A Rehabilomics framework for personalized and translational rehabilitation research and care for individuals with disabilities: Perspectives and considerations for spinal cord injury

Unlocking the Black Box? A Comprehensive Exploration of Large Language Models in Rehabilitation

ABSTRACT

Rehabilitation is a vital component of health care, aiming to restore function and improve the well-being of individuals with disabilities or injuries. Nevertheless, the rehabilitation process is often likened to a " black box ," with complexities that pose challenges for comprehensive analysis and optimization. The emergence of large language models offers promising solutions to better understand this " black box ." Large language models excel at comprehending and generating human-like text, making them valuable in the healthcare sector. In rehabilitation, healthcare professionals must integrate a wide range of data to create effective treatment plans, akin to selecting the best ingredients for the " black box. " Large language models enhance data integration, communication, assessment, and prediction.This article delves into the ground-breaking use of large language models as a tool to further understand the rehabilitation process. Large language models address current rehabilitation issues, including data bias, contextual comprehension, and ethical concerns. Collaboration with healthcare experts and rigorous validation is crucial when deploying large language models. Integrating large language models into rehabilitation yields insights into this intricate process, enhancing data-driven decision making, refining clinical practices, and predicting rehabilitation outcomes. Although challenges persist, large language models represent a significant stride in rehabilitation, underscoring the importance of ethical use and collaboration.

Technological Features of Immersive Virtual Reality Systems for Upper Limb Stroke Rehabilitation: A Systematic Review

Stroke is the second most common cause of death worldwide, and it greatly impacts the quality of life for survivors by causing impairments in their upper limbs. Due to the difficulties in accessing rehabilitation services, immersive virtual reality (IVR) is an interesting approach to improve the availability of rehabilitation services. This systematic review evaluates the technological characteristics of IVR systems used in the rehabilitation of upper limb stroke patients. Twenty-five publications were included. Various technical aspects such as game engines, programming languages, headsets, platforms, game genres, and technical evaluation were extracted from these papers. Unity 3D and C# are the primary tools for creating IVR apps, while the Oculus Quest (Meta Platforms Technologies, Menlo Park, CA, USA) is the most often used headset. The majority of systems are created specifically for rehabilitation purposes rather than being readily available for purchase (i.e., commercial games). The analysis also highlights key areas for future research, such as game assessment, the combination of hardware and software, and the potential integration incorporation of biofeedback sensors. The study highlights the significance of technological progress in improving the effectiveness and user-friendliness of IVR. It calls for additional research to fully exploit IVR's potential in enhancing stroke rehabilitation results.

STASISM: A Versatile Serious Gaming Multi-Sensor Platform for Personalized Telerehabilitation and Telemonitoring

Telemonitoring and telerehabilitation have shown promise in delivering individualized healthcare remotely. We introduce STASISM, a sensor-based telerehabilitation and telemonitoring system, in this work. This platform has been created to facilitate individualized telerehabilitation and telemonitoring for those who need rehabilitation or ongoing monitoring. To gather and analyze pertinent and validated physiological, kinematic, and environmental data, the system combines a variety of sensors and data analytic methodologies. The platform facilitates customized rehabilitation activities based on individual needs, allows for the remote monitoring of a patient's progress, and offers real-time feedback. To protect the security of patient data and to safeguard patient privacy, STASISM also provides secure data transmission and storage. The platform has the potential to significantly improve the accessibility and efficacy of telerehabilitation and telemonitoring programs, enhancing patients' quality of life and allowing healthcare professionals to provide individualized care outside of traditional clinical settings.

NeBULA: A Standardized Protocol for the Benchmarking of Robotic-based Upper Limb Neurorehabilitation

The use of robotic technologies in neurorehabilitation is growing, because they allow highly repeatable exercise protocols and patient-tailored therapies. However, there is a lack of objective methods for assessing these technologies, which makes it difficult to determine their value in rehabilitation settings. While there exist many outcome measurements for motor assessment from a clinical standpoint (such as the Fugl-Meyer scale), the evaluation of performance and clinical benefits of technology for rehabilitation still lacks a standardized approach from a technical standpoint.In this work, we describe NeBULA (Neuromechanical Biomarkers for Upper Limb Assessment), a benchmarking platform for evaluating robotic technology for upper limb neurorehabilitation. By utilizing standardized neuromechanical biomarkers, NeBULA aims at providing a groundwork for assessing and comparing neurorehabilitation robots. We describe its implementation and preliminary results assessing a novel upper limb exoskeleton.Clinical Relevance- Standardized evaluation of neurorehabilitation robots can lead to better patient outcomes, optimizing resources by identifying the most effective technology and by boosting their use in clinical practice. This would provide quantitative and objective information to complement clinical motor evaluation - preventing suboptimal treatments and ensuring that patients receive personalized care. It can also facilitate the transfer of technologyto clinics, identifying the most promising ones for further investment and research.

Lissencephaly-1 mutations enhance traumatic brain injury outcomes in Drosophila

Traumatic brain injury (TBI) outcomes vary greatly among individuals, but most of the variation remains unexplained. Using a Drosophila melanogaster TBI model and 178 genetically diverse lines from the Drosophila Genetic Reference Panel (DGRP), we investigated the role that genetic variation plays in determining TBI outcomes. Following injury at 20-27 days old, DGRP lines varied considerably in mortality within 24 h ("early mortality"). Additionally, the disparity in early mortality resulting from injury at 20-27 vs 0-7 days old differed among DGRP lines. These data support a polygenic basis for differences in TBI outcomes, where some gene variants elicit their effects by acting on aging-related processes. Our genome-wide association study of DGRP lines identified associations between single nucleotide polymorphisms in Lissencephaly-1 (Lis-1) and Patronin and early mortality following injury at 20-27 days old. Lis-1 regulates dynein, a microtubule motor required for retrograde transport of many cargoes, and Patronin protects microtubule minus ends against depolymerization. While Patronin mutants did not affect early mortality, Lis-1 compound heterozygotes (Lis-1x/Lis-1y) had increased early mortality following injury at 20-27 or 0-7 days old compared with Lis-1 heterozygotes (Lis-1x/+), and flies that survived 24 h after injury had increased neurodegeneration but an unaltered lifespan, indicating that Lis-1 affects TBI outcomes independently of effects on aging. These data suggest that Lis-1 activity is required in the brain to ameliorate TBI outcomes through effects on axonal transport, microtubule stability, and other microtubule proteins, such as tau, implicated in chronic traumatic encephalopathy, a TBI-associated neurodegenerative disease in humans.

Integrating Rehabilomics into the Multi-Omics Approach in the Management of Multiple Sclerosis: The Way for Precision Medicine?

Over recent years, significant improvements have been made in the understanding of (epi)genetics and neuropathophysiological mechanisms driving the different forms of multiple sclerosis (MS). For example, the role and importance of the bidirectional communications between the brain and the gut-also referred to as the gut-brain axis-in the pathogenesis of MS is receiving increasing interest in recent years and is probably one of the most promising areas of research for the management of people with MS. However, despite these important advances, it must be noted that these data are not-yet-used in rehabilitation. Neurorehabilitation is a cornerstone of MS patient management, and there are many techniques available to clinicians and patients, including technology-supported rehabilitation. In this paper, we will discuss how new findings on the gut microbiome could help us to better understand how rehabilitation can improve motor and cognitive functions. We will also see how the data gathered during the rehabilitation can help to get a better diagnosis of the patients. Finally, we will discuss how these new techniques can better guide rehabilitation to lead to precision rehabilitation and ultimately increase the quality of patient care.

Machine learning methods for functional recovery prediction and prognosis in post-stroke rehabilitation: a systematic review

BACKGROUND

Rehabilitation medicine is facing a new development phase thanks to a recent wave of rigorous clinical trials aimed at improving the scientific evidence of protocols. This phenomenon, combined with new trends in personalised medical therapies, is expected to change clinical practice dramatically. The emerging field of Rehabilomics is only possible if methodologies are based on biomedical data collection and analysis. In this framework, the objective of this work is to develop a systematic review of machine learning algorithms as solutions to predict motor functional recovery of post-stroke patients after treatment.

METHODS

We conducted a comprehensive search of five electronic databases using the Patient, Intervention, Comparison and Outcome (PICO) format. We extracted health conditions, population characteristics, outcome assessed, the method for feature extraction and selection, the algorithm used, and the validation approach. The methodological quality of included studies was assessed using the prediction model risk of bias assessment tool (PROBAST). A qualitative description of the characteristics of the included studies as well as a narrative data synthesis was performed.

RESULTS

A total of 19 primary studies were included. The predictors most frequently used belonged to the areas of demographic characteristics and stroke assessment through clinical examination. Regarding the methods, linear and logistic regressions were the most frequently used and cross-validation was the preferred validation approach.

CONCLUSIONS

We identified several methodological limitations: small sample sizes, a limited number of external validation approaches, and high heterogeneity among input and output variables. Although these elements prevented a quantitative comparison across models, we defined the most frequently used models given a specific outcome, providing useful indications for the application of more complex machine learning algorithms in rehabilitation medicine.

Neuromechanical Biomarkers for Robotic Neurorehabilitation

One of the current challenges for translational rehabilitation research is to develop the strategies to deliver accurate evaluation, prediction, patient selection, and decision-making in the clinical practice. In this regard, the robot-assisted interventions have gained popularity as they can provide the objective and quantifiable assessment of the motor performance by taking the kinematics parameters into the account. Neurophysiological parameters have also been proposed for this purpose due to the novel advances in the non-invasive signal processing techniques. In addition, other parameters linked to the motor learning and brain plasticity occurring during the rehabilitation have been explored, looking for a more holistic rehabilitation approach. However, the majority of the research done in this area is still exploratory. These parameters have shown the capability to become the “biomarkers” that are defined as the quantifiable indicators of the physiological/pathological processes and the responses to the therapeutical interventions. In this view, they could be finally used for enhancing the robot-assisted treatments. While the research on the biomarkers has been growing in the last years, there is a current need for a better comprehension and quantification of the neuromechanical processes involved in the rehabilitation. In particular, there is a lack of operationalization of the potential neuromechanical biomarkers into the clinical algorithms. In this scenario, a new framework called the “Rehabilomics” has been proposed to account for the rehabilitation research that exploits the biomarkers in its design. This study provides an overview of the state-of-the-art of the biomarkers related to the robotic neurorehabilitation, focusing on the translational studies, and underlying the need to create the comprehensive approaches that have the potential to take the research on the biomarkers into the clinical practice. We then summarize some promising biomarkers that are being under investigation in the current literature and provide some examples of their current and/or potential applications in the neurorehabilitation. Finally, we outline the main challenges and future directions in the field, briefly discussing their potential evolution and prospective.

Estimating Range of Lower Body Joint Angles with a Sensorized Overground Body-Weight Support System

Recent trends in rehabilitation and therapy are turning to data-driven approaches to personalize treatment. Due to such approaches, data collection methods have become more complex and expensive, in terms of financial resources, technological knowledge, and time required to implement the data collection method. Such costs might deter clinical applications of otherwise good data collection methods. Hence, a method to collect data in a non-intrusive manner is proposed. Sensors are embedded into a commonly used rehabilitation tool, the walking trainer, for gait data collection. This study shows that, in principle, lower body joint angles can be collected in a non-intrusive manner, with a slight trade off to precision. In this study, the focus would be on the pelvic and hip movements, since the pelvic segment of the human body is implicated in a variety of gait problemsClinical relevance - The proposed usage model allows clinicians access to additional kinematic data, while minimizing changes to existing clinical evaluation processes and being non-intrusive. Having additional kinematic data would give further insight into a patient's current state, thereby improving the efficiency of individualized therapy.

A Sensorized Overground Body Weight Support System for Assessing Gait Parameters During Walking Rehabilitation

Although the needs of individuals undertaking gait rehabilitation sessions may appear similar, they present facets that may assist therapists to come up with more targeted treatment. However, acquiring such aspects is a major problem for rehabilitation personnel due to time constraints and/or complexity. In this paper, we propose an alternative method for estimating gait parameters for individuals requiring Body Weight Support (BWS) during gait training. Results show that the proposed device is able to acquire step length and the amount of body weight unloaded with relatively high accuracy. This reduces the need to set up external sensors to measure patients. Moreover, it can provide gait parameters for patients evaluation which can be used for more personalized treatment.Clinical relevance - Tracking patient progress during therapy is an important part of personalized therapy. The proposed device is a simple, low-cost method of collecting gait parameters from patients, without the use of expensive motion tracking and force sensors.

Ketogenic diet reduces early mortality following traumatic brain injury in Drosophila via the PPARγ ortholog Eip75B

Traumatic brain injury (TBI) is a common neurological disorder whose outcomes vary widely depending on a variety of environmental factors, including diet. Using a Drosophila melanogaster TBI model that reproduces key aspects of TBI in humans, we previously found that the diet consumed immediately following a primary brain injury has a substantial effect on the incidence of mortality within 24 h (early mortality). Flies that receive equivalent primary injuries have a higher incidence of early mortality when fed high-carbohydrate diets versus water. Here, we report that flies fed high-fat ketogenic diet (KD) following TBI exhibited early mortality that was equivalent to that of flies fed water and that flies protected from early mortality by KD continued to show survival benefits weeks later. KD also has beneficial effects in mammalian TBI models, indicating that the mechanism of action of KD is evolutionarily conserved. To probe the mechanism, we examined the effect of KD in flies mutant for Eip75B, an ortholog of the transcription factor PPARγ (peroxisome proliferator-activated receptor gamma) that contributes to the mechanism of action of KD and has neuroprotective effects in mammalian TBI models. We found that the incidence of early mortality of Eip75B mutant flies was higher when they were fed KD than when they were fed water following TBI. These data indicate that Eip75B/PPARγ is necessary for the beneficial effects of KD following TBI. In summary, this work provides the first evidence that KD activates PPARγ to reduce deleterious outcomes of TBI and it demonstrates the utility of the fly TBI model for dissecting molecular pathways that contribute to heterogeneity in TBI outcomes.

Challenges of Prevention for a Sustainable Personalized Medicine

The development and implementation of the approaches of personalized medicine for disease prevention are still at infancy, although preventive activities in healthcare represent a key pillar to guarantee health system sustainability. There is an increasing interest in finding informative markers that indicate the disease risk before the manifestation of the disease (primary prevention) or for early disease detection (secondary prevention). Recently, the systematic collection and study of clinical phenotypes and biomarkers consented to the advance of Rehabilomics in tertiary prevention. It consents to identify relevant molecular and physiological factors that can be linked to plasticity, treatment response, and natural recovery. Implementation of these approaches would open avenues to identify people at high risk and enable new preventive lifestyle interventions or early treatments targeted to their individual genomic profile, personalizing prevention and rehabilitation. The integration of personalized medicine into prevention may benefit citizens, patients, healthcare professionals, healthcare authorities, and industry, and ultimately will seek to contribute to better health and quality of life for Europe’s citizens.

TBI Rehabilomics Research: Conceptualizing a humoral triad for designing effective rehabilitation interventions

Most areas of medicine use biomarkers in some capacity to aid in understanding how personal biology informs clinical care. This article draws upon the Rehabilomics research model as a translational framework for programs of precision rehabilitation and intervention research focused on linking personal biology to treatment response using biopsychosocial constructs that broadly represent function and that can be applied to many clinical populations with disability. The summary applies the Rehabilomics research framework to the population with traumatic brain injury (TBI) and emphasizes a broad vision for biomarker inclusion, beyond typical brain-derived biomarkers, to capture and/or reflect important neurological and non-neurological pathology associated with TBI as a chronic condition. Humoral signaling molecules are explored as important signaling and regulatory drivers of these chronic conditions and their impact on function. Importantly, secondary injury cascades involved in the humoral triad are influenced by the systemic response to TBI and the development of non-neurological organ dysfunction (NNOD). Biomarkers have been successfully leveraged in other medical fields to inform pre-randomization patient selection for clinical trials, however, this practice largely has not been utilized in TBI research. As such, the applicability of the Rehabilomics research model to contemporary clinical trials and comparative effectiveness research designs for neurological and rehabilitation populations is emphasized. Potential points of intervention to modify inflammation, hormonal, or neurotrophic support through rehabilitation interventions are discussed. This article is part of the Special Issue entitled "Novel Treatments for Traumatic Brain Injury".

TBI Rehabilomics Research: an Exemplar of a Biomarker-Based Approach to Precision Care for Populations with Disability

PURPOSE OF REVIEW

The purpose of this review is to summarize how "-omics" technologies can inform rehabilitation-relevant outcomes for a range of populations with neurologically related disability by including outcome metrics linked to the World Health Organization's International Classification of Functioning, Disability, and Health (WHO-ICF) domains of impairments in body function, activity limitations, and participation restrictions.

RECENT FINDINGS

To date, nearly every area of medicine uses biomarkers in some capacity to aid in understanding how personal biology informs clinical care. "-Omics"-based approaches use high throughput genomics, proteomics, and transcriptomics assay platforms to tailor and personalize treatments for subgroups of similar individuals based on these results. The recent Precision Medicine Initiative (PMI), sponsored by the National Institutes of Health (NIH), has propelled biomarker-based and genomics research to the forefront of many translational research and care programs addressing a variety of medical populations. Yet, the literature is sparse on precision medicine approaches for those with neurologically related and other disability. We demonstrate how the Rehabilomics Research model represents a translational framework for programs of precision rehabilitation research and care focused on linking personal biology to the biopsychosocial constructs that represent the WHO-ICF model and multidimensional outcome. We provide multiple exemplars from our own research program involving individuals with moderate-to-severe traumatic brain injury (TBI) to demonstrate how genomics and other biomarkers can be identified and assessed for their capacity to assist with personalized (precision) neurorehabilitation care and management.

Acute CSF interleukin-6 trajectories after TBI: associations with neuroinflammation, polytrauma, and outcome

Traumatic brain injury (TBI) results in a significant inflammatory burden that perpetuates the production of inflammatory mediators and biomarkers. Interleukin-6 (IL-6) is a pro-inflammatory cytokine known to be elevated after trauma, and a major contributor to the inflammatory response following TBI. Previous studies have investigated associations between IL-6 and outcome following TBI, but to date, studies have been inconsistent in their conclusions. We hypothesized that cohort heterogeneity, temporal inflammatory profiles, and concurrent inflammatory marker associations are critical to characterize when targeting subpopulations for anti-inflammatory therapies. Toward this objective, we used serial cerebrospinal fluid (CSF) samples to generate temporal acute IL-6 trajectory (TRAJ) profiles in a prospective cohort of adults with severe TBI (n=114). We examined the impact of injury type on IL-6 profiles, and how IL-6 profiles impact sub-acute (2weeks-3months) serum inflammatory marker load and long-term global outcome 6-12months post-injury. There were two distinct acute CSF IL-6 profiles, a high and low TRAJ group. Individuals in the high TRAJ had increased odds of unfavorable Glasgow Outcome Scale (GOS) scores at 6months (adjusted OR=3.436, 95% CI: 1.259, 9.380). Individuals in the high TRAJ also had higher mean acute CSF inflammatory load compared to individuals in the low TRAJ (p⩽0.05). The two groups did not differ with respect acute serum profiles; however, individuals in the high CSF IL-6 TRAJ also had higher mean sub-acute serum IL-1β and IL-6 levels compared with the low TRAJ group (p⩽0.05). Lastly, injury type (isolated TBI vs. TBI+polytrauma) was associated with IL-6 TRAJ group (χ(2)=5.31, p=0.02). Specifically, there was 70% concordance between those with TBI+polytrauma and the low TRAJ; in contrast, isolated TBI was similarly distributed between TRAJ groups. These data provide evidence that sustained, elevated levels of CSF IL-6 are associated with an increased inflammatory load, and these increases are associated with increased odds for unfavorable global outcomes in the first year following TBI. Future studies should explore additional factors contributing to IL-6 elevations, and therapies to mitigate its detrimental effects on outcome.