AI predicts response to antipsychotic drugs, could distinguish between disorders

Lawson Health Research Institute, Mind Research Network and Brainnetome Center researchers have developed an algorithm that analyzes brain scans to classify illness in patients with complex mood disorders and help predict their response to medication.

A recent study analyzed and compared fMRI scans of those with MDD, bipolar I,  and no history of mental illness, and found that each group’s brain networks differed, including regions in the default mode network and thalamus.

When tested against participants with a known MDD or Bipolar I diagnosis, the algorithm correctly classified illness with 92.4 per cent accuracy.

The team also imaged the brains of 12 complex mood disorder patients with out a clear diagnosis, to predict diagnosis and examine medication response.

The researchers hypothesized that participants classified by the algorithm as having MDD would respond to antidepressants while those classified as having bipolar I would respond to mood stabilizers. When tested with the complex patients, 11 out of 12 responded to the medication predicted by the algorithm.

According to lead researcher Elizabeth Osuch:: “This study takes a major step towards finding a biomarker of medication response in emerging adults with complex mood disorders. It also suggests that we may one day have an objective measure of psychiatric illness through brain imaging that would make diagnosis faster, more effective and more consistent across health care providers.”


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

AI speeds MRI scans

Facebook and NYU’s fastMRI project, led by Larry Zitnick, uses AI in an attempt to make MRI imaging 10 times faster. Neural networks will be trained to fill in missing or degraded parts of scans, turning them from low resolution into high. The goal is to significantly reduce the time patients must lie motionless inside an MRI machine.


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

Wireless system could track tumors, dispense medicine

Dina Katabi and MIT CSAIL colleagues have developed ReMix, which uses lo power wireless signals to pinponit the location of implants in the body.  The tiny implants could be used as tracking devices on shifting tumors to monitor  movements, and in the future to deliver drugs to specific regions.

The technology showed centimeter-level accuracy in animal tests.

Markers in the body reflect the signal transmitted by the wireless device outside the body, therefore a battery or external power source are not required.


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

Invasive deep brain stimulation for alcoholism?

Stanford’s Casey Halpern and Allen Ho have used deep brain stimulation to target nucleus accumbens, thought to reduce impulsive behavior, to combat alcoholism in animal and pilot human studies.

DBS is used in severe Parkinson’s disease and is not approved by the FDA for addiction. Infection and other complications are risks of this invasive surgery.

ApplySci hopes that strides in behavioral therapy, including Alcoholics Anonymous, will continue to improve outcomes in addicted individuals, diminishing the need for invasive procedures.

The Stanford study was published in Neurosurgical Focus.


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

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

Wrist wearable measures blood counts, bacteria, air particles

Rutgers scientists Mehdi Javanmard and Abbas Furniturewalla have developed a wrist wearable that can count particles, including blood cells, bacteria, and organic or inorganic air particles. Red blood cell counts can indicate internal bleeding. High or low white blood cell counts can indicate cancers, such as leukemia, or other illnesses.

The plastic wristband includes a flexible circuit board and a thin biosensor with a channel, or pipe, with embedded gold electrodes. A circuit processes electrical signals, and a micro-controller digitizes data, which is transmitted via bluetooth. Blood samples are obtained through pinpricks, and fed through the channel, where the cells counted.

The goal is rapid blood test results with out  lab-based equipment.


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

Hydrogen peroxide sensor to determine effective chemotherapy

MIT’s Hadley Sikes has developed a sensor that determines whether cancer cells respond to a particular type of chemotherapy by detecting hydrogen peroxide inside human cells.

The technology could help identify new cancer drugs that boost levels of hydrogen peroxide, which induces programmed cell death. The sensors could also be adapted to screen individual patients’ tumors to predict whether such drugs would be effective against them.


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

Continuous blood pressure monitoring glasses

Microsoft’s Glabella glasses, developed by Christian Holz and Edward Wang, will have integrated optical sensors that take pulse wave readings from three areas around the face, according to their recently granted patent.

Blood pressure is calculated by measuring the time between when blood is ejected from the heart and reaches the face. The researchers believe that the device can unobtrusively and continuously measure blood pressure.


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

Jason Heikenfeld on sweat-based biometric monitoring | ApplySci @ Stanford

University of Cincinnati and Eccrine Systems‘ Jason Heikenfeld discussed sweat-based biometric monitoring at ApplySci’s recent Wearable Tech + Digital Health + Neurotech conference at Stanford:


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 – Sean Lane

Just announced:  Ed Simcox, CTO of the US Department of Health and Human Services, will be the closing speaker at ApplySci’s Digital Health + Neurotech Boston conference on September 24, 2018