The Eighty Five Percent Rule for optimal learning

A multi-institutional machine learning algorithm for prognosticating facial nerve injury following microsurgical resection of vestibular schwannoma

Vestibular schwannomas (VS) are the most common tumor of the skull base with available treatment options that carry a risk of iatrogenic injury to the facial nerve, which can significantly impact patients' quality of life. As facial nerve outcomes remain challenging to prognosticate, we endeavored to utilize machine learning to decipher predictive factors relevant to facial nerve outcomes following microsurgical resection of VS. A database of patient-, tumor- and surgery-specific features was constructed via retrospective chart review of 242 consecutive patients who underwent microsurgical resection of VS over a 7-year study period. This database was then used to train non-linear supervised machine learning classifiers to predict facial nerve preservation, defined as House-Brackmann (HB) I vs. facial nerve injury, defined as HB II-VI, as determined at 6-month outpatient follow-up. A random forest algorithm demonstrated 90.5% accuracy, 90% sensitivity and 90% specificity in facial nerve injury prognostication. A random variable (rv) was generated by randomly sampling a Gaussian distribution and used as a benchmark to compare the predictiveness of other features. This analysis revealed age, body mass index (BMI), case length and the tumor dimension representing tumor growth towards the brainstem as prognosticators of facial nerve injury. When validated via prospective assessment of facial nerve injury risk, this model demonstrated 84% accuracy. Here, we describe the development of a machine learning algorithm to predict the likelihood of facial nerve injury following microsurgical resection of VS. In addition to serving as a clinically applicable tool, this highlights the potential of machine learning to reveal non-linear relationships between variables which may have clinical value in prognostication of outcomes for high-risk surgical procedures.

A Comparison of Veterans with Problematic Opioid Use Identified through Natural Language Processing of Clinical Notes versus Using Diagnostic Codes

Opioid use disorder is known to be under-coded as a diagnosis, yet problematic opioid use can be documented in clinical notes, which are included in electronic health records. We sought to identify problematic opioid use from a full range of clinical notes and compare the demographic and clinical characteristics of patients identified as having problematic opioid use exclusively in clinical notes to patients documented through ICD opioid use disorder diagnostic codes. We developed and applied a natural language processing (NLP) tool that combines rule-based pattern analysis and a trained support vector machine to the clinical notes of a patient cohort (n = 222,371) from two Veteran Affairs service regions to identify patients with problematic opioid use. We also used a set of ICD diagnostic codes to identify patients with opioid use disorder from the same cohort. The NLP tool achieved 96.6% specificity, 90.4% precision/PPV, 88.4% sensitivity/recall, and 94.4% accuracy on unseen test data. NLP exclusively identified 57,331 patients; 6997 patients had positive ICD code identifications. Patients exclusively identified through NLP were more likely to be women. Those identified through ICD codes were more likely to be male, younger, have concurrent benzodiazepine prescriptions, more comorbidities, and more care encounters, and were less likely to be married. Patients in both these groups had substantially elevated comorbidity levels compared with patients not documented through either method as experiencing problematic opioid use. Clinicians may be reluctant to code for opioid use disorder. It is therefore incumbent on the healthcare team to search for documentation of opioid concerns within clinical notes.

Effect of immersive virtual reality-based cognitive remediation in patients with mood or psychosis spectrum disorders: study protocol for a randomized, controlled, double-blinded trial

BACKGROUND

Cognitive impairments are prevalent across mood disorders and psychosis spectrum disorders, but there is a lack of real-life-like cognitive training programmes. Fully immersive virtual reality has the potential to ensure motivating and engaging cognitive training directly relevant to patients' daily lives. We will examine the effect of a 4-week, intensive virtual reality-based cognitive remediation programme involving daily life challenges on cognition and daily life functioning in patients with mood disorders or psychosis spectrum disorders and explore the neuronal underpinnings of potential treatment efficacy.

METHODS

The trial has a randomized, controlled, double-blinded, parallel-group design. We will include 66 symptomatically stable outpatients with mood disorders or psychosis spectrum disorders aged 18-55 years with objective and subjective cognitive impairment. Assessments encompassing a virtual reality test of daily life cognitive skills, neuropsychological testing, measures of daily life functioning, symptom ratings, questionnaires on subjective cognitive complaints, and quality of life are carried out at baseline, after the end of 4 weeks of treatment and at a 3-month follow-up after treatment completion. Functional magnetic resonance imaging scans are performed at baseline and at the end of treatment. The primary outcome is a broad cognitive composite score comprising five subtasks on a novel ecologically valid virtual reality test of daily life cognitive functions. Two complete data sets for 54 patients will provide a power of 80% to detect a clinically relevant between-group difference in the primary outcome. Behavioural data will be analysed using linear mixed models in SPSS, while MRI data will be analysed with the FMRIB Expert Analysis Tool (FEAT). Treatment-related changes in neural activity from baseline to end of treatment will be investigated for the dorsal prefrontal cortex and hippocampus as the regions of interest.

DISCUSSION

The results will provide insight into whether virtual reality-based cognitive remediation has beneficial effects on cognition and functioning in symptomatically stable patients with mood disorders or psychosis spectrum disorders, which can aid future treatment development.

TRIAL REGISTRATION

ClinicalTrials.gov NCT06038955. Registered on September 15, 2023.

IgG Antibody Responses to Epstein-Barr Virus in Myalgic Encephalomyelitis/Chronic Fatigue Syndrome: Their Effective Potential for Disease Diagnosis and Pathological Antigenic Mimicry

Background and Objectives: The diagnosis and pathology of myalgic encephalomyelitis/chronic fatigue syndrome (ME/CFS) remain under debate. However, there is a growing body of evidence for an autoimmune component in ME/CFS caused by the Epstein-Barr virus (EBV) and other viral infections. Materials and Methods: In this work, we analyzed a large public dataset on the IgG antibodies to 3054 EBV peptides to understand whether these immune responses could help diagnose patients and trigger pathological autoimmunity; we used healthy controls (HCs) as a comparator cohort. Subsequently, we aimed at predicting the disease status of the study participants using a super learner algorithm targeting an accuracy of 85% when splitting data into train and test datasets. Results: When we compared the data of all ME/CFS patients or the data of a subgroup of those patients with non-infectious or unknown disease triggers to the data of the HC, we could not find an antibody-based classifier that would meet the desired accuracy in the test dataset. However, we could identify a 26-antibody classifier that could distinguish ME/CFS patients with an infectious disease trigger from the HCs with 100% and 90% accuracies in the train and test sets, respectively. We finally performed a bioinformatic analysis of the EBV peptides associated with these 26 antibodies. We found no correlation between the importance metric of the selected antibodies in the classifier and the maximal sequence homology between human proteins and each EBV peptide recognized by these antibodies. Conclusions: In conclusion, these 26 antibodies against EBV have an effective potential for disease diagnosis in a subset of patients. However, the peptides associated with these antibodies are less likely to induce autoimmune B-cell responses that could explain the pathogenesis of ME/CFS.

Leveraging Digital Workflows to Transition the Orthotics and Prosthetics Profession Toward a Client-Centric and Values-Based Care Model

The orthotics and prosthetics (O&P) profession has a history of responding to market demands in a reactive rather than proactive manner. This has created significant impacts including shrinkage in scope of practice and constraint in remuneration for professional services due to a fee-for-device third party payer system. Rapid changes in technology and healthcare combined with an outdated device-centric reimbursement system are creating unprecedented challenges that threaten sustainability of the O&P profession. Hence, a reassessment of the value of O&P care, and the O&P workflow process is necessary to inform an update to the value proposition and practice model for sustainability. This article reviews key factors contributing to the current state of O&P, and potential solutions involving an update in practitioner competencies, and the care delivery model (from device-centric to client-centric and values-based). Updates could be achieved by leveraging the use of digital workflows that increase efficiencies and enhance the value of clinical outcomes. Eventually, these updates could enable the O&P profession to elevate the value proposition that aligns with its most important stakeholders: client-patients and third-party reimbursement agencies in a rapidly changing technology and healthcare landscape.

Maximizing reusability of learning objects through machine learning techniques

Maximizing the reusability of learning objects through machine learning techniques has significantly transformed the landscape of e-learning systems. This progress has fostered authentic resource sharing and expanded opportunities for learners to explore these materials with ease. Consequently, a pressing need arises for an efficient categorization system to organize these learning objects effectively. This study consists of two primary phases. Firstly, we extract metadata from learning objects using web exploration algorithms, specifically employing feature selection techniques to identify the most relevant features while eliminating redundant ones. This step drastically reduces the dataset's dimensionality, enabling the creation of practical and useful models. In the second phase, we employ machine learning algorithms to categorize learning objects based on their specific forms of similarity. These algorithms are adept at accurately classifying objects by measuring their similarity using Euclidean distance metrics. To evaluate the effectiveness of learning objects through machine learning techniques, a series of experimental studies were conducted using a real-world dataset. The results of this study demonstrate that the proposed machine learning approach surpasses traditional methods, yielding promising and efficient outcomes for enhancing learning object reusability.

Development of a program to determine optimal settings for robot-assisted rehabilitation of the post-stroke paretic upper extremity: a simulation study

Robot-assisted therapy can effectively treat upper extremity (UE) paralysis in patients who experience a stroke. Presently, UE, as a training item, is selected according to the severity of the paralysis based on a clinician's experience. The possibility of objectively selecting robot-assisted training items based on the severity of paralysis was simulated using the two-parameter logistic model item response theory (2PLM-IRT). Sample data were generated using the Monte Carlo method with 300 random cases. This simulation analyzed sample data (categorical data with three difficulty values of 0, 1, and 2 [0: too easy, 1: adequate, and 2: too difficult]) with 71 items per case. First, the most appropriate method was selected to ensure the local independence of the sample data necessary to use 2PLM-IRT. The method was to exclude items with low response probability (maximum response probability) within a pair in the Quality of Compensatory Movement Score (QCM) 1-point item difficulty curve, items with low item information content within a pair in the QCM 1-point item difficulty curve, and items with low item discrimination. Second, 300 cases were analyzed to determine the most appropriate model (one-parameter or two-parameter item response therapy) to be used and the most favored method to establish local independence. We also examined whether robotic training items could be selected according to the severity of paralysis based on the ability of a person (θ) in the sample data as calculated by 2PLM-IRT. Excluding items with low response probability (maximum response probability) in a pair in the categorical data 1-point item difficulty curve was effective in ensuring local independence. Additionally, to ensure local independence, the number of items should be reduced to 61 from 71, indicating that the 2PLM-IRT was an appropriate model. The ability of a person (θ) calculated by 2PLM-IRT suggested that seven training items could be estimated from 300 cases according to severity. This simulation made it possible to objectively estimate the training items according to the severity of paralysis in a sample of approximately 300 cases using this model.

Effective practice and instruction: A skill acquisition framework for excellence

We revisit an agenda that was outlined in a previous paper in this journal focusing on the importance of skill acquisition research in enhancing practice and instruction in sport. In this current narrative review, we reflect on progress made since our original attempt to highlight several potential myths that appeared to exist in coaching, implying the existence of a theory-practice divide. Most notably, we present five action points that would impact positively on coaches and practitioners working to improve skill learning across sports, as well as suggesting directions for research. We discuss the importance of practice quality in enhancing learning and relate this concept to notions of optimising challenge. We discuss how best to assess learning, the right balance between repetition and practice that is specific to competition, the relationship between practice conditions, instructions, and individual differences, and why a more "hands-off" approach to instruction may have advantages over more "hands-on" methods. These action points are considered as a broad framework for advancing skill acquisition for excellence (SAFE) in applied practice. We conclude by arguing the need for increased collaboration between researchers, coaches, and other sport practitioners.

Pushing the Bounds of Bounded Optimality and Rationality

All forms of cognition, whether natural or artificial, are subject to constraints of their computing architecture. This assumption forms the tenet of virtually all general theories of cognition, including those deriving from bounded optimality and bounded rationality. In this letter, we highlight an unresolved puzzle related to this premise: what are these constraints, and why are cognitive architectures subject to cognitive constraints in the first place? First, we lay out some pieces along the puzzle edge, such as computational tradeoffs inherent to neural architectures that give rise to rational bounds of cognition. We then outline critical next steps for characterizing cognitive bounds, proposing that some of these bounds can be subject to modification by cognition and, as such, are part of what is being optimized when cognitive agents decide how to allocate cognitive resources. We conclude that these emerging views may contribute to a more holistic perspective on the nature of cognitive bounds, as well as their alteration subject to cognition.

Assessing evidence accumulation and rule learning in humans with an online game

Evidence accumulation, an essential component of perception and decision making, is frequently studied with psychophysical tasks involving noisy or ambiguous stimuli. In these tasks, participants typically receive verbal or written instructions that describe the strategy that should be used to guide decisions. Although convenient and effective, explicit instructions can influence learning and decision making strategies and can limit comparisons with animal models, in which behaviors are reinforced through feedback. Here, we developed an online video game and nonverbal training pipeline, inspired by pulse-based tasks for rodents, as an alternative to traditional psychophysical tasks used to study evidence accumulation. Using this game, we collected behavioral data from hundreds of participants trained with an explicit description of the decision rule or with experiential feedback. Participants trained with feedback alone learned the game rules rapidly and used strategies and displayed biases similar to those who received explicit instructions. Finally, by leveraging data across hundreds of participants, we show that perceptual judgments were well described by an accumulation process in which noise scaled nonlinearly with evidence, consistent with previous animal studies but inconsistent with diffusion models widely used to describe perceptual decisions in humans. These results challenge the conventional description of the accumulation process and suggest that online games provide a valuable platform to examine perceptual decision making and learning in humans. In addition, the feedback-based training pipeline developed for this game may be useful for evaluating perceptual decision making in human populations with difficulty following verbal instructions.NEW & NOTEWORTHY Perceptual uncertainty sets critical constraints on our ability to accumulate evidence and make decisions; however, its sources remain unclear. We developed a video game, and feedback-based training pipeline, to study uncertainty during decision making. Leveraging choices from hundreds of subjects, we demonstrate that human choices are inconsistent with popular diffusion models of human decision making and instead are best fit by models in which perceptual uncertainty scales nonlinearly with the strength of sensory evidence.

Average reward rates enable motivational transfer across independent reinforcement learning tasks

Outcomes and feedbacks on performance may influence behavior beyond the context in which it was received, yet it remains unclear what neurobehavioral mechanisms may account for such lingering influences on behavior. The average reward rate (ARR) has been suggested to regulate motivated behavior, and was found to interact with dopamine-sensitive cognitive processes, such as vigilance and associative memory encoding. The ARR could therefore provide a bridge between independent tasks when these are performed in temporal proximity, such that the reward rate obtained in one task could influence performance in a second subsequent task. Reinforcement learning depends on the coding of prediction error signals by dopamine neurons and their downstream targets, in particular the nucleus accumbens. Because these brain regions also respond to changes in ARR, reinforcement learning may be vulnerable to changes in ARR. To test this hypothesis, we designed a novel paradigm in which participants (n = 245) performed two probabilistic reinforcement learning tasks presented in interleaved trials. The ARR was controlled by an "induction" task which provided feedback with a low (p = 0.58), a medium (p = 0.75), or a high probability of reward (p = 0.92), while the impact of ARR on reinforcement learning was tested by a second "reference" task with a constant reward probability (p = 0.75). We find that performance was significantly lower in the reference task when the induction task provided low reward probabilities (i.e., during low levels of ARR), as compared to the medium and high ARR conditions. Behavioral modeling further revealed that the influence of ARR is best described by models which accumulates average rewards (rather than average prediction errors), and where the ARR directly modulates the prediction error signal (rather than affecting learning rates or exploration). Our results demonstrate how affective information in one domain may transfer and affect motivated behavior in other domains. These findings are particularly relevant for understanding mood disorders, but may also inform abnormal behaviors attributed to dopamine dysfunction.

An analytical theory of curriculum learning in teacher-student networks

In animals and humans, curriculum learning-presenting data in a curated order-is critical to rapid learning and effective pedagogy. A long history of experiments has demonstrated the impact of curricula in a variety of animals but, despite its ubiquitous presence, a theoretical understanding of the phenomenon is still lacking. Surprisingly, in contrast to animal learning, curricula strategies are not widely used in machine learning and recent simulation studies reach the conclusion that curricula are moderately effective or even ineffective in most cases. This stark difference in the importance of curriculum raises a fundamental theoretical question: when and why does curriculum learning help? In this work, we analyse a prototypical neural network model of curriculum learning in the high-dimensional limit, employing statistical physics methods. We study a task in which a sparse set of informative features are embedded amidst a large set of noisy features. We analytically derive average learning trajectories for simple neural networks on this task, which establish a clear speed benefit for curriculum learning in the online setting. However, when training experiences can be stored and replayed (for instance, during sleep), the advantage of curriculum in standard neural networks disappears, in line with observations from the deep learning literature. Inspired by synaptic consolidation techniques developed to combat catastrophic forgetting, we propose curriculum-aware algorithms that consolidate synapses at curriculum change points and investigate whether this can boost the benefits of curricula. We derive generalisation performance as a function of consolidation strength (implemented as an L 2 regularisation/elastic coupling connecting learning phases), and show that curriculum-aware algorithms can yield a large improvement in test performance. Our reduced analytical descriptions help reconcile apparently conflicting empirical results, trace regimes where curriculum learning yields the largest gains, and provide experimentally-accessible predictions for the impact of task parameters on curriculum benefits. More broadly, our results suggest that fully exploiting a curriculum may require explicit adjustments in the loss.

Don't watch your step: gaze behavior adapts with practice of a target stepping task

Vision plays a vital role in locomotor learning, providing feedback information to correct movement errors, and feedforward information to inform learned movement plans. Gaze behavior, or the distribution of fixation locations, can quantify how visual information is used during the motor learning process. How gaze behavior adapts during motor learning and in response to changing motor performance is poorly understood. This study examines if and how an individual's gaze behavior adapts during a sequence learning, target stepping task. We monitored the gaze behavior of 12 healthy young adults while they walked on a treadmill and attempted to precisely step on moving targets that were separated by variable distances (80%, 100%, and 120% of preferred step length). Participants completed a total of 11 trial blocks of 102 steps each. We hypothesized that both mean fixation distance would increase (participants would look farther ahead), and step error would decrease with experience. Following practice, participants significantly increased their fixation distance (P < 0.001) by 0.27 ± 0.18 steps and decreased their step error (P < 0.001) by 4.0 ± 1.7 cm, supporting our hypothesis. Our results suggest that early in the learning process, participants gaze behavior emphasized gathering visual information necessary for feedback motor control. As motor performance improved with experience, participants shifted their gaze fixation farther ahead placing greater emphasis on the visual information used for feedforward motor control. These findings provide important information about how gaze behavior changes in parallel with improvements in walking performance.NEW & NOTEWORTHY People consistently vary how they use visual information to inform walking. However, what drives this variation and how sampled visual information changes with locomotor learning is not well understood. Here, we find that gaze fixation locations moved farther ahead while step error decreases as participants practice a target stepping task. The results suggest that participants increasingly used a feedforward locomotor control strategy with practice.

The global contribution of invasive vertebrate eradication as a key island restoration tool

Islands are global hotspots for biodiversity and extinction, representing ~ 5% of Earth's land area alongside 40% of globally threatened vertebrates and 61% of global extinctions since the 1500s. Invasive species are the primary driver of native biodiversity loss on islands, though eradication of invasive species from islands has been effective at halting or reversing these trends. A global compendium of this conservation tool is essential for scaling best-practices and enabling innovations to maximize biodiversity outcomes. Here, we synthesize over 100 years of invasive vertebrate eradications from islands, comprising 1550 eradication attempts on 998 islands, with an 88% success rate. We show a significant growth in eradication activity since the 1980s, primarily driven by rodent eradications. The annual number of eradications on islands peaked in the mid-2000s, but the annual area treated continues to rise dramatically. This trend reflects increases in removal efficacy and project complexity, generating increased conservation gains. Our synthesis demonstrates the collective contribution of national interventions towards global biodiversity outcomes. Further investment in invasive vertebrate eradications from islands will expand biodiversity conservation while strengthening biodiversity resilience to climate change and creating co-benefits for human societies.

Using Large-Scale Sensor Data to Test Factors Predictive of Perseverance in Home Movement Rehabilitation: Optimal Challenge and Steady Engagement

Persevering with home rehabilitation exercise is a struggle for millions of people in the US each year. A key factor that may influence motivation to engage with rehabilitation exercise is the challenge level of the assigned exercises, but this hypothesis is currently supported only by subjective, self-report. Here, we studied the relationship between challenge level and perseverance using long-term, self-determined exercise patterns of a large number of individuals (N = 2,581) engaging in home rehabilitation with a sensor-based exercise system without formal supervision. FitMi is comprised of two puck-like sensors and a library of 40 gamified exercises for the hands, arms, trunk, and legs that are designed for people recovering from a stroke. We found that individuals showed the greatest perseverance with the system over a 2-month period if they had (1) a moderate level of motor impairment and (2) high but not perfect success during the 1st week at completing the exercise game. Further, a steady usage pattern (vs. accelerating or decelerating use) was associated with more overall exercise, and declines in exercise amount over time were associated with exponentially declining session initiation probability rather than decreasing amounts of exercise once a session was initiated. These findings confirm that an optimized challenge level and regular initiation of exercise sessions predict achievement of a greater amount of overall rehabilitation exercise in a group of users of commercial home rehabilitation technology and suggest how home rehabilitation programs and exercise technologies can be optimized to promote perseverance.

Proteome-wide and matrisome-specific atlas of the human ovary computes fertility biomarker candidates and open the way for precision oncofertility

Our modern era is witnessing an increasing infertility rate worldwide. Although some of the causes can be attributed to our modern lifestyle (e.g., persistent organic pollutants, late pregnancy), our knowledge of the human ovarian tissue has remained limited and insufficient to reverse the infertility statistics. Indeed, all efforts have been focused on the endocrine and cellular function in support of the cell theory that dates back to the 18th century, while the human ovarian matrisome is still under-described. Hereby, we unveil the extracellular side of the story during different periods of the ovary life, demonstrating that follicle survival and development, and ultimately fertility, would not be possible without its involvement. We examined the human ovarian matrisome and described its remodeling from prepuberty until menopause, creating the first ovarian proteomic codex. Here, we confidently identified and quantified 98 matrisome proteins present in the three ovary groups. Among them, 26 were expressed differently among age groups, delineating a peculiar matrisomal fingerprint at each stage. Such proteins could be potential biomarkers phenotyping ovarian ECM at each age phase of female reproductive life. Beyond proteomics, our study presents a unique approach to understanding the data and depicting the spatiotemporal ECM-intracellular signaling networks and remodeling with age through imaging, advanced text-mining based on natural language processing technology, machine learning, and data sonification. Our findings provide essential context for healthy ovarian physiology, identifying and characterizing disease states, and recapitulating physiological tissues or development in vitro. This comprehensive proteomics analysis represents the ovarian proteomic codex and contributes to an improved understanding of the critical roles that ECM plays throughout the ovarian life span.

An extended challenge-based framework for practice design in sports coaching

The challenge-point framework as a model for thinking about motor learning was first proposed in 2004. Although it has been well-cited, surprisingly this framework has not made its way into much of the applied sport science literature. One of the reasons for this omission is that the original framework had not been encapsulated into a paper accessible for sports practitioners. The framework had mostly a theoretical focus, providing a mechanistic summary of motor learning research. Our aims in this paper were to explain and elaborate on the challenge point framework to present an applied framework guiding practice design. We connect the framework to other theories that involve predictive coding, where information is attended when it disconfirms current predictions, providing a strong signal for learning. We also consider how two new dimensions (learners' motivation and practice specificity) need to be considered when designing practice settings. By moving around the different dimensions of functional difficulty, motivation, and specificity, coaches can optimize practice to achieve different learning goals. Specifically, we present three general "types" of practice: practice to learn, to transfer to competition, and to maintain current skills. Practical examples are given to illustrate how this framework can inform coach practice.

Long-Term Motor Learning in the "Wild" With High Volume Video Game Data

Motor learning occurs over long periods of practice during which motor acuity, the ability to execute actions more accurately, precisely, and in less time, improves. Laboratory-based studies of motor learning are typically limited to a small number of participants and a time frame of minutes to several hours per participant. There is a need to assess the generalizability of theories and findings from lab-based motor learning studies on larger samples and time scales. In addition, laboratory-based studies of motor learning use relatively simple motor tasks which participants are unlikely to be intrinsically motivated to learn, limiting the interpretation of their findings in more ecologically valid settings ("in the wild"). We studied the acquisition and longitudinal refinement of a complex sensorimotor skill embodied in a first-person shooter video game scenario, with a large sample size (N = 7174, 682,564 repeats of the 60 s game) over a period of months. Participants voluntarily practiced the gaming scenario for up to several hours per day up to 100 days. We found improvement in performance accuracy (quantified as hit rate) was modest over time but motor acuity (quantified as hits per second) improved considerably, with 40-60% retention from 1 day to the next. We observed steady improvements in motor acuity across multiple days of video game practice, unlike most motor learning tasks studied in the lab that hit a performance ceiling rather quickly. Learning rate was a non-linear function of baseline performance level, amount of daily practice, and to a lesser extent, number of days between practice sessions. In addition, we found that the benefit of additional practice on any given day was non-monotonic; the greatest improvements in motor acuity were evident with about an hour of practice and 90% of the learning benefit was achieved by practicing 30 min per day. Taken together, these results provide a proof-of-concept in studying motor skill acquisition outside the confines of the traditional laboratory, in the presence of unmeasured confounds, and provide new insights into how a complex motor skill is acquired in an ecologically valid setting and refined across much longer time scales than typically explored.

Evaluating students' engagement with an online learning environment during and after COVID-19 related school closures: A survival analysis approach

Background

Due to the COVID-19 pandemic schools all over the world were closed and thereby students had to be instructed from distance. Consequently, the use of online learning environments for online distance learning increased massively. However, the perseverance of using online learning environments during and after school closures remains to be investigated.

Method

We examined German students’ (n ≈ 300,000 students; ≈ 18 million computed problem sets) engagement in an online learning environment for mathematics by means of survival analysis.

Results

We observed that the total number of students who registered increased considerably during and after school closures compared to the previous three years. Importantly, however, the proportion of students engaged also decreased more rapidly over time.

Conclusion

The application of survival analysis provided valuable insights into students’ engagement in online learning - or conversely students’ increased dropout rates - over time. Its application to educational settings allows to address a broader range of questions on students’ engagement in online learning environments in the future.

Application of the Challenge Point Framework During Treatment of Speech Sound Disorders

Purpose The purpose of this article is to provide trial-by-trial practice performance data in relation to learning (outcome probe data) as collected from 18 treatment sessions provided to children with severe speech sound disorders. The data illustrate the practice-learning paradox: Specific, perfect practice performance is not required for speech production learning. Method We detailed how nine student speech-language pathologists (SSLPs) implemented and modified the motor learning practice conditions to reach a proposed challenge point during speech practice. Eleven participants diagnosed with a severe speech sound disorder received high-intensity speech therapy 3 times per week for 6 weeks. SSLPs implemented treatment procedures with the goal of achieving at least 100 practice trials while manipulating practice parameters to maintain practice at the challenge point. Specifically, child performance was monitored for accuracy in five-trial increments, and practice parameters were changed to increase functional task difficulty when the child's performance was high (four or five correct responses) or to decrease functional task difficulty when the child's performance was low (fewer than four correct responses). The practice stimulus, type and amount of feedback, structure of practice, or level of support might be changed to ensure practice at the challenge point. Results On average, the children achieved 102 practice trials per session at a level of 58% correct responses. Fast achievement of connected speech with the lowest amount of support was associated with high scores on generalization probes. Even with high levels of error during practice, the children improved percent consonants correct with maintenance of learning 3 months posttreatment. Conclusion The results of this study show that it may not be necessary to overpractice or maintain a high degree of performance accuracy during treatment sessions to achieve transfer and retention of speech production learning.

Behavioral, Physiological, and Neural Signatures of Surprise during Naturalistic Sports Viewing

Surprise signals a discrepancy between past and current beliefs. It is theorized to be linked to affective experiences, the creation of particularly resilient memories, and segmentation of the flow of experience into discrete perceived events. However, the ability to precisely measure naturalistic surprise has remained elusive. We used advanced basketball analytics to derive a quantitative measure of surprise and characterized its behavioral, physiological, and neural correlates in human subjects observing basketball games. We found that surprise was associated with segmentation of ongoing experiences, as reflected by subjectively perceived event boundaries and shifts in neocortical patterns underlying belief states. Interestingly, these effects differed by whether surprising moments contradicted or bolstered current predominant beliefs. Surprise also positively correlated with pupil dilation, activation in subcortical regions associated with dopamine, game enjoyment, and long-term memory. These investigations support key predictions from event segmentation theory and extend theoretical conceptualizations of surprise to real-world contexts.

Dynamic Data Selection for Curriculum Learning via Ability Estimation

Curriculum learning methods typically rely on heuristics to estimate the difficulty of training examples or the ability of the model. In this work, we propose replacing difficulty heuristics with learned difficulty parameters. We also propose Dynamic Data selection for Curriculum Learning via Ability Estimation (DDaCLAE), a strategy that probes model ability at each training epoch to select the best training examples at that point. We show that models using learned difficulty and/or ability outperform heuristic-based curriculum learning models on the GLUE classification tasks.

From Knowledge Transmission to Knowledge Construction: A Step towards Human-Like Active Learning

Machines usually employ a guess-and-check strategy to analyze data: they take the data, make a guess, check the answer, adjust it with regard to the correct one if necessary, and try again on a new data set. An active learning environment guarantees better performance while training on less, but carefully chosen, data which reduces the costs of both annotating and analyzing large data sets. This issue becomes even more critical for deep learning applications. Human-like active learning integrates a variety of strategies and instructional models chosen by a teacher to contribute to learners’ knowledge, while machine active learning strategies lack versatile tools for shifting the focus of instruction away from knowledge transmission to learners’ knowledge construction. We approach this gap by considering an active learning environment in an educational setting. We propose a new strategy that measures the information capacity of data using the information function from the four-parameter logistic item response theory (4PL IRT). We compared the proposed strategy with the most common active learning strategies—Least Confidence and Entropy Sampling. The results of computational experiments showed that the Information Capacity strategy shares similar behavior but provides a more flexible framework for building transparent knowledge models in deep learning.

Brain-Machine Neurofeedback: Robotics or Electrical Stimulation?

Neurotechnology such as brain-machine interfaces (BMI) are currently being investigated as training devices for neurorehabilitation, when active movements are no longer possible. When the hand is paralyzed following a stroke for example, a robotic orthosis, functional electrical stimulation (FES) or their combination may provide movement assistance; i.e., the corresponding sensory and proprioceptive neurofeedback is given contingent to the movement intention or imagination, thereby closing the sensorimotor loop. Controlling these devices may be challenging or even frustrating. Direct comparisons between these two feedback modalities (robotics vs. FES) with regard to the workload they pose for the user are, however, missing. Twenty healthy subjects controlled a BMI by kinesthetic motor imagery of finger extension. Motor imagery-related sensorimotor desynchronization in the EEG beta frequency-band (17–21 Hz) was turned into passive opening of the contralateral hand by a robotic orthosis or FES in a randomized, cross-over block design. Mental demand, physical demand, temporal demand, performance, effort, and frustration level were captured with the NASA Task Load Index (NASA-TLX) questionnaire by comparing these workload components to each other (weights), evaluating them individually (ratings), and estimating the respective combinations (adjusted workload ratings). The findings were compared to the task-related aspects of active hand movement with EMG feedback. Furthermore, both feedback modalities were compared with regard to their BMI performance. Robotic and FES feedback had similar workloads when weighting and rating the different components. For both robotics and FES, mental demand was the most relevant component, and higher than during active movement with EMG feedback. The FES task led to significantly more physical (p = 0.0368) and less temporal demand (p = 0.0403) than the robotic task in the adjusted workload ratings. Notably, the FES task showed a physical demand 2.67 times closer to the EMG task, but a mental demand 6.79 times closer to the robotic task. On average, significantly more onsets were reached during the robotic as compared to the FES task (17.22 onsets, SD = 3.02 vs. 16.46, SD = 2.94 out of 20 opportunities; p = 0.016), even though there were no significant differences between the BMI classification accuracies of the conditions (p = 0.806; CI = −0.027 to −0.034). These findings may inform the design of neurorehabilitation interfaces toward human-centered hardware for a more natural bidirectional interaction and acceptance by the user.

Algorithm-Based Practice Schedule and Task Similarity Enhance Motor Learning in Older Adults

According to the challenge point framework, task difficulty has to be appropriate to learner skill level. The pure blocked or random practice controls the task difficulty during practice monotonically. Therefore, the purpose of this study was to investigate the effect of algorithm-based practice schedule and task similarity on motor learning in older adults. For this purpose, 60 older adults were randomly assigned into six groups of blocked-similar, algorithm-similar, random-similar, blocked-dissimilar, algorithm-dissimilar, and random-dissimilar. Sequential motor tasks were used for learning. Participants practiced absolute timing goals in similar (1350, 1500, 1650 ms) or dissimilar (1050, 1500, 1950 ms) conditions according to their practice schedule. Twenty-four hours after the acquisition phase, retention, and transfer tests were performed. Algorithm-practice was a hybrid practice schedule (blocked, serial, and random practice in forward/backward switching) that switching the schedules was according to error trial number (n ≤ 33%) in each block based on error range of absolute timing goals (± 5%). The results showed that the blocked-practice outperforms the other groups during the acquisition phase, whereas the algorithm-practice outperforms the other groups in retention and transfer in both similar and dissimilar conditions. These findings were discussed according to the challenge point framework.

Neural Mechanisms of the Contextual Interference Effect and Parameter Similarity on Motor Learning in Older Adults: An EEG Study

The purpose of this study was to investigate the neural mechanisms of the contextual interference effect (CIE) and parameter similarity on motor learning in older adults. Sixty older adults (mean age, 67.68 ± 3.95 years) were randomly assigned to one of six experimental groups: blocked-similar, algorithm-similar, random-similar, blocked-dissimilar, algorithm-dissimilar, and random-dissimilar. Algorithm practice was a hybrid practice schedule (a combination of blocked, serial, and random practice) that switching between practice schedules were based on error trial number, ≤33%. The sequential motor task was used to record the absolute timing for the absolute timing goals (ATGs). In similar conditions, the participants’ performance was near ATGs (1,350, 1,500, 1,650 ms) and in dissimilar conditions, they performed far ATGs (1,050, 1,500, 1,950 ms) with the same spatial sequence for all groups. EEG signals were continuously collected during the acquisition phase and delayed retention. Data were analyzed in different bands (alpha and beta) and scalp locations (frontal: Fp1, Fp2, F3, F4; central: C3, C4; and parietal: P3, P4) with repeated measures on the last factor. The analyses were included motor preparation and intertrial interval (motor evaluation) periods in the first six blocks and the last six blocks, respectively. The results of behavioral data indicated that algorithm practice resulted in medium error related to classic blocked and random practice during the acquisition, however, algorithm practice outperformed the classic blocked and random practice in the delayed retention test. The results of EEG data demonstrated that algorithm practice, due to optimal activity in the frontal lobe (medium alpha and beta activation at prefrontal), resulted in increased activity of sensorimotor areas (high alpha activation at C3 and P4) in older adults. Also, EEG data showed that similar conditions could affect the intertrial interval period (medium alpha and beta activation in frontal in the last six-block), while the dissimilar conditions could affect the motor preparation period (medium alpha and beta activation in frontal in the first six-block). In conclusion, algorithm practice can enhance motor learning and optimize the efficiency of brain activity, resulting in the achievement of a desirable goal in older adults.

A Functional Contextualist Approach to Mastery Learning in Vocational Education and Training

Along with technological progress, vocational education and training (VET) is consistently changing. Workforce disruption has serious consequences for workers and international economies, often requiring adults to transition into different occupations or to upskill to maintain employment. We review recent literature covering VET trends, theoretical considerations for the 21st century, and present an approach to workforce training to help workers not only learn necessary skills but also become adaptable to constant change. We suggest a functional contextualist approach to mastery learning achieves this aim. Specifically, we offer suggestions for pedagogy that not only develop skills but also encourage higher order thinking. Within a novice to expert continuum, we suggest deliberate practice, mental simulation, and reflective meaning making as methods to achieve efficiency and transfer-learning outcomes relevant to a changing workforce. This approach recognizes that learning is context bound and should promote broader human capabilities that support both employability and the continuing development of life literacies.