machine-learning

Fully-automated analysis of voice recordings–from neuropsychological tests–found to help differentiate normal cognition from dementia and mild cognitive impairment

by

Cred­it: James Byrne

Voice Record­ings Spot Cog­ni­tive Impair­ment (Med­Page Today):

A machine-learn­ing mod­el iden­ti­fied mild cog­ni­tive impair­ment and demen­tia from dig­i­tal voice record­ings of neu­ropsy­cho­log­i­cal tests, an ear­ly study showed.

Among 1,084 peo­ple in the Fram­ing­ham Heart Study whose tests were record­ed, the aver­age area under the curve (AUC) reached 92.6% for dif­fer­en­ti­at­ing nor­mal cog­ni­tion from demen­tia, 88.0% for dis­cern­ing nor­mal cog­ni­tion or mild cog­ni­tive impair­ment from demen­tia, and 74.4% for dis­tin­guish­ing nor­mal cog­ni­tion from mild cog­ni­tive impair­ment. [Read more…] about Ful­ly-auto­mat­ed analy­sis of voice recordings–from neu­ropsy­cho­log­i­cal tests–found to help dif­fer­en­ti­ate nor­mal cog­ni­tion from demen­tia and mild cog­ni­tive impairment

Geisinger and Eisai to test real-world validity of AI-powered Passive Digital Marker (PDM) in detecting early cognitive impairment and dementia

by

Research col­lab­o­ra­tion will test nov­el algorithm’s effec­tive­ness on Geisinger data (press release):

Geisinger and Eisai Inc. today announced a col­lab­o­ra­tive effort to study the poten­tial effec­tive­ness of an arti­fi­cial intel­li­gence (AI) tool in the detec­tion of cog­ni­tive impair­ment that could iden­ti­fy demen­tias, includ­ing Alzheimer’s dis­ease (AD). If effec­tive, the AI tool could poten­tial­ly be devel­oped to sup­port the ear­ly detec­tion and stag­ing of cog­ni­tive impair­ment and demen­tia, lead­ing to appro­pri­ate addi­tion­al test­ing for the clin­i­cal, bio­log­i­cal diag­no­sis and treat­ment of demen­tias such as AD. [Read more…] about Geisinger and Eisai to test real-world valid­i­ty of AI-pow­ered Pas­sive Dig­i­tal Mark­er (PDM) in detect­ing ear­ly cog­ni­tive impair­ment and dementia

Could I be wrong? Exploring cognitive bias, curiosity, intellectual humility, and lifelong learning

by

Wel­come to a new edi­tion of Sharp­Brains’ e‑newsletter, fea­tur­ing eight time­ly sci­en­tif­ic and indus­try news plus a few fun teasers to appre­ci­ate our unique human brains.

#1. Could I be wrong? Explor­ing research on cog­ni­tive bias, curios­i­ty, intel­lec­tu­al humil­i­ty, and life­long learning

“None of us thinks that our beliefs and atti­tudes are incor­rect; if we did, we obvi­ous­ly wouldn’t hold those beliefs and atti­tudes. Yet, despite our sense that we are usu­al­ly cor­rect, we must accept that our views may some­times turn out to be wrong. This kind of humil­i­ty isn’t sim­ply virtuous—the research sug­gests that it results in bet­ter deci­sions, rela­tion­ships, and out­comes. So, the next time you feel cer­tain about some­thing, you might stop and ask your­self: Could I be wrong?”

#2. Great inter­view on bilin­gual­ism, sports, edu­ca­tion and neu­ro­plas­tic­i­ty — en español

#3. Should old­er politi­cians, and oth­er lead­ers, under­go cog­ni­tive test­ing? The debate con­tin­ues … here are some good com­ments from the online debate we had last summer:

  • PRO: “Def­i­nite­ly. We rou­tine­ly screen appli­cants for a wide range of jobs. Apply for the police, you will be test­ed. Join the mil­i­tary, you will be eval­u­at­ed. Should we not know if a can­di­date for the high­est posi­tion in the coun­try has a seri­ous emo­tion­al, intel­lec­tu­al or psy­cho­log­i­cal impairment?”
  • CON: “I dis­agree because these tests are very bad at pre­dict­ing how good some­one would be in lead­ing a coun­try. It doesn’t require the abil­i­ty to store a lot of infor­ma­tion in your work­ing mem­o­ry. Being a good leader requires only one essen­tial thing: hav­ing the right priorities.”
  • IT DEPENDS: “Who makes the test? What cog­ni­tive met­rics do we use? The bias­es in that design could lead to sig­nif­i­cant unex­pect­ed or even inten­tion­al­ly skewed results.”

#4. Click Ther­a­peu­tics rais­es fur­ther $52M to build up dig­i­tal ther­a­peu­tics pipeline for depres­sion, insom­nia, smok­ing ces­sa­tion and more

What a year for Click and for dig­i­tal therapeutics!

#5. The Amer­i­can Med­ical Association’s (AMA) to ease access to remote Cog­ni­tive Behav­ioral Ther­a­py Monitoring

The road to heav­en is paved with good decisions…

#6. FDA-approved, Cybin-spon­sored clin­i­cial tri­al to mea­sure ketamine’s impact on the brain via Ker­nel Flow neu­roimag­ing helmet

“The word psy­che­del­ic means ‘mind-man­i­fest­ing,’ but what has been miss­ing is use­ful ‘mind-imaging’—the abil­i­ty to dynam­i­cal­ly trace the neur­al cor­re­lates of human con­scious expe­ri­ence. Con­ven­tion­al neu­roimag­ing just isn’t dynam­ic enough to study the psy­che­del­ic expe­ri­ence in the brain as it hap­pens. This study of ketamine’s psy­che­del­ic effects while wear­ing head­gear equipped with sen­sors to record brain activ­i­ty could open up new fron­tiers of under­stand­ing” — Dr. Alex Belser, Cybin’s Chief Clin­i­cal Officer

#7. Bea­con Biosig­nals rais­es $27M to scale EEG, AI-based neu­ro­bio­mark­er dis­cov­ery platform

“ana­lyz­ing EEGs is labor inten­sive and inter­pre­ta­tion of these tests can vary from one clin­i­cian to another..…Beacon Biosig­nals has assem­bled what it claims is one of the world’s largest clin­i­cal EEG data­bas­es. By apply­ing its pro­pri­etary machine-learn­ing algo­rithms to the data­base, the com­pa­ny says it has iden­ti­fied neurobiomarkers—biological indi­ca­tors that are asso­ci­at­ed with cer­tain groups of patients, drug activ­i­ty, and ther­a­peu­tic efficacy.”

#8. Amy­loid-relat­ed imag­ing abnor­mal­i­ties (ARIA) found in approx­i­mate­ly 40% of patients tak­ing “Alzheimer’s drug” Aduhelm

Not good, yet com­plete­ly pre­dictable, and let’s remem­ber this is for a “treat­ment” cost­ing as much as $100,000/ year with exact­ly ZERO proven clin­i­cal ben­e­fit: “…The researchers found 425 cas­es in the com­bined adu­canum­ab group expe­ri­enced ARIA (41.3%), and ARIA-ede­ma was iden­ti­fied in 362 patients or 35.2%. Of them, 94 (26%) had symp­toms, such as headache, con­fu­sion, dizzi­ness and nau­sea. They found ARIA-micro­he­m­or­rhage and ARIA-super­fi­cial sidero­sis in 197 patients (19.1%) and 151 patients (14.7%), respectively.”

Final­ly, Let’s Thank our unique Human Brains and Minds with a few fam­i­ly-friend­ly riddles

Q: What does, “you must come and vis­it us some­time!” actu­al­ly mean?

 

Wish­ing you and yours a Hap­py & Healthy Hanukkah, Decem­ber and Christmas,

The Sharp­Brains Team

 

Beacon Biosignals raises $27M to scale EEG, AI-based neurobiomarker discovery platform

by

Neu­rotech start­up Bea­con Biosig­nals scores $27M to bring AI to EEG analy­sis (Med­C­i­ty News):

Elec­troen­cephalog­ra­phy is a decades-old tech­nique for cap­tur­ing brain activ­i­ty, data that are used to eval­u­ate brain dis­or­ders. Bea­con Biosig­nals is apply­ing arti­fi­cial intel­li­gence to these tests, and the neu­rotech­nol­o­gy start­up has found a ready mar­ket in phar­ma­ceu­ti­cal com­pa­nies inter­est­ed in assess­ing how their exper­i­men­tal brain ther­a­pies are work­ing. Now Bea­con Biosig­nals has some­thing else: $27 mil­lion in financ­ing. [Read more…] about Bea­con Biosig­nals rais­es $27M to scale EEG, AI-based neu­ro­bio­mark­er dis­cov­ery platform

Cumulus Neuroscience raises $8.3M to develop EEG-based wireless ‘Fitbit for the brain’

by

Belfast-based Cumu­lus rais­es €6.9m for its ‘Fit­bit for the brain’ (The Irish Times):

… For­mer­ly known as Brain­Wave­Bank, the com­pa­ny has devel­oped a wire­less elec­troen­cephalo­gram (EEG) head­set and pro­pri­etary soft­ware plat­form that use advanced ana­lyt­ics and machine learn­ing to mea­sure cog­ni­tive fitness.

“This fund­ing will allow us to build on the ground-break­ing advances we have made in remote, fre­quent mon­i­tor­ing of brain activ­i­ty and cog­ni­tive func­tion in the home, in part­ner­ship with lead­ing devel­op­ers of dig­i­tal bio­mark­ers,” said Mr Cun­ning­ham, the company’s chief exec­u­tive. [Read more…] about Cumu­lus Neu­ro­science rais­es $8.3M to devel­op EEG-based wire­less ‘Fit­bit for the brain’

Reading Our Minds: New book issues strong call to action to modernize psychiatry

by

The Rise of Big Data Psy­chi­a­try (The Wall Street Journal):

As a physi­cian, I need to fig­ure out three things when a new patient walks into my office: what their life is typ­i­cal­ly like, what has changed that made them seek treat­ment and what I can do to help them. It’s a com­plex prob­lem, and most fields of med­i­cine approach it by tak­ing mea­sure­ments. If I were a car­di­ol­o­gist eval­u­at­ing a patient’s chest pain, for instance, I would speak with the patient, but then I would lis­ten to their heart and mea­sure their pulse and blood pres­sure. I might order an elec­tro­car­dio­gram or a car­diac stress test, tools that weren’t avail­able a cen­tu­ry ago.

Because I’m a psy­chi­a­trist, how­ev­er, I eval­u­ate patients in pre­cise­ly the same way that my pre­de­ces­sors did in 1920: I ask them to tell me what’s wrong, and while they’re talk­ing I care­ful­ly observe their speech and behav­ior. But psy­chi­a­try has remained large­ly immune to mea­sure­ment. At no point in the exam­i­na­tion do I gath­er numer­i­cal data about the patient’s life or behav­ior, even though tools for tak­ing such mea­sure­ments already exist. In fact, you like­ly are car­ry­ing one around in your pock­et right now. Keep read­ing essay HERE, adapt­ed from the new book Read­ing Our Minds: The Rise of Big Data Psy­chi­a­try by psy­chi­a­trist Daniel Bar­ron. [Read more…] about Read­ing Our Minds: New book issues strong call to action to mod­ern­ize psychiatry