Data-Driven Decisions in Healthcare – An Overview of the Opening Workshop

The following is from Ray Falk, from OptInference LLC, who participated in the opening workshop for SAMSI’s Data-Driven Decisions in Healthcare program.

Ray Falk looking at Banafsheh Behzad’s poster as she explains the research she is doing at the Data-Driven Decisions in Healthcare Opening Workshop.

I found the kick-off workshop, Data-Driven Decisions in Healthcare, tightly focused on methodologically tractable projects with ‘shovel-ready’ data sources, primarily in the areas of operational patient, provider, and (material) resource allocation and scheduling and patient-centered (personalized) effectiveness assessment.

Avi Mandelbaum

Avi Mandelbaum of Technion gave a lecture at the opening workshop.

Inference, analysis and control of service systems were developed via extension of existing results and observations from call center management (Avi Mandelbaum), including stabilization of performance under time-varying conditions (Yunan Liu).  Prodigiously comprehensive tracking of patient flows through the ICU (Carri Chan) and the remaining non-intensive departments of a hospital (Jim Dai) were related to specific insights regarding options for intervention (including proportional and absolute threshold effects), both for providers and patients.  An interesting discussion addressed dependence of service times on (new vs. readmitted) patient status (Guodong Pang).

Bob Obenchain

Bob Obenchain at the poster session Monday evening.

Personalized medicine was addressed from several perspectives, including heterogeneous treatment effects (with a heuristic re-sampling based approaches from Bob Obenchain and Sheldon Jacobson), appropriately targeted decision analysis based on high-dimensional modeling from large populations (centered on ROC curves from validation data sequestered from model development), and availability of comprehensive data, as well as methodologies for data acquisition and alignment, inference, and modeling(OMOP) (David Madigan, Patrick Ryan) .  Assessment and prediction from retrospective observational studies and tracking data was addressed via meta-analysis, propensity matching or weighting, and spontaneous event reporting (with no identifiable population at risk) (Alan Menius)

Guidance and policy for the national initiative in patient-centered evidence-based assessment of medical effectiveness was addressed via standards elaborated via PCORI (Constantine Gatsonis, Sally Morton).  Issues and perspectives included:
Value of Information for  prioritization, Efficiency of adaptive experimental design, individually heterogeneous treatment effects, observational vs. prospective randomized trials, data infrastructure (storage of electronic records and ontologies for integrated access), and technology assessment and dissemination, hyper-inclusive access to results for review (beyond standard publications in English).  An auxiliary resource is the Society for Medical Decision Making (Turgay Ayer).

– Ray Falk


SAMSI Renewed for Another Five Years!

SAMSI is happy to announce that the National Science Foundation’s Division of Mathematical Sciences (NSF DMS) has again renewed SAMSI’s five-year grant to 2017.

SAMSI one of eight mathematical institutes that are funded by the NSF DMS, but this is the only one that focuses on statistics and applied mathematics. It was originally founded in 2002 and is now celebrating its tenth anniversary.

The grant is a collaboration between Duke University, North Carolina State University (NCSU), the University of North Carolina at Chapel Hill (UNC) and the National Institute of Statistical Sciences (NISS) along  with the William Kenan Jr. Institute for Engineering, Technology and Science.

Each year, SAMSI holds one to two major programs along with a couple of summer programs that focus on cutting-edge research in statistics and applied mathematics, motivated by various disciplinary sciences. It also hosts several workshops for undergraduate and graduate students, some of which are directly linked to the major programs and giving students the opportunity to meet some of the top researchers in the mathematical sciences.

SAMSI’s 2013-14 programs are Computational Methods in Social Sciences and Low Dimensional Structure in High-Dimensional Systems, and the summer 2013 program is Neuroimaging Data Analysis.

Apply Now for the 2-Day Undergraduate Workshop at SAMSI October 26-27

group of undergraduate students from 2011

Last year’s undergraduate workshop group.

SAMSI is accepting applications for the two-day undergraduate workshop that will focus on Statistical and Computational Methodology for Massive Datasets. The workshop will be held October 26-27 at SAMSI in Research Triangle Park, NC. The program begins at 9:30am on Friday, October 26 and ends at noon on Saturday, October 27.

Applications received by Friday, September 28 will receive full consideration. SAMSI will reimburse appropriate travel expenses, including food and lodging. Participants are urged to arrive on Thursday evening.

The Statistical and Computational Methodology for Massive Datasets program focuses on fundamental methodological questions of statistics, mathematics and computer science posed by massive datasets, with applications to astronomy, high energy physics, and the environment. Serious challenges posed by massive datasets have to do with “scalability” and “data streaming.”

More Impressions from the Computational Advertising Summer Program

Last Friday the Computational Advertising summer program at SAMSI came to an end. The working groups that had met throughout the second week of the program met to talk about the work they had conducted and to talk about potential collaborations for the future.

people listening to lectures the first week

The first week was spent listening to lectures about Computational Advertising.

A couple more people wanted to share their comments about the program, so we are sharing them here:

Zhou Li, Notre Dame University

“I’m just so glad that I’ve come to this workshop. At the beginning, I was not very sure about this program because I didn’t have any clue about computational  advertising. But the workshop did such a good job in introducing this subject. The first 3 days, the lectures given by experts in Computational Advertising provided some important ideas about what this area is all about, and we also got the chance to talk with them in person at a very relaxing atmosphere. As to the following week, it’s all about hands on research experience and group working. I have to say l love the group I worked with. We have people from very different backgrounds and of very different personalities. Actually, it is not only a great chance to learn (D.r Huo is such a knowledgeable scholar in the subject sponsored search bidding,the topic we were working on) but a chance to make friends.
I have to thank Dr. Banks, he is such an awesome  person. We had a great time at his place. Thanks to all the people in SAMSI for organizing the workshop.”

people standing around posters during poster session

A poster session and reception was held the first night to introduce more concepts and give people a chance to socialize.

Qiyi Lu, SUNY Binghampton

“This may be one of the greatest workshops I have attended. The best thing about the program is joining in the working groups.  Our group consists of 8 people, with different backgrounds and skills. I am new to this area. The working group helped me get a deeper understanding of the topics, and the interactions with other participants are a great experience. I spent the best part of my summer here! ”

group sitting at a conference table with laptops

The second week was spent in smaller working groups.

Impressions from the Computational Advertising Summer Program

working group in action at SAMSI

One of three working groups meeting during the second week of the summer program.

We asked several of the participants of the Computational Advertising summer program to give us their impressions of the program. Here are a few of them:

David Banks, Professor of Statistics, Duke University and one of the organizers of the program

“SAMSI summer programs are great.  I was previously involved with an outstanding one on psychometrics, and this new one on computational advertising is even better.  We have three working groups, and each team is writing a research paper.  One group has found that keyword bidding generally conforms to theoretically optimal behavior in a first-price auction, with some interpretable exceptions.  Another group is modifying the regularization analysis that was used to win the Netflix prize to improve a music recommendation system.  And the third group is analyzing co-cluster structure and time dynamics in click-through rates for on-line news articles.

“The best thing about the program is the energy within the working groups.  Each consists of a team of six to eight people, with widely different ages, perspectives, backgrounds, and technical skills. I’m sitting with the bidding behavior group now, and eavesdropping on my colleagues as pairs and triplets of the participants sort out anomalies, compare different visualizations, speculate about causal mechanisms, and debate competitive strategies. There is a real team feeling here, and I don’t get to experience that in my usual academic life.  It is a lot of fun.”

David Banks and Noah Silverman

Noah Silverman, UCLA (left) and David Banks, Duke (right) collaborating in a working group.

Reginald Roberts, Chief Statistician, Rapp

“David was awesome. What a great facilitator! I come from industry and it was intimidating being around so many academics. David made tremendous efforts to make sure our thoughts and opinions were integrated into the various streams of intellectual thought and that we were important piece in research teams in the second week.”

Tuwaner Lamar, Assistant Professor of Mathematics, Morehouse College

“I like the workshop portion of the conference.  This is good because it requires a deeper understanding to the topic.  A month ago I asked the question why this resurgence in this area of statistics?  Because of the research done for the problem I’m working on, with my group, I have the answer.  I, also, like the SAMSI healthy, nutritious unique dishes served at lunch and I value the discussions over lunch.”

Tuwaner Lamar

Reginald Roberts, Rapp

Piaomu Liu, Ph.D. candidate, University of South Carolina

“The two-week long SAMSI workshop experience probably has been the best part of my summer! Cutting-edge research presentations from both academia and the industry gave me, a graduate student in statistics exposure to different research areas. I am definitely continuing to learn more about computational advertising beyond the workshop. Whether you are new to computational advertising like me, or have begun researching in this area, the workshop is devoted to facilitating learning, discussions, and making connections.  David and Karem have the best smiles in the world!:) ”

Chirag Lakhani, Postdoctoral Research Associate, Electrical Engineering, North Carolina State University

“The computational advertising workshop has been a very fun and informative experience.  On the first day I came into the workshop half-asleep and not sure what to expect but I was greeted by a very animated and congenial statistics professor.  He was able to wake me up from my slumber and made me realize this would be a great experience.  It was great to meet so many people from both academia and industry.  I have learned a great deal about the inner workings of people in industry.  The problems we have worked on in the working group have also been very helpful.  It gave me a great opportunity to get my hands dirty with data and also learn great techniques in machine learning.  This may be one of the most informative workshops I have attended.  It is a great model for other workshops.”

Chirag Lakhani in a working group

Chirag Lakhani, NCSU

Yi Jiang, Rapp

“David gave us great experience with a computational advertising workshop that had both theory from academia and application from industry. He made tremendous efforts to arrange the presentations and projects so that we can practice what we just learned right away, particularly with the extra helpful guidance from him. He was awesome!!”

Zainab Jamal, HP

“I had a great experience at the conference and workshop. I found the talks at the conference where a great mix of industry perspectives and the academics perspectives. I especially liked the talks by Mark Handcock and Tian Zheng on social networks, Liang Zhang’s talk on personalization of content and Mike Taddy’s talk on  extracting information from unstructured text data and the talks by Christian Posse(linked in) and Neel Sudarsan (eBay).

“I found the workshop very useful as I learned to wrap my head around large data –  – from loading it to manipulating it to running models on it efficiently. The interactions with other participants was great as I felt one with the ‘geeks’ and learned a lot.

“And last but not least, Prof Banks was warm and helpful and full of great ideas to make us think and I really appreciated that.”

Giri Gopalan, Ph.D. Candidate, Statistics, Harvard University

“It has been a great privilege to attend the 2012 SAMSI Workshop on Computational Advertising. What has been particularly marvelous about the workshop has been the synergy fostered between academia and industry. The speakers come from a wide range of backgrounds including research labs, start-ups, and universities. This confluence of variegated individuals has supplied me with a unique perspective on  both the theory and application of ubiquitous modern topics such as high dimensional statistics, machine learning, and networks. This synergy has also been evident in the working groups. Being able to interact with individuals from academia, research labs, and universities has imparted an educational experience that I cannot imagine receiving anywhere else.”

Xiaoming Huo, Professor, IySE, Georgia Tech

“The talks in the first week were informative. The data sets that are presented on the last Friday are quite interesting. During the working group (2nd week), we seem to get a lot of things done. Overall, it is a good experience: we learned quite a few things; made some friends; and maybe more… ”

group in front of a restaurant

Some folks got together for dinner during the summer program.

Computational Advertising Summer Program

The SAMSI computational advertising summer program is heating up! Last week, the group met at the Radisson RTP and had a great series of lectures from both professors at various universities from around the country to some of the cutting edge research happening at companies like LinkedIn, Yahoo!, Facebook, AT&T and Maxpoint Interactive.

Christian Posse from LinkedIn before speaking at the workshop

Christian Posse from LinkedIn talked to the people attending the computational advertising summer program at SAMSI.

Some of the people who spoke last week have shared their lectures and are available to view on the SAMSI website.

Zainab Jamal from HP presenting her poster

Zainab Jamal from Hewlett-Packard sharing her poster at the Computational Advertising poster session.

Several of the participants of this program will be sharing their experiences with you in the next few days. Stay tuned for more on this subject!

Welcome to SAMSI’s Blog

Welcome to SAMSI Blog, a new blog that will cover events and ideas that are being explored at the Statistical and Applied Mathematical Sciences Institute (SAMSI).

This blog will feature statisticians and applied mathematicians from around the world who are involved with SAMSI programs and workshops. It will have first-hand accounts from some of the workshops, abstracts of some of the lectures, and highlights from some of our events. We hope this blog will be informative and entertaining . You play a role in this blog as well, because the comments and interactions from entries to the blog will be important to keeping the discussion going.

So, stay tuned to see upcoming blog entries and consider following our RSS feed. Any topics you think we should be covering? Send us your ideas!