The Price of Anarchy on the roads and how to reduce it
We are publishing a new paper in the Proceedings of the IEEE which used minute-by-minute traffic data from the Boston area to estimate the effect on traffic congestion of drivers' selfish route selection as opposed to a more coordinated, socially optimal routing scheme. We found that during certain very congested periods, socially optimal routing can lead to as much as 50% reduction in congestion. This work is in collaboration with my colleague Christos Cassandras and two of our students, Jing Zhang and Sepideh Pourazarm. It was completed while I was on sabbatical at MIT.
A press release was released by MIT Sloan and KPCC, the southern California NPR station, aired a segment and posted a story on this work.
A related story appeared on the web site of the Center for Information and Systems Engineering.
We are grateful to the Boston region Metropolitan Planning Organization and to the City of Boston for providing access to the traffic data that made this work possible.
Developing a New Score: How Machine Learning Improves Risk Prediction
A Medical Device and Diagnostic Industry publication describes efforts in health predictive analytics and refers to our work.
Harvard Business Review Publishes our Opinion Article on Predictive Health Analytics
The Harvard Business Review has published our opinion article describing "How Machine Learning Is Helping Us Predict Heart Disease and Diabetes."
NSF, CISE Look to the Future of Smart Healthcare at Campus Workshop
By Sara Cody
As the National Science Foundation looks to the future of science in smart and connected health, the agency partnered with the Center for Information and Systems Engineering to convene a gathering of principal investigators and other research leaders on the BU campus this month. The interdisciplinary researchers discussed their progress and identified new areas for future research.
“The meeting looked at cutting-edge innovations, from smart analytics to bring about personalized health solutions, to devices and algorithms that close the loop and control important physiological variables, and to ways in which we, as humans, can better interface with technology to improve our health,” said Professor Ioannis Paschalidis (ECE, BME, SE), who spearheaded the event steering committee along with Professor Christos Cassandras (ECE, SE) and Professor William Adams (MED). “It was an honor and a privilege to host this event at Boston University, welcoming many distinguished colleagues, and showcasing the important interdisciplinary work we have been doing in this fascinating arena.”
The three-day program interspersed presentations with breakout sessions in which attendees gathered together in smaller groups to discuss new ideas and presented their findings to the entire group. Presentations covered themes in connected healthcare, big data and analysis, harnessing the power of the Internet of Things to personalize healthcare, and the challenges associated with handling privacy and implementation. The first day of the workshop, titled “Visioning,” hosted a forum of more than 60 research leaders.
“The goal of this workshop is to have brilliant people weigh in about where smart health should go, and the material we gain from that will be pulled together to publish and present to NSF leadership in order to keep moving that needle,” said Wendy Nilsen, director of the NSF’s Smart and Connected Health program. “We are focused on using science to solve problems with societal value and we are calling on this community we built to come together and look to the future.”
Professor Edward Damiano (BME) presented the iLetTM bionic pancreas as an example of a smart and connected health system that “closes the loop” by automating the dosing process to treat type 1 diabetes, relieving patients and their caretakers of the burdensome task. Motivated by his infant son David’s diagnosis, Damiano has spent the last 15 years developing the bionic pancreas. The technology optimizes blood sugar levels by using dosing algorithms to automatically calculate and precisely dispense two hormones every five minutes: insulin when blood sugar levels are high; and glucagon when they are low.
“With this disease data changes every day, minute to minute, person to person. It is a day and night disease that requires round the clock care and a lot of impractical cognitive input and the current tools are failing patients,” said Damiano. “The iLetTMlearns from your ever-changing glucose needs, making 288 decisions every day, which amounts to once every five minutes, and adjusting the medication as subtly or dramatically as the patient requires.”
The Principal Investigator meeting was held on the second day and brought together more than 120 researchers representing more than $150 million NSF investment in smart and connected health. In addition to summarizing the previous day, the meeting featured 84 ignite talks — 90-second research overviews summarizing interesting insights and hopes for the future of smart connected health.
“The Smart and Connected Health Visioning and PI meetings were remarkable for their collaborative focus on the future,” said Nilsen. “Participants, supported by the multidisciplinary environment at BU, envisioned future scientific needs through the lens of fundamental and applied sciences to identify the prime potential areas of research.”
ICRA 2016 Paper is Finalist for Best Paper Award
The paper “Cooperative Multi-Quadrotor Pursuit of an Evader in an Environment with No-Fly Zones”, by Alyssa Pierson, Armin Ataei, Ioannis Paschalidis, and Mac Schwager, which appeared in the Proceedings of the IEEE International Conference on Robotics and Automation (ICRA), May 16-21, 2016, Stockholm, Sweden, was a finalist for the conference Best Paper Award.
A video demonstrating the algorithm in the paper:
Tsinghua University partners with the BU Division of Systems Engineering
In the current spirit of promoting scientific and educational collaborations across departments, campuses, and universities, Boston University has reached out transnationally by signing a significant agreement on Friday, May 6, 2016 with Tsinghua University, Beijing, China for the establishment of a dual degree program. The agreement was signed by Boston University President, Dr. Robert A. Brown and Tsinghua President, Dr. Qiu Yong.
The College of Engineering, in particular, the Division of Systems Engineering, initiated the discussions with Tsinghua, with Dean Kenneth Lutchen of the College of Engineering, Professor Christos Cassandras, Head of the Division of Systems Engineering, and Hua Wang, Associate Head of the Division of Systems Engineering leading negotiations on behalf of Boston University.
“Tsinghua University is one of the premier universities in China with well-established educational and research activities in Systems Engineering. Several members of the Center for Information and Systems Engineering (CISE) and the Division of Systems Engineering, have existing collaborations with Tsinghua faculty members. We expect that this agreement will build on those existing collaborative relationships by further advancing joint graduate degree programs, as well as strengthen research collaborations involving faculty and students,” stated Professor Cassandras.
Designed by the Department of Automation at Tsinghua and the Division of Systems Engineering, the dual degree program will attract exceptional undergraduate students from Tsinghua to the M.S. program in Systems Engineering at Boston University. In some cases, admitted students completing two semesters of course work at BU will return to Tsinghua and complete a final practicum requirement in Beijing. Professor Hua Wang, enthusiastic about the new program, stated that “with this agreement, we not only can enhance our research collaborations with our colleagues at Tsinghua, but we are particularly excited to work with Tsinghua students selected through a rigorous evaluation and admissions process. We have designed a curriculum featuring the best courses and projects to take advantage of the synergistic relationship between the two institutions. This collaboration will add an exciting dimension to the academic programs of both sides.”
A previous collaboration with China was established in October 2014 when BU signed an agreement with Zhejiang University, setting a precedent for a successful international collaboration with a Chinese institution of higher education. That agreement was spearheaded by Professor Ioannis Paschalidis, Director of the Center for Information and Systems Engineering (CISE) and established a framework of cooperation between the College of Engineering at BU through CISE and the Faculty of Information Technology at Zhejiang through its State Key Laboratory of Industrial Control Technology.
Health informatics work wins 3rd place IEEE Computer Society 70th Anniversary Student Challenge
Theodora Brisimi was awarded 3rd prize and the Crowd Sourcing Prize, by the IEEE Computer Society 70th Anniversary Student Challenge, for her project “Healthcare Analytics: Predicting Hospitalizations Based on Electronic Health Records,” which was based on joint work with Prof. Yannis Paschalidis.
Workshop: Control and Observability of Network Dynamics, April 11-15, 2016
John Ballieul was an organizer for the Control and Observability of Network Dynamics workshop at the Mathematical Biosciences Institute at The Ohio State University, Ohio, which brought together many well known people in the control field. Yannis Paschalidis (CISE director) presented a paper at this workshop.
Fundraising for a good cause: BU Academy Robotics
BUA Robots.
Dear friends,
Among all of the opportunities I have had at both BU and my school Boston University Academy, my involvement on the FIRST Robotics Team 246 has meant the most to me. I enjoy the six weeks of building the robot, using the cool machines to cut metal into parts and build them into a incredible machine. And then, the real fun begins with the competitions and the strategic decision of forming alliances with other teams. I believe that robotics and the experiences on the team have taught me so many valuable life lessons and decision making skills. From interacting with members of other teams to being able to make a game changing decisions in a heartbeat, robotics has shaped my life. In addition, it has taught me the crucial skill of time management. Every day after class, I go to the lab for an hour or two, straight to swimming practice, and then home to finish my day. This year as one of the drivers for the team, I look forward to spending even more time with my teammates and I hope we have a great season.
The team has just launched a fundraising campaign this week with a goal to raise $5,000 for competitions, travel, and building supplies for the robot. We only have a month to raise this money, and we are hoping to start out strong! Every gift counts, so I hope you will join me in supporting a team that has helped me develop engineering skills, professional skills, and wonderful friendships. Please check out our fundraising page at https://crowdfunding.bu.edu/project/1484.
For more information about the team, please take a look at our website: http://www.bu.edu/bufirst/!
Thanks so much for your support!
All the best,
Aris Paschalidis
P.S. If you have a moment, would you please share this with anyone else you know who might be interested? I would really appreciate it!
Clinicians and Computer Scientists Come Together to Predict Health Outcomes
Bill Adams and Yannis Paschalidis
Some things in life, like sunrises and sunsets, are predictable. Others, like traffic or the weather, are much harder to predict. Health outcomes tend to fall somewhere in the middle, but Bill Adams, MD, a Boston Medical Center pediatrician, and Yannis Paschalidis, PhD, a Boston University data scientist, are attempting to make more health outcomes predictable with an algorithm that utilizes electronic medical record data.
Their system, which is funded by a five-year grant from the National Science Foundation, utilizes anonymous data from BMC patients, which is stored in a database called I2B2. This data dates back to 2000 and includes diagnoses, procedures, admissions, length of stay, and basic demographic data. Adams had been using this data to study what works and what doesn’t work in terms of health outcomes for urban patients and teamed up with Paschalidis and a team of graduate students to develop and test algorithms that can identify opportunities to alter health outcomes, some of which might be missed by researchers. Currently the team is working on an algorithm to predict whether individual patients with a history of heart disease will be hospitalized within a year. In testing this algorithm, they have been able to predict approximately 80 percent of hospitalizations.
“The health care system is not very efficient,” says Paschalidis. “We spend lots of money on diseases that can be prevented. With an algorithm that can predict re-hospitalization of high-risk patients, doctors can pay more attention to those patients, and potentially prevent the predicted hospitalization. Hospitalization is very expensive, but other health care costs are modest, so predicting re-hospitalization and preventing it is better for both patients in terms of health and hospitals in terms of costs. In fact, the National Institutes of Health found that $30 billion is spent in the U.S. every year on preventable hospitalizations, so we have the opportunity to save huge amounts of money.”
The goal is to have algorithms that will run in the background when providers see patients and alert providers when something in a patient’s record suggests that he or she is at risk of a negative health outcome. It would prompt doctors to intervene during visits and case managers (if applicable) to intervene outside of doctor visits.
“While some risk factors, like smoking, are obvious to doctors, there are some, such as trends in laboratory data, that are harder to see,” says Adams. “The challenge in medicine isn’t to know that someone is high risk, but to know what type of risk they have and how to intervene. Our algorithm is a useful tool to help doctors intervene early before negative outcomes happen, instead of waiting for them to happen and then starting treatment.”
The heart disease algorithm primarily uses outpatient data to make predictions, because most long-term health outcomes are treated in outpatient settings. Currently the algorithm pulls in data from Logician, and STK, the hospital’s registration system, but soon will begin adding information from eMERGE now that the new electronic medical record system is live across the hospital. While the new system won’t change the type of data that the algorithm uses, it will allow the researchers to share their work with people across the country who also use Epic electronic medical records. It will also allow researchers to better integrate inpatient and outpatient data.
The software built on the algorithm is not in use yet, but Adams and Paschalidis expect to finish testing by the end of the year and start running focus group tests with BMC doctors next year. These groups will allow Adams and Paschalidis to refine the type of information their algorithm uncovers and how the data is presented to providers, to create a valuable tool. They also plan to expand the use of the algorithm to include diabetes patients and are in talks with the Department of Surgery to predict re-hospitalization of patients who have undergone surgery – this is an important metric for Medicare quality measures. Eventually the goal is to create an algorithm that can provide recommendations for intervention, which will involve further partnerships between providers and computer scientists.
“This is a cutting-edge approach,” says Adams. “There is general interest across the country in trying to use electronic data to predict health outcomes, but the BMC/BU team is special in that it combines the clinical expertise of the medical campus with expertise in engineering and computer science from BU. In addition, this type of project is not something generally undertaken in safety net hospitals, which makes our algorithm unique. Our goal is to make this data into something meaningful and useful for the direct care of our patients, and while we’re not there yet, I believe we will be soon.”
(The story appeared at the May 15, 2015, Volume 4, Issue 6, Boston Medical Center Brief.)
