Search

We present a framework for an explainable and statistically validated ensemble clustering model applied to Traumatic Brain Injury (TBI). The objective of our analysis is to identify patient injury severity subgroups and key phenotypes that delineate these subgroups using varied clinical and computed tomography data. Explainable and statistically-validated models are essential because a data-driven identification of subgroups is an inherently multidisciplinary undertaking. In our case, this procedure yielded six distinct patient subgroups with respect to mechanism of injury, severity of presentation, anatomy, psychometric, and functional outcome. This framework for ensemble cluster analysis fully integrates statistical methods at several stages of analysis to enhance the quality and the explainability of results. This methodology is applicable to other clinical data sets that exhibit significant heterogeneity as well as other diverse data science applications in biomedicine and elsewhere.

Traumatic brain injury (TBI) imposes a significant economic and social burden. The diagnosis and prognosis of mild TBI, also called concussion, is challenging. Concussions are common among contact sport athletes. After a blow to the head, it is often difficult to determine who has had a concussion, who should be withheld from play, if a concussed athlete is ready to return to the field, and which concussed athlete will develop a post-concussion syndrome. Biomarkers can be detected in the cerebrospinal fluid and blood after traumatic brain injury and their levels may have prognostic value. Despite significant investigation, questions remain as to the trajectories of blood biomarker levels over time after mild TBI. Modeling the kinetic behavior of these biomarkers could be informative. We propose a one-compartment kinetic model for S100B, UCH-L1, NF-L, GFAP, and tau biomarker levels after mild TBI based on accepted pharmacokinetic models for oral drug absorption. We approximated model parameters using previously published studies. Since parameter estimates were approximate, we did uncertainty and sensitivity analyses. Using estimated kinetic parameters for each biomarker, we applied the model to an available post-concussion biomarker dataset of UCH-L1, GFAP, tau, and NF-L biomarkers levels. We have demonstrated the feasibility of modeling blood biomarker levels after mild TBI with a one compartment kinetic model. More work is needed to better establish model parameters and to understand the implications of the model for diagnostic use of these blood biomarkers for mild TBI.

Concussions represent a growing health concern that are challenging to diagnose and manage. Roughly four million concussions are diagnosed every year in the United States. While research in machine learning applications for concussions has focused on using advanced metrics such neuroimaging techniques and blood biomarkers, these metrics are yet to be implemented at a clinical level due to cost and reliability concerns. Therefore, concussion diagnosis is still reliant on clinical evaluations of symptoms, balance, and neurocognitive status and function. The lack of a universal threshold on these assessments makes the diagnosis process reliant on a physician’s interpretation of these assessment scores. This study aims to explore the use of machine learning techniques to aid the concussion diagnosis process. These models could provide an automated means to flag concussed patients even before being seen by a doctor as well as expand the scope of concussion diagnosis to remote locations and areas with limited access to doctors.

Clinicians need better tools to assess severity, prognosis, and recovery from mild Traumatic Brain Injury (mTBI), which can cause long term impairment. To enable better mTBI outcome prediction, an initial step is to analyze the trajectory of recovery metrics over time. This study provides an assessment of recovery trajectories of mTBI while incorporating heterogeneity of individual responses. We analyze the trajectories over multiple discrete time points from baseline to 6 months post injury using a combination of neurocognitive and postural stability assessments and serum biomarkers. The data, obtained from FITBIR, consists of concussed subjects and a matched control group, to allow for comparison in prognostic assessment. Outcomes derived from this exploratory analysis will aid future studies in developing a mTBI recovery timeline model.Clinical relevance— This study further informs clinicians as to the recovery trajectory of clinical measures and biomarkers after mTBI to support return to play decisions. GFAP biomarker and measures related to balance, memory, orientation, and concentration were significantly different than controls early after mTBI.

Background Patient distances can be calculated based on signs and symptoms derived from an ontological hierarchy. There is controversy as to whether patient distance metrics that consider the semantic similarity between concepts can outperform standard patient distance metrics that are agnostic to concept similarity. The choice of distance metric can dominate the performance of classification or clustering algorithms. Our objective was to determine if semantically augmented distance metrics would outperform standard metrics on machine learning tasks. Methods We converted the neurological findings from 382 published neurology cases into sets of concepts with corresponding machine-readable codes. We calculated patient distances by four different metrics (cosine distance, a semantically augmented cosine distance, Jaccard distance, and a semantically augmented bipartite distance). Semantic augmentation for two of the metrics depended on concept similarities from a hierarchical neuro-ontology. For machine learning algorithms, we used the patient diagnosis as the ground truth label and patient findings as machine learning features. We assessed classification accuracy for four classifiers and cluster quality for two clustering algorithms for each of the distance metrics. Results Inter-patient distances were smaller when the distance metric was semantically augmented. Classification accuracy and cluster quality were not significantly different by distance metric. Conclusion Although semantic augmentation reduced inter-patient distances, we did not find improved classification accuracy or improved cluster quality with semantically augmented patient distance metrics when applied to a dataset of neurology patients. Further work is needed to assess the utility of semantically augmented patient distances.

The flipped classroom has the potential to improve student performance. Because flipping involves both preclass preparation and problem solving in the classroom, the means by which increased learning occurs and whether the method of delivering content matters is of interest. In a partially flipped cell biology course, students were assigned online videos before the flipped class and textbook reading before lectures. Low-stakes assessments were used to incentivize both types of preclass preparation. We hypothesized that more students would watch the videos than read the textbook and that both types of preparation would positively affect exam performance. A multiple linear regression analysis showed that both reading and video viewing had a significant positive impact on exam score, and this model was predictive of exam scores. In contrast to our expectations, most students prepared by both watching videos and reading the textbook and did not exhibit a pattern of solely watching videos. This analysis supports previous findings that engagement with material outside class is partly responsible for the improved outcomes in a flipped classroom and shows that both reading and watching videos are effective at delivering content outside class.

Heterogeneity in Autism Spectrum Disorder (ASD) is complex including variability in behavioral phenotype as well as clinical, physiologic, and pathologic parameters. The fifth edition of the Diagnostic and Statistical Manual of Mental Disorders (DSM-5) now diagnoses ASD using a 2-dimensional model based social communication deficits and fixated interests and repetitive behaviors. Sorting out heterogeneity is crucial for study of etiology, diagnosis, treatment and prognosis. In this paper, we present an ensemble model for analyzing ASD phenotypes using several machine learning techniques and a k-dimensional subspace clustering algorithm. Our ensemble also incorporates statistical methods at several stages of analysis. We apply this model to a sample of 208 probands drawn from the Simon Simplex Collection Missouri Site patients. The results provide useful evidence that is helpful in elucidating the phenotype complexity within ASD. Our model can be extended to other disorders that exhibit a diverse range of heterogeneity.

Controversy remains regarding the neurotoxicity of clade C human immunodeficiency virus (HIV-C). When examined in preclinical studies, a cysteine to serine substitution in the C31 dicysteine motif of the HIV-C Tat protein (C31S) results in less severe brain injury compared to other viral clades. By contrast, patient cohort studies identify significant neuropsychological impairment among HIV-C individuals independent of Tat variability. The present study clarified this discrepancy by examining neuroimaging markers of brain integrity among HIV-C individuals with and without the Tat substitution. Thirty-seven HIV-C individuals with the Tat C31S substitution, 109 HIV-C individuals without the Tat substitution (C31C), and 34 HIV− controls underwent 3T structural magnetic resonance imaging (MRI) and diffusion tensor imaging (DTI). Volumes were determined for the caudate, putamen, thalamus, corpus callosum, total gray matter, and total white matter. DTI metrics included fractional anisotropy (FA), radial diffusivity (RD), and axial diffusivity (AD). Tracts of interest included the anterior thalamic radiation (ATR), cingulum bundle (CING), uncinate fasciculus (UNC), and corpus callosum (CC). HIV+ individuals exhibited smaller volumes in subcortical gray matter, total gray matter and total white matter compared to HIV− controls. HIV+ individuals also exhibited DTI abnormalities across multiple tracts compared to HIV− controls. By contrast, neither volumetric nor diffusion indices differed significantly between the Tat C31S and C31C groups. Tat C31S status is not a sufficient biomarker of HIV-related brain integrity in patient populations. Clinical attention directed at brain health is warranted for all HIV+ individuals, independent of Tat C31S or clade C status.