Can educational video resources improve learning when used to augment traditional teaching of clinical examination? A randomized control trial of novice medical students.

BACKGROUND: Good clinical examination skills can both increase the quality of patient care and reduce its cost. A previous study by our group demonstrated that face-to-face training is the gold standard for teaching these skills. It is unclear if high quality educational videos can augment this teaching. METHODS: Forty-two Medical Students naïve to large joint examination were recruited and block randomised to two groups. The control group had face-to-face teaching alone. The intervention group had their teaching augmented with a custom educational video accessed via a web portal. Participants were assessed on their examination of a large joint using a previously standardised assessment tool at baseline and 7 days post intervention. Assessors were blinded to intervention type. RESULTS: There was no significant difference in the mean baseline scores. Mean baseline scores were 3.35 (11.2%, SD = 2.2, SE = 0.49) for the face-to-face only group and 2.65 (8.8%, SD = 1.39, SE = 0.31) for the video adjunct group [p = 0.137]. There was a significant difference in the improvement in score after intervention between each group [p = 0.005]. The mean improvement in score was 15.42 (SD = 5.64, SE = 1.29) for the face-to-face only group and 20.68 (SD = 4.33,SE = 0.99) for the video adjunct group. CONCLUSION: When used as an adjunct to more traditional face-to-face teaching methods, a custom-made educational video significantly improves the teaching of clinical examination skills and there is a role for these resources in augmenting traditional teaching methods.

Measuring motion-to-photon latency for sensorimotor experiments with virtual reality systems.

Consumer virtual reality (VR) systems are increasingly being deployed in research to study sensorimotor behaviors, but properties of such systems require verification before being used as scientific tools. The 'motion-to-photon' latency (the lag between a user making a movement and the movement being displayed within the display) is a particularly important metric as temporal delays can degrade sensorimotor performance. Extant approaches to quantifying this measure have involved the use of bespoke software and hardware and produce a single measure of latency and ignore the effect of the motion prediction algorithms used in modern VR systems. This reduces confidence in the generalizability of the results. We developed a novel, system-independent, high-speed camera-based latency measurement technique to co-register real and virtual controller movements, allowing assessment of how latencies change through a movement. We applied this technique to measure the motion-to-photon latency of controller movements in the HTC Vive, Oculus Rift, Oculus Rift S, and Valve Index, using the Unity game engine and SteamVR. For the start of a sudden movement, all measured headsets had mean latencies between 21 and 42 ms. Once motion prediction could account for the inherent delays, the latency was functionally reduced to 2-13 ms, and our technique revealed that this reduction occurs within ~25-58 ms of movement onset. Our findings indicate that sudden accelerations (e.g., movement onset, impacts, and direction changes) will increase latencies and lower spatial accuracy. Our technique allows researchers to measure these factors and determine the impact on their experimental design before collecting sensorimotor data from VR systems.

Distinct Neural Signatures of Outcome Monitoring After Selection and Execution Errors.

Losing a point in tennis could result from poor shot selection or faulty stroke execution. To explore how the brain responds to these different types of errors, we examined feedback-locked EEG activity while participants completed a modified version of a standard three-armed bandit probabilistic reward task. Our task framed unrewarded outcomes as the result of either errors of selection or errors of execution. We examined whether amplitude of a medial frontal negativity (the feedback-related negativity [FRN]) was sensitive to the different forms of error attribution. Consistent with previous reports, selection errors elicited a large FRN relative to rewards, and amplitude of this signal correlated with behavioral adjustment after these errors. A different pattern was observed in response to execution errors. These outcomes produced a larger FRN, a frontocentral attenuation in activity preceding this component, and a subsequent enhanced error positivity in parietal sites. Notably, the only correlations with behavioral adjustment were with the early frontocentral attenuation and amplitude of the parietal signal; FRN differences between execution errors and rewarded trials did not correlate with subsequent changes in behavior. Our findings highlight distinct neural correlates of selection and execution error processing, providing insight into how the brain responds to the different classes of error that determine future action.

Sensorimotor ability and inhibitory control independently predict attainment in mathematics in children and adolescents.

We previously linked interceptive timing performance to mathematics attainment in 5- to 11-yr-old children, which we attributed to the neural overlap between spatiotemporal and numerical operations. This explanation implies that the relationship should persist through the teenage years. Here, we replicated this finding in adolescents (n = 200, 11-15 yr). However, an alternative explanation is that sensorimotor proficiency and academic attainment are both consequences of executive function. To assess this competing hypothesis, we developed a measure of a core executive function, inhibitory control, from the kinematic data. We combined our new adolescent data with the original children's data (total n = 568), performing a novel analysis controlling for our marker of executive function. We found that the relationship between mathematics and interceptive timing persisted at all ages. These results suggest a distinct functional link between interceptive timing and mathematics that operates independently of our measure of executive function.NEW & NOTEWORTHY Previous research downplays the role of sensorimotor skills in the development of higher-order cognitive domains such as mathematics: using inadequate sensorimotor measures, differences in "executive function" account for any shared variance. Utilizing a high-resolution, kinematic measure of a sensorimotor skill previously linked to mathematics attainment, we show that inhibitory control alone cannot account for this relationship. The practical implication is that the development of children's sensorimotor skills must be considered in their intellectual development.

The impact of acoustic stimulation during sleep on memory and sleep architecture: A meta-analysis.

The relationship between sleep and cognition has long been recognized, with slow-wave sleep thought to play a critical role in long-term memory consolidation. Recent research has presented the possibility that non-invasive acoustic stimulation during sleep could enhance memory consolidation. Herein, we report a random-effects model meta-analysis examining the impact of this intervention on memory and sleep architecture in healthy adults. Sixteen studies were identified through a systematic search. We found a medium significant effect of acoustic stimulation on memory task performance (g = 0.68, p = .031) in young adults <35 years of age, but no statistically significant effect in adults >35 years of age (g = -0.83, p = .223). In young adults, there was a large statistically significant effect for declarative memory tasks (g = 0.87, p = .014) but no effect for non-declarative tasks (g = -0.25, p = .357). There were no statistically significant differences in polysomnography-derived sleep architecture values between sham and stimulation conditions in either young or older adults. Based on these results, it appears that acoustic stimulation during sleep may only be an effective intervention for declarative memory consolidation in young adults. However, the small number of studies in this area, their small sample sizes, the short-term nature of most investigations and the high between-studies heterogeneity highlight a need for high-powered and long-term experiments to better elucidate, and subsequently maximise, any potential benefits of this novel approach.

Performance Evaluation of a Smart Bed Technology against Polysomnography.

The Sleep Number smart bed uses embedded ballistocardiography, together with network connectivity, signal processing, and machine learning, to detect heart rate (HR), breathing rate (BR), and sleep vs. wake states. This study evaluated the performance of the smart bed relative to polysomnography (PSG) in estimating epoch-by-epoch HR, BR, sleep vs. wake, mean overnight HR and BR, and summary sleep variables. Forty-five participants (aged 22-64 years; 55% women) slept one night on the smart bed with standard PSG. Smart bed data were compared to PSG by Bland-Altman analysis and Pearson correlation for epoch-by-epoch HR and epoch-by-epoch BR. Agreement in sleep vs. wake classification was quantified using Cohen's kappa, ROC analysis, sensitivity, specificity, accuracy, and precision. Epoch-by-epoch HR and BR were highly correlated with PSG (HR: r = 0.81, |bias| = 0.23 beats/min; BR: r = 0.71, |bias| = 0.08 breaths/min), as were estimations of mean overnight HR and BR (HR: r = 0.94, |bias| = 0.15 beats/min; BR: r = 0.96, |bias| = 0.09 breaths/min). Calculated agreement for sleep vs. wake detection included kappa (prevalence and bias-adjusted) = 0.74 ± 0.11, AUC = 0.86, sensitivity = 0.94 ± 0.05, specificity = 0.48 ± 0.18, accuracy = 0.86 ± 0.11, and precision = 0.90 ± 0.06. For all-night summary variables, agreement was moderate to strong. Overall, the findings suggest that the Sleep Number smart bed may provide reliable metrics to unobtrusively characterize human sleep under real life-conditions.

Brain-computer interface robotics for hand rehabilitation after stroke: a systematic review.

BACKGROUND: Hand rehabilitation is core to helping stroke survivors regain activities of daily living. Recent studies have suggested that the use of electroencephalography-based brain-computer interfaces (BCI) can promote this process. Here, we report the first systematic examination of the literature on the use of BCI-robot systems for the rehabilitation of fine motor skills associated with hand movement and profile these systems from a technical and clinical perspective. METHODS: A search for January 2010-October 2019 articles using Ovid MEDLINE, Embase, PEDro, PsycINFO, IEEE Xplore and Cochrane Library databases was performed. The selection criteria included BCI-hand robotic systems for rehabilitation at different stages of development involving tests on healthy participants or people who have had a stroke. Data fields include those related to study design, participant characteristics, technical specifications of the system, and clinical outcome measures. RESULTS: 30 studies were identified as eligible for qualitative review and among these, 11 studies involved testing a BCI-hand robot on chronic and subacute stroke patients. Statistically significant improvements in motor assessment scores relative to controls were observed for three BCI-hand robot interventions. The degree of robot control for the majority of studies was limited to triggering the device to perform grasping or pinching movements using motor imagery. Most employed a combination of kinaesthetic and visual response via the robotic device and display screen, respectively, to match feedback to motor imagery. CONCLUSION: 19 out of 30 studies on BCI-robotic systems for hand rehabilitation report systems at prototype or pre-clinical stages of development. We identified large heterogeneity in reporting and emphasise the need to develop a standard protocol for assessing technical and clinical outcomes so that the necessary evidence base on efficiency and efficacy can be developed.

Capturing the non-technical skills of a technical skills trainer (NTS-TeST) during simulation.

OBJECTIVE: To develop an assessment instrument that can be used as a comprehensive feedback record to convey to a trainer the non-technical aspects of skill acquisition and training. METHODS: The instrument was developed across three rounds. In Round 1, 6 endourological consultants undertook a modified Delphi process. Round 2 included 10 trainers who assessed each question's relevance and practicability. Round 3 involved a pilot study with fifteen urology residents who participated in a technical skills simulation session with the incorporation of the instrument. We report the content, face, and construct validity, and the internal consistency of an NTS instrument for trainers. RESULTS: The instrument had a consistent and a high positive average for each of the 4 sections of the instrument, regardless of the type of user. Positive Spearman's correlation coefficients (0.02 to .64) for content validity and Cronbach's alpha (a = 0.70) indicated good validity and moderate reliability of the instrument. CONCLUSION: We propose a novel NTS instrument for trainers during a simulation. This instrument can be used for benchmarking the quality of technical skills simulation training.

Does learning the Qur'an improve memory capacity? Practical and theoretical implications.

Our understanding of human memory has gained greatly from the study of individuals with impaired memory but rather less from outstandingly high levels of memory performance. Exceptions include the case of London taxi drivers whose extensive route learning results in modification of their hippocampus. Our study involves a group whose extensive verbal learning potentially provides a similar natural experiment. The Muslim faith encourages followers to memorise the whole of the Qur'an, some 77,449 words in its classic Arabic form. Successful memorisers are known as "Hafiz". We tested 10 Hafiz, 12 background-matched Muslim controls and 10 non-Muslim participants, on their detailed knowledge of the Qur'an and on their performance on standard measures of verbal and visuospatial learning. We found no differences between the three groups in their capacity to memorise verbal or visuospatial material and hence no evidence of generalisation of learning capacity in the Hafiz group. More surprisingly, however, half of the Hafiz group did not understand Arabic but were equivalent in Qur'anic memory to those who did. Given the importance that meaning is typically assumed to play in long-term memory, this was unexpected. We discuss the practical and theoretical implications of these results for verbal memory and long-term learning.

Studying human behavior with virtual reality: The Unity Experiment Framework.

Virtual reality (VR) systems offer a powerful tool for human behavior research. The ability to create three-dimensional visual scenes and to measure responses to the visual stimuli enables the behavioral researcher to test hypotheses in a manner and scale that were previously unfeasible. For example, a researcher wanting to understand interceptive timing behavior might wish to violate Newtonian mechanics so that objects can move in novel 3-D trajectories. The same researcher might wish to collect such data with hundreds of participants outside the laboratory, and the use of a VR headset makes this a realistic proposition. The difficulty facing the researcher is that sophisticated 3-D graphics engines (e.g., Unity) have been created for game designers rather than behavioral scientists. To overcome this barrier, we have created a set of tools and programming syntaxes that allow logical encoding of the common experimental features required by the behavioral scientist. The Unity Experiment Framework (UXF) allows researchers to readily implement several forms of data collection and provides them with the ability to easily modify independent variables. UXF does not offer any stimulus presentation features, so the full power of the Unity game engine can be exploited. We use a case study experiment, measuring postural sway in response to an oscillating virtual room, to show that UXF can replicate and advance upon behavioral research paradigms. We show that UXF can simplify and speed up the development of VR experiments created in commercial gaming software and facilitate the efficient acquisition of large quantities of behavioral research data.

Hitting the Target: Mathematical Attainment in Children Is Related to Interceptive-Timing Ability.

Interceptive timing is a fundamental ability underpinning numerous actions (e.g., ball catching), but its development and relationship with other cognitive functions remain poorly understood. Piaget suggested that children need to learn the physical rules that govern their environment before they can represent abstract concepts such as number and time. Thus, learning how objects move in space and time may underpin the development of related abstract representations (i.e., mathematics). To test this hypothesis, we captured objective measures of interceptive timing in 309 primary school children (5-11 years old), alongside scores for general motor skill and national standardized academic attainment. Bayesian estimation showed that interceptive timing (but not general motor capability) uniquely predicted mathematical ability even after we controlled for age, reading, and writing attainment. This finding demonstrates that interceptive timing is distinct from other motor skills with specificity in predicting childhood mathematical ability independently of other forms of attainment and motor capability.

Counting on the mental number line to make a move: sensorimotor ('pen') control and numerical processing.

Mathematics is often conducted with a writing implement. But is there a relationship between numerical processing and sensorimotor 'pen' control? We asked participants to move a stylus so it crossed an unmarked line at a location specified by a symbolic number (1-9), where number colour indicated whether the line ran left-right ('normal') or vice versa ('reversed'). The task could be simplified through the use of a 'mental number line' (MNL). Many modern societies use number lines in mathematical education and the brain's representation of number appears to follow a culturally determined spatial organisation (so better task performance is associated with this culturally normal orientation-the MNL effect). Participants (counter-balanced) completed two consistent blocks of trials, 'normal' and 'reversed', followed by a mixed block where line direction varied randomly. Experiment 1 established that the MNL effect was robust, and showed that the cognitive load associated with reversing the MNL not only affected response selection but also the actual movement execution (indexed by duration) within the mixed trials. Experiment 2 showed that an individual's motor abilities predicted performance in the difficult (mixed) condition but not the easier blocks. These results suggest that numerical processing is not isolated from motor capabilities-a finding with applied consequences.

Mental practice with interactive 3D visual aids enhances surgical performance.

BACKGROUND: Evidence suggests that Mental Practice (MP) could be used to finesse surgical skills. However, MP is cognitively demanding and may be dependent on the ability of individuals to produce mental images. In this study, we hypothesised that the provision of interactive 3D visual aids during MP could facilitate surgical skill performance. METHODS: 20 surgical trainees were case-matched to one of three different preparation methods prior to performing a simulated Laparoscopic Cholecystectomy (LC). Two intervention groups underwent a 25-minute MP session; one with interactive 3D visual aids depicting the relevant surgical anatomy (3D-MP group, n = 5) and one without (MP-Only, n = 5). A control group (n = 10) watched a didactic video of a real LC. Scores relating to technical performance and safety were recorded by a surgical simulator. RESULTS: The Control group took longer to complete the procedure relative to the 3D&MP condition (p = .002). The number of movements was also statistically different across groups (p = .001), with the 3D&MP group making fewer movements relative to controls (p = .001). Likewise, the control group moved further in comparison to the 3D&MP condition and the MP-Only condition (p = .004). No reliable differences were observed for safety metrics. CONCLUSION: These data provide evidence for the potential value of MP in improving performance. Furthermore, they suggest that 3D interactive visual aids during MP could potentially enhance performance, beyond the benefits of MP alone. These findings pave the way for future RCTs on surgical preparation and performance.

Drilling into the functional significance of stereopsis: the impact of stereoscopic information on surgical performance.

PURPOSE: One suggested advantage of human binocular vision is the facilitation of sophisticated motor control behaviours via stereopsis - but little empirical evidence exists to support this suggestion. We examined the functional significance of stereopsis by exploring whether stereopsis is used to perform a highly skilled real-world motor task essential for the occupational practice of dentistry. METHODS: We used a high fidelity virtual reality simulator to study how dentists' performance is affected by the removal of horizontal retinal image disparities under direct and indirect (mirror) observation. Thirteen qualified dentists performed a total of four different dental tasks under non-stereoscopic and stereoscopic vision conditions, with two levels of task complexity (direct and indirect observation) using a virtual reality dental simulator. RESULTS: Depth related errors were significantly higher under non-stereoscopic viewing but lateral errors did not differ between conditions. Indirect observation led to participants drilling less of the target area compared to direct viewing, but this did not interact with the stereopsis manipulation. CONCLUSIONS: The data confirm that dental practitioners use stereopsis and its presence results in improved dental performance. It remains to be determined whether individuals with stereo-deficits can compensate adequately. Nevertheless, these findings suggest an important role for stereopsis within at least one occupation and justify the design of simulators with 3D displays.

Randomised prior feedback modulates neural signals of outcome monitoring.

Substantial evidence indicates that decision outcomes are typically evaluated relative to expectations learned from relatively long sequences of previous outcomes. This mechanism is thought to play a key role in general learning and adaptation processes but relatively little is known about the determinants of outcome evaluation when the capacity to learn from series of prior events is difficult or impossible. To investigate this issue, we examined how the feedback-related negativity (FRN) is modulated by information briefly presented before outcome evaluation. The FRN is a brain potential time-locked to the delivery of decision feedback and it is widely thought to be sensitive to prior expectations. We conducted a multi-trial gambling task in which outcomes at each trial were fully randomised to minimise the capacity to learn from long sequences of prior outcomes. Event-related potentials for outcomes (Win/Loss) in the current trial (Outcomet) were separated according to the type of outcomes that occurred in the preceding two trials (Outcomet-1 and Outcomet-2). We found that FRN voltage was more positive during the processing of win feedback when it was preceded by wins at Outcomet-1 compared to win feedback preceded by losses at Outcomet-1. However, no influence of preceding outcomes was found on FRN activity relative to the processing of loss feedback. We also found no effects of Outcomet-2 on FRN amplitude relative to current feedback. Additional analyses indicated that this effect was largest for trials in which participants selected a decision different to the gamble chosen in the previous trial. These findings are inconsistent with models that solely relate the FRN to prediction error computation. Instead, our results suggest that if stable predictions about future events are weak or non-existent, then outcome processing can be determined by affective systems. More specifically, our results indicate that the FRN is likely to reflect the activity of positive affective systems in these contexts. Importantly, our findings indicate that a multifactorial explanation of the nature of the FRN is necessary and such an account must incorporate affective and motivational factors in outcome processing.

The relationship between manual coordination and mental health.

Motor coordination impairments frequently co-occur with other developmental disorders and mental health problems in clinically referred populations. But does this reflect a broader dimensional relationship within the general population? A clearer understanding of this relationship might inform improvements in mental health service provision. However, ascertainment and referral bias means that there is limited value in conducting further research with clinically referred samples. We, therefore, conducted a cross-sectional population-based study investigating children's manual coordination using an objective computerised test. These measures were related to teacher-completed responses on a behavioural screening questionnaire [the Strength and Difficulties Questionnaire (SDQ)]. We sampled 298 children (4-11 years old; 136 males) recruited from the general population. Hierarchical (logistic and linear) regression modelling indicated significant categorical and continuous relationships between manual coordination and overall SDQ score (a dimensional measure of psychopathology). Even after controlling for gender and age, manual coordination explained 15 % of the variance in total SDQ score. This dropped to 9 % after exclusion of participants whose SDQ responses indicated potential mental health problems. These results: (1) indicate that there is a clear relationship between children's motor and mental health development in community-based samples; (2) demonstrate the relationship's dimensional nature; and (3) have implications for service provision.

Diagnosis, medication, and surgical management for patients with trigeminal neuralgia: a qualitative study.

BACKGROUND: Trigeminal neuralgia (TN) is a serious health problem, causing brief, recurrent episodes of stabbing or burning facial pain, which patients describe as feeling like an electric shock. The consequences of living with the condition are severe. There is currently no cure for TN and management of the condition can be complex, often delayed by misdiagnosis. Patients' qualitative experiential accounts of TN have not been reported in the literature. Capturing subjective experiences can be used to inform the impact of the condition on quality of life and may contribute to a better understanding of current clinical practice with the aim of improving patient care. METHODS: Participants with TN (n = 16; 11 female), including those who have and have not undergone surgical intervention(s), took part in one of four focus groups. We conducted a thematic analysis within an essentialist framework using transcripts. RESULTS: The impact of TN and treatment on the lives of participants emerged as four predominant themes: (1) diagnosis and support with TN, (2) living in fear of TN pain, (3) isolation and social withdrawal, and (4) medication burden and looking for a cure. Each theme is discussed and illustrated with extracts from the transcripts. CONCLUSIONS: Key issues to address in the management of patients with TN include continued delays in diagnosis, persistent side effects from medication, and a lack of psychological support. Developing strategies to enhance the management of patients with TN, informed by a biopsychosocial approach and multidisciplinary team working, is essential to enhancing the provision of current care.

The relationship between a child's postural stability and manual dexterity.

The neural systems responsible for postural control are separate from the neural substrates that underpin control of the hand. Nonetheless, postural control and eye-hand coordination are linked functionally. For example, a stable platform is required for precise manual control tasks (e.g. handwriting) and thus such skills often cannot develop until the child is able to sit or stand upright. This raises the question of the strength of the empirical relationship between measures of postural stability and manual motor control. We recorded objective computerised measures of postural stability in stance and manual control in sitting in a sample of school children (n = 278) aged 3-11 years in order to explore the extent to which measures of manual skill could be predicted by measures of postural stability. A strong correlation was found across the whole sample between separate measures of postural stability and manual control taken on different days. Following correction for age, a significant but modest correlation was found. Regression analysis with age correction revealed that postural stability accounted for between 1 and 10% of the variance in manual performance, dependent on the specific manual task. These data reflect an interdependent functional relationship between manual control and postural stability development. Nevertheless, the relatively small proportion of the explained variance is consistent with the anatomically distinct neural architecture that exists for 'gross' and 'fine' motor control. These data justify the approach of motor batteries that provide separate assessments of postural stability and manual dexterity and have implications for therapeutic intervention in developmental disorders.

Children's head movements and postural stability as a function of task.

Manual dexterity and postural control develop throughout childhood, leading to changes in the synergistic relationships between head, hand and posture. But the postural developments that support complex manual task performance (i.e. beyond pointing and grasping) have not been examined in depth. We report two experiments in which we recorded head and posture data whilst participants simultaneously performed a visuomotor task. In Experiment 1, we explored the extent to which postural stability is affected by concurrently performing a visual and manual task whilst standing (a visual vs. manual-tracking task) in four age groups: 5-6 years (n = 8), 8-9 years (n = 10), 10-11 years (n = 7) and 19-21 years (n = 9). For visual tracking, the children's but not adult's postural movement increased relative to baseline with a larger effect for faster moving targets. In manual tracking, we found greater postural movement in children compared to adults. These data suggest predictive postural compensation mechanisms develop during childhood to improve stability whilst performing visuomotor tasks. Experiment 2 examined the extent to which posture is influenced by manual activity in three age groups of children [5-6 years (n = 14), 7-8 years (n = 25), and 9-10 years (n = 24)] when they were seated, given that many important tasks (e.g. handwriting) are learned and performed whilst seated. We found that postural stability varied in a principled manner as a function of task demands. Children exhibited increased stability when tracing a complex shape (which required less predictive postural adjustment) and decreased stability in an aiming task (which required movements that were more likely to perturb posture). These experiments shed light on the task-dependant relationships that exist between postural control mechanisms and the development of specific types of manual control.

Fine tuned personalized machine learning models to detect insomnia risk based on data from a smart bed platform.

Introduction: Insomnia causes serious adverse health effects and is estimated to affect 10-30% of the worldwide population. This study leverages personalized fine-tuned machine learning algorithms to detect insomnia risk based on questionnaire and longitudinal objective sleep data collected by a smart bed platform. Methods: Users of the Sleep Number smart bed were invited to participate in an IRB approved study which required them to respond to four questionnaires (which included the Insomnia Severity Index; ISI) administered 6 weeks apart from each other in the period from November 2021 to March 2022. For 1,489 participants who completed at least 3 questionnaires, objective data (which includes sleep/wake and cardio-respiratory metrics) collected by the platform were queried for analysis. An incremental, passive-aggressive machine learning model was used to detect insomnia risk which was defined by the ISI exceeding a given threshold. Three ISI thresholds (8, 10, and 15) were considered. The incremental model is advantageous because it allows personalized fine-tuning by adding individual training data to a generic model. Results: The generic model, without personalizing, resulted in an area under the receiving-operating curve (AUC) of about 0.5 for each ISI threshold. The personalized fine-tuning with the data of just five sleep sessions from the individual for whom the model is being personalized resulted in AUCs exceeding 0.8 for all ISI thresholds. Interestingly, no further AUC enhancements resulted by adding personalized data exceeding ten sessions. Discussion: These are encouraging results motivating further investigation into the application of personalized fine tuning machine learning to detect insomnia risk based on longitudinal sleep data and the extension of this paradigm to sleep medicine.