisms developed in the last decade:

PROforma,
Asbru,
GLIF,
SAGE
GLARE,
EON,…

BPM round table, Eindhoven, Nov 5th, 3

SLIDE 4

What BPMN can provide for modeling?

“At enactment time, the temporal perspective of the workflow specification leads to the ability to precisely schedule a process and its resources”

Denis Gagné and André Trudel,“Time-BPMN”, First Workshop on BPMN, 2009

BPMN able to represent roles/participants
T

emporal 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)

BPM round table, Eindhoven, Nov 5th, 4

SLIDE 5

Enabling Organizational Workflow & Therapy Planning



Physicians:



Did the patient take medication?



Who did what? Who is in charge of what?



Don't forget the lab test!



Am I following evidence during treatment?



How many times did I change dosages/plan?



Provide recommendations compatible with CPOE



Patients:



Allow them a personalized care



Remind them next steps



Record their recommendations/actions (PHR)



Personalized CPs adapted to patient’s insurance coverage



Managers:



Are we running out of resources?



How many nurses do we need next week?



Do we have a peak of patients at any moment?



It is safe to reassign resources?



Are we following evidence GL?



Show insurance companies that we did according to Clinical Guidelines

“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

BPM round table, Eindhoven, Nov 5th, 5

SLIDE 6

Figure extracted from R. Lenz, M. Reichert “IT support for healthcare processes – premises, challenges, perspectives”, Data & Knowledge Engineering 61, 2007

Care Pathways

BPM round table, Eindhoven, Nov 5th, 6

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 care

SLIDE 7

How can HTN AI planning help?

BPM round table, Eindhoven, Nov 5th, 7

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 knowledge HTN: Hierarchical Task Network

SLIDE 8

Integrating technologies

BPM round table, Eindhoven, Nov 5th, 8

 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

rganizational views

 Can model heuristics to drive the search of the goal plan

SLIDE 9

AI Planning approaches

BPM round table, Eindhoven, Nov 5th, 9



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



Dynamically building a simple process, perhaps the most likely to be successful until the end or until an intermediate milestone, try to execute it, discard it when it fails, and quickly re-build a new one

Deliberative Reactive BPM Continual

In preparing for battle I have always found that plans are useless, but planning is indispensable Dwight D. Eisenhower

SLIDE 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 : http://sites.google.com/site/bpm2hth/



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

BPM round table, Eindhoven, Nov 5th, 10

SLIDE 11

11

SLIDE 12

Powered by

SLIDE 13

Spain National Informatics Congress. Best Application Using Artificial Intelligence. CEDI 2005, Spain.

Cognocare is based on IActive’s award-wining technology

International Conference on Planning & Scheduling. Award for Excellence in Knowledge Engineering. ICAPS 2009. Tesalónica, Greece.

Award-winning Artificial Intelligence engine

Global Awards for Excellence in Adaptive Case Management. Gold Winner of the Healthcare category. Workflow Management Coalition 2012, USA. International Conference on Planning & Scheduling. Award for Best Application. ICAPS 2006. United Kingdom.

BPM round table, Eindhoven, Nov 5th, 13

“How Knowledge Workers Get Things Done: Real-World Adaptive Case Management”, 2012

SLIDE 14

The Cancer Problem

High incidence, prevalence and cost

Evidence-based medicine is not personalized

High complexity Constant change of patient conditions

BPM round table, Eindhoven, Nov 5th, 14

SLIDE 15

What do physicians need?

T

design personalized

treatments efficiently T

conform to

evidence-based medicine T

keep up with the

latest practice guidelines T

react to patient’s

changing conditions

I

At the point of care!

I I I BPM round table, Eindhoven, Nov 5th, 15

SLIDE 16

Alerts about scheduled lab tests Detailedexplanations about dosages Physicians maymodify the details of the treatment Next scheduled test Tentative forecast of the treatment (subject to labtests) Log of every decision made

SLIDE 17

Estimation of Resources

BPM round table, Eindhoven, Nov 5th, 17

Difficulties

Integration with EMRs
Integration of the provided output with CPOEs

SLIDE 18

to enable this bridge we need someone smart

Knowledge-Data: The good & evil simile

BPM round table, Eindhoven, Nov 5th, 18

SLIDE 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,1998

BPM round table, Eindhoven, Nov 5th, 19

SLIDE 20

Knowledge-Data Mapping +

How to evaluate if a patient is pregnant? Clinical concept (pregnancy) is clear to doctors, and to all of us data representation of this concept can be very different

BPM round table, Eindhoven, Nov 5th, 20

SLIDE 21

MobiGuide (www.mobiguide-project.eu)

CIG

PHR

EMR1 EMR2 BAN

Knowledge-Data mapping

CDSS

CIG KB

recommendations

The MobiGuide project develops an intelligent system for patients with chronic illnesses, such as cardiac arrhythmias, diabetes, and high blood pressure. The patients wear sensors that can monitor bio-signals (e.g., heart rate, blood pressure); the signals are transmitted to their Smartphone. The MobiGuide decision-support tools analyse the data, alert the patient about actions that should be taken, ask the patient questions (in the case that additional information is needed) and make recommendations regarding lifestyle changes or contacting care providers. All recommendations regarding therapy are transmitted to the patients' care providers.

BPM round table, Eindhoven, Nov 5th, 21

SLIDE 22

‘There is no worse death than the end of hope’

BPM round table, Eindhoven, Nov 5th, 22