August 11, 2016
3:00PM
4:00PM
EDT
Registration
Fee:
Free for AMIA members and students of Academic Forum member institutions; Others: $50
Presenters:
David L. Masica, PhD
A novel approach for selecting combination clinical markers of pathology applied to a large retrospective cohort of surgically resected pancreatic cysts.
David Masica will discuss this month's JAMIA Journal Club selection:
Masica DL. Dal Molin M. Wolfgang CL, et al. A novel approach for selecting combination clinical markers of pathology applied to a large retrospective cohort of surgically resected pancreatic cysts. J Am Med Inform Assoc. 2016 Jun 21. pii: ocw069. doi: 10.1093/jamia/ocw069. [Epub ahead of print]
Presenter
David L. Masica, PhD
Assistant Research Professor
Department of Biomedical Engineering and the Institute for Computational Medicine
The Johns Hopkins University
Baltimore, MD
Dr. Masica develops informatics- and statistics-based algorithms for classifying genetic variation and for deriving diagnostic biomarkers. In particular, his work aims to account for the clinical, genetic, and environmental factors that influence health and disease, because considering these factors independently often results in incomplete disease models.
Format
40-minute discussion between the authors and the JAMIA Student Editorial Board moderators including salient features of the published study and its potential impact on practice.
20-minute discussion of questions submitted by listeners via the webinar tools.
Interactive/Evaluations
Follow @AMIAinformatics and #JAMIAJC for Journal Club information.
Participants also receive short feedback surveys to evaluate the JAMIA JC webinar.
Managers
JAMIA Journal Club managers are JAMIA Student Editorial Board members:
Mary Regina Boland, MA, Department of Biomedical Informatics, Columbia University
Matthew K. Breitenstein, PhD, Department of Health Sciences Research, Mayo Clinic
Citation
The PubMed citation for the paper under discussion is:
Masica DL. Dal Molin M. Wolfgang CL, et al. A novel approach for selecting combination clinical markers of pathology applied to a large retrospective cohort of surgically resected pancreatic cysts. J Am Med Inform Assoc. 2016 Jun 21. pii: ocw069. doi: 10.1093/jamia/ocw069. [Epub ahead of print]
Fee Statement
Students who are not AMIA members, but whose academic institutions are members of the Academic Forum, are eligible for a complimentary JAMIA Journal Club registration. Please contact Susanne Arnold at susanne@amia.org for the discount code. In the email, please include: full name, Academic Department, and the primary Academic Forum representative of that Academic Department. Note that AMIA Student memberships are $45, which allow access to JAMIA, all JAMIA Journal Clubs, and other webinars of interest to the biomedical informatics community.
Statement of Purpose
When designed properly, composite markers, as opposed to single-parameter markers, increase statistical power relative to the individual features they comprise and improve important diagnostic metrics such as sensitivity and specificity. However, the large possible number of ways to combine individual parameters (“combinatorics”) can lead to false inferences of association and hamper optimal analysis of data.
The Multivariate Organization of Combinatorial Alterations (MOCA) algorithm is a bioinformatics approach for identifying individual and composite genetic markers of phenotype. The algorithm can rapidly test millions of combinations of markers while conservatively controlling the false discovery rate and selecting the most predictive and recurrent feature combinations from cross-validation testing. MOCA has previously been used to identify genes important in glioblastoma progression and to predict response to anticancer therapeutics.
The present study expanded MOCA’s utility to handle diverse datatypes, and identified combinatorial clinical markers for pancreatic cyst classification that had improved performance relative to the individual features they comprise. In principle, MOCA can be applied to any dataset comprising binary, categorical, and continuous-valued parameters, and could complement traditional and ad hoc marker-selection approaches in many contexts and clinical settings
Target Audience
The target audience for this activity is professionals and students interested in biomedical and health informatics.
Learning Objective
After this live activity, the participant should be better able to:
Consider strategies for deriving composite markers that achieve desired diagnostic utility. For instance, individual parameters that indicate a disease is present and those that indicate a disease is absent must be combined if one wishes to derive combinatorial markers that simultaneously optimize sensitivity and specificity.
Consider common pitfalls in the design of combinatorial markers, which can ultimately result in markers that do not translate/validate. As an example, selecting combinatorial markers can introduce unique multiple-testing problems, compared with traditional single-parameter markers.
Faculty
David L. Masica, PhD
Assistant Research Professor
Department of Biomedical Engineering and the Institute for Computational Medicine
The Johns Hopkins University
Baltimore, MD
Accreditation Statement
The American Medical Informatics Association is accredited by the Accreditation Council for Continuing Medical Education to provide continuing medical education for physicians.
Credit Designation Statement
The American Medical Informatics Association designates this live activity for a maximum of 1 AMA PRA Category 1 Credit(s). Physicians should claim only the credit commensurate with the extent of their participation in the activity.
Criteria for Successful Completion
Completion of this live activity is demonstrated by:
Viewing the live webinar
Optional submission of questions via webinar feature; option to follow @AMIAinformatics and tweet via #JAMIAJC
Completion of the evaluation survey at https://www.surveymonkey.com/r/JJC_Aug_2016 and
Verification of attendance through the participant's electronic report through the individual login at www.amia.org.
The physician participant will be able to generate a CME certificate through the AMIA automated system.
For a certificate of completion, contact Pesha@amia.org.
Commercial Support
No commercial support was received for this activity.
Disclosure Policy
As a provider accredited by the ACCME, AMIA requires that everyone who is in a position to control the content of an educational activity disclose all relevant financial relationships with any commercial interest for 12 months prior to the educational activity.
The ACCME considers relationships of the person involved in the CME activity to include financial relationships of a spouse or partner.
Faculty and planners who refuse to disclose relevant financial relationships will be disqualified from participating in the CME activity. For an individual with no relevant financial relationship(s), the participants must be informed that no conflicts of interest or financial relationship(s) exist.
AMIA uses a number of methods to resolve potential conflicts of interest, including: limiting content of the presentation to that which has been reviewed by one or more peer reviewers; ensuring that all scientific research referred to conforms to generally accepted standards of experimental design, data collection, and analysis; undertaking review of the educational activity by a content reviewer to evaluate for potential bias, balance in presentation, evidence-based content or other indicators of integrity, and absence of bias; monitoring the educational activity to evaluate for commercial bias in the presentation; and/or reviewing participant feedback to evaluate for commercial bias in the activity.
Disclosures for this Activity
These faculty, planners, and staff who are in a position to control the content of this activity disclose that they and their life partners have no relevant financial relationships with commercial interests:
Faculty: David L. Masica, PhD
JAMIA Journal Club planners: Mary Regina Boland, Matthew Breitenstein
AMIA staff: Susanne Arnold, Pesha Rubinstein
JAMIA Journal Club planner Michael Chiang discloses the following:
Received Grant/Research support from the National Institutes of Health
Is an unpaid member of the Scientific Advisory Board of Clarity Medical Systems
Instructions for Claiming CME/CE Credit
CME site (MyAMIA) works best with IE 8 or above version, Chrome, Safari, and Firefox.
Login to the AMIA site
Go to “My Events" under Membership/Activities
Click “Apply for Credits" link for meeting or event you attended.
Follow the instructions on the Credit Registration page.
Physicians: To print out your certificate, go to "My CME/CE Credits" under Membership/Activities.
Other attendees: if you require a certificate of participation, please contact pesha@amia.org
Contact Info
For questions about content or CE, email pesha@amia.org.