Prediction of segmental motor outcomes in traumatic spinal cord injury: Advances beyond sum scores.

BACKGROUND AND OBJECTIVES: Neurological and functional recovery after traumatic spinal cord injury (SCI) is highly challenged by the level of the lesion and the high heterogeneity in severity (different degrees of in/complete SCI) and spinal cord syndromes (hemi-, ant-, central-, and posterior cord). So far outcome predictions in clinical trials are limited in targeting sum motor scores of the upper (UEMS) and lower limb (LEMS) while neglecting that the distribution of motor function is essential for functional outcomes. The development of data-driven prediction models of detailed segmental motor recovery for all spinal segments from the level of lesion towards the lowest motor segments will improve the design of rehabilitation programs and the sensitivity of clinical trials. METHODS: This study used acute-phase International Standards for Neurological Classification of SCI exams to forecast 6-month recovery of segmental motor scores as the primary evaluation endpoint. Secondary endpoints included severity grade improvement, independent walking, and self-care ability. Different similarity metrics were explored for k-nearest neighbor (kNN) matching within 1267 patients from the European Multicenter Study about Spinal Cord Injury before validation in 411 patients from the Sygen trial. The kNN performance was compared to linear and logistic regression models. RESULTS: We obtained a population-wide root-mean-squared error (RMSE) in motor score sequence of 0.76(0.14, 2.77) and competitive functional score predictions (AUCwalker = 0.92, AUCself-carer = 0.83) for the kNN algorithm, improving beyond the linear regression task (RMSElinear = 0.98(0.22, 2.57)). The validation cohort showed comparable results (RMSE = 0.75(0.13, 2.57), AUCwalker = 0.92). We deploy the final historic control model as a web tool for easy user interaction (https://hicsci.ethz.ch/). DISCUSSION: Our approach is the first to provide predictions across all motor segments independent of the level and severity of SCI. We provide a machine learning concept that is highly interpretable, i.e. the prediction formation process is transparent, that has been validated across European and American data sets, and provides reliable and validated algorithms to incorporate external control data to increase sensitivity and feasibility of multinational clinical trials.

Data-driven prediction of spinal cord injury recovery: An exploration of current status and future perspectives.

Spinal Cord Injury (SCI) presents a significant challenge in rehabilitation medicine, with recovery outcomes varying widely among individuals. Machine learning (ML) is a promising approach to enhance the prediction of recovery trajectories, but its integration into clinical practice requires a thorough understanding of its efficacy and applicability. We systematically reviewed the current literature on data-driven models of SCI recovery prediction. The included studies were evaluated based on a range of criteria assessing the approach, implementation, input data preferences, and the clinical outcomes aimed to forecast. We observe a tendency to utilize routinely acquired data, such as International Standards for Neurological Classification of SCI (ISNCSCI), imaging, and demographics, for the prediction of functional outcomes derived from the Spinal Cord Independence Measure (SCIM) III and Functional Independence Measure (FIM) scores with a focus on motor ability. Although there has been an increasing interest in data-driven studies over time, traditional machine learning architectures, such as linear regression and tree-based approaches, remained the overwhelmingly popular choices for implementation. This implies ample opportunities for exploring architectures addressing the challenges of predicting SCI recovery, including techniques for learning from limited longitudinal data, improving generalizability, and enhancing reproducibility. We conclude with a perspective, highlighting possible future directions for data-driven SCI recovery prediction and drawing parallels to other application fields in terms of diverse data types (imaging, tabular, sequential, multimodal), data challenges (limited, missing, longitudinal data), and algorithmic needs (causal inference, robustness).

Exploring the potential of routine serological markers in predicting neurological outcomes in spinal cord injury.

Spinal cord injury (SCI) is a rare condition with a heterogeneous presentation, making the prediction of recovery challenging. However, serological markers have been shown to be associated with severity and long-term recovery following SCI. Therefore, our investigation aimed to assess the feasibility of translating this association into a prediction of the lower extremity motor scores (LEMS) at chronic stage (52 weeks after initial injury) in patients with SCI using routine serological markers. Serological markers, assessed within the initial seven days post-injury in the observational cohort study from the Trauma Hospital Murnau underwent diverse feature engineering approaches. These involved arithmetic measurements such as mean, median, minimum, maximum, and range, as well as considerations of the frequency of marker testing and whether values fell within the normal range. To predict LEMS scores at the chronic stage, eight different regression models (including linear, tree-based, and ensemble models) were used to quantify the predictive value of serological markers relative to a baseline model that relied on the very acute LEMS score and patient age alone. The inclusion of serological markers did not improve the performance of the prediction model. The best-performing approach including serological markers achieved a mean absolute error (MAE) of 6.59 (2.14), which was equivalent to the performance of the baseline model. As an alternative approach, we trained separate models based on the LEMS observed at the very acute stage after injury. Specifically, we considered individuals with an LEMS of 0 or an LEMS exceeding zero separately. This strategy led to a mean improvement in MAE across all cohorts and models, of 1.20 (2.13). We conclude that, in our study, routine serological markers hold limited power for prediction of LEMS. However, the implementation of model stratification by the very acute LEMS markedly enhanced prediction performance. This observation supports the inclusion of clinical knowledge in the modeling of prediction tasks for SCI recovery. Additionally, it lays the path for future research to consider stratified analyses when investigating the predictive power of potential biomarkers.

Potential thresholds of critically increased cardiac-related spinal cord motion in degenerative cervical myelopathy.

Introduction: New diagnostic techniques are a substantial research focus in degenerative cervical myelopathy (DCM). This cross-sectional study determined the significance of cardiac-related spinal cord motion and the extent of spinal stenosis as indicators of mechanical strain on the cord. Methods: Eighty-four DCM patients underwent MRI/clinical assessments and were classified as MRI+ [T2-weighted (T2w) hyperintense lesion in MRI] or MRI- (no T2w-hyperintense lesion). Cord motion (displacement assessed by phase-contrast MRI) and spinal stenosis [adapted spinal canal occupation ratio (aSCOR)] were related to neurological (sensory/motor) and neurophysiological readouts [contact heat evoked potentials (CHEPs)] by receiver operating characteristic (ROC) analysis. Results: MRI+ patients (N = 31; 36.9%) were more impaired compared to MRI- patients (N = 53; 63.1%) based on the modified Japanese Orthopedic Association (mJOA) subscores for upper {MRI+ [median (Interquartile range)]: 4 (4-5); MRI-: 5 (5-5); p < 0.01} and lower extremity [MRI+: 6 (6-7); MRI-: 7 (6-7); p = 0.03] motor dysfunction and the monofilament score [MRI+: 21 (18-23); MRI-: 24 (22-24); p < 0.01]. Both patient groups showed similar extent of cord motion and stenosis. Only in the MRI- group displacement identified patients with pathologic assessments [trunk/lower extremity pin prick score (T/LEPP): AUC = 0.67, p = 0.03; CHEPs: AUC = 0.73, p = 0.01]. Cord motion thresholds: T/LEPP: 1.67 mm (sensitivity 84.6%, specificity 52.5%); CHEPs: 1.96 mm (sensitivity 83.3%, specificity 65.6%). The aSCOR failed to show any relation to the clinical assessments. Discussion: These findings affirm cord motion measurements as a promising additional biomarker to improve the clinical workup and to enable timely surgical treatment particularly in MRI- DCM patients. Clinical trial registration: www.clinicaltrials.gov, NCT02170155.

A review of mechanistic learning in mathematical oncology.

Mechanistic learning refers to the synergistic combination of mechanistic mathematical modeling and data-driven machine or deep learning. This emerging field finds increasing applications in (mathematical) oncology. This review aims to capture the current state of the field and provides a perspective on how mechanistic learning may progress in the oncology domain. We highlight the synergistic potential of mechanistic learning and point out similarities and differences between purely data-driven and mechanistic approaches concerning model complexity, data requirements, outputs generated, and interpretability of the algorithms and their results. Four categories of mechanistic learning (sequential, parallel, extrinsic, intrinsic) of mechanistic learning are presented with specific examples. We discuss a range of techniques including physics-informed neural networks, surrogate model learning, and digital twins. Example applications address complex problems predominantly from the domain of oncology research such as longitudinal tumor response predictions or time-to-event modeling. As the field of mechanistic learning advances, we aim for this review and proposed categorization framework to foster additional collaboration between the data- and knowledge-driven modeling fields. Further collaboration will help address difficult issues in oncology such as limited data availability, requirements of model transparency, and complex input data which are embraced in a mechanistic learning framework.

Studying missingness in spinal cord injury data: challenges and impact of data imputation.

BACKGROUND: In the last decades, medical research fields studying rare conditions such as spinal cord injury (SCI) have made extensive efforts to collect large-scale data. However, most analysis methods rely on complete data. This is particularly troublesome when studying clinical data as they are prone to missingness. Often, researchers mitigate this problem by removing patients with missing data from the analyses. Less commonly, imputation methods to infer likely values are applied. OBJECTIVE: Our objective was to study how handling missing data influences the results reported, taking the example of SCI registries. We aimed to raise awareness on the effects of missing data and provide guidelines to be applied for future research projects, in SCI research and beyond. METHODS: Using the Sygen clinical trial data (n = 797), we analyzed the impact of the type of variable in which data is missing, the pattern according to which data is missing, and the imputation strategy (e.g. mean imputation, last observation carried forward, multiple imputation). RESULTS: Our simulations show that mean imputation may lead to results strongly deviating from the underlying expected results. For repeated measures missing at late stages (> = 6 months after injury in this simulation study), carrying the last observation forward seems the preferable option for the imputation. This simulation study could show that a one-size-fit-all imputation strategy falls short in SCI data sets. CONCLUSIONS: Data-tailored imputation strategies are required (e.g., characterisation of the missingness pattern, last observation carried forward for repeated measures evolving to a plateau over time). Therefore, systematically reporting the extent, kind and decisions made regarding missing data will be essential to improve the interpretation, transparency, and reproducibility of the research presented.

Exercise and aerobic capacity in individuals with spinal cord injury: A systematic review with meta-analysis and meta-regression.

BACKGROUND: A low level of cardiorespiratory fitness [CRF; defined as peak oxygen uptake ([Formula: see text]O2peak) or peak power output (PPO)] is a widely reported consequence of spinal cord injury (SCI) and a major risk factor associated with chronic disease. However, CRF can be modified by exercise. This systematic review with meta-analysis and meta-regression aimed to assess whether certain SCI characteristics and/or specific exercise considerations are moderators of changes in CRF. METHODS AND FINDINGS: Databases (MEDLINE, EMBASE, CENTRAL, and Web of Science) were searched from inception to March 2023. A primary meta-analysis was conducted including randomised controlled trials (RCTs; exercise interventions lasting >2 weeks relative to control groups). A secondary meta-analysis pooled independent exercise interventions >2 weeks from longitudinal pre-post and RCT studies to explore whether subgroup differences in injury characteristics and/or exercise intervention parameters explained CRF changes. Further analyses included cohort, cross-sectional, and observational study designs. Outcome measures of interest were absolute (A[Formula: see text]O2peak) or relative [Formula: see text]O2peak (R[Formula: see text]O2peak), and/or PPO. Bias/quality was assessed via The Cochrane Risk of Bias 2 and the National Institute of Health Quality Assessment Tools. Certainty of the evidence was assessed using the Grading of Recommendations Assessment, Development and Evaluation (GRADE) approach. Random effects models were used in all meta-analyses and meta-regressions. Of 21,020 identified records, 120 studies comprising 29 RCTs, 67 pre-post studies, 11 cohort, 7 cross-sectional, and 6 observational studies were included. The primary meta-analysis revealed significant improvements in A[Formula: see text]O2peak [0.16 (0.07, 0.25) L/min], R[Formula: see text]O2peak [2.9 (1.8, 3.9) mL/kg/min], and PPO [9 (5, 14) W] with exercise, relative to controls (p < 0.001). Ninety-six studies (117 independent exercise interventions comprising 1,331 adults with SCI) were included in the secondary, pooled meta-analysis which demonstrated significant increases in A[Formula: see text]O2peak [0.22 (0.17, 0.26) L/min], R[Formula: see text]O2peak [2.8 (2.2, 3.3) mL/kg/min], and PPO [11 (9, 13) W] (p < 0.001) following exercise interventions. There were subgroup differences for R[Formula: see text]O2peak based on exercise modality (p = 0.002) and intervention length (p = 0.01), but there were no differences for A[Formula: see text]O2peak. There were subgroup differences (p ≤ 0.018) for PPO based on time since injury, neurological level of injury, exercise modality, and frequency. The meta-regression found that studies with a higher mean age of participants were associated with smaller changes in A[Formula: see text]O2peak and R[Formula: see text]O2peak (p < 0.10). GRADE indicated a moderate level of certainty in the estimated effect for R[Formula: see text]O2peak, but low levels for A[Formula: see text]O2peak and PPO. This review may be limited by the small number of RCTs, which prevented a subgroup analysis within this specific study design. CONCLUSIONS: Our primary meta-analysis confirms that performing exercise >2 weeks results in significant improvements to A[Formula: see text]O2peak, R[Formula: see text]O2peak, and PPO in individuals with SCI. The pooled meta-analysis subgroup comparisons identified that exercise interventions lasting up to 12 weeks yield the greatest change in R[Formula: see text]O2peak. Upper-body aerobic exercise and resistance training also appear the most effective at improving R[Formula: see text]O2peak and PPO. Furthermore, acutely injured, individuals with paraplegia, exercising for ≥3 sessions/week will likely experience the greatest change in PPO. Ageing seemingly diminishes the adaptive CRF responses to exercise training in individuals with SCI. REGISTRATION: PROSPERO: CRD42018104342.

Pharmacological management of acute spinal cord injury: a longitudinal multi-cohort observational study.

Multiple types and classes of medications are administered in the acute management of traumatic spinal cord injury. Prior clinical studies and evidence from animal models suggest that several of these medications could modify (i.e., enhance or impede) neurological recovery. We aimed to systematically determine the types of medications commonly administered, alone or in combination, in the transition from acute to subacute spinal cord injury. For that purpose, type, class, dosage, timing, and reason for administration were extracted from two large spinal cord injury datasets. Descriptive statistics were used to describe the medications administered within the first 60 days after spinal cord injury. Across 2040 individuals with spinal cord injury, 775 unique medications were administered within the two months after injury. On average, patients enrolled in a clinical trial were administered 9.9 ± 4.9 (range 0-34), 14.3 ± 6.3 (range 1-40), 18.6 ± 8.2 (range 0-58), and 21.5 ± 9.7 (range 0-59) medications within the first 7, 14, 30, and 60 days post-injury, respectively. Those enrolled in an observational study were administered on average 1.7 ± 1.7 (range 0-11), 3.7 ± 3.7 (range 0-24), 8.5 ± 6.3 (range 0-42), and 13.5 ± 8.3 (range 0-52) medications within the first 7, 14, 30, and 60 days post-injury, respectively. Polypharmacy was commonplace (up to 43 medications per day per patient). Approximately 10% of medications were administered acutely as prophylaxis (e.g., against the development of pain or infections). To our knowledge, this was the first time acute pharmacological practices have been comprehensively examined after spinal cord injury. Our study revealed a high degree of polypharmacy in the acute stages of spinal cord injury, raising the potential to impact neurological recovery. All results can be interactively explored on the RXSCI web site ( https://jutzelec.shinyapps.io/RxSCI/ ) and GitHub repository ( https://github.com/jutzca/Acute-Pharmacological-Treatment-in-SCI/ ).

Walking Outcome After Traumatic Paraplegic Spinal Cord Injury: The Function of Which Myotomes Makes a Difference?

BACKGROUND: Accurate prediction of walking function after a traumatic spinal cord injury (SCI) is crucial for an appropriate tailoring and application of therapeutical interventions. Long-term outcome of ambulation is strongly related to residual muscle function acutely after injury and its recovery potential. The identification of the underlying determinants of ambulation, however, remains a challenging task in SCI, a neurological disorder presented with heterogeneous clinical manifestations and recovery trajectories. OBJECTIVES: Stratification of walking function and determination of its most relevant underlying muscle functions based on stratified homogeneous patient subgroups. METHODS: Data from individuals with paraplegic SCI were used to develop a prediction-based stratification model, applying unbiased recursive partitioning conditional inference tree (URP-CTREE). The primary outcome was the 6-minute walk test at 6 months after injury. Standardized neurological assessments ≤15 days after injury were chosen as predictors. Resulting subgroups were incorporated into a subsequent node-specific analysis to attribute the role of individual lower extremity myotomes for the prognosis of walking function. RESULTS: Using URP-CTREE, the study group of 361 SCI patients was divided into 8 homogeneous subgroups. The node specific analysis uncovered that proximal myotomes L2 and L3 were driving factors for the differentiation between walkers and non-walkers. Distal myotomes L4-S1 were revealed to be responsible for the prognostic distinction of indoor and outdoor walkers (with and without aids). CONCLUSION: Stratification of a heterogeneous population with paraplegic SCI into more homogeneous subgroups, combined with the identification of underlying muscle functions prospectively determining the walking outcome, enable potential benefit for application in clinical trials and practice.

Lithium treatment extends human lifespan: findings from the UK Biobank.

Lithium is a nutritional trace element that is also used pharmacologically for the management of bipolar and related psychiatric disorders. Recent studies have shown that lithium supplementation can extend health and lifespan in different animal models. Moreover, nutritional lithium uptake from drinking water was repeatedly found to be positively correlated with human longevity. By analyzing a large observational aging cohort (UK Biobank, n = 501,461 individuals) along with prescription data derived from the National Health Services (NHS), we here find therapeutic supplementation of lithium linked to decreased mortality (p = 0.0017) of individuals diagnosed with affective disorders. Subsequent multivariate survival analyses reveal lithium to be the strongest factor in regards to increased survival effects (hazard ratio = 0.274 [0.119-0.634 CI 95%, p = 0.0023]), corresponding to 3.641 times lower (95% CI 1.577-8.407) chances of dying at a given age for lithium users compared to users of other anti-psychotic drugs. While these results may further support the use of lithium as a geroprotective supplement, it should be noted that doses applied within the UK Biobank/NHS setting require close supervision by qualified medical professionals.

International surveillance study in acute spinal cord injury confirms viability of multinational clinical trials.

BACKGROUND: The epidemiological international landscape of traumatic spinal cord injury (SCI) has evolved over the last decades along with given inherent differences in acute care and rehabilitation across countries and jurisdictions. However, to what extent these differences may influence neurological and functional recovery as well as the integrity of international trials is unclear. The latter also relates to historical clinical data that are exploited to inform clinical trial design and as potential comparative data. METHODS: Epidemiological and clinical data of individuals with traumatic and ischemic SCI enrolled in the European Multi-Center Study about Spinal Cord Injury (EMSCI) were analyzed. Mixed-effect models were employed to account for the longitudinal nature of the data, efficiently handle missing data, and adjust for covariates. The primary outcomes comprised demographics/injury characteristics and standard scores to quantify neurological (i.e., motor and sensory scores examined according to the International Standards for the Neurological Classification of Spinal Cord Injury) and functional recovery (walking function). We externally validated our findings leveraging data from a completed North American landmark clinical trial. RESULTS: A total of 4601 patients with acute SCI were included. Over the course of 20 years, the ratio of male to female patients remained stable at 3:1, while the distribution of age at injury significantly shifted from unimodal (2001/02) to bimodal distribution (2019). The proportional distribution of injury severities and levels remained stable with the largest percentages of motor complete injuries. Both, the rate and pattern of neurological and functional recovery, remained unchanged throughout the surveillance period despite the increasing age at injury. The findings related to recovery profiles were confirmed by an external validation cohort (n=791). Lastly, we built an open-access and online surveillance platform ("Neurosurveillance") to interactively exploit the study results and beyond. CONCLUSIONS: Despite some epidemiological changes and considerable advances in clinical management and rehabilitation, the neurological and functional recovery following SCI has remained stable over the last two decades. Our study, including a newly created open-access and online surveillance tool, constitutes an unparalleled resource to inform clinical practice and implementation of forthcoming clinical trials targeting neural repair and plasticity in acute spinal cord injury.

Cell-based and stem-cell-based treatments for spinal cord injury: evidence from clinical trials.

Spinal cord injury is a severely disabling neurological condition leading to impaired mobility, pain, and autonomic dysfunction. Most often, a single traumatic event, such as a traffic or recreational accident, leads to primary spinal cord damage through compression and laceration, followed by secondary damage consisting of inflammation and ischaemia, and culminating in substantial tissue loss. Patients need appropriate timely surgical and critical care, followed by neurorehabilitation to facilitate neuronal reorganisation and functional compensation. Although some neurological function might be regained, most patients with initially complete lesions have severe, irreversible neurological impairment. Cell-based and stem-cell-based therapies are recognised as promising candidates to promote functional recovery. However, no trials of these therapies in patients have yet provided reproducible evidence for clinical efficacy, challenged by small effect sizes, low immune suppression, and low sensitivity study designs. Nevertheless, in the past decade, clinical trials have shown the feasibility and long-term safety of cell transplantation into the injured spinal cord. This crucial milestone has paved the way to consider refinements and combined therapies, such as the use of biomaterials to augment the effects of cell transplantation. In the future, emerging cell types, scaffolding, and cell engineering might improve cell survival, integration, and therapeutic efficiency.

Physical Activity and Health-Related Quality of Life in Adults With a Neurologically-Related Mobility Disability During the COVID-19 Pandemic: An Exploratory Analysis.

Background: During the coronavirus-19 (COVID-19) pandemic various containment strategies were employed. Their impact on individuals with neurological conditions, considered vulnerable to COVID-19 complications, remains to be determined. Objective: To investigate associations between physical activity and health-related quality of life outcomes in individuals with a neurological condition during government mandated COVID-19 restrictions. Methods: An e-survey assessing fear of COVID-19, physical activity level and health-related quality of life outcomes (functional disability and pain, anxiety and depression, loneliness, fatigue, and vitality) was distributed to individuals with a neurologically-related mobility disability living in the United Kingdom. Open-ended questions were also included to contextualize barriers and facilitators to engage in physical activity during the COVID-19 pandemic. Gamma-weighted generalized linear models and tree-structured regression models were employed to determine the associations between physical activity and health-related quality of life. Results: Of 199 responses, 69% reported performing less physical activity compared to pre-pandemic. Tree-structured regression models revealed that lower leisure-time physical activity was significantly associated (p ≤ 0.009) with higher depression and fatigue, but lower vitality. The closure of leisure facilities and organized sport (27%) was the most commonly cited barrier to engage in physical activity, while 31% of participants mentioned concerns around their physical and mental health as a facilitator. Conclusion: Our analysis identified homogenous subgroups for depression, fatigue, and vitality based specifically on leisure-time physical activity cut points, irrespective of additional demographic or situational characteristics. Findings highlight the importance of and need to safely promote leisure-time physical activity during the COVID-19 pandemic in this at-risk population to help support health-related quality of life.

Early Prediction of Sepsis in the ICU Using Machine Learning: A Systematic Review.

Background: Sepsis is among the leading causes of death in intensive care units (ICUs) worldwide and its recognition, particularly in the early stages of the disease, remains a medical challenge. The advent of an affluence of available digital health data has created a setting in which machine learning can be used for digital biomarker discovery, with the ultimate goal to advance the early recognition of sepsis. Objective: To systematically review and evaluate studies employing machine learning for the prediction of sepsis in the ICU. Data Sources: Using Embase, Google Scholar, PubMed/Medline, Scopus, and Web of Science, we systematically searched the existing literature for machine learning-driven sepsis onset prediction for patients in the ICU. Study Eligibility Criteria: All peer-reviewed articles using machine learning for the prediction of sepsis onset in adult ICU patients were included. Studies focusing on patient populations outside the ICU were excluded. Study Appraisal and Synthesis Methods: A systematic review was performed according to the PRISMA guidelines. Moreover, a quality assessment of all eligible studies was performed. Results: Out of 974 identified articles, 22 and 21 met the criteria to be included in the systematic review and quality assessment, respectively. A multitude of machine learning algorithms were applied to refine the early prediction of sepsis. The quality of the studies ranged from "poor" (satisfying ≤ 40% of the quality criteria) to "very good" (satisfying ≥ 90% of the quality criteria). The majority of the studies (n = 19, 86.4%) employed an offline training scenario combined with a horizon evaluation, while two studies implemented an online scenario (n = 2, 9.1%). The massive inter-study heterogeneity in terms of model development, sepsis definition, prediction time windows, and outcomes precluded a meta-analysis. Last, only two studies provided publicly accessible source code and data sources fostering reproducibility. Limitations: Articles were only eligible for inclusion when employing machine learning algorithms for the prediction of sepsis onset in the ICU. This restriction led to the exclusion of studies focusing on the prediction of septic shock, sepsis-related mortality, and patient populations outside the ICU. Conclusions and Key Findings: A growing number of studies employs machine learning to optimize the early prediction of sepsis through digital biomarker discovery. This review, however, highlights several shortcomings of the current approaches, including low comparability and reproducibility. Finally, we gather recommendations how these challenges can be addressed before deploying these models in prospective analyses. Systematic Review Registration Number: CRD42020200133.

Natural Progression of Routine Laboratory Markers after Spinal Trauma: A Longitudinal, Multi-Cohort Study.

Our objective was to track and quantify the natural course of serological markers over the 1st year following spinal cord injury. For that purpose, data on serological markers, demographics, and injury characteristics were extracted from medical records of a clinical trial (Sygen) and an ongoing observational cohort study (Murnau study). The primary outcomes were concentration/levels/amount of commonly collected serological markers at multiple time points. Two-way analysis of variance (ANOVA) and mixed-effects regression techniques were used to account for the longitudinal data and adjust for potential confounders. Trajectories of serological markers contained in both data sources were compared using the slope of progression. Our results show that, at baseline (≤ 2 weeks post-injury), most serological markers were at pathological levels, but returned to normal values over the course of 6-12 months post-injury. The baseline levels and longitudinal trajectories were dependent on injury severity. More complete injuries were associated with more pathological values (e.g., hematocrit, ANOVA test; χ2 = 68.93, df = 3, adjusted p value <0.001, and χ2 = 73.80, df = 3, adjusted p value <0.001, in the Sygen and Murnau studies, respectively). Comparing the two databases revealed some differences in the serological markers, which are likely attributable to differences in study design, sample size, and standard of care. We conclude that because of trauma-induced physiological perturbations, serological markers undergo marked changes over the course of recovery, from initial pathological levels that normalize within a year. The findings from this study are important, as they provide a benchmark for clinical decision making and prospective clinical trials. All results can be interactively explored on the Haemosurveillance web site (https://jutzelec.shinyapps.io/Haemosurveillance/) and GitHub repository (https://github.com/jutzca/Systemic-effects-of-Spinal-Cord-Injury).

An intensity matched comparison of laser- and contact heat evoked potentials.

Previous studies comparing laser (LEPs) and contact heat evoked potentials (CHEPs) consistently reported higher amplitudes following laser compared to contact heat stimulation. However, none of the studies matched the perceived pain intensity, questioning if the observed difference in amplitude is due to biophysical differences between the two methods or a mismatch in stimulation intensity. The aims of the current study were twofold: (1) to directly compare the brain potentials induced by intensity matched laser and contact heat stimulation and (2) investigate how capsaicin-induced secondary hyperalgesia modulates LEPs and CHEPs. Twenty-one healthy subjects were recruited and measured at four experimental sessions: (1) CHEPs + sham, (2) LEPs + sham, (3) CHEPs + capsaicin, and (4) LEPs + capsaicin. Baseline (sham) LEPs latency was significantly shorter and amplitude significantly larger compared to CHEPs, even when matched for perceived pain. Neither CHEPs nor LEPs was sensitive enough to detect secondary hyperalgesia. These differences provide evidence that a faster heating rate results in an earlier and more synchronized LEPs than CHEPs. To our knowledge, this was the first study to match perceived intensity of contact heat and laser stimulations, revealing distinct advantages associated with the acquisition of LEPs.

Routine Blood Chemistry Predicts Functional Recovery After Traumatic Spinal Cord Injury: A Post Hoc Analysis.

BACKGROUND: Spinal cord injury (SCI) leads to various degrees of lifelong functional deficits. Most individuals with incomplete SCI experience a certain degree of functional recovery, especially within the first-year postinjury. However, this is difficult to predict, and surrogate biomarkers are urgently needed. OBJECTIVE: We aimed to (1) determine if routine blood chemistry parameters are related to neurological recovery after SCI, (2) evaluate if such parameters could predict functional recovery, and (3) establish cutoff values that could inform clinical decision-making. METHODS: We performed a post hoc analysis of routine blood chemistry parameters in patients with traumatic SCI (n = 676). Blood samples were collected between 24 and 72 hours as well as at 1, 2, 4, 8, and 52 weeks postinjury. Linear mixed models, regression analysis, and unbiased recursive partitioning (URP) of blood chemistry data were used to relate to and predict walking recovery 1 year postinjury. RESULTS: The temporal profile of platelet counts and serum levels of albumin, alkaline phosphatase, and creatinine differentiated patients who recovered walking from those who remained wheelchair bound. The 4 blood chemistry parameters from the sample collection 8 weeks postinjury predicted functional recovery observed 1 year after incomplete SCI. Finally, URP defined a cutoff for serum albumin at 3.7 g/dL, which in combination with baseline injury severity differentiates individuals who regain ambulation from those not able to walk. Specifically, about 80% of those with albumin >3.7 g/dL recovered walking. CONCLUSIONS: Routine blood chemistry data from the postacute phase, together with baseline injury severity, predict functional outcome after incomplete SCI.

Single-trial averaging improves the physiological interpretation of contact heat evoked potentials.

Laser and contact heat evoked potentials (LEPs and CHEPs, respectively) provide an objective measure of pathways and processes involved in nociception. The majority of studies analyzing LEP or CHEP outcomes have done so based on conventional, across-trial averaging. With this approach, evoked potential components are potentially confounded by latency jitter and ignore relevant information contained within single trials. The current study addressed the advantage of analyzing nociceptive evoked potentials based on responses to noxious stimulations within each individual trial. Single-trial and conventional averaging were applied to data previously collected in 90 healthy subjects from 3 stimulation locations on the upper limb. The primary analysis focused on relationships between single and across-trial averaged CHEP outcomes (i.e., N2P2 amplitude and N2 and P2 latencies) and subject characteristics (i.e., age, sex, height, and rating of perceived intensity), which were examined by way of linear mixed model analysis. Single-trial averaging lead to larger N2P2 amplitudes and longer N2 and P2 latencies. Age and ratings of perceived intensity were the only subject level characteristics associated with CHEPs outcomes that significantly interacted with the method of analysis (conventional vs single-trial averaging). The strength of relationships for age and ratings of perceived intensity, measured by linear fit, were increased for single-trial compared to conventional across-trial averaged CHEP outcomes. By accounting for latency jitter, single-trial averaging improved the associations between CHEPs and physiological outcomes and should be incorporated as a standard analytical technique in future studies.

Machine Learning for Biomedical Time Series Classification: From Shapelets to Deep Learning.

With the biomedical field generating large quantities of time series data, there has been a growing interest in developing and refining machine learning methods that allow its mining and exploitation. Classification is one of the most important and challenging machine learning tasks related to time series. Many biomedical phenomena, such as the brain's activity or blood pressure, change over time. The objective of this chapter is to provide a gentle introduction to time series classification. In the first part we describe the characteristics of time series data and challenges in its analysis. The second part provides an overview of common machine learning methods used for time series classification. A real-world use case, the early recognition of sepsis, demonstrates the applicability of the methods discussed.

Tardive neurotoxicity of anticholinergic drugs: A review.

The cholinergic system is a complex neurotransmitter system with functional involvement at multiple levels of the nervous system including the cerebral cortex, spinal cord, autonomic nervous system, and neuromuscular junction. Anticholinergic medications are among the most prescribed medications, making up one-third to one-half of all medications prescribed for seniors. Recent evidence has linked long-term use of anticholinergic medications and dementia. Emerging evidence implicates the cholinergic system in the regulation of cerebral vasculature as well as neuroinflammation, suggesting that anticholinergic medications may contribute to absolute risk and progression of neurodegenerative diseases. In this review, we explore the involvement of the cholinergic system in various neurodegenerative diseases and the possible detrimental effects of anticholinergic medications on the onset and progression of these disorders. We identified references by searching the PubMed and Cochrane database between January 1990 and September 2019 for English-language animal and human studies including randomized clinical trials (RCTs), meta-analyses, systematic reviews, and observational studies. In addition, we conducted a manual search of reference lists from retrieved studies. Long-term anticholinergic medication exposure may have detrimental consequences beyond well-documented short-term cognitive effects, through a variety of mechanisms either directly impacting cholinergic neurotransmission or through receptors expressed on the vasculature or immune cells, providing a pathophysiological framework for complex interactions across the entire neuroaxis.