A Path to Quicker Innovation: A Boon for Medicine

For anyone that has any experience trying to create and commercialize a medical device one of the most challenging, frustrating, and intimidating obstacles is obtaining FDA approval. It’s complicated, it’s expensive and more than anything it’s LONG.

There are currently a number of different ways that someone can obtain FDA approval. The two most common are the 510(k) pathway and the Premarket Approval (PMA) pathway.

The 510(k) is a pathway that can only be followed by devices that can prove they are substantially similar to a pre-existing device on the market. In doing so, devices that pass by FDA approval through the 510(k) do not have to undergo clinical trial for approval. (Although for more complicated devices trials are also necessary to show validation to the market). Most Class I and Class II devices are approved using this pathway.

However, for inventors and companies with groundbreaking technology that is not similar the PMA pathway is often the only option. This is an extremely stringent and time consuming process that is often an enormous barrier to entry for startups.

An expedited pathway to approval called the FDA Fast Track Development Program has existed for a few years in the pharmaceutical industry that can accelerate approval time  to only 60 days. Drugs that offer solutions to unmet needs are appropriate for this program like novel cancer drugs.

But for some reason no such equivalent has existed for medical devices. Well hopefully the wait is over.

Just yesterday the FDA announced proposed the Expedited Access Premarket Approval Application, a program for medical devices that will help new and novel technology that is needed by patients and the medical community to obtain faster FDA approval.

Technology has been growing at an incredibly rapid pace, and technological marvels are all around you. Unfortunately, the medical environment has been resistant to change and slow to evolve. Part of that has always been the huge obstacle associated with FDA approval.

Hopefully, this new process will make things a little bit easier. 

http://www.reuters.com/article/2014/04/22/us-fda-medicaldevice-idUSBREA3L10120140422

SAM App Review Revisited

http://sam-app.org.uk/

Just For Fun: Clinical Trials Email Digests

Source: Wikipedia

Source: Wikipedia

In order to tackle the problem of low clinical trial accrual, my group has decided to work on designing the general solution of a Clinical Trials Navigator (CTN). While I am satisfied with this as a good general solution, there are other specific solutions that could be beneficial. Especially being a computer science major who loves to build software, I can’t help but toy with these other solutions. So just for fun, I will change gears and write a slightly more technical blog post that describes the architecture for a solution that I would like to implement in the future (when I have time!).

The idea is a service that sends patients email digests for new trials that are relevant to them. A digest contains a simple list of potential clinical trials that the patient might qualify for, and is interested in. The flow of the application is described below.

Basic Architecture

Digest Diagram

The use case for a user is that they register online for the digest service and choose the corresponding types of trials that they would be interested in. After this simple registration, the user does not have to initiate any more contact with the service. From the user’s perspective, digests with aggregated clinical trials information will come in at a fairly steady pace. This saves the patient from the headache of sifting through trials themselves.

But how does the user receive this neat packaged digest of relevant clinical trials? The solution I have thought up is simple:

  1. The listing of all clinical trials on clinicaltrials.gov is freely available and is updated every day. The end goal is to detect new trials, so what we will do is index all current trials, and then check every day to see if there are non-indexed trials (which means they are new).

  2. When new trials are added, we check against our database of registered users to check whether or not the trials would be relevant. If they would be, then we make a note to include the trial in the user’s next digest.

  3. Once a digest has reached a tipping point (a point where any more trials would clutter the digest) or a time of inactivity (below the tipping point, but there are trials that are getting stale), then we send the user the email digest.

  4. In the email the user has the option to unsubscribe themselves from the digest.

 

Although this solution does not help patients who are not already engaged patients, I hope that it might help those who are not against the idea of trials, but have not the energy, time, or knowledge to sift through trials online.

 

Increasing the Scope of mHealth: Telemedicine Behind Bars

Screen Shot 2014-04-23 at 2.32.46 PM

In designing mHealth solutions, one of the most important initial steps is identifying the target population. Asking “Who will benefit?” is one of the best ways to kick-off a successful, targeted mHealth campaign. To do this, we spend time gathering statistics about how many people own mobile phones, who owns smartphones, who texts, who tweets, and who talks. As we narrow down our target population to a specific subset, certain groups will inevitably be left out. One such population, is the incarcerated.

While inmates are not generally allowed access to mobile phones, mobile health, specifically telemedicine, holds a lot of promise in improving healthcare among this population. In December 2013, mHealth News reported that the Louisiana Department of Corrections (DOC) was planning to increase the use of telemedicine in their prisons three-fold as the primary healthcare delivery system for its inmates. By collaborating with AMD Global Telemedicine Inc—the leading Telemedicine Encounter Management Solutions supplier—the DOC hopes to serve over 50,000 inmates. Prior to this innovation, handcuffed prisoners had to be transported 150 miles by bus to reach the nearest healthcare facility, where all prisoners had to remain until everyone had been seen.

By establishing a telemedicine infrastructure—training doctors and healthcare professionals and purchasing video and medical equipment—inmates can be screened for the few that need face-to-face interaction, while the others can be seen virtually from the prison. With the technology provided by AMD, up to 15 patients can be seen by a single physician in just four hours. In addition to increasing productivity and tailoring care, the increased use of telemedicine is also cost-effective. Using telemedicine will greatly reduce transportation costs and payment for personnel who need to be transported from the prison. Additionally, the DOC is receiving additional funding from the state, which will allow it to pay for the aforementioned training and purchases.

Telemedicine is also especially valuable because it provides an opportunity for the consolidation of medical information through the digital interface. An article in PRWEb covering this telehealth development describes the program’s capacity to “deliver live medical images from connected medical devices and scopes, real-time video from an examination camera, and the ability to view patient documents and vital signs data all in the same online platform.” Furthermore, patients can use telemedicine to access physicians of 16 different medical specialties, including primary care, neurology, and endocrinology.

Telemedicine provides a very promising avenue for using media and digital technology to reach underserved populations. The incarcerated community is oftentimes overlooked for many medical innovations. However, this is one valuable opportunity in which such innovations can, and most likely will, be both highly useful and significantly impactful. While it is simple enough to design media solutions for educated professionals, the potential of mHealth is much more expansive, and should be utilized in as many ways as possible.

 

http://www.mhealthnews.com/news/telemedicine-behind-bars-prison-mobile-mHealth?page=0

http://www.prweb.com/releases/2014/02/prweb11575342.htm

Artificial Intelligence and Healthcare

I’m taking a philosophy class that touches a lot upon what cognition really means. Which led me to thinking – if we’re becoming closer and closer to developing artificial intelligence that rivals human intelligence, could we develop artificial intelligence to solve problems within healthcare?

Solutions are already in the works. A 2013 study from Indiana University showed that artificial intelligence machines were able to diagnose and reduce the cost of healthcare better than physicians by 50%! Using 500 randomly selected patients from that group for simulations, the two compared actual doctor performance and patient outcomes against sequential decision-making models, all using real patient data. They found great disparity in the cost per unit of outcome change when the artificial intelligence model’s cost of $189 was compared to the treatment-as-usual cost of $497.

However, one problem with replacing physicians with artificial intelligence may be the possibility of removing the doctor-patient relationship from the equation and undermines the importance of human relationship in the treatment process.

We are reaching a time in our society that we are slowly developing the tools needed to create intelligent beings that could solve problems. But a key distinction so far is that our goals in artificial intelligence have always been to create something as good or better than an average human.

But what if we switched that around? What if our goal was actually to create an artificial intelligence that had a problem itself? For example, could we develop an artificial intelligence that thinks like a patient in order to understand patient behavior?

There are plenty of virtual reality programs that exist for doctors to test their skills on surgery on specific parts of the human body, and now we know artificial intelligence could even replace doctors in diagnosis, but could there be one day be an artificial intelligence modeled after a sick person – an intelligent agent that may not be biologically (mainly because if it’s a robot it may not be made of biological parts) sick but we install a state of mind into it that would make it behave as it was sick? I’m talking about creating a robot patient who we would somehow program into thinking it has cancer, and doctors could be able to talk to the robot and it would respond and behave the same way as a cancer patient. It would be a great tool for doctors to understand patient behavior and how to meet their needs relationally, and I can see the uses it may have in studying psychology and philosophy as well.

As a Cognitive Science major, I can’t help but wonder since scientists, philosophers, and engineers have not been able to agree on an exact theory and replica of an artificial intelligence that represents a normal, healthy human, then how much harder would it be to create an accurate artificial intelligence that is a replica of someone who is sick.  After all, to model something that we might called defective, do you need to have a complete understanding of the original, non-defective object first?

Another complication would be distinguishing whether we could create a patient based on what is called “weak artificial intelligence” vs. “strong artificial intelligence”. Weak artificial intelligence is being able to create a machine that behaves intelligently, but strong artificial intelligence is creating a machine that can actually think. The current goal of researchers is to create strong artificial intelligence, which is why you have supercomputers like Watson who apparently can solve problems and answer questions by finding the information on its own. So if we even were able to create a machine that can behave like a patient, would it be because it has weak or strong artificial intelligence?

I believe there are many factors to consider both in philosophy and in technology before this possibility could ever be achieved. But for now, perhaps the best way to understand patient behavior is to communicate with the patient.

 

Follow

Get every new post delivered to your Inbox

Join other followers: