An international study presenting a federated learning AI platform for pediatric brain tumors.

While multiple factors impact disease, artificial intelligence (AI) studies in medicine often use small, non-diverse patient cohorts due to data sharing and privacy issues. Federated learning (FL) has emerged as a solution, enabling training across hospitals without direct data sharing. Here, we present FL-PedBrain, an FL platform for pediatric posterior fossa brain tumors, and evaluate its performance on a diverse, realistic, multi-center cohort. Pediatric brain tumors were targeted due to the scarcity of such datasets, even in tertiary care hospitals. Our platform orchestrates federated training for joint tumor classification and segmentation across 19 international sites. FL-PedBrain exhibits less than a 1.5% decrease in classification and a 3% reduction in segmentation performance compared to centralized data training. FL boosts segmentation performance by 20 to 30% on three external, out-of-network sites. Finally, we explore the sources of data heterogeneity and examine FL robustness in real-world scenarios with data imbalances.

Cerebroventricular deformation and vector mapping, a topographic visualizer for surgical interventions in pediatric hydrocephalus.

OBJECTIVE: Hydrocephalus is a challenging neurosurgical condition due to nonspecific symptoms and complex brain-fluid pressure dynamics. Typically, the assessment of hydrocephalus in children requires radiographic or invasive pressure monitoring. There is usually a qualitative focus on the ventricular spaces even though stress and shear forces extend across the brain. Here, the authors present an MRI-based vector approach for voxelwise brain and ventricular deformation visualization and analysis. METHODS: Twenty pediatric patients (mean age 7.7 years, range 6 months-18 years; 14 males) with acute, newly diagnosed hydrocephalus requiring surgical intervention for symptomatic relief were randomly identified after retrospective chart review. Selection criteria included acquisition of both pre- and posttherapy paired 3D T1-weighted volumetric MRI (3D T1-MRI) performed on 3T MRI systems. Both pre- and posttherapy 3D T1-MRI pairs were aligned using image registration, and subsequently, voxelwise nonlinear transformations were performed to derive two exemplary visualizations of compliance: 1) a whole-brain vector map projecting the resulting deformation field on baseline axial imaging; and 2) a 3D heat map projecting the volumetric changes along ventricular boundaries and the brain periphery. RESULTS: The patients underwent the following interventions for treatment of hydrocephalus: endoscopic third ventriculostomy (n = 6); external ventricular drain placement and/or tumor resection (n = 10); or ventriculoperitoneal shunt placement (n = 4). The mean time between pre- and postoperative imaging was 36.5 days. Following intervention, the ventricular volumes decreased significantly (mean pre- and posttherapy volumes of 151.9 cm3 and 82.0 cm3, respectively; p < 0.001, paired t-test). The largest degree of deformation vector changes occurred along the lateral ventricular spaces, relative to the genu and splenium. There was a significant correlation between change in deformation vector magnitudes within the cortical layer and age (p = 0.011, Pearson), as well as between the ventricle size and age (p = 0.014, Pearson), suggesting higher compliance among infants and younger children. CONCLUSIONS: This study highlights an approach for deformation analysis and vector mapping that may serve as a topographic visualizer for therapeutic interventions in patients with hydrocephalus. A future study that correlates the degree of cerebroventricular deformation or compliance with intracranial pressures could clarify the potential role of this technique in noninvasive pressure monitoring or in cases of noncompliant ventricles.

A survey of the members of the American Society of Pediatric Neurosurgeons and factors associated with well-being.

OBJECTIVE: The goal of this study was to survey the members of the American Society of Pediatric Neurosurgeons (ASPN) to assess the prevalence and associated risks of burnout among pediatric neurosurgeons. The authors aimed to identify the factors that most significantly contributed to this risk to provide a baseline group of characteristics to improve physician well-being. METHODS: Institutional Review Board approval from the University of Arizona was obtained, and the 7-question and 9-question Mayo Physician Well-Being Index (WBI) was distributed to members of the ASPN (n = 275). This index screens for many different aspects of distress for physicians, including burnout risk, stress, depression, fatigue, suicidal ideation, and low career satisfaction. RESULTS: An analysis of 111 pediatric neurosurgeons (111/275 [40% response rate]) was completed. Respondent ages were distributed, with those aged 56-60 years representing the highest proportion (20%). University practice represented a majority (72%). One-third (32%) of respondents reported practicing greater than 25 years, and most physicians in the survey were married (76%). One-third of surgeons spend 61-70 hours working per week (33%), and a plurality are on call between 6 and 10 days per month (42%). Most surgeons reported treating fewer than 200 cases per year (37% reported 100-150 cases; 23%, 151-200). Most pediatric neurosurgeons (63%) stated their annual salary was sufficient. Analysis of each WBI question was performed to identify which factors specifically contributed to the risk of burnout. An overwhelming majority of respondents reported that they make significant efforts to do at least one thing each week that brings them joy (97%), and they either agree or strongly agree that they perform meaningful work (98% of all participants, 97% of females, and 98% of men, p = 0.010). Nearly half of all respondents (49%) reported feelings of burnout and a majority of them were female (67% of women and 42% of men, p = 0.021). Time, environment, case volumes, and quality-of-life concerns are all factors that significantly contribute to the overall risk of burnout and well-being. CONCLUSIONS: This survey study of the ASPN membership revealed a 49% rate of burnout with females at higher risk (67%). Factors associated with burnout were salary, more than 10 days on call per month, electronic medical record stressors, and work-life incongruity. The aforementioned notwithstanding, respondents believe pediatric neurosurgery is a meaningful career. This study provides evidence supporting a moral imperative toward recognition of burnout symptoms and a pivot point toward implementing change.

The role of occipital condyle and atlas anomalies on occipital cervical fusion outcomes in Chiari malformation type I with syringomyelia: a study from the Park-Reeves Syringomyelia Research Consortium.

OBJECTIVE: Congenital anomalies of the atlanto-occipital articulation may be present in patients with Chiari malformation type I (CM-I). However, it is unclear how these anomalies affect the biomechanical stability of the craniovertebral junction (CVJ) and whether they are associated with an increased incidence of occipitocervical fusion (OCF) following posterior fossa decompression (PFD). The objective of this study was to determine the prevalence of condylar hypoplasia and atlas anomalies in children with CM-I and syringomyelia. The authors also investigated the predictive contribution of these anomalies to the occurrence of OCF following PFD (PFD+OCF). METHODS: The authors analyzed the prevalence of condylar hypoplasia and atlas arch anomalies for patients in the Park-Reeves Syringomyelia Research Consortium database who underwent PFD+OCF. Condylar hypoplasia was defined by an atlanto-occipital joint axis angle (AOJAA) ≥ 130°. Atlas assimilation and arch anomalies were identified on presurgical radiographic imaging. This PFD+OCF cohort was compared with a control cohort of patients who underwent PFD alone. The control group was matched to the PFD+OCF cohort according to age, sex, and duration of symptoms at a 2:1 ratio. RESULTS: Clinical features and radiographic atlanto-occipital joint parameters were compared between 19 patients in the PFD+OCF cohort and 38 patients in the PFD-only cohort. Demographic data were not significantly different between cohorts (p > 0.05). The mean AOJAA was significantly higher in the PFD+OCF group than in the PFD group (144° ± 12° vs 127° ± 6°, p < 0.0001). In the PFD+OCF group, atlas assimilation and atlas arch anomalies were identified in 10 (53%) and 5 (26%) patients, respectively. These anomalies were absent (n = 0) in the PFD group (p < 0.001). Multivariate regression analysis identified the following 3 CVJ radiographic variables that were predictive of OCF occurrence after PFD: AOJAA ≥ 130° (p = 0.01), clivoaxial angle < 125° (p = 0.02), and occipital condyle-C2 sagittal vertical alignment (C-C2SVA) ≥ 5 mm (p = 0.01). A predictive model based on these 3 factors accurately predicted OCF following PFD (C-statistic 0.95). CONCLUSIONS: The authors' results indicate that the occipital condyle-atlas joint complex might affect the biomechanical integrity of the CVJ in children with CM-I and syringomyelia. They describe the role of the AOJAA metric as an independent predictive factor for occurrence of OCF following PFD. Preoperative identification of these skeletal abnormalities may be used to guide surgical planning and treatment of patients with complex CM-I and coexistent osseous pathology.

AI-Based Denoising of Head Impact Kinematics Measurements With Convolutional Neural Network for Traumatic Brain Injury Prediction.

OBJECTIVE: Wearable devices are developed to measure head impact kinematics but are intrinsically noisy because of the imperfect interface with human bodies. This study aimed to improve the head impact kinematics measurements obtained from instrumented mouthguards using deep learning to enhance traumatic brain injury (TBI) risk monitoring. METHODS: We developed one-dimensional convolutional neural network (1D-CNN) models to denoise mouthguard kinematics measurements for tri-axial linear acceleration and tri-axial angular velocity from 163 laboratory dummy head impacts. The performance of the denoising models was evaluated on three levels: kinematics, brain injury criteria, and tissue-level strain and strain rate. Additionally, we performed a blind test on an on-field dataset of 118 college football impacts and a test on 413 post-mortem human subject (PMHS) impacts. RESULTS: On the dummy head impacts, the denoised kinematics showed better correlation with reference kinematics, with relative reductions of 36% for pointwise root mean squared error and 56% for peak absolute error. Absolute errors in six brain injury criteria were reduced by a mean of 82%. For maximum principal strain and maximum principal strain rate, the mean error reduction was 35% and 69%, respectively. On the PMHS impacts, similar denoising effects were observed and the peak kinematics after denoising were more accurate (relative error reduction for 10% noisiest impacts was 75.6%). CONCLUSION: The 1D-CNN denoising models effectively reduced errors in mouthguard-derived kinematics measurements on dummy and PMHS impacts. SIGNIFICANCE: This study provides a novel approach for denoising head kinematics measurements in dummy and PMHS impacts, which can be further validated on more real-human kinematics data before real-world applications.

Neurosurgical Outcomes Among Non-English Speakers: A Systematic Review and a Framework for Future Research.

OBJECTIVE: In 2019, 22% of adults in the United States reported speaking a language other than English at home, representing 52% growth since 2000. This diversity in languages - and resulting possible communication barriers - represents a potential challenge to effective care. In this manuscript, we summarize clinical outcomes and healthcare utilization patterns of adult and pediatric neurosurgical patients who are non-English primary language speakers (NEPLS). METHODS: We systematically queried 5 databases from inception through October 2022. The Preferred Reporting Items for Systematic Reviews and Meta-Analyses guidelines were followed to identify studies for inclusion. The Newcastle-Ottawa Scale was used to assess the quality of studies. Additionally, a retrospective chart review was conducted to assess differences in postoperative communication patterns in a cohort of English and Spanish speaking patients with craniosynostosis at our institution. RESULTS: Our search yielded 442 abstracts; ten were included in the final cohort. Outcomes for 973 unique NEPLS with a neurosurgical condition were included; Spanish was the most represented language. Delivery and timing of surgical treatment was the most frequently reported metric; 75% of studies demonstrated a statistically significant delay in time to surgery or decreased likelihood for NEPLS to receive surgical treatment. Length of stay was reported in 3 studies; all demonstrated that NEPLS had longer length of stay. CONCLUSIONS: There is a paucity of literature reporting outcomes among NEPLS. It is critical to examine NEPLS patients' outcomes and experiences, as language barriers are potentially modifiable demographic factors. We present a framework that demonstrates opportunities for further research to improve quality of care.

Brain Deformation Estimation With Transfer Learning for Head Impact Datasets Across Impact Types.

OBJECTIVE: The machine-learning head model (MLHM) to accelerate the calculation of brain strain and strain rate, which are the predictors for traumatic brain injury (TBI), but the model accuracy was found to decrease sharply when the training/test datasets were from different head impacts types (i.e., car crash, college football), which limits the applicability of MLHMs to different types of head impacts and sports. Particularly, small sizes of target dataset for specific impact types with tens of impacts may not be enough to train an accurate impact-type-specific MLHM. METHODS: To overcome this, we propose data fusion and transfer learning to develop a series of MLHMs to predict the maximum principal strain (MPS) and maximum principal strain rate (MPSR). RESULTS: The strategies were tested on American football (338), mixed martial arts (457), reconstructed car crash (48) and reconstructed American football (36) and we found that the MLHMs developed with transfer learning are significantly more accurate in estimating MPS and MPSR than other models, with a mean absolute error (MAE) smaller than 0.03 in predicting MPS and smaller than [Formula: see text] in predicting MPSR on all target impact datasets. High performance in concussion detection was observed based on the MPS and MPSR estimated by the transfer-learning-based models. CONCLUSION: The MLHMs can be applied to various head impact types for rapidly and accurately calculating brain strain and strain rate. SIGNIFICANCE: This study enables developing MLHMs for the head impact type with limited availability of data, and will accelerate the applications of MLHMs.

Expanding eligibility for intracranial electroencephalography using Dexmedetomidine Hydrochloride in children with behavioral dyscontrol.

INTRODUCTION: Invasive intracranial electroencephalography (IEEG) is advantageous for identifying epileptogenic foci in pediatric patients with medically intractable epilepsy. Patients with behavioral challenges due to autism, intellectual disabilities, and hyperactivity have greater difficulty tolerating prolonged IEEG recording and risk injuring themselves or others. There is a need for therapies that increase the safety of IEEG but do not interfere with IEEG recording or prolong hospitalization. Dexmedetomidine Hydrochloride's (DH) use has been reported to improve safety in patients with behavioral challenges during routine surface EEG recording but has not been characterized during IEEG. Here we evaluated DH administration in pediatric patients undergoing IEEG to assess its safety and impact on the IEEG recordings. METHODS: A retrospective review identified all pediatric patients undergoing IEEG between January 2016 and September 2022. Patient demographics, DH administration, DH dose, hospital duration, and IEEG seizure data were analyzed. The number of seizures recorded for each patient was divided by the days each patient was monitored with IEEG. The total number of seizures, as well as seizures per day, were compared between DH and non-DH patients via summary statistics, multivariable linear regression, and univariate analysis. Other data were compared across groups with univariate statistics. RESULTS: Eighty-four pediatric patients met the inclusion criteria. Eighteen (21.4 %) received DH treatment during their IEEG recording. There were no statistical differences between the DH and non-DH groups' demographic data, length of hospital stays, or seizure burden. Non-DH patients had a median age of 12.0 years (interquartile range: 7.25-15.00), while DH-receiving patients had a median age of 8.0 years old (interquartile range: 3.00-13.50) (p = 0.07). The non-DH cohort was 57.6 % male, and the DH cohort was 50.0 % male (p = 0.76). The median length of IEEG recordings was 5.0 days (interquartile range: 4.00-6.25) for DH patients versus 6.0 days (interquartile range: 4.00-8.00) for non-DH patients (p = 0.25). Median total seizures recorded in the non-DH group was 8.0 (interquartile range: 5.00-13.25) versus 15.0 in the DH group (interquartile range: 5.00-22.25) (p = 0.33). Median total seizures per day of IEEG monitoring were comparable across groups: 1.50 (interquartile range: 0.65-3.17) for non-DH patients compared to 2.83 (interquartile range: 0.89-4.35) (p = 0.25) for those who received DH. Lastly, non-DH patients were hospitalized for a median of 8.0 days (interquartile range: 6.00-11.25), while DH patients had a median length of stay of 7.00 days (interquartile range: 5.00-8.25) (p = 0.27). No adverse events were reported because of DH administration. CONCLUSIONS: Administration of DH was not associated with adverse events. Additionally, the frequency of seizures captured on the IEEG, as well as the duration of hospitalization, were not significantly different between patients receiving and not receiving DH during IEEG. Incorporating DH into the management of patients with behavioral dyscontrol and intractable epilepsy may expand the use of IEEG to patients who previously could not tolerate it, improve safety, and preserve epileptic activity during the recording period.

Approach, complications, and outcomes for 37 consecutive pediatric patients undergoing laser ablation for medically refractory epilepsy at Stanford Children's Health.

OBJECTIVE: The objective of this study was to better understand the safety and efficacy of laser interstitial thermal therapy (LITT) for children with medically refractory epilepsy. METHODS: Thirty-seven consecutive pediatric epilepsy patients at a single pediatric center who underwent LITT ablation of epileptogenic foci between May 2017 and December 2021 were retrospectively reviewed. Patient demographics, medication use, seizure frequency, prior surgical interventions, procedural details, and pre- and postoperative seizure history were analyzed. RESULTS: Thirty-seven pediatric patients (24 male, 13 female) with severe medically refractory epilepsy were included; all underwent stereo-electroencephalography (SEEG) prior to LITT. The SEEG electrode placement was based on the preoperative workup and tailored to each patient by the epileptologist and neurosurgeons working together to identify the epileptic network and hopefully quiet borders. Seizure onset was at a mean age of 2.70 ± 2.82 years (range 0.25-12 years), and the mean age at the time of LITT was 9.46 ± 5.08 years (range 2.41-17.86 years). Epilepsy was lesional in 23 patients (18 tuberous sclerosis, 4 focal cortical dysplasia, 1 gliosis) and nonlesional in 14. Eighteen patients had prior surgical interventions including open resections (n = 13: 11 single and 2 multiple), LITT (n = 4), or both (n = 1). LITT targeted a region adjacent to the previous target in 5 cases. The median number of lasers placed during the procedure was 3 (range 1-5). Complications occurred in 14 (37.8%) cases, only 3 (8.11%) of which resulted in a permanent deficit: 1 venous hemorrhage requiring evacuation following laser ablation, 1 aseptic meningitis, 2 immediate postoperative seizures, and 10 neurological deficits (7 transient and 3 permanent). Postoperatively, 22 (59.5%) patients were seizure free at the last follow-up (median follow-up 18.35 months, range 7.40-48.76 months), and the median modified Engel class was I (Engel class I in 22 patients, Engel class II in 2, Engel class III in 2, and Engel class IV in 11). Patients having tried a greater number of antiseizure medications before LITT were less likely to achieve seizure improvement (p = 0.046) or freedom (p = 0.017). Seizure improvement following LITT was associated with a shorter duration of epilepsy prior to LITT (p = 0.044), although postoperative seizure freedom was not associated with a shorter epilepsy duration (p = 0.667). Caregivers reported postoperative neurocognitive improvement in 17 (45.9%) patients. CONCLUSIONS: In this large single-institution cohort of pediatric patients with medically refractory seizures due to various etiologies, LITT was a relatively safe and effective surgical approach for seizure reduction and seizure freedom at 1 year of follow-up.

Treatment Course and Outcomes of Intracranial Teratomas in Pediatric Patients: A Retrospective 15-Year Case Series Study.

INTRODUCTION: There is no standard treatment paradigm for intracranial teratomas, a rare subset of primary intracranial non-germinomatous germ cell tumors (NGGCT), which comprise less than 1% of pediatric brain tumors. This case series retrospectively analyzes treatment and outcomes of pediatric intracranial teratomas from a single institution. METHODS: Authors reviewed a comprehensive pathology database at Stanford's Lucile Packard Children's Hospital for intracranial teratomas in pediatric patients treated from 2006 to 2021; their demographics, treatment, and clinical course were analyzed. RESULTS: Among 14 patients, median follow-up time was 4.6 years and mean age at diagnosis was 10.5 years. Ten had elevated tumor markers and underwent chemotherapy as initial treatment for NGGCT. Ultimately, these patients all required surgery for progressive or residual disease. Two patients did not undergo radiation. After biopsy or resection, 8 patients had pure mature teratoma, five had mixed germ cell tumor with teratoma component, and one had immature teratoma. The patient with immature teratoma died during chemotherapy from septic shock. No patients experienced recurrence. Common sequelae were endocrine (42.8%) and eye movement (50.0%) abnormalities. DISCUSSION/CONCLUSION: We highlight the variable treatment course and outcome for pediatric patients with intracranial teratomas. Elevated tumor markers at presentation, along with imaging findings, favor chemotherapy initiation for presumed NGGCT. Resection of residual tumor is recommended even if tumor markers return to normal. Prognosis remains excellent; no patients had recurrence with a median follow-up of 4.6 years.

Disparities in Postoperative Communication Patterns Among Spanish-speaking Pediatric Patients with Hydrocephalus.

OBJECTIVE: To determine if differences exist in postoperative communication patterns or healthcare use among English-speaking patients (ESPs) and Spanish-speaking patients (SSPs) with childhood hydrocephalus. STUDY DESIGN: A single-institution, retrospective cohort study was conducted. Through simple random sampling, 50 ESPs and 50 SSPs (<18 years old) who underwent a ventriculoperitoneal shunt or endoscopic third ventriculostomy were identified. Demographics, communication with clinic (eg, number of calls or messages postoperatively), and healthcare use were collected. Multiple linear regressions assessed the significance of predictors on communication frequency and use. RESULTS: SSPs were more likely to have a comorbidity and ventriculoperitoneal shunt than ESPs. SSPs had longer median postoperative length of stay (P < .01) and 30-day readmission rate (P < .01) than ESPs. Only 18% of SSPs communicated with clinic; 11 total calls or messages were from SSPs vs 57 from ESPs (P < .01). The most common reason for outreach among both cohorts was a new symptom. ESP outreach most frequently resulted in reassurance or medical course changes on an outpatient basis (30% ESPs vs 0% SSPs; P = .04), whereas SSP outreach most frequently resulted in guidance to present to the emergency department (3% ESPs vs 36% SSPs; P < .01). Language remained a significant predictor for number of calls or messages, even after adjusting for comorbidity, operation type, and insurance (P < .01). CONCLUSIONS: Despite having more complex disease, only 18% of SSPs communicated with the neurosurgical team postoperatively and were more frequently sent to the emergency department for management. Future research will explore communication barriers and preferences to ensure postoperative care is timely and patient centered.

Clinical Applications of Immunotherapy for Recurrent Glioblastoma in Adults.

Glioblastoma (GBM) is the most common malignant primary brain tumor in adults. Despite standard therapies, including resection and chemoradiation, recurrence is virtually inevitable. Current treatment for recurrent glioblastoma (rGBM) is rapidly evolving, and emerging therapies aimed at targeting primary GBM are often first tested in rGBM to demonstrate safety and feasibility, which, in recent years, has primarily been in the form of immunotherapy. The purpose of this review is to highlight progress in clinical trials of immunotherapy for rGBM, including immune checkpoint blockade, oncolytic virotherapy, chimeric antigen receptor (CAR) T-cell therapy, cancer vaccine and immunotoxins. Three independent reviewers covered literature, published between the years 2000 and 2022, in various online databases. In general, the efficacy of immunotherapy in rGBM remains uncertain, and is limited to subsets/small cohorts of patients, despite demonstrating feasibility in early-stage clinical trials. However, considerable progress has been made in understanding the mechanisms that may preclude rGBM patients from responding to immunotherapy, as well as in developing new approaches/combination strategies that may inspire optimism for the utility of immunotherapy in this devastating disease. Continued trials are necessary to further assess the best therapeutic avenues and ascertain which treatments might benefit each patient individually.

Vein of Galen malformations in the newborn: case series.

BACKGROUND: Vein of Galen malformations (VoGMs) in newborns often represent life-threatening emergencies. Outcome is difficult to predict. The authors review 50 VoGM cases to correlate anatomical types with treatment and outcome. OBSERVATIONS: Four distinct types of VoGMs are identified: mural simple (type I), mural complex (type II), choroidal (type III), and choroidal with deep venous drainage (type IV). Seven patients presented with mural simple VoGMs with a "single hole" fistula supplied by only one large feeder. These patients were treated electively at >6 months; development was normal. Fifteen patients presented with complex mural VoGMs. Multiple large feeders joined a single fistulous point within the wall of the varix. Patients typically presented with congestive heart failure (CHF) and required emergent transarterial intervention. Mortality was 7.7% with less than two-thirds developing normally. Twenty-five patients presented with choroidal VoGMs. Multiple large arterial feeders joined at multiple fistulous sites. Severe CHF in most patients required emergent transarterial and sometimes transvenous intervention. Mortality was 9.5%; two-thirds of the patients had a normal development. Three babies presented with choroidal VoGMs with deep intraventricular venous drainage. This phenomenon caused fatal "melting brain syndrome" in all three patients. LESSONS: Recognition of the specific VoGM type determines treatment options and sets outcome expectations.

Padded Helmet Shell Covers in American Football: A Comprehensive Laboratory Evaluation with Preliminary On-Field Findings.

Protective headgear effects measured in the laboratory may not always translate to the field. In this study, we evaluated the impact attenuation capabilities of a commercially available padded helmet shell cover in the laboratory and on the field. In the laboratory, we evaluated the padded helmet shell cover's efficacy in attenuating impact magnitude across six impact locations and three impact velocities when equipped to three different helmet models. In a preliminary on-field investigation, we used instrumented mouthguards to monitor head impact magnitude in collegiate linebackers during practice sessions while not wearing the padded helmet shell covers (i.e., bare helmets) for one season and whilst wearing the padded helmet shell covers for another season. The addition of the padded helmet shell cover was effective in attenuating the magnitude of angular head accelerations and two brain injury risk metrics (DAMAGE, HARM) across most laboratory impact conditions, but did not significantly attenuate linear head accelerations for all helmets. Overall, HARM values were reduced in laboratory impact tests by an average of 25% at 3.5 m/s (range: 9.7 to 39.6%), 18% at 5.5 m/s (range: - 5.5 to 40.5%), and 10% at 7.4 m/s (range: - 6.0 to 31.0%). However, on the field, no significant differences in any measure of head impact magnitude were observed between the bare helmet impacts and padded helmet impacts. Further laboratory tests were conducted to evaluate the ability of the padded helmet shell cover to maintain its performance after exposure to repeated, successive impacts and across a range of temperatures. This research provides a detailed assessment of padded helmet shell covers and supports the continuation of in vivo helmet research to validate laboratory testing results.

Machine-learning-based head impact subtyping based on the spectral densities of the measurable head kinematics.

BACKGROUND: Traumatic brain injury can be caused by head impacts, but many brain injury risk estimation models are not equally accurate across the variety of impacts that patients may undergo, and the characteristics of different types of impacts are not well studied. We investigated the spectral characteristics of different head impact types with kinematics classification. METHODS: Data were analyzed from 3262 head impacts from lab reconstruction, American football, mixed martial arts, and publicly available car crash data. A random forest classifier with spectral densities of linear acceleration and angular velocity was built to classify head impact types (e.g., football, car crash, mixed martial arts). To test the classifier robustness, another 271 lab-reconstructed impacts were obtained from 5 other instrumented mouthguards. Finally, with the classifier, type-specific, nearest-neighbor regression models were built for brain strain. RESULTS: The classifier reached a median accuracy of 96% over 1000 random partitions of training and test sets. The most important features in the classification included both low- and high-frequency features, both linear acceleration features and angular velocity features. Different head impact types had different distributions of spectral densities in low- and high-frequency ranges (e.g., the spectral densities of mixed martial arts impacts were higher in the high-frequency range than in the low-frequency range). The type-specific regression showed a generally higher R2 value than baseline models without classification. CONCLUSION: The machine-learning-based classifier enables a better understanding of the impact kinematics spectral density in different sports, and it can be applied to evaluate the quality of impact-simulation systems and on-field data augmentation.