Member Wiki

Dear Colleague:

I am pleased to announce that I am participating as a presenter at the Tenth Annual Bio-IT World Conference & Expo 2011 taking place April 12-14, 2011 in Boston, MA. I will be a part of the “(W9) Utilization of EHRs/EMRs to Further Drug and Disease Related Research” pre-conference workshop and discussions and I think you would enjoy this workshop and set of topics. It’s a great gathering every year and I encourage you to attend the conference, specifically join the discussion at this EHR workshop.

CHI is offering AMIA colleagues discounted conference registrations to attend:

$100 off a commercial registration    

$50 off an academic/government registration

Register on-line and mention Priority Keycode “WKSCLN” to receive this discount or call CHI +1 781-972-5400.*

Please take a look at the agendas at: www.bio-itworldexpo.com (expo) & www.bio-itworldexpo.com/Workshop-EMR (workshop). I hope to see you at the event!

Sincerely,

Zhaohui (John) Cai

Journal of Cognitive Engineering and Decision Making

Call for Papers for Special Issue on “Computational Cognitive Modeling for System Design”

Overview

The design or redesign of systems can be difficult for many reasons, including inherent complexities in domain knowledge, processes, infrastructure, and environment. For some such application areas, traditional usability testing is typically not sufficient - additional analytic techniques must be brought to design and development. Healthcare is one domain where comprehensive or holistic system design can be extremely challenging due to factors such as a fragmented and insular infrastructure, distributed decision making, complex and dynamic knowledge bases, tight coupling between subsystems, and a widely varied user base. Realistic usability testing in healthcare is also constrained by patient safety, privacy, and the availability of users. Cognitive modeling is a tool that can augment traditional design techniques and mitigate many of the challenges posed by inherent system complexities.

The aim of cognitive modeling is both to understand performance factors in existing systems and to predict performance requirements for systems still under design. For the development of complex systems, cognitive modeling can provide designers with both qualitative and quantitative insights into critical human factors throughout the development process, but particularly in early design. Even when realistic system usage scenarios are difficult to capture (let alone replicate), cognitive modeling can help to identify critical design flaws and error modes. 

Computational cognitive models that embody system usage in an executable software application have the additional benefit that multiple usage scenarios can be tested and system functionality can be more easily explored. This allows designers to better understand global implications for local design changes and to consider system suitability for users overall work needs beyond that which could be modeled from a single task. Many computational cognitive modeling environments embody some form of psychological architecture that imposes realistic constraints on resulting models. 

Despite much progress in the area of computational cognitive modeling, many challenges remain. In the design of healthcare systems, for example, design decisions often require tradeoffs between multiple competing priorities such as efficiency, learnability, user acceptance, information security, patient privacy, error tolerance, and legal obligations. Yet, any of these metrics can be overruled by the priority for patient safety. Computational cognitive modeling holds the potential to empower designers to better understand such complex systems and their underlying constraints, and to make principled, informed design decisions that will result in more usable systems that better meet the needs of all stakeholders. 

Objectives

The objective of this special issue of the Journal of Cognitive Engineering and Decision Making (JCEDM) is to explore the nexus between the Cognitive Engineering and Decision Making, Human Performance Modeling, and Health Care communities within Human Factors. We are interested in papers on basic or applied research of computational cognitive modeling tools, techniques, and methodologies. While work focusing on healthcare domains/applications is highly encouraged, all studies involving a computational cognitive modeling component are welcome for submission. Topics of interest within the scope of this special issue include (but are not limited to):

1.        Overviews or surveys of computational cognitive modeling within health care.

2.        Factors in system design that motivate the need for or benefit of computational cognitive modeling.

3.        Translating modeling results into design knowledge.

4.        Use of computational cognitive modeling for error-tolerant design.

5.        Tools for modeling or integrating target system devices with cognitive models.

6.        Research or application of normative or descriptive, veridical or conceptual, models that support system design.

7.        Novel uses of computational cognitive modeling throughout the development process.

8.        Computational models that focus on information content and structure, as it informs system design.

9.        The integration of cognitive modeling within a broader development context.

10.     Meta-modeling techniques for integrating complementary modeling approaches. 

11.     Techniques for verification and validation of computational cognitive models.

This body of work is expected to represent a broad view of the state-of-the-art in computational cognitive modeling as it relates to health care, health information technology, and related domains. This will include tools for application of computational cognitive models, architectures for modeling cognition and human performance, barriers and techniques for applying computational cognitive modeling to health care, research needs, and future directions.

Schedule for Submissions

Manuscript Submission Deadline: December 17, 2010

Acceptance Notification: March 15, 2011

Final Manuscript Due: June 15, 2011

Publication: To be determined

Formatting and Submission Instructions

Authors must follow the JCEDM guidelines regarding manuscript preparation. Detailed instructions can be viewed at: http://www.hfes.org/web/PubPages/JCEDMauthorinfo.pdf. In general, authors should use the format prescribed in the APA Publication Manual ( 6^th edition). Manuscripts should be submitted electronically via http://mc.manuscriptcentral.com/jcedm. 

Special Issue Guest Editor 

Scott D. Wood, Ph.D.

VA National Center for Patient Safety

scottdwood@acm.org

Hi,

I am a practicing psychiatrist in Northern Virginia.  I would like to know about training/educational opportunities in the field of medical informatics.  I would like to continue full-time clinical work while getting training, so I am looking for online medical informatics programs, or part-time, intensive or weekend type programs.  However, I would like to make sure these types of training programs are respected credentials in the field.  I did a search and the Northwetern online masters of science in medical informatics seemed as though it could meet my needs. 

I would appreciate some mentorship on good ways to train and get education in the field of medical informatics, and also ways I could start working in this field.  Thanks.

Richard Kim, MD

I am attempting  to compile a comparison matrix of the top EMR vendors and the pertinent data regarding their products. (IE Cerner, Epic, Eclipsys)

 I am doing this for the Clinical Decision Support vendors as well. (IE Zynx,etc)

If you have any data or if this has been created previously, I would be grateful for the information.  Once compiled I will be happy to share if anyone is interested.

Thank you in advance for any information you can send.

Dear Colleagues,

May be you are interested in RODES (Reversing Ordinary Differential Equations Systems) - the class of algorithms I developed to automate modeling high-throughput time course data, with ordinary differential equations systems; they are based on computational intelligence - genetic programming and neural network control. Please find bellow the abstract of a book chapter and the link to full access:

http://sciyo.com/articles/show/title/toward-personalized-therapy-using-artificial-intelligence-tools-to-understand-and-control-drug-gene-

Comments are welcomed.

Toward Personalized Therapy Using Artificial Intelligence Tools to Understand and Control Drug Gene Networks

Alexandru G. Floares

SAIA - Solutions of Artificial Intelligence Applications;

IOCN - Oncological Institute Cluj-Napoca   

Romania

The real implementation of individualized therapy and gene therapy of multigene disorders are important goals of modern personalized medicine. A rational foundation for this requires knowing which genes are expressed, when, where, and to what extent. The regulation of gene expression is achieved through complex regulatory systems - gene regulatory networks or simply gene networks - which are networks of interactions among DNA, RNA, proteins, and small molecules. Not only a key ingredient but a whole dimension is missing from this view. A large variety of external molecular species interfere with gene networks, but we will focus only on drugs, drug discovery being one of the important routes to personalized medicine. A more general concept of drug gene regulatory networks or simply drug gene networks is introduced together with some mathematically definitions. Besides the high-throughput experimental approaches, allowing to simultaneously monitor thousands of genes or other molecular species, mathematical modeling is essential for understanding and controlling gene networks by drugs or gene replacements. Various formalisms, such as Bayesian networks, Boolean networks, differential equation models, qualitative differential equations, stochastic equations, and rule-based systems, have been used. The ordinary differential equations approach tries to elucidate a deeper understanding of the exact nature of the regulatory circuits and their regulation mechanisms, but is also difficult. There is a need for algorithms to automatically infer such models from high-throughput time-series data, and artificial intelligence is better suited than conventional modeling. We proposed a reverse engineering algorithm for drug gene networks, based on artificial intelligence methods: neural networks for identification and control, and genetic programming for symbolic regression. It takes as inputs high-throughput (e.g., microarray) time-series data and automatically infer an accurate ordinary differential equations model, revealing the networks structure and parameter and giving insights into the molecular mechanisms involved. RODES, from reversing ordinary differential equations systems, decouples the systems of differential equations, reducing the problem to that of revere engineering individual algebraic equations. Usually, due to various experimental constraints, essential information is missing from data, and even the most powerful artificial intelligence techniques are not creating information but just extracting it from data. In the present context, not all variables or time-series are simultaneously measured, as it is required to reconstruct the drug gene networks, as systems of ordinary differential equations. One of the unique features of RODES is its ability to deal with the common but challenging situations of information missing from data. Thinking in a systemic way one can conjecture that, due to the interactions in these networks, information must be implicitly present in the data. Most if not all data mining techniques are dealing exclusively with explicit information extraction from data. Therefore we used some ideas from control theory, choosing a simple but powerful technique, feedback linearization. To automate the algorithm the neural networks counterpart of the conventional method was used. Applied to drug gene networks this algorithm enable and automate the  reconstruction of the time-series of the transcription factors, microRNA, or drug related compounds which are usually missing in microarray experiments. RODES is also able to incorporate common a priori knowledge. To our knowledge, this is the first realistic reverse engineering algorithm, based on genetic programming and neural networks, applicable to large gene networks.

Alexandru Floares, MD, PhD

Head of 
Artificial Intelligence Department 
Cancer Institute Cluj-Napoca
400015, Str. Republicii, Nr. 34-36, 
Cluj-Napoca, Romania
Email: alexandru.floares@iocn.ro

President of 
SAIA Group
400310 Str. Al. Vlahuta, Bl. Lama C, Ap. 45, 
Cluj-Napoca, Romania
Email: alexandru.floares@saia.ro

What happened to MDConsult? That was one of the best member benefits in my opinion.

Cecil Lynch