AI – optimized glioblastoma chemotherapy

Pratik Shah, Gregory Yauney,  and MIT Media Lab researchers have developed an AI  model that could make glioblastoma chemotherapy regimens less toxic but still effective. It analyzes current regimens and iteratively adjusts doses to optimize treatment with the lowest possible potency and frequency toreduce tumor sizes.

In simulated trials of 50 patients, the machine-learning model designed treatment cycles that reduced the potency to a quarter or half of the doses It often skipped administration, which were then scheduled twice a year instead of monthly.

Reinforced learning was used to teach the model to favor certain behavior that lead to a desired outcome.  A combination of  temozolomide and procarbazine, lomustine, and vincristine, administered over weeks or months, were studied.

As the model explored the regimen, at each planned dosing interval it decided on actions. It either initiated or withheld a dose. If it administered, it then decided if the entire dose, or a portion, was necessary. It pinged another clinical model with each action to see if the the mean tumor diameter shrunk.

When full doses were given, the model was penalized, so it instead chose fewer, smaller doses. According to Shah, harmful actions were reduced to get to the desired outcome.

The J Crain Venter Institute’s Nicholas Schork said that the model offers a major improvement over the conventional “eye-balling” method of administering doses, observing how patients respond, and adjusting accordingly.


Join ApplySci at the 9th Wearable Tech + Digital Health + Neurotech Boston conference on September 24, 2018 at the MIT Media Lab.  Speakers include:  Rudy Tanzi – Mary Lou Jepsen – George ChurchRoz PicardNathan IntratorKeith JohnsonJuan EnriquezJohn MattisonRoozbeh GhaffariPoppy Crum – Phillip Alvelda Marom Bikson – Ed Simcox – Sean Lane

Sensor could continuously monitor brain aneurysm treatment

Georgia Tech’s Woon-Hong Yeo has  developed a proof of concept, flexible, stretchable sensor that can continuously monitor hemodynamics when integrated with a stent like flow diverter after a brain aneurysm. Blood flow is measured using  capacitance changes.

According to Pittsburgh professor Youngjae Chun, who collaborated with Yeo, “We have developed a highly stretchable, hyper-elastic flow diverter using a highly-porous thin film nitinol,” Chun explained. “None of the existing flow diverters, however, provide quantitative, real-time monitoring of hemodynamics within the sac of cerebral aneurysm. Through the collaboration with Dr. Yeo’s group at Georgia Tech, we have developed a smart flow-diverter system that can actively monitor the flow alterations during and after surgery.”

The goal is a batteryless, wireless device that is extremely stretchable and flexible that can be miniaturized enough to be routed through the tiny and complex blood vessels of the brain and then deployed without damage  According to Yeo, “It’s a very challenging to insert such electronic system into the brain’s narrow and contoured blood vessels.”

The sensor uses a micro-membrane made of two metal layers surrounding a dielectric material, and wraps around the flow diverter. The device is a few hundred nanometers thick, and is produced using nanofabrication and material transfer printing techniques, encapsulated in a soft elastomeric material.

“The membrane is deflected by the flow through the diverter, and depending on the strength of the flow, the velocity difference, the amount of deflection changes,” Yeo explained. “We measure the amount of deflection based on the capacitance change, because the capacitance is inversely proportional to the distance between two metal layers.”

Because the brain’s blood vessels are so small, the flow diverters can be no more than five to ten millimeters long and a few millimeters in diameter. That rules out the use of conventional sensors with rigid and bulky electronic circuits.

“Putting functional materials and circuits into something that size is pretty much impossible right now,” Yeo said. “What we are doing is very challenging based on conventional materials and design strategies.”

The researchers tested three materials for their sensors: gold, magnesium and the nickel-titanium alloy known as nitinol. All can be safely used in the body, but magnesium offers the potential to be dissolved into the bloodstream after it is no longer needed.

The proof-of-principle sensor was connected to a guide wire in the in vitro testing, but Yeo and his colleagues are now working on a wireless version that could be implanted in a living animal model. While implantable sensors are being used clinically to monitor abdominal blood vessels, application in the brain creates significant challenges.

“The sensor has to be completely compressed for placement, so it must be capable of stretching 300 or 400 percent,” said Yeo. “The sensor structure has to be able to endure that kind of handling while being conformable and bending to fit inside the blood vessel.”


Join ApplySci at the 9th Wearable Tech + Digital Health + Neurotech Boston conference on September 24, 2018 at the MIT Media Lab.  Speakers include:  Rudy Tanzi – Mary Lou Jepsen – George ChurchRoz PicardNathan IntratorKeith JohnsonJuan EnriquezJohn MattisonRoozbeh GhaffariPoppy Crum – Phillip Alvelda Marom Bikson – Ed Simcox – Sean Lane

Google incorporates depression screening in search

Google has introduced a new depression screening feature.  When the word “depression” is used in search, mobile users are offered a PHQ-9 questionnaire, which recognizes symptoms. A “Knowledge Panel” containing information and potential treatments appears on top of the page.

The goal is self awareness, and encouragement to seek help when needed.

Another company dedicated to improving brain health through mobile technology is Mindstrong Health.  The startup is developing clinically validated, phone-based mental illness screening, monitoring and treatment methods.  Co-founder Tom Insel will discuss their work at ApplySci’s upcoming Wearable Tech + Digital Health + Neurotech conference, on September 19th at the MIT Media Lab.


Join ApplySci at Wearable Tech + Digital Health + NeuroTech Boston on September 19, 2017 at the MIT Media Lab – featuring  Joi Ito – Ed Boyden – Roz Picard – George Church – Nathan Intrator –  Tom Insel – John Rogers – Jamshid Ghajar – Phillip Alvelda – Michael Weintraub – Nancy Brown – Steve Kraus – Bill Geary – Mary Lou Jepsen

Registration rates increase Friday, August 25th.


ANNOUNCING WEARABLE TECH + DIGITAL HEALTH + NEUROTECH SILICON VALLEY – FEBRUARY 26 -27, 2018 @ STANFORD UNIVERSITY –  FEATURING:  ZHENAN BAO – JUSTIN SANCHEZ – BRYAN JOHNSON – NATHAN INTRATOR – VINOD KHOSLA

Trial: Improved sense of touch and control in prosthetic hand

http://stm.sciencemag.org/content/6/222/222ra19

In the ongoing effort to improve the dexterity of prosthetics, a recent trial showed an improved sense of touch and control over a prosthetic hand.  EPFL professor Silvestro Micera and colleagues surgically attached electrodes from a robotic hand to a volunteer’s median and ulnar nerves. Those nerves carry sensations that correspond with the volunteer’s index finger and thumb, and with his pinky finger and the edge of his hand, respectively. The volunteer controlled the prosthetic with small muscle movements detected by sEMG, a non-invasive method that measures electrical signals through the skin.

Over seven days, the volunteer was asked to grasp something with a light grip, a medium grip, and a hard grip, and to evaluate the shape and stiffness of three kinds of objects. During 710 tests, he wore a blindfold and earphones so that he could not use his vision or sound to guide the prosthetic. The researchers also sometimes turned off the sensory feedback to test whether he was using time to modulate his grip.

The subject was able to complete the requested tasks with his prosthetic thumb and index finger 67 percent of the time the first day and 93 percent of the time by the seventh day of the experiment. His pinky finger was harder to control: he was only able to accomplish the requested grip 83 percent of the time. In both the grip strength tests and in detecting the stiffness of objects, the volunteer made mistakes with the medium setting and object, but he never confused the softest and hardest objects. The ability to modulate his grip strength is this study’s main progress over previous work by the same group.

Nobel-worthy stem cell discovery

http://www.nature.com/news/acid-bath-offers-easy-path-to-stem-cells-1.14600

Haruko Obokata and colleagues at the RIKEN Center for Developmental Biology have created embryonic stem cells from a single blood cell by putting white blood cells from a baby mouse in a mild acid solution. Eventually a few stem cells emerge that can turn into any other cell in the body including skin, heart, liver or neurons.

Scientists have long searched for ways to make human embryonic stem cells that did not destroy human embryos. These cells hold great potential for treating Alzheimer’s, Parkinson’s, heart disease and diabetes.

Obokata put the blood cells in a mild acid for about 30 minutes. The pH of the solution was about 5.7. A few days later, the cells stopped acting like blood and started behaving like stem cells.  When the researchers injected the cells into a mouse embryo, the cells acted just like other stem cells: They created all the organs needed for an adult mouse. The team named the cells stimulus-triggered acquisition of pluripotency, or STAP.

This breakthrough could enable scientists to create stem cells from any person, thus controlling genetic similarity, and use them to repair nerve injuries.