A Medical Decision Support System That Learns



Loading...

Best Practices Winner: Children’s Hospital of Philadelphia
Project: Pediatric Knowledgebase
Category: Judges’ Prize

By Allison Proffitt

August 6, 2009
| “Wouldn’t it be great if we could [build a system] that ‘learned’ every time a patient walked in the door?” asks Jeff Barrett, director, Pediatric Pharmacology Research Unit, at the Children’s Hospital of Philadelphia, or CHOP. He’s envisioning a solution that’s part electronic medical record, part drug encyclopedia, and part patient chart. The result was the Pediatric Knowledgebase (PKB).

PKB was designed to meet many of the challenges of pediatric pharmacotherapy including, 1) provide dosing guidance consistent with formulary standard of care, 2) examine patient pharmacotherapeutic indices with respect to agent performance relative to controls derived from the hospital data warehouse, 3) explore treatment-diagnoses-drug correlation in conjunction with use and 4) educate physicians on clinical pharmacologic principles specific to population and drug combinations of interest.”

The PKB integrates the hospital’s medical records with drug-specific decision support generated by clinical pharmacology experts and clinical caregivers and predictive models generated by CHOP’s pharmacometric and informatics team. Forecasting tools evaluate dosing scenarios to be explored via a user friendly interface that front-ends a pediatric population-based PK/PD model. The result is therapeutic drug monitoring for children that uses patient data to help predict outcomes and inform clinical decisions in individual patients.

“Drug monitoring with a decision support system is sort of novel,” says Barrett. “There are services for [drug monitoring], but it’s disconnected from the patient’s history.” The PKB solution, however, is closely tied to personal data. The interface currently has drug dashboard prototypes for methotrexate (chemotherapeutic agent), tacrolimus (used to prevent organ rejection) and vancomycin (antibiotic) that are being evaluated clinically. “The dashboards are based on one drug, but they’re designed to go across drugs as well and monitor drug interactions,” explains Barrett.

Building the system was a multidisciplinary project, Barrett says. “We have an extremely varied group of individuals [involved in the project], and it’s the primary reason we’ve been able to get this far: pharmacometrics, clinical pharmacology, clinical/medical roles, programming/information technology, bioinformatics, data management and data integration.”

The project demanded that both the IT and the clinical communities be able to “look behind the curtain,” says Barrett. “We are integrated with the hospital’s information management system, [and]… we’ve got investment from the care givers. We knew that unless they were part of the process and actually designed what these systems looked like, [it wouldn’t work]. ”

In order for PKB to grow, partnerships have to expand outside of CHOP. The drug dashboards will eventually be populated with data through external collaborations. CHOP is part of the Pediatric Pharmacology Research Unit Network of children’s hospitals, Barrett says, and the PKB will receive data from several member hospitals. “This environment accumulates clinical outcomes including adverse events in a HIPAA-compliant informatics system,” the entry states.

Full Production
At CHOP, the production version of the PKB is waiting for the hospital’s new EMR system to be fully rolled out. It is  planned for piloting at Cincinnati Children’s Hospital and LeBonheur Children’s Medical Center in Memphis. The results have been good with “emphasis on clinical outcomes including reduced medication errors and length of hospital stay have been used to demonstrate the ROI for individual dashboards.”

The PKB was designed to work with various EMR systems, though customization will be required for each implementation. “It’s web based, and we want to see it go globally… first within the U.S., but there is some very strong expertise particularly in Europe and in the Netherlands especially. They’ve been doing [therapeutic drug monitoring] a lot longer.”

In the meantime, the team is “trying to create a consortium around this so that we have other folks participate in the development of this system. Cincinnati Children’s has already committed to going down this path with us,” Barrett says.

“We have an external advisory board that helps us plan for the IT challenges across the globe.” Specifically, the PKB plans to make use of technology solutions that have broad appeal, “in particular SAS and the JMP product.” Also in the works: “We’re planning for a PKB-Lite version that allows people to upload data into a larger system, meant to accommodate a smaller outpatient setting.”

“This has been such a blessing for us,” says Barrett of winning the Best Practices award. “As we’re putting together the documentation for the consortium and identifying what the PKB is and seeks to do, we [now] have some external validation that this is a project that’s been well thought out and has the right sorts of teams interested. It will improve the visibility of our efforts and we’re looking at this to kind of kick this over the top.


This article also appeared in the July-August 2009 issue of Bio-IT World Magazine.
Subscriptions are free for qualifying individuals. Apply today.

Click here to login and leave a comment.  

1 Comments

  • avatar

    Hello, I was wondering: Does this system involve a Prolog (or Datalog in general) part/module? If not, has it been considered?

    Kind Regards
    Samuel Lampa

Add Comment

Text Only 2000 character limit

Page 1 of 1

White Papers & Special Reports

sapiosciences
The Workflow Driven Lab
Sponsored by Sapio Sciences

Many companies have recognized that their internal business units operate as a set of business processes. These business processes are also called workflows. Modern Laboratories are highly suitable to this workflow driven approach. In fact, the lab environments successful operation is predicated on the successful definition and adherence to workflows. It could be said that a modern  laboratory is an advanced process implementing construct. It is important that laboratory management software mirrors the process driven nature of the lab thereby increasing automation, shortening learning curves, improving data quality and increasing lab throughput.

  • The modern laboratory is an advanced workflow implementing construct
  • Laboratory Management Software solutions should fully embrace and mirror this process driven approach
  • Effective information management of workflow processes with a LIMS results in increased automation, reduced training curves, better data quality and increased lab throughput


panasas
Curing Life Sciences Data Management Challenges with Scalable Storage
Sponsored by Panasas

High performance storage systems are a given to meet today’s life sciences R&D computational challenges. But with the explosive growth in data produced by next-gen lab equipment, scalability and long-term data management issues must also be addressed. Read this paper to learn:

  • Why new lab equipment will impact R&D workflows
  • How to avoid the hidden costs of long-term data management
  • What approach you should take to accommodate today’s data while having the flexibility to scale to meet future demands.


Quantum
StorNext 4.0: Technical Product Brief
Sponsored by Quantum

 
Proven in the world’s most data intensive industries, Quantum StorNext is a scalable, high-performance file system which allows data sharing across Linux, Mac, Unix, and Windows operating systems and manages data in enterprise storage environments. In this Technical Brief you'll learn:

  • How a high-performing file system can accelerate your business
  • How to simplify your data management
  • How a tiered storage approach can save you money


Life Science Webcasts & Podcasts

Predict or Perish! Shaping the Practices of Clinical Trials
Decisionview webinarSponsored by:  DecisionView

Predictive Analytics are a key differentiator in running your clinical trials successfully through 2010 and beyond. They will help you to optimize your patient enrollment, reduce your clinical operations costs and minimize your financial liability in the clinical supply chain. In this session, you will:
• Learn what predictive analytics are and what they are not
• Understand why you need predictive analytics to run your clinical trials, and
• Explore how predictive analytics will shape the future of clinical trials

Download Now. 

 



More Podcasts

Job Openings

The University of Washington Department of Genome Sciences is seeking a LINUX SYSTEMS ENGINEERING MANAGER to lead a team in a diverse scientific computing environment that includes multiple HPC systems, petascale storage, and custom application servers. Apply online at UW Hires for req number 61505.  http://www.washington.edu/admin/hr/jobs/

Loading...

For reprints and/or copyright permission, please contact The YGS Group, 3650 West Market Street, York, PA;

(717) 505-9701 ext. 125, or via email to Ashley.Zander@theYGSgroup.com.