Kira Seiger

  • Student

Submitted

Partners Healthcare and Machine Learning: Building Efficiencies in Diagnostics and Data Interpretation
Kira Seiger
Posted on November 13, 2018 at 7:16 pm
How can hospitals better utilize patient data by applying machine learning technologies to augment diagnosis and clinical decision making? Partners Healthcare has launched the Clinical Center for Data Science to lead the charge.

Activity Feed

On November 15, 2018, Kira Seiger commented on Open for Business: Harnessing Open Innovation at the Massachusetts Bay Transportation Authority :

I love the idea of the MBTA crowdsourcing ideas from the public, who often view public transportation as more stagnant than innovative. Not only can this help the MBTA identify creative solutions from others in the transportation space and the (too few) transportation enthusiasts not associated with for-profit entities, but it can also help change the public perception of the MBTA. Open innovation shows that the MBTA is aware that there are logistical problems that need to be improved, demonstrates that they value the people they serve, and exemplifies a commitment to new ideas and innovation.

In response to the fact that the MBTA is limited in its resources and has difficulty reviewing all of the evaluations, I wonder if they could also crowdsource responses to the different ideas rather than just crowdsource ideas themselves. Individuals could upvote ideas that resonate with them, thereby creating a triaged list of proposals that align with the needs of the community. In addition to providing the MBTA management with an already prioritized order of evaluations to review, this could also help solve the issue of the comparatively low engagement of individuals who utilize public transportation vs. for-profit entities.

On November 15, 2018, Kira Seiger commented on Nike’s Stance on 3D Printing: Just Do It :

I see 3D printing as being beneficial to Nike from a marketing perspective, especially if they can capitalize on first-mover advantage! Consumers have traditionally valued Nike as an innovator in shoe technologies that improve performance, so people will have significant reason to believe that Nike’s use of 3D printing offers a higher performance, lighter shoe. Given the survey results you cited and increasing buzz about 3D printing, I imagine that this will be a huge market for Nike. (I want to buy a pair!)

I do worry about their ability to scale given the controversy about whether 3D printing is truly prepared for mass production. Typically, 3D printing is employed when complex processes cannot be completed successfully or quickly enough otherwise, which is not the case for Nike shoes. I therefore wonder if Nike will be able to appropriately lower their costs associated with 3D printing to make mass production sustainable.

On November 15, 2018, Kira Seiger commented on Can Organovo Bio-print a Human Organ Before Money Runs Out? :

Because of the limited number of available livers for transplantation, organs are allocated to individuals based on severity of illness. During the month I spent working with a transplant surgery team, we would use MELD (model for end stage liver disease) scores to help determine patients’ eligibility for transplant and the severity of their disease. Watching the MELD scores of patients creep up as they waited desperately for a liver to be available for transplantation was heartbreaking. Providers may be fairly certain that some patients will require a transplant in the future but won’t be able to add them to the organ list based on the early stage of their disease because of the limited availability of livers.

I am intrigued by Organovo’s goal of bio-printing implantable tissue to decrease the likelihood of further decompensation for these patients and decrease the dependency on available livers for transplantation. Ideally, this could help patients avoid liver transplants altogether, thereby avoiding the significant risks associated with surgery, including bleeding and rejection. It could also allow for earlier intervention that could lead to improved quality of life and decreased morbidity, as well as decreased costs for the healthcare system.

With regards to the question about vascularization, the broader extracellular environment is extremely important to ensuring that cells function appropriately and could be a limiting factor in Organovo’s success. For those interested in an interesting approach to this problem, Dr. Harold Ott, MD at Massachusetts General Hospital is researching the use of organ scaffolds. The goal is to use a process called perfusion decellularization to remove damaged cells from an organ while preserving its extracellular matrix, which is the architectural environment that helps cells function properly. These organ scaffolds can then be repopulated with regenerated functional cells.

See below for a video on this unique approach:
https://vimeo.com/119468303

More about the Ott Lab:
http://ottlab.mgh.harvard.edu/?page_id=2

Academic paper on decellularized scaffolds:
https://www.ncbi.nlm.nih.gov/pmc/articles/PMC4568185/

User deleted this comment on November 15, 2018
On November 15, 2018, Kira Seiger commented on Can Organovo Bio-print a Human Organ Before Money Runs Out? :

Because of the limited number of available livers for transplantation, organs are allocated to individuals based on severity of illness. During the month I spent working with a transplant surgery team, we would use MELD (model for end stage liver disease) scores to help determine patients’ eligibility for transplant and the severity of their disease. Watching the MELD scores of patients creep up as they waited desperately for a liver to be available for transplantation was heartbreaking. Providers may be fairly certain that some patients will require a transplant in the future but won’t be able to add them to the organ list based on the early stage of their disease because of the limited availability of livers.

I am intrigued by Organovo’s goal of bio-printing implantable tissue to decrease the likelihood of further decompensation for these patients. Ideally, this could help patients avoid liver transplants altogether, thereby avoiding the significant risks associated with surgery, including bleeding and rejection.

With regards to the question about vascularization, the broader extracellular environment is extremely important to ensuring that cells function appropriately and could be a limiting factor in Organovo’s success. For those interested in an interesting approach to this problem, Dr. Harold Ott, MD at Massachusetts General Hospital is researching the use of organ scaffolds. The goal is to use a process called perfusion decellularization to remove damaged cells from an organ while preserving its extracellular matrix, which is the architectural environment that helps cells function properly. These organ scaffolds can then be repopulated with regenerated functional cells.

See below for a video on this unique approach:
https://vimeo.com/119468303

More about the Ott Lab:
http://ottlab.mgh.harvard.edu/?page_id=2

Academic paper on decellularized scaffolds:
https://www.ncbi.nlm.nih.gov/pmc/articles/PMC4568185/

On November 15, 2018, Kira Seiger commented on The government wants you…to hack it? :

I have always felt the government should consider more ways to use open innovation to crowdsource ideas and talent across a variety of sectors. This strategy offers a means to increase, encourage, and capitalize on civic engagement, allows the government to include constituents in an effective way, and respond to their ideas and beliefs to better serve the people at large.

In the case of federal cybersecurity, open innovation is a brilliant way to engage top programming talent. Programmers are enticed by the growing number of large technology firms, and as the industry continues to boom, the government will increasingly struggle to employ top talent. Open innovation offers a way for the government to access engineers and capitalize on the creativity and skills of its constituents.

I agree that there is a unique risk in providing transparency with regards to federal cybersecurity systems, and that transparency could indeed be counterproductive to the government’s mission of cyber protection. The government must consider how to encourage engagement and collaboration among participating programmers while maintaining control and being judicious about which information it exposes to whom.

User deleted this comment on November 15, 2018
On November 15, 2018, Kira Seiger commented on The government wants you…to hack it? :

I have always felt the government should consider more ways to use open innovation to crowdsource ideas and talent across a variety of sectors. This strategy offers a means to increase, encourage, and capitalize on civic engagement, allows the government to include constituents in an effective way, and respond to their ideas and beliefs to better serve the people at large.

In the case of federal cybersecurity, open innovation is a brilliant way to engage top programming talent. Programmers are enticed by the growing number of large technology firms, and as the industry continues to boom, the government will increasingly struggle to employ top talent. Open innovation offers a way for the government to access engineers and capitalize on the creativity and skills of its constituents.

I agree that there is a unique risk in providing transparency into federal approaches to preventing cyberattacks and that transparency could indeed be counterproductive to the government’s mission. The government must consider how to encourage engagement and collaboration among participating programmers while maintaining control and being judicious about which information to hide or release.

On November 15, 2018, Kira Seiger commented on Predictive Policing: Promoting Peace or Perpetuating Prejudice? :

This technology poses a huge risk for racial profiling and can exacerbate mistrust in communities. It could have profoundly damaging psychological effects and possibly physical safety risks for those who are inappropriately targeted based on their characteristics. If we want to be proactive about ending crime, we need to invest in schools, rehabilitation programs, and social services. To me, the problem is less about identifying individuals struggling with mental illness, drug addiction, and poverty, and way more about the lack of resources available to help these individuals. If you enter any hospital or emergency department for example, you’ll be able to identify individuals struggling with these issues, and you’ll also find providers and social workers with minimal resources with which to create lasting change.

I would suggest that those implementing predictive policing technologies think critically about the type and magnitude of crime they are trying to prevent using this technology. How they implement this technology to identify human trafficking and search for trafficking victims, for example, may be very different from how they would deploy the technology in an attempt to prevent other crimes.

For those interested in learning more about building trust between police and communities, My90 is a start-up that amplifies voices in the community by allowing people to anonymously share feedback about their experience with law enforcement: http://www.textmy90.com/

On November 15, 2018, Kira Seiger commented on Buoy Health’s mission to debunk Dr. Internet :

I believe there is immense value in having more targeted, relevant information available to patients. There is a great deal of difficulty and danger in attempting to diagnose yourself by typing your symptoms into a search engine instead of seeking professional assistance. However, as we all know, seeking medical advice in the US is extremely complicated given the financial burden, long waits, full schedules, transportation challenges, inefficient appointment scheduling processes, poor understanding of insurance benefits and cost sharing, and general complexity surrounding which type of doctor to see. So in the context of our healthcare structure, Googling symptoms is often the first logical step that many people take, and Buoy Health therefore has an intriguing value proposition.

Incorporating personal characteristics, such as sex and age, in addition to symptoms is crucial. For example, in the case of upper abdominal pain, a heart attack would be higher up on the list of possible diagnoses for a woman than for a man, since more women with heart attacks present with abdominal pain than men with the same diagnosis. In terms of age, it would be highly unlikely for a child or young adult with upper abdominal pain to be experiencing a heart attack!

I see Buoy as a means to encourage individuals to seek care who otherwise wouldn’t, since many individuals wait too long to seek care. On the flip side, I would be very hesitant to tell someone who thinks they need medical assistance to stay home based on reassuring Buoy results. In other words, I think this should be marketed towards being a safety net and improving outcomes for individuals who consider themselves fairly healthy and low risk, as opposed to a tool for more high-risk individuals with complicated medical problems to search for a reason to not seek professional care. Because of this belief, I’m not sure I agree with marketing this to employers and insurers, since if people use it as I described, it would actually increase costs. Certainly, having greater access to the healthcare system can lower costs in the long-run by keeping people’s medical problems more controlled, but insurers and employers generally don’t keep the same individuals for the whole course of their life and therefore may not see a financial benefit from this. (It’s similar to the debate about technology like Fitbit, where many insurers feel they won’t actually realize financial gains from the incremental health benefits of Fitbit because people may switch insurers multiple times in their lifetime as their employment changes. In other words, is the insurer paying more upfront to make someone healthier for their next insurer?)

An advantage I see for Buoy is that patients may be more likely to enter more private, sensitive information on their platform than voice that information to a doctor. For example, a person may be more likely to be honest on Buoy about how many cigarettes per day they smoke than when they have to voice that number out loud to a physician. However, there are many subtleties about the patient-doctor interaction that will be hard to replace with technology and AI and there is much that a physician can glean from talking to or even observing an individual.