Less Experience Leads to Faster Neural Adaptation

 How EXACTLY will your competent? doctor use this to get you fully recovered? Completely upend their rehab protocols! Repetition has always been the mantra for stroke rehab.

Less Experience Leads to Faster Neural Adaptation

Summary: For over a century, the cornerstone of psychology has been the Pavlovian idea that we learn through repetition—the more a bell rings before food, the stronger the association. However, a groundbreaking study is upending this 100-year-old assumption.

Researchers discovered that the brain actually learns more efficiently when rewards are rare and spaced far apart. Rather than “practice makes perfect,” the brain’s dopamine system prioritizes the timing between events. This discovery suggests that our neural circuitry is designed to extract maximum information from infrequent experiences, providing a new biological explanation for why “cramming” for exams fails while spaced-out learning succeeds.

Key Facts

• The Timing Rule: The brain determines how much to learn based on the time between cue-reward pairings, rather than the total number of repetitions.
• Dopamine Acceleration: When rewards are spaced further apart, the brain requires significantly fewer repetitions before it begins releasing dopamine in anticipation of the reward.
• Sparse Learning Efficiency: Mice that received rewards only 10% of the time learned at the same rate—or faster—than those who received rewards 20 times more frequently.
• The “Cramming” Effect: When experiences happen too close together, the brain “downregulates” its learning, explaining why frequent, repetitive exposure can lead to diminishing returns in memory.
• AI Implications: This discovery could lead to faster artificial intelligence. Current AI requires billions of data points to learn, but a model based on this “sparse learning” theory could learn more quickly from fewer experiences.

Source: UCSF

More than a century ago, Pavlov trained his dog to associate the sound of a bell with food. Ever since, scientists assumed the dog learned this through repetition: The more times the dog heard the bell and then got fed, the better it learned that the sound meant food would soon follow.

Now, scientists at UC San Francisco are upending this 100-year-old assumption about associative learning. The new theory asserts that it depends less on how many times something happens and more on how much time passes between rewards.

New research reveals that the brain’s dopamine system is tuned to prioritize the time between rewards rather than the sheer number of repetitions, upending a century of learning theory. Credit: Neuroscience News

“It turns out that the time between these cue-reward pairings helps the brain determine how much to learn from that experience,” said Vijay Mohan K. Namboobidiri, PhD, an associate professor of Neurology and senior author of the study, published Feb. 12 in Nature Neuroscience.

When the experiences happen closer together, the brain learns less from each instance, Namboodiri said, adding that this could explain why students who cram for exams don’t do as well as those who studied throughout the semester.

Learning the cues

Scientists have traditionally thought of associative learning as a process of trial and error. Once the brain has detected that certain cues might lead to rewards, it begins to predict them. Scientists have postulated that at first the brain only releases dopamine when a reward like tasty food arrives. 

But if the reward arrives often enough, the brain begins to anticipate it with a release of dopamine as soon as it gets the cue. The dopamine hit refines the brain’s prediction, the theory goes, strengthening the link with the cue if the reward arrives — or weakening it if the reward fails to appear. 

Namboodiri and postdoctoral scholar Dennis Burke, PhD, trained mice to associate a brief sound with getting sugar-sweetened water, varying the time between trials. They spaced the trials 30 to 60 seconds apart for some of the mice, and five to 10 minutes apart, or more, for others. The result was that the mice whose trials were closer together received many more rewards than those who trials were spaced farther apart in the same amount of time. 

If associative learning depended only on repetition, the mice with more trials should have learned faster. Instead, the mice that got very few rewards learned the same amount as those that got 20 times more trials over the same amount of time. 

“What this tells us is that associative learning is less ‘practice makes perfect’ and more ‘timing is everything,’” said Burke, the first author of the study. 

Namboodiri and Burke then looked at what dopamine was doing in the mouse brain. 

When the rewards were spaced further apart, the mice needed fewer repetitions before their brains began to respond to the sound with dopamine.

Then, the researchers tried a different variation. They repeatedly played the sound — spacing the cues 60 seconds apart — but only gave the mice sugar water 10% of the time. These mice needed far fewer rewards before they began releasing dopamine after the cue, regardless of whether it was followed by a reward. 

More rapid learning

The findings could shift the way we look at learning and addiction. Smoking, for example, is intermittent and can involve cues — like the sight or smell of cigarettes — that increase the urge to smoke. Because a nicotine patch delivers nicotine constantly, it may disrupt the brain’s association between nicotine and the resulting dopamine reward, blunting the urge to smoke and making it easier to quit. 

Next, Namboodiri plans to investigate how his new theory could speed up artificial intelligence. Current AI systems learn quite slowly, because they are based on the prevailing model of associative learning, making small refinements after every interaction between billions of data points. 

“A model that borrows from what we’ve discovered could potentially learn more quickly from fewer experiences,” Namboodiri said. “For the moment, though, our brains can learn a lot faster than our machines and this study helps explain why.”

Authors: Additional authors on the study include Annie Taylor, Huijeong Jeong, SeulAh Lee, Leo Zsembik, Brenda Wu, Joseph Floeder, Gautam Naik, and Ritchie Chan, all of UCSF.

Funding: This work was supported by the National Institutes of Health (grants R00MH118422, R01MH129582, F32DA060044). the National Science Foundation, the Klingenstein-Simons Fellowship, the David and Lucile Packard Foundation, and Shurl and Kay Curci Foundation.

Key Questions Answered:

Q: Does this mean I should stop practicing things every day?

A: Not necessarily, but it means “spacing” is more important than “grinding.” If you’re trying to learn a new language or instrument, your brain will actually absorb more from three 20-minute sessions spread throughout the day than one solid hour of repetition.

Q: Why would the brain prefer rare events over common ones?

A: From an evolutionary standpoint, rare rewards (like finding a hidden fruit tree) are more “informative” than common ones. If something happens all the time, the brain treats it as background noise. If it’s rare, the brain pays extra attention to the timing to make sure it doesn’t miss the next opportunity.

Q: How does this link to addiction?

A: It explains why intermittent rewards (like gambling or social media notifications) are so addictive. Because the rewards are unpredictable and spaced out, the brain’s dopamine system remains highly sensitive and “learns” the habit much more deeply than if the reward was constant.

Editorial Notes:

• This article was edited by a Neuroscience News editor.
• Journal paper reviewed in full.
• Additional context added by our staff.

About this learning and neuroscience research

Author: Laura Kurtzman
Source: UCSF
Contact: Laura Kurtzman – UCSF
Image: The image is credited to Neuroscience News

Original Research: Open access.
“Duration between rewards controls the rate of behavioral and dopaminergic learning” by Dennis A. Burke, Annie Taylor, Huijeong Jeong, SeulAh Lee, Leo Zsembik, Brenda Wu, Joseph R. Floeder, Gautam A. Naik, Ritchie Chen & Vijay Mohan K Namboodiri. Nature Neuroscience
DOI:10.1038/s41593-026-02206-2

Electronic Mesh Wraps Around Mini-Brains to Eavesdrop on Neural Circuits

 With this our researchers could listen in on neuroplasticity signals and figure out how to make them repeatable on demand, thus ensuring recovery! At least if we had ANY LEADERSIP AT ALL IN STROKE!

But the stroke leaders would already have ensured that listening to brain signals by using one of these already! Add sarcasm tag here.

1. Use nanowires to listen in on single neurons

2. Or lay a grid across the cortex to listen in.

3. Electronic tattoo decodes brainwaves January 2025

But we have NO stroke leaders, nothing will get done until we get survivors in charge.

Leaders solve problems, they don't run away from them.

The latest here:

Electronic Mesh Wraps Around Mini-Brains to Eavesdrop on Neural Circuits

Summary: For the first time, scientists can record the full “electrical dialogue” occurring across an entire lab-grown human organoid. While these “mini-brains” are powerful tools for studying development and disease, previous technology could only sample a tiny fraction of their activity using flat, rigid sensors.

A new study reveals a breakthrough: a soft, 3D bioelectronic framework that “pops up” to envelope the organoid like a high-tech mesh. With hundreds of miniaturized electrodes, this device captures synchronized rhythms spanning the entire tissue, allowing researchers to see how neural networks communicate, respond to drugs, and even grow into specific shapes.

Key Facts

• Full-Network Mapping: The device covers over 90% of the organoid’s surface, moving beyond localized probing to capture coordinated, whole-tissue neural rhythms.
• The “Pop-Up” Mechanism: Using mechanical buckling similar to a 3D pop-up book, the device transforms from a flat lattice into a spherical cage that gently hugs the tissue.
• Miniaturized Precision: The array features 240 electrodes, each only 10 microns in diameter—roughly the size of an individual human cell.
• Breathable Bioelectronics: The mesh is porous, allowing the living tissue to “breathe” by letting oxygen and nutrients in while waste products flow out.
• Growth Engineering: Beyond recording, the framework can be engineered into cubes or hexagons, forcing the organoids to grow into specific shapes for potential “stacking” in future multi-organ models.

Source: Northwestern University

A team led by Northwestern University and Shirley Ryan AbilityLab scientists have developed a new technology that can eavesdrop on the hidden electrical dialogues unfolding inside miniature, lab-grown human brain-like tissues.

Known as human neural organoids — and sometimes called “mini brains” — these millimeter-sized structures are powerful models of brain development and disease. But until now, scientists could only record and stimulate activity from a small fraction of their neurons — missing network-wide dynamics that give rise to coordinated rhythms, information processing and the complex patterns of activity that define brain function.

The soft, three-dimensional (3D) electronic framework wraps around an organoid like a breathable, high-tech mesh. Rather than sampling select regions, it delivers near-complete, shape-conforming coverage with hundreds of miniaturized electrodes. Credit: John A. Rogers/Northwestern University

For the first time, the new technology overcomes that stubborn limitation. The soft, three-dimensional (3D) electronic framework wraps around an organoid like a breathable, high-tech mesh.

Rather than sampling select regions, it delivers near-complete, shape-conforming coverage with hundreds of miniaturized electrodes. That dense, three-dimensional interfacing enables scientists to map and manipulate neural activity across almost the entire organoid.

By moving from localized probing to true whole-network mapping, the work brings organoid research closer to capturing how real human brains develop, function and even fail.

The study was published today (Feb. 18) in the journal Nature Biomedical Engineering.

“Human stem cell-derived organoids have become a major focus of biomedical research because they enable patient-specific studies of how tissues respond to drugs and emerging therapies,” said Northwestern bioelectronic pioneer John A. Rogers, who led the device development.

“Labs in academia and industry have developed these tissue constructs over the years, and the National Institutes of Health (NIH) has initiated funding streams to accelerate work in this direction. A key missing component is hardware technology that can interrogate, stimulate and manipulate these tiny analogs to organs in the human body.”

“This advance is really about building the right tools for a new class of biological models,” said Dr. Colin Franz, who led the organoid development.

“Human neural organoids are living 3D tissues that contain active neural circuits communicating through electrical signals. However, the state-of-the-art instruments we use to study them were originally designed for flat layers of cells and do not interface well with organoids that are spherical and three dimensional. 

“By creating soft, shape-matched electronics that conform to the organoid’s geometry, we can now record from and stimulate hundreds of locations across its surface at once. This allows us to study neural activity at the level of whole networks rather than isolated signals.”

Rogers is the Louis Simpson and Kimberly Querrey Professor of Materials Science and Engineering, Biomedical Engineering and Neurological Surgery at Northwestern, where he has appointments in the McCormick School of Engineering and Northwestern University Feinberg School of Medicine. He also directs the Querrey Simpson Institute for Bioelectronics and the Querrey Simpson Institute for Translational Engineering for Advanced Medical Systems.

An expert in regenerative neuroscience, Franz is a physician-scientist at Shirley Ryan AbilityLab and an associate professor of physical medicine & rehabilitation, medicine (pulmonary and critical care) and neurology at Feinberg and an attending physician. Rogers and Franz co-led the study with Yihui Zhang of Tsinghua University in China and John Finan of the University of Illinois Chicago.

From fragments to full networks

Over the past decade, scientists have moved from flat dishes of neurons to self-organizing, 3D mini brains grown from human stem cells. These organoids can develop interconnected neural circuits and generate synchronized electrical rhythms reminiscent of early brain development. 

“Human-derived, 3D tissue models like organoids are beginning to change how we study disease and develop treatments,” Franz said. “They also have the potential to reduce our reliance on animal models.”

Yet even as these organoids form intricate neural networks, researchers can hear only fragments of their electrical conversations. Because they are flat and rigid, existing recording technologies cannot conform to the brain’s natural curves and wrinkles. By sampling activity from a mere handful of sites on the organoid, researchers risk missing the coordinated activity that emerges across the entire structure.

“Integrated circuits in consumer electronics are perfectly planar, sitting on wafer-based substrates,” Rogers said. “That conventional layout represents a very significant geometrical mismatch relative to the spherical shapes of these organoids.”

A bioelectronic ‘pop-up book’

To overcome this limitation, the Northwestern team designed a soft, porous scaffold that begins as a flat, rubbery lattice and then transforms into a precisely engineered 3D shape. A controlled mechanical buckling drives the transformation — the same mechanism that causes flat paper to convert into 3D structures in a “pop-up” book.

This framework gently envelopes the organoid, matching its curvature. The mesh-like perforations allow oxygen and nutrients to flow into the organoid and carbon dioxide and waste products to flow out.

“The device’s structure needs to support these metabolic processes to sustain the viability of the tissue,” Rogers said. “Basically, the organoid needs to breathe. The hardware must not significantly constrain or suffocate it.”

One version of the device covered 91% of an organoid’s surface and incorporated 240 individually addressable microelectrodes. Because organoids are often just a millimeter in diameter, the engineers had to push the size of the electrodes to the extreme. They developed highly miniaturized electrodes, measuring just 10 microns in diameter — about the size of an individual cell.

When the team tested systems with only eight or 32 electrodes, they captured limited, localized signals. With the full 240-channel array, the team recorded synchronized oscillatory waves spanning the entire organoid. Because the researchers know each electrode’s exact position, they can create a 3D map of the organoid’s electrical activity.

Shaping and studying living neural systems

In experiments, the team watched signals spark in one region and ripple across the network. By revealing split-second delays between distant areas, the technology picked up clear signs of coordinated communication within the organoid’s neurons.

Beyond mapping neural activity in detail, the platform also proved sensitive to the effects of drugs. The team tested several compounds and observed clear, predictable changes in how the organoids’ networks fired. For example, exposure to 4-aminopyridine — a medication used to improve walking in people with multiple sclerosis — increased neural signaling. 

But exposure to botulinum toxin, which blocks communication between nerve cells and is used to treat muscle spasticity, disrupted coordinated activity. These results show that the bioelectronic interface can detect meaningful drug responses in living human neural tissue models, demonstrating its potential as a powerful tool for testing therapies.

But the system doesn’t just listen — it also speaks. It can deliver tiny electrical pulses, triggering responses in specific regions. When combined with imaging and optogenetics, the system enables scientists to observe and influence neural activity.

The scientists also discovered that the device can shape how organoids grow. By modifying the microlattice design, the team engineered non-spherical geometries, including hexagonal and cubic shapes. Inside those frameworks, the organoids grew into matching shapes.

“With this ability, we can imagine assembling different types of organoids to create miniature versions of the human body,” Rogers said. “With cube-shaped organoids, we could stack them together like Lego blocks.”

What’s next

With more work, organoids could play a powerful role in the future of medicine. Because they are grown from human stem cells — even a patient’s own cells — organoids offer a way to model disease and test treatments in living, 3D neural networks. Researchers also could use them to study how brain disorders develop, evaluate drug responses and assess whether experimental regenerative strategies can restore lost, coordinated brain activity.

With tools that map activity across nearly the entire organoid, scientists can assess whether potential regenerative treatments truly rebuild functional circuits — a critical step toward developing effective therapies for brain disorders.

“As organoids become a growing priority for NIH initiatives and for industry drug development efforts, technologies like this will be essential for turning these sophisticated tissue models into practical platforms for understanding disease, testing therapies and advancing clinical neuroscience,” Franz said.

Funding: The study, “Shape-conformal porous frameworks for full coverage of neural organoids and high-resolution electrophysiology,” was supported by the Querrey Simpson Institute for Bioelectronics, National Institutes of Health (award number R01NS113935), the National Science Foundation, the Belle Carnell Regenerative Neurorehabilitation Fund, the New Cornerstone Science Foundation and the Haythornthwaite Foundation Research Initiation Grant.

Key Questions Answered:

Q: Are these “mini-brains” actually thinking?

A: They aren’t conscious, but they do generate synchronized electrical pulses similar to those seen in the early stages of human brain development. This new mesh allows us to finally “hear” the full complexity of those pulses for the first time.

Q: Why do we need to grow these organoids into cubes?

A: Standard organoids are spherical, which makes them hard to connect. By growing them into cubes using the mesh scaffold, scientists can imagine stacking them like LEGO blocks to create complex, multi-layered models of the human nervous system.

Q: How does this help patients with brain diseases?

A: Because these organoids can be grown from a specific patient’s stem cells, doctors can use the electronic mesh to test how that patient’s actual brain tissue responds to different medications—all in a lab dish before a single pill is prescribed.

About this neurotech research news

Author: Amanda Morris
Source: Northwestern University
Contact: Amanda Morris – Northwestern University
Image: The image is credited to John A. Rogers/Northwestern University

Original Research: Open access.
“Shape-conformal porous frameworks for full coverage of neural organoids and high-resolution electrophysiology” by Naijia Liu, Shahrzad Shiravi, Tianqi Jin, Jiaqi Liu, Zhengguang Zhu, Jiying Li, Ingrid Cheung, Haohui Zhang, Yue Wang, Qingyuan Li, Zijie Xu, Liangsong Zeng, Maria Jose Quezada, Andres Villalobos, Yasaman Samei, Shreyaa Khanna, Shuozhen Bao, Mingzheng Wu, Sida Liang, Xu Cheng, Zengyao Lv, Woo-Youl Maeng, Yamin Zhang, Haiwen Luan, Stephen A. Boppart, Yonggang Huang, Yihui Zhang, Colin K. Franz, John D. Finan & John A. Rogers. Nature Biomedical Engineering
DOI:10.1038/s41551-026-01620-y

High relative cerebral blood volume strongly predicts early neurological improvement and good functional outcome in ischemic stroke patients undergoing mechanical thrombectomy

 Are these a solution? You mean your incompetent? doctor and hospital have nothing to deliver better blood flow and oxygen to your brain immediately post stroke! And your board of directors is so incompetent they don't recognize incompetence in their hospital?

Dose Escalation and Safety of Capsaicin for Cerebral Perfusion Augmentation July 2021

cerebral blood flow (51 posts to December 2015)

oxygen delivery (41 posts to June 2016)

High relative cerebral blood volume strongly predicts early neurological improvement and good functional outcome in ischemic stroke patients undergoing mechanical thrombectomy

Paweł Wrona, Dominik Wróbel, Julia Staniszewska, Gabriela Kapral, Milena Derechowska, Gabriela Turaj, Tadeusz Popiela, Agnieszka Słowik, Wojciech Turaj

DOI: 10.5603/pjnns.106870

Pubmed: 41705962

Abstract

Aim of the study. Despite advancements in mechanical thrombectomy (MT) in the treatment of acute ischemic stroke (AIS) due to large vessel occlusion, nearly half of patients with successful recanalization do not achieve good functional outcome (GFO). We aimed to analyze the association between novel perfusion-based biomarkers and prognosis after AIS.Clinical rationale for the study. The role of perfusion imaging biomarkers, particularly relative cerebral blood volume (rCBV), as an indicator of tissue-level collateral circulation and a predictor of post-MT clinical trajectory remains insufficiently explored.

Material and methods. This single-center retrospective study included patients with anterior circulation AIS who achieved successful recanalization following MT at the Comprehensive Stroke Center, University Hospital, Krakow, between January 2019 and July 2023. We evaluated the predictive value of rCBV for early neurological improvement (ENI) and long-term GFO and compared its prognostic utility with other perfusion-based parameters. Furthermore, we assessed the extent to which the effect of rCBV on GFO was mediated by its influence on ENI. Early neurological improvement was defined as a ≥ 4-point reduction in the National Institutes of Health Stroke Scale score or complete symptom resolution within 24 hours post-admission. GFO was defined as a modified Rankin Scale score of < 3 at 90 days.

Results. Relative cerebral blood volume was an independent predictor of 90-day GFO after multivariable adjustment (adjusted odds ratio [aOR] = 1.38; 95% confidence interval [CI]: 1.19–1.6; p < 0.001). Additionally, total hypoperfusion volume (T6max) independently contributed to GFO prediction when included alongside rCBV (aOR = 0.96 per 10 mL increase; 95% CI: 0.94–0.99; p = 0.019), enhancing prognostic accuracy. Relative cerebral blood volume was also a strong predictor of ENI (aOR = 1.35; 95% CI: 1.19–1.54; p < 0.001), with 35% (4–67%; p = 0.029) of its effect on GFO mediated through its impact on ENI.

Conclusion and clinical implications. Relative cerebral blood volume is a robust predictor of both early neurological recovery and long-term functional outcome following MT. Moreover, T6max provides independent prognostic value when assessed in conjunction with rCBV, suggesting that these parameters complement each other. Their combined assessment provides a more comprehensive understanding of ischemic tissue fate, aiding clinical decision-making in patients selected for MT.

(My conclusion, you completely failed in your research; DIDN'T CREATE A PROTOCOL TO DELIVER THE BETTER BLOOD FLOW!)

Keywords: mechanical thrombectomycomputed tomography perfusionacute ischemic strokerelative cerebral blood volume

Article available in PDF format

The application of convolutional neural networks for brain age prediction: A systematic review

 Your competent? doctor should be measuring your brain age on a regular basis to prove that the protocols used actually recover your 5 lost years of brain cognition due to your stroke

The application of convolutional neural networks for brain age prediction: A systematic review

Author links open overlay panel, , 

https://doi.org/10.1016/j.bspc.2026.109812Get rights and content

Abstract

Deep learning (DL) has revolutionized neuroimaging, particularly with convolutional neural networks (CNNs) leading the charge, delivering unprecedented accuracy in brain age prediction. This systematic review meticulously investigates the strides made in CNNs for this critical task, pivotal to understanding variations in brain development and aging. Our exhaustive literature search spanning 2018 to 2024 using PRISMA principles and protocol identified 71 studies meeting stringent criteria, forming the basis of our analysis. Our examination delves deep into the neuroimaging data powering brain age prediction via CNNs, highlighting diverse model architectures and their real-world applications. We provide an intricate analysis of these architectures and methodologies, highlighting the shift towards 3D CNNs and the integration of multimodal neuroimaging data. Additionally, the review stresses the significance of model generalization and the hurdles posed by dataset limitations. Moreover, we underscore the imperative for models capable of generalizing effectively across varied demographics, underscoring the potential of CNNs to propel personalized medicine forward. This review encapsulates not only the current landscape but also points towards future directions, advocating for continued innovation to unlock the full potential of CNNs in deciphering the complexities of brain aging and beyond.

Introduction

Aging is a continuous and inexorable process that gradually reduces physiological functions and exerts negative effects on human functional capacity. The rapid aging of our global population is of great concern, with projections indicating that by 2050, approximately 21% of the world’s population will be over 60 years of age [1]. This significant demographic transition presents considerable challenges to healthcare systems, social care institutions, and the overall economy [2]. Of particular significance in the context of aging is the issue of cognitive decline. This multifaceted challenge encompasses adverse effects on various cognitive domains, including memory, attention, and executive function, consequently affecting the quality of life of older individuals [3]. A comprehensive understanding of the underlying mechanisms of cognitive aging is imperative in the pursuit of effective preventative strategies. Recent advancements in neuroimaging techniques have proven to be indispensable tools in the identification of both anatomical and functional changes that occur in the aging brain. Notably, structural changes represent a hallmark of normal aging and are often characterized by extensive gray matter atrophy [4]. However, these changes are not evenly distributed across the brain, with the frontal and temporal lobes exhibiting the most pronounced degrees of atrophy. Additionally, changes have also been observed in the parietal lobe, while the occipital lobe tends to maintain relative stability [5]. In conjunction with structural changes, aging is also closely associated with disruptions in the anatomical connections of white matter tracts. Specifically, the frontal white matter, anterior cingulum, and genu of the corpus callosum have been identified as regions particularly susceptible to aging processes [6]. Moreover, studies have identified decreased functional connectivity over time within the frontoparietal network and the salience network. These alterations lead to disruptions in the overall functionality of brain networks during the aging process [7].

The traditional measure of aging, chronological age (CA), has long served as a fundamental metric. However, contemporary research underscores the considerable variability in the rates and patterns of aging experienced by individuals. These variations are influenced by a complex interplay of factors, including genotypes, environment, and lifestyles. Consequently, individuals of the same CA can exhibit diverse physiological functions and abilities. For instance, a 60-year-old may exhibit signs of aging similar to those of a person who is 65 years old, depending on factors such as medical history, lifestyle choices, and environmental exposure. Notably, even in monozygotic twins with identical chronologies, the extent and rate of age-related changes can differ significantly [8], [9]. Consequently, relying solely on CA for aging assessment can be misleading. To address the limitations of CA as a comprehensive measure of aging, the concept of biological age (BA) has emerged as a valuable alternative. BA serves as a standardized metric that quantifies an individual’s physiological aging trajectory relative to the average age-matched individual [10]. This nuanced measure provides a more accurate estimate of an individual’s aging process compared to the conventional use of CA [11]. Research in this realm has investigated the potential predictive value of BA regarding age-related diseases, yielding remarkable findings [12], [13], [14]. Concurrently, brain age estimation has emerged as a promising instrument for assessing an individual’s brain age by scrutinizing the intricate dynamics between brain structure and function [10].

Machine learning (ML) has become increasingly popular in recent years as a powerful tool that enables computers to learn and improve from experience. The fusion of ML algorithms with neuroimaging has opened new opportunities for predicting brain age [15]. A burgeoning body of research has demonstrated the promise of ML in accurately predicting brain age using various neuroimaging modalities such as structural magnetic resonance imaging (MRI), functional MRI (fMRI), and diffusion tensor imaging (DTI). For example, an innovative study conducted by Franke et al. skillfully harnessed a combination of structural MRI and ML algorithms to accurately predict brain age [16]. Meanwhile, Baecker et al. and colleagues undertook a comparative analysis, scrutinizing the performance of three commonly employed ML methods in the prediction of brain age [17]. In parallel, Xiong et al. established a multimodal dataset, engaging six distinct ML methods, culminating in a definitive demonstration of the remarkable predictive prowess of MRI and DTI data. Their findings pointed to Lasso as the most precise ML algorithm for predicting brain age [18]. Within the expansive realm of ML, DL assumes a notable role, encompassing neural networks with multiple layers to learn progressively more abstract and hierarchical representations of input data. Specifically, CNNs, a subcategory of DL methods, have demonstrated exceptional performance in the analysis of medical imaging, including neuroimaging data. Neuroimaging datasets are renowned for their complex and substantial variable, making it challenging for traditional ML algorithms in feature extraction. However, CNNs exhibit a unique aptitude for addressing this challenge, as they are adept at learning intricate feature hierarchies that capture pivotal patterns inherent in raw input data. The proficiency of CNNs in mastering complex feature hierarchies bestows upon them a diverse range of valuable neuroimaging applications, including predicting brain age. When compared to traditional ML algorithms, CNNs consistently outperform due to their capability to generalize acquired representations to previously unseen data. This trait is particularly useful in the analysis of extensive volumes of imaging data.

In parallel, a series of comprehensive review articles have illuminated the field of automatic brain age prediction utilizing neuroimaging data. These reviews have predominantly explored the integration of ML methodologies and have substantially contributed to our understanding of neuroimaging-driven brain age estimation as a robust biomarker for a range of brain conditions. For instance, Mishra’s work in 2021 offers an extensive examination of neuroimaging-driven brain age estimation, meticulously categorizing frameworks based on image modality and clinical applications. This review effectively underscores the importance of brain age estimation in the context of disease detection and serves as a catalyst for future research directions [10]. Baecker and colleagues, in their 2021 work, have concentrated on the crucial role of ML in predicting brain age from neuroimaging data. Their work introduces the concept of the “brain-age gap” as a potential marker for brain health, demonstrating its utility in early detection and personalized interventions for age-related disorders [19]. Sajedi et al. have contributed a comprehensive overview of age prediction using brain MRIs. This review encompasses a spectrum of aspects, including preprocessing techniques, tools, and estimation methods. Importantly, it categorizes these approaches based on image processing and ML, emphasizing the remarkable efficacy of DL techniques in enhancing predictive accuracy. The historical landscape of literature reviews in this field has predominantly centered on ML, with relatively limited exploration into the realm of DL [20]. The exhaustive review conducted by Tanveer and his colleagues has marked a significant departure from prior works in the field of brain age prediction spanning from 2017 to March 2022. Their comprehensive assessment of DL models has offered a substantial and consequential contribution to the existing body of knowledge [21]. Building upon this foundation, our current review endeavors to offer a more deliberate and specialized investigation, specifically focusing on CNNs, a subdomain nestled within the expansive domain of DL. Our foremost aim in this comprehensive review is to provide an exhaustive and intricately detailed exposition of the methodologies and strategic foundations that underpin the application of CNNs in the domain of brain age prediction. Central to our examination lies the innovative and meticulously engineered architectural design inherent to these neural networks. Our intention is to methodically dissect the inherent complexities within these models, thereby illuminating the technical intricacies that confer upon them exceptional efficacy, rendering them indispensable tools for the precise prediction of brain age. Moreover, our review not only integrates the latest findings spanning from 2018 to April 2024 but also scrutinizes the practical applications and generalizability of CNNs across various age groups, thus ensuring a comprehensive understanding of their utility in diverse contexts. By focusing on the cutting-edge developments in CNNs for brain age prediction, we provide a detailed and up-to-date perspective poised to inform and guide future research and applications in this dynamic field. This approach contributes to the ongoing evolution of brain age prediction methodologies, fostering advancements that hold significant promise for both scientific inquiry and practical applications.

Access through your organization

Transfer Delays Tied to Worse Acute Stroke Intervention Results

 With proper leadership creating 100% recovery protocols these delays would not be allowed as an excuse anymore. SO, SOLVE THE FUCKING 100% RECOVERY PROBLEM! 

Transfer Delays Tied to Worse Acute Stroke Intervention Results

The study underscores the importance of door-in-door-out time as a metric associated with patient outcomes, one expert says.(Wrong metric, you blithering idiots! 100% RECOVERY is the only goal in stroke. You measure that, nothing else matters to survivors!)

byTodd Neale

For patients with acute ischemic stroke who require transfer to another hospital for endovascular therapy, spending more time in the initial emergency department is associated poorer short-term outcomes, an analysis of the Get With The Guidelines-Stroke registry shows.

Patients who had door-in-door-out (DIDO) times that exceeded the guideline-recommended target of 90 minutes or less at the receiving hospital were less likely to undergo endovascular therapy at the thrombectomy-capable hospital, were more likely to have complications from the procedure, and had worse functional outcomes at discharge, researchers led by Regina Royan, MD, and Brian Stamm, MD (both from University of Michigan, Ann Arbor), report in a study published in the February 2026 issue of the Lancet Neurology.

“We know that ‘time is brain’ for acute stroke treatment, so we hypothesized that longer DIDO delays would be associated with worse outcomes. Yet, there were several prior, small studies with conflicting results regarding the association between DIDO time and stroke outcomes,” Stamm told TCTMD via email. “Our comprehensive, national study now provides compelling evidence that DIDO time is strongly associated with outcomes from stroke.”

Here is your business101 requirements. Not measuring 100% recovery is the height of incompetence!

“What's measured, improves.” So said management legend and author Peter F. Drucker  

More than 40% of patients with acute ischemic stroke will need to be transferred between hospitals to receive endovascular therapy, and a prior study by these investigators showed that DIDO time at the first center often exceeded the goal of 90 minutes or less recommended in guidelines from the American Heart Association/American Stroke Association (AHA/ASA).

Commenting for TCTMD, Michael Mullen, MD (Temple University Hospital, Philadelphia, PA), a member of the stroke systems of care advisory group of the AHA/ASA, said this new study, “by quantifying not just the overall benefits of moving faster, but the benefits of a shorter door-in-door-out time, really helps to underscore the importance of DIDO and provides a very actionable target for future quality-improvement initiatives.”

DIDO Has Greater Impact in Patients Treated With Thrombectomy

The study included data on 22,410 patients (median age 70 years; 50.1% women) from the Get With The Guidelines-Stroke registry who were transferred from an acute care hospital to one of 489 thrombectomy-capable centers for endovascular therapy evaluation between 2019 and 2023.

The median DIDO time at the initial emergency department was 121 minutes, with only 26.3% of patients having a time of 90 minutes or less. Roughly three-quarters of patients received endovascular thrombectomy after transfer.

The primary outcome was the ordinal modified Rankin Scale (mRS) score at hospital discharge. After adjustment for potential confounders, having a DIDO time longer than 90 minutes, across multiple thresholds, was associated with greater odds of having a 1-point increase in mRS score at discharge:

• 91-180 minutes (adjusted OR 1.29; 95% CI 1.20-1.37)
• 181-270 minutes (adjusted OR 1.49; 95% CI 1.36-1.64)
• > 270 minutes (OR 1.70; 95% CI 1.53-1.89)

Moreover, patients with a longer DIDO time were less likely to undergo endovascular therapy:

• 91-180 minutes (adjusted OR 0.71; 95% CI 0.65-0.79)
• 181-270 minutes (adjusted OR 0.50; 95% CI 0.44-0.57)
• > 270 minutes (adjusted OR 0.35; 95% CI 0.30-0.40)

The link between longer DIDO times and worse functional outcomes was stronger in patients who ultimately received endovascular therapy than in those who didn’t. DIDO times greater than 90 minutes also were associated with lower odds of independent ambulation at discharge and of complication-free reperfusion therapy.

Altogether, Stamm said, “these findings underscore the importance of optimizing DIDO times to improve stroke outcomes.”

Targeting Speedier Transfers

Although the study was not designed to identify what factors played into longer DIDO times, Stamm said that prior research has identified multiple variables that are important when thinking about shortening delays, including rapid identification of stroke symptoms at the initial center, use of workflows that bundle required brain imaging, and optimization of ambulance availability for patient transport.

The ongoing HI-SPEED trial, which is led by the senior author of the current study, Shyam Prabhakaran, MD (University of Chicago Medicine, IL), “seeks to further understand the major barriers and test interventions to improve DIDO times,” Stamm noted.

There are two major components to improving the speed at which patients are transferred from one center to another for endovascular therapy, Mullen said. First, “there’s going to need to be a push to move as efficiently as possible at the primary stroke centers, at the acute stroke ready hospitals, and that will include getting advanced imaging whenever possible,” he said.

Second, there will have to be a focus on transport, with considerations dictated by system- and region-specific variables, Mullen said, noting, for example, that some centers use their own transport companies and others use outside services. “Every health system or different region is going to probably have slightly different pressures or barriers to getting an appropriate transport at the initial hospital as quickly as possible.”

Exact solutions are beyond the scope of the paper, but the study is helpful for setting DIDO time goals that hospitals can work toward, Mullen said.

“If these data are used to create quality targets, I think we’ll be surprised at how well we’ll be able to drive that time down if it’s appropriately incentivized,” he said. “We see that all over the place, whether it’s door-to-needle times for IV thrombolysis for stroke or door-to-balloon times for the cardiac space.”

by Todd Neale Editor, AI Exchange

Todd Neale is the Associate News Editor for TCTMD and a Senior Medical Journalist. He got his start in journalism at …

 Read Full Bio