Scar tissue, also known as fibrosis, is the scourge of medical device implants. Even when receiving potentially life saving drug treatments, patients’ bodies often form scarring around the foreign object, thus eventually forcing the implant to malfunction or fail. This reaction can drastically limit a procedure’s efficacy, but a new breakthrough combining soft robotics and artificial intelligence could soon clear the troublesome hurdle.
According to a new study published with Science Robotics, a collaboration between researchers at MIT and the University of Galway resulted in new medical device tech that relies on AI and a malleable body to evade scar tissue buildup.
“Imagine a therapeutic implant that can also sense its environment and respond as needed using AI,” Rachel Beatty, co-lead author and postdoctoral candidate at the University of Galway, said in a statement. “This approach could generate revolutionary changes in implantable drug delivery for a range of chronic diseases.”
The technology’s secret weapon is its conductive, porous membrane capable of detecting when it is becoming blocked by scar tissue. When this begins to occur, a machine learning algorithm kicks in to oversee an emerging treatment known as mechanotherapy, in which soft robotic implants inflate and deflate at various speeds and sizes to deter scar tissue formation.
[Related: A micro-thin smart bandage can quickly heal and monitor wounds.]
Ellen Roche, an MIT professor of mechanical engineering and study co-author, explains that personalized, precision drug delivery systems could greatly benefit from responding to individuals’ immune system responses. Additionally, such devices could reduce “off-target effects” while ensuring the right drug dosages are delivered at the right times.
“The work presented here is a step towards that goal,” she added in a statement.
In training simulations, the team’s device could develop personalized, consistent dosage regimes in situations involving significant fibrosis. According to researchers, the new device’s AI could effectively control drug release even in a “worst-case scenario of very thick and dense scar tissue,” per the August 31 announcement.
According to Garry Duffy, the study’s senior author and a professor of anatomy and regenerative medicine at the University of Galway, the team initially focused on using the new robot for diabetes treatment. “Insulin delivery cannulas fail due to the foreign body response and have to be replaced often (approx. every 3-5 days),” told PopSci via email. “If we can increase the longevity of the cannula, we can then maintain the cannula for longer with less changes of the set required by the person living with diabetes.”
Beyond diabetes, they envision a future where the device can be easily adapted to a variety of medical situations and drug delivery regimens. According to Duffy, the advances could soon “provide consistent and responsive dosing over long periods, without clinician involvement, enhancing efficacy and reducing the need for device replacement because of fibrosis,” he said in the August 31 statement.
