Previous month:
August 2014
Next month:
October 2014

September 2014

Leon Botstein's quote

I read this quote by Bard College president Leon Botstein about U.S. News in a recent issue of the New Yorker (here is the full article). "It's one of the real black marks on the history of higher education that an entire industry that's supposedly populated by the best minds in the country - theoretical physicists, writers, critics - is bamboozled by a third-rate news magazine." It is interesting, isn't it, that the organizations that come up with rankings aren't foundations or nonprofits, but the magazines that will sell those rankings as special issues?

The New Yorker article itself (a profile of Botstein by Alice Gregory) is a great read. Gregory has a way with words too, just like Botstein, but I'll let you judge for yourselves. (She happens to be a Bard graduate.) The article seems to be available in its full version online, even for non-subscribers. And here is the link to Bard College's website, if you'd like to learn more about it. It seems like a fascinating, innovative institution. Gregory about the students Bard strives to attract: "Rather than being student-body presidents or varsity point guards, they took black-and-white photographs of their friends’ shoes, wrote first chapters of postmodern novels, and played in noise bands... Though sixty-five per cent of Bard’s student body receives financial aid, and twenty-two per cent of this year’s entering class is eligible for Pell Grants, there’s a small but culturally significant population of extremely wealthy kids on campus—the children of media moguls, rock stars, and Hollywood actors." Botstein has chosen to attract public intellectuals - poets, filmmakers, novelists - rather than star PhDs to teach Bard students, an endeavor undoubtedly helped by the relative proximity of Bard College to New York City. Bard College comes across as a remarkable institution, and Botstein as, well, a very complicated individual with very strong opinions that is not without reminding me (because of his leadership style) of NYU President John Sexton as profiled in the New Yorker in 2013 by Rachel Aviv, although no one can beat Botstein's rhetorical flourish and idiosyncrasies. One of a kind, made likable in spite of everything by that quote of Faulkner's Absalom, Absalom! a former faculty member used to describe him ("he had been too successful, you see; his was that solitude of contempt and distrust which success brings to him who gained it because he was strong instead of merely lucky") and Gregory's portrayal of his childhood, which resulted in "an lifelong allegiance to underdogs". Welcome to the club. Maybe that's what it took to make Bard what it is today - while its financial outlook is not as secure as one would like, as explained in the article, it does seem like a unique, special place for tomorrow's public intellectuals, taught by today's.


Robust Investment Management with Uncertainty in Fund Managers' Asset Allocation

I am happy to report that my recently graduated PhD student Yang Dong (now Dr. Yang Dong!), who just joined JP Morgan in New York City as a senior quantitative analyst, has been named a finalist in the INFORMS Financial Services Section paper competition for work based on our paper, "Robust investment management with uncertainty in fund managers' asset allocation." Yang truly did outstanding work on that paper and I am thrilled to see her efforts rewarded at the national level.

Abstract: "We consider a problem where an investment manager must allocate an available budget among a set of fund managers, whose asset allocations are not precisely known to the investment manager. In this paper, we propose a robust framework that takes into account the uncertainty stemming from the fund managers' allocation, as well as the more traditional uncertainty due to uncertain asset returns, in the context of manager selection and portfolio management. We assume that only bounds on the fund managers' holdings (expressed as fractions of the portfolio) are available, and fractions must sum to 1 for each fund manager. We define worst-case risk as the largest variance attainable by the investment manager's portfolio over that uncertainty set. We propose two exact approaches (of different complexity) and a heuristic one to solve the problem efficiently. Numerical experiments suggest that our robust model provides better protection against risk than the nominal model when the fund managers' allocations are not known precisely."

Full paper: here.

Congratulations to Yang on closing her time at Lehigh in such a distinguished manner and starting a new chapter in her life and career! 


Using Big Data To Transform Healthcare

7.cover-2The July 2014 issue of Health Affairs is on "Using Big Data To Transform Care." Here are some papers that caught my attention.

Big Data in Health Care: Using Analytics To Identify and Manage High-Risk and High-Cost Patients, by D. Bates, S. Saria, L. Ohno-Machado, A. Shah and G. Escobar. (Paper) This article presents, at a high level, six use cases "where some of the clearest opportunities exist to reduce costs through the use of big data: high-cost patients, readmissions, triage, decompensation (when a patient's condition worsens), adverse events, and treatment optimization for diseases affecting multiple organ systems."

Optum Labs: Building a Novel Node in the Learning Health Care System, by P. Wallace, N. Shah, T. Dennen, P. Bleicher and W. Crown. (Paper) This paper is about Optum Labs, a joint entity created in early 2013 between the Mayo Clinic and Optum, an organization part of UnitedHealth Group. Partners now include AARP, AMGA (the American Medical Group Association), Boston Scientific, Boston University School of Public Health, Lehigh Valley Health Network, Mayo Clinic, Optum, Pfizer, Rensselaer, Tufts Medical Center and the University of Minnesota School of Nursing.

Here are examples of research findings:

  • There are a number of seemingly equivalent choices for second-line medication treatment for uncomplicated type 2 diabetes. (Second-line medication is medication you give if the patient doesn't respond as expected to first-choice or first-line medication.) An analysis of the Optum data, however, showed that a specific drug led to less cost and a longer interval until insulin was required. This has the potential to change guidelines used by care providers.
  • Another Optum study showed the number of total knee replacement surgeries has increased steadily for all age groups, as has the prevalence of diabetes and obesity among patients undergoing these surgeries. Hence, it seems important in future studies to differentiate patients with multiple comorbidities.
  • Another Optum study showed that "the statistical linkage of clinical information from laboratory test results to claims data reduced bias in treatment effects estimates by 24 percent for all ambulatory visits and by 79 percent for visits related to Hepatitis C, relative to the use of claims data alone."

A key overall challenge (and priority) remains to "enable clinicians to connect findings from big-data analyses directly to the care of an individual patient".

Leveraging the Big-Data Revolution: CMS is Expanding Capabilities to Spur Health System Transformation, by N. Brennan, A. Oelschlaeger, C. Cox and Marilyn Tavenner. (Paper) CMS has collected claims, assessments and surveys for many years, and has long made them available to researchers. However, data was previously shipped to researchers in the form of encrypted hard drives, at a rather significant cost for the researchers. In late 2013, the agency launched the CMS Virtual Research Data Center. Researchers can now access the data from their own computers but they "may download only aggregated data sets and analytic results." This is obviously expected to decrease the cost to the researchers (no more encrypted hard drives arrivign through the mail!) Innovations have also been made in the qualified entity program to improve provider quality reporting and in sharing data with providers and states. Further, the Blue Button program "allows patients to easily access their own health information in electronic form."

Early Experiences with Big Data at an Academic Medical Center, by J. Halamka. (Paper) This describes the experience of Beth Israel Deaconess Medical Center (BIDMC) in the Boston area in adopting electronic applications. While data storage now amounts to 3 petabytes (1 PB = 10^(15) bytes) and grows at a rate of 25% a year, the main issue has shifted to the transformation of this raw data into usable information.

In order to gain insights, BIDMC created "Clinical Query, a web-based tool that allows for analysis and visualization of the clinical data collected by BIDMC." The author explains: "The principle behind Clinical Query is that investigators will want to ask questions before conducting research that will help them understand the potential statistical power of a clinical trial or the availability of data for clinical research." The resulting web-based query tool uses Boolean (and/or) expressions and open-source code from the Harvard's Integrating Information from Bench to Bedside project. The author identifies the potential issues related to Big Data: (1) data quality, (2) variations in data collection over time, (3) inconsistent use of medical terminology, (4) patient privacy concerns, (5) need for experts to meaningfully analyze data.

This issue of Health Affairs was very interesting. I do wish that an InnoCentive-type competition where de-identified claims and diagnostics data would be posted online (perhaps using the CMS virtual system with its built-in protections) for all interested parties to study and analyze. When the data is only accessible to some groups of researchers, opportunities for insights are lost because other teams of researchers may have approached the problem a different way or tested a different hypothesis. Further, I also think that the field is ill-served by the current lack of mathematical models on the topic. Health Affairs never presents mathematical models to begin with, but when it comes to analytics, there comes a point where the buzzwords have to stop and the analytical insights have to begin - and those analytical insights have to extend beyond the data-mining insights that are already being derived. (Data-mining is a good first step, but operations research can do so much more.) Given the tremendous progress that has been made in a few short years, though, the state of analytics applied to healthcare treatments is sure to become quite impressive indeed.


Fall 2006's first IE316 handout

And (following up on my previous post on IE 316 material), here is the first handout I used for my elective course IE 316: Operations Research Models and Applications back in Fall 2006. (I made some changes to the handouts over the years but overall they remained very similar to each other, up until last year.)

As I mentioned in my earlier post, for that part of the course I used the linear optimization chapter in the Data, Models and Decisions textbook by D.Bertsimas and R.Freund. My motivation was that I felt that IE undergraduates should at least know what MBA students are taught in operations research, and then build on that. (So we also covered the integer and nonlinear optimization chapters of the book, and I also had them learn AMPL although the DMD textbook only uses Excel Solver.) I also posted software files - Excel and AMPL - on the course webpage, which at the time was on Blackboard.

What I liked most about my handout -- besides the great examples from the DMD textbook -- was that I left blanks for students to fill in their answers. It seems silly, but the students appeared to like that so that they could be more engaged in the lecture by writing the answers as we went along. (This was also the time where I didn't post lecture notes so they either had to write the answers themselves or ask a friend in the class for their notes.)

Now, I wasn't always optimal in figuring out the proper size of the blanks to leave, and I had an unfortunate tendency of repeating some question numbers, but overall I was happy with what I did for that course that semester.

If anyone cares to get a good introduction to linear optimization applied to business problems, I recommend Chapter 7 in the DMD textbook. 


Last year's first IE316 handout: e-book

Last year when I taught IE316: Operations Research Models and Applications, I tried to innovate and posted the handout in e-book formats: .epub and .azw3 (.azw3 is a Kindle format and .epub is a format readable by other e-books). It contains the questions we solved in class for the first part of the first topic. Here it is for the world to admire:

Some of the tables may seem too big for the page but you just have to adjust the size of the Kindle window and/or the number of words on a page to make the entire rows of some tables fit. I have not looked at the handout again and, since last year was the first year I used that handout, it is very possible I left some typos. Before the fall of 2013, I used a variety of sources, with the beginning of the course drawing heavily from the chapter on linear optimization in the Data, Models and Decisions textbook by D. Bertsimas and R. Freund (MIT MBA students will know what I am talking about).

Obscure comment if anyone actually plans to read it: In that earlier version, the example with 2 decision variables, with the wrenches and the pliers from the DMD textbook, was a lot more intuitive than the one I made for the write-up for last year by simplifying a problem with 4 decision variables. In hindsight, I would probably put back a simple problem with 2 variables in the write-up (e-book) instead of simplifying a problem with 4 decision variables because a lot of intuition was lost when trying to explain what happens in sensitivity analysis when the right-hand side of the constraint increases by 1. The e-book doesn't have the solutions - those are in my handwritten notes.

Anyway, I post this online because I think e-books are the future of higher education and other professors might be interested in producing e-books of their own handouts. So, the $1,000,000 question: how did I do it? I used a software called Calibre. You can download it for free online. It takes the .docx file and turns it into the e-book format of your choice. Can't get any easier than this. I haven't tried using the .epub files, but double-clicking on the .azw3 file automatically opens it using the Kindle for Mac program that I downloaded for free from the Amazon website. Hopefully it also works easily on other devices. Enjoy!