Intensive Outpatient Program Response Among Service Members With Mild Traumatic Brain Injury: Change Between Distinct Post-Concussive Symptom Subgroups.

OBJECTIVE: Among service members (SMs) with mild traumatic brain injury (mTBI) admitted to an intensive outpatient program (IOP), we identified qualitatively distinct subgroups based on post-concussive symptoms (PCSs) and characterized changes between subgroups from admission to discharge. Further, we examined whether co-morbid posttraumatic stress disorder (PTSD) influenced changes between subgroups. DESIGN: Quasi-experimental. Latent transition analysis identified distinctive subgroups of SMs and examined transitions between subgroups from admission to discharge. Logistic regression examined the effect of PTSD on transition to the Minimal subgroup (low probability of any moderate-very severe PCS) while adjusting for admission subgroup designation. SETTING: National Intrepid Center of Excellence (NICoE) at Walter Reed National Military Medical Center. PARTICIPANTS: 1141 active duty SMs with persistent PCS despite prior treatment (N=1141). INTERVENTIONS: NICoE 4-week interdisciplinary IOP. MAIN OUTCOME MEASURE(S): Subgroups identified using Neurobehavioral Symptom Inventory items at admission and discharge. RESULTS: Model fit indices supported a 7-class solution. The 7 subgroups of SMs were distinguished by diverging patterns of probability for specific PCS. The Minimal subgroup was most prevalent at discharge (39.4%), followed by the Sleep subgroup (high probability of sleep problems, low probability of other PCS; 26.8%). 41% and 25% of SMs admitted within the Affective (ie, predominantly affective PCS) and Sleep subgroups remained within the same group at discharge, respectively. The 19% of SMs with co-morbid PTSD were less likely to transition to the Minimal subgroup (odds ratio=0.28; P<.001) and were more likely to remain in their admission subgroup at discharge (35.5% with PTSD vs 22.2% without). CONCLUSIONS: Most of SMs achieved symptom resolution after participation in the IOP, with most transitioning to subgroups characterized by reduced symptom burden. SMs admitted in the Affective and Sleep subgroups, as well as those with PTSD, were most likely to have continuing clinical needs at discharge, revealing priority targets for resource allocation and follow-up treatment.

NSI and PCL-5 Normative Tables for Active Duty Service Members Affected by Traumatic Brain Injury.

INTRODUCTION: Many service members (SMs) have been diagnosed with traumatic brain injury. Currently, military treatment facilities do not have access to established normative tables which can assist clinicians in gauging and comparing patient-reported symptoms. The aim of this study is to provide average scores for both the Neurobehavioral Symptom Inventory (NSI) and Posttraumatic Stress Disorder Checklist for DSM-5 (PCL-5) for active duty SMs based upon varying demographic groups. METHODS: Average scores were calculated for both the NSI and PCL-5 surveys from SMs who attended a military outpatient traumatic brain injury clinic. For this analysis, only the initial surveys for each SM were considered. The identifying demographics included age group, gender, grade, and race. RESULTS: Four normative tables were created to show the average scores of both the NSI and PCL-5 surveys grouped by demographics. The tables are grouped by Age Group/Gender/Race and Grade/Gender/Race. CONCLUSION: Clinicians and healthcare administrators can use the scores reported in this study to determine where SM NSI or PCL-5 scores fall within the average for their demographic group.

Correlations Between the Neurobehavioral Symptom Inventory and Other Commonly Used Questionnaires for Traumatic Brain Injury.

OBJECTIVE: To evaluate the correlations between the Neurobehavioral Symptom Inventory (NSI) and other questionnaires commonly administered within military traumatic brain injury clinics. SETTING: Military outpatient traumatic brain injury clinics. PARTICIPANTS: In total, 15,428 active duty service members who completed 24,162 NSI questionnaires between March 2009 and May 2020. DESIGN: Observational retrospective analysis of questionnaires collected as part of standard clinical care. MAIN MEASURES: NSI, Post-Traumatic Stress Disorder Checklist for DSM-5 and Military Version, Patient Health Questionnaire (PHQ), Generalized Anxiety Disorder, Headache Impact Test (HIT-6), Insomnia Severity Index (ISI), Epworth Sleepiness Scale (ESS), Activities-Specific Balance Confidence Scale (ABC), Dizziness Handicap Inventory (DHI), Alcohol Use Disorders Identification Test (AUDIT), and the World Health Organization Quality of Life Instrument-Abbreviated Version. Only questionnaires completed on the same date as the NSI were examined. RESULTS: The total NSI score was moderately to strongly correlated with all questionnaires except for the AUDIT. The strongest correlation was between the NSI Affective Score and the PHQ9 (r = 0.86). The NSI Vestibular Score was moderately correlated with the ABC (r = -0.55) and strongly correlated with the DHI (r = 0.77). At the item level, the HIT-6 showed strong correlation with NSI headache (r = 0.80), the ISI was strongly correlated with NSI difficulty sleeping (r = 0.63), and the ESS was moderately correlated with NSI fatigue (r = 0.39). CONCLUSION: Clinicians and healthcare administrators can use the correlations reported in this study to determine if questionnaires add incremental value for their clinic as well as to make more informed decisions regarding which questionnaires to administer.

Burden of Behavioral Health Comorbidities on Outpatient Health Care Utilization by Active Duty Service Members With a First Documented mTBI.

OBJECTIVE: More than 280,000 Active Duty Service Members (ADSMs) sustained a mild traumatic brain injury (mTBI) between 2000 and 2019 (Q3). Previous studies of veterans have shown higher utilization of outpatient health clinics by veterans diagnosed with mTBI. Additionally, veterans with mTBI and comorbid behavioral health (BH) conditions such as post-traumatic stress disorder, depression, and substance use disorders have significantly higher health care utilization than veterans diagnosed with mTBI alone. However, few studies of the relationship between mTBI, health care utilization, and BH conditions in the active duty military population currently exist. We examined the proportion of ADSMs with a BH diagnosis before and after a first documented mTBI and quantified outpatient utilization of the Military Health System in the year before and following injury. MATERIALS AND METHODS: Retrospective analysis of 4,901,840 outpatient encounters for 39,559 ADSMs with a first documented diagnosis of mTBI recorded in the Department of Defense electronic health record, subsets of who had a BH diagnosis. We examined median outpatient utilization 1 year before and 1 year after mTBI using Wilcoxon signed rank test, and the results are reported with an effect size r. Outpatient utilization is compared by BH subgroups. RESULTS: Approximately 60% of ADSMs experience a first mTBI with no associated BH condition, but 17% of men and women are newly diagnosed with a BH condition in the year following mTBI. ADSMs with a history of a BH condition before mTBI increased their median outpatient utilization from 23 to 35 visits for men and from 32 to 42 visits for women. In previously healthy ADSMs with a new BH condition following mTBI, men more than tripled median utilization from 7 to 24 outpatient visits, and women doubled utilization from 15 to 32 outpatient visits. CONCLUSIONS: Behavioral health comorbidities affect approximately one-third of ADSMs following a first mTBI, and approximately 17% of previously healthy active duty men and women will be diagnosed with a new BH condition in the year following a first mTBI. Post-mTBI outpatient health care utilization is highly dependent on the presence or absence of BH condition and is markedly higher is ADSMs with a BH diagnosis in the year after a first documented mTBI.

Evaluation of Machine Learning Techniques to Predict the Likelihood of Mental Health Conditions Following a First mTBI.

OBJECTIVE: Limited research has evaluated the utility of machine learning models and longitudinal data from electronic health records (EHR) to forecast mental health outcomes following a traumatic brain injury (TBI). The objective of this study is to assess various data science and machine learning techniques and determine their efficacy in forecasting mental health (MH) conditions among active duty Service Members (SMs) following a first diagnosis of mild traumatic brain injury (mTBI). MATERIALS AND METHODS: Patient demographics and encounter metadata of 35,451 active duty SMs who have sustained an initial mTBI, as documented within the EHR, were obtained. All encounter records from a year prior and post index mTBI date were collected. Patient demographics, ICD-9-CM and ICD-10 codes, enhanced diagnostic related groups, and other risk factors estimated from the year prior to index mTBI were utilized to develop a feature vector representative of each patient. To embed temporal information into the feature vector, various window configurations were devised. Finally, the presence or absence of mental health conditions post mTBI index date were used as the outcomes variable for the models. RESULTS: When evaluating the machine learning models, neural network techniques showed the best overall performance in identifying patients with new or persistent mental health conditions post mTBI. Various window configurations were tested and results show that dividing the observation window into three distinct date windows [-365:-30, -30:0, 0:14] provided the best performance. Overall, the models described in this paper identified the likelihood of developing MH conditions at [14:90] days post-mTBI with an accuracy of 88.2%, an AUC of 0.82, and AUC-PR of 0.66. DISCUSSION: Through the development and evaluation of different machine learning models we have validated the feasibility of designing algorithms to forecast the likelihood of developing mental health conditions after the first mTBI. Patient attributes including demographics, symptomatology, and other known risk factors proved to be effective features to employ when training ML models for mTBI patients. When patient attributes and features are estimated at different time window, the overall performance increase illustrating the importance of embedding temporal information into the models. The addition of temporal information not only improved model performance, but also increased interpretability and clinical utility. CONCLUSION: Predictive analytics can be a valuable tool for understanding the effects of mTBI, particularly when identifying those individuals at risk of negative outcomes. The translation of these models from retrospective study into real-world validation models is imperative in the mitigation of negative outcomes with appropriate and timely interventions.

Evaluating visual analytics for health informatics applications: a systematic review from the American Medical Informatics Association Visual Analytics Working Group Task Force on Evaluation.

OBJECTIVE: This article reports results from a systematic literature review related to the evaluation of data visualizations and visual analytics technologies within the health informatics domain. The review aims to (1) characterize the variety of evaluation methods used within the health informatics community and (2) identify best practices. METHODS: A systematic literature review was conducted following PRISMA guidelines. PubMed searches were conducted in February 2017 using search terms representing key concepts of interest: health care settings, visualization, and evaluation. References were also screened for eligibility. Data were extracted from included studies and analyzed using a PICOS framework: Participants, Interventions, Comparators, Outcomes, and Study Design. RESULTS: After screening, 76 publications met the review criteria. Publications varied across all PICOS dimensions. The most common audience was healthcare providers (n = 43), and the most common data gathering methods were direct observation (n = 30) and surveys (n = 27). About half of the publications focused on static, concentrated views of data with visuals (n = 36). Evaluations were heterogeneous regarding setting and measurements used. DISCUSSION: When evaluating data visualizations and visual analytics technologies, a variety of approaches have been used. Usability measures were used most often in early (prototype) implementations, whereas clinical outcomes were most common in evaluations of operationally-deployed systems. These findings suggest opportunities for both (1) expanding evaluation practices, and (2) innovation with respect to evaluation methods for data visualizations and visual analytics technologies across health settings. CONCLUSION: Evaluation approaches are varied. New studies should adopt commonly reported metrics, context-appropriate study designs, and phased evaluation strategies.

A Grammar-based Approach for Modeling User Interactions and Generating Suggestions During the Data Exploration Process.

Despite the recent popularity of visual analytics focusing on big data, little is known about how to support users that use visualization techniques to explore multi-dimensional datasets and accomplish specific tasks. Our lack of models that can assist end-users during the data exploration process has made it challenging to learn from the user's interactive and analytical process. The ability to model how a user interacts with a specific visualization technique and what difficulties they face are paramount in supporting individuals with discovering new patterns within their complex datasets. This paper introduces the notion of visualization systems understanding and modeling user interactions with the intent of guiding a user through a task thereby enhancing visual data exploration. The challenges faced and the necessary future steps to take are discussed; and to provide a working example, a grammar-based model is presented that can learn from user interactions, determine the common patterns among a number of subjects using a K-Reversible algorithm, build a set of rules, and apply those rules in the form of suggestions to new users with the goal of guiding them along their visual analytic process. A formal evaluation study with 300 subjects was performed showing that our grammar-based model is effective at capturing the interactive process followed by users and that further research in this area has the potential to positively impact how users interact with a visualization system.

A Large-Scale Informatics Database to Advance Research and Discovery of the Effects of Mild Traumatic Brain Injury.

Clinical research advances in traumatic brain injury (TBI) and behavioral health have always been restricted by the quantity and quality of the data as well as the difficulty of collecting standardized clinical elements. Those barriers, together with the complexity of evaluating TBI, have resulted in serious challenges for clinicians, researchers, and organizations interested in analyzing the short- and long-term effects of TBI. In an effort to raise awareness about existing and cost-effective ways to collect clinical data within the Department of Defense, this article describes some of the steps taken to quickly build a large-scale informatics database to facilitate collection of standardized clinical data and obtain trends of the longitudinal outcomes of service members diagnosed with mild TBI. The database was built following the Defense of Health Agency guidelines and currently has millions of longitudinal clinical data points, Department of Defense-wide clinical data for service members diagnosed with mild TBI to support population studies, and multiple built-in analytical applications to enable interactive data exploration and analysis.

A K-Reversible Approach to Model Clinical Trajectories.

A clinical trajectory can be defined as the path followed by patients between an initial heath state Si such as being healthy to another state Sj such as being diagnosed with a specific clinical condition. Being able to identify the common trajectories that a group of patients take can benefit clinicians at identifying the current state of patient and potentially provide early treatment to avoid going towards specific paths. In this paper we present our approach that enables a clinical dataset of patient encounters to be clustered into groups of similarity and run through our algorithm which produces an automaton displaying the most common trajectories taken by patients. Furthermore, we explore a dataset of patients that have experienced mild traumatic brain injuries (mTBI) to show that our approach is effective at clustering and identifying common trajectories for patients that develop headaches, sleep, and post traumatic stress disorder (PTSD) post concussion.

Five-dimensional ultrasound system for soft tissue visualization.

PURPOSE: A five-dimensional ultrasound (US) system is proposed as a real-time pipeline involving fusion of 3D B-mode data with the 3D ultrasound elastography (USE) data as well as visualization of these fused data and a real-time update capability over time for each consecutive scan. 3D B-mode data assist in visualizing the anatomy of the target organ, and 3D elastography data adds strain information. METHODS: We investigate the feasibility of such a system and show that an end-to-end real-time system, from acquisition to visualization, can be developed. We present a system that consists of (a) a real-time 3D elastography algorithm based on a normalized cross-correlation (NCC) computation on a GPU; (b) real-time 3D B-mode acquisition and network transfer; (c) scan conversion of 3D elastography and B-mode volumes (if acquired by 4D wobbler probe); and (d) visualization software that fuses, visualizes, and updates 3D B-mode and 3D elastography data in real time. RESULTS: We achieved a speed improvement of 4.45-fold for the threaded version of the NCC-based 3D USE versus the non-threaded version. The maximum speed was 79 volumes/s for 3D scan conversion. In a phantom, we validated the dimensions of a 2.2-cm-diameter sphere scan-converted to B-mode volume. Also, we validated the 5D US system visualization transfer function and detected 1- and 2-cm spherical objects (phantom lesion). Finally, we applied the system to a phantom consisting of three lesions to delineate the lesions from the surrounding background regions of the phantom. CONCLUSION: A 5D US system is achievable with real-time performance. We can distinguish between hard and soft areas in a phantom using the transfer functions.

Circulating sex hormones and terminal duct lobular unit involution of the normal breast.

BACKGROUND: Terminal duct lobular units (TDLU) are the predominant source of breast cancers. Lesser degrees of age-related TDLU involution have been associated with increased breast cancer risk, but factors that influence involution are largely unknown. We assessed whether circulating hormones, implicated in breast cancer risk, are associated with levels of TDLU involution using data from the Susan G. Komen Tissue Bank (KTB) at the Indiana University Simon Cancer Center (2009-2011). METHODS: We evaluated three highly reproducible measures of TDLU involution, using normal breast tissue samples from the KTB (n = 390): TDLU counts, median TDLU span, and median acini counts per TDLU. RRs (for continuous measures), ORs (for categorical measures), 95% confidence intervals (95% CI), and Ptrends were calculated to assess the association between tertiles of estradiol, testosterone, sex hormone-binding globulin (SHBG), progesterone, and prolactin with TDLU measures. All models were stratified by menopausal status and adjusted for confounders. RESULTS: Among premenopausal women, higher prolactin levels were associated with higher TDLU counts (RRT3vsT1:1.18; 95% CI: 1.07-1.31; Ptrend = 0.0005), but higher progesterone was associated with lower TDLU counts (RRT3vsT1: 0.80; 95% CI: 0.72-0.89; Ptrend < 0.0001). Among postmenopausal women, higher levels of estradiol (RRT3vsT1:1.61; 95% CI: 1.32-1.97; Ptrend < 0.0001) and testosterone (RRT3vsT1: 1.32; 95% CI: 1.09-1.59; Ptrend = 0.0043) were associated with higher TDLU counts. CONCLUSIONS: These data suggest that select hormones may influence breast cancer risk potentially through delaying TDLU involution. IMPACT: Increased understanding of the relationship between circulating markers and TDLU involution may offer new insights into breast carcinogenesis. Cancer Epidemiol Biomarkers Prev; 23(12); 2765-73. ©2014 AACR.

Quantitative Analysis of TDLUs using Adaptive Morphological Shape Techniques.

Within the complex branching system of the breast, terminal duct lobular units (TDLUs) are the anatomical location where most cancer originates. With aging, TDLUs undergo physiological involution, reflected in a loss of structural components (acini) and a reduction in total number. Data suggest that women undergoing benign breast biopsies that do not show age appropriate involution are at increased risk of developing breast cancer. To date, TDLU assessments have generally been made by qualitative visual assessment, rather than by objective quantitative analysis. This paper introduces a technique to automatically estimate a set of quantitative measurements and use those variables to more objectively describe and classify TDLUs. To validate the accuracy of our system, we compared the computer-based morphological properties of 51 TDLUs in breast tissues donated for research by volunteers in the Susan G. Komen Tissue Bank and compared results to those of a pathologist, demonstrating 70% agreement. Secondly, in order to show that our method is applicable to a wider range of datasets, we analyzed 52 TDLUs from biopsies performed for clinical indications in the National Cancer Institute's Breast Radiology Evaluation and Study of Tissues (BREAST) Stamp Project and obtained 82% correlation with visual assessment. Lastly, we demonstrate the ability to uncover novel measures when researching the structural properties of the acini by applying machine learning and clustering techniques. Through our study we found that while the number of acini per TDLU increases exponentially with the TDLU diameter, the average elongation and roundness remain constant.

Enhancing image analytic tools by fusing quantitative physiological values with image features.

Computer-aided diagnosis systems (CADs) can quantify the severity of diseases by analyzing a set of images and employing prior statistical models. In general, CADs have proven to be effective at providing quantitative measurements of the extent of a particular disease, thus helping physicians to better monitor the progression of cancer, infectious diseases, and other health conditions. Electronic Health Records frequently include a large amount of clinical data and medical history that can provide critical information about the underlying condition of a patient. We hypothesize that the fusion of image and clinical-physiological features can be used to enhance the accuracy of automatic image classification models. In particular, this paper shows how image analytic tools can move beyond classical image interpretation models to broader systems where image and physiological measurements are fused and used to create more generic detection models. To test our hypothesis, a CAD system capable of quantifying the severity of patients with pulmonary fibrosis has been developed. Results show that CAD systems augmented with multimodal physiological values are more robust and accurate at determining the severity of the disease.

Characterizing non-linear dependencies among pairs of clinical variables and imaging data.

Advances in computer-aided diagnosis (CAD) systems have shown the benefits of using computer-based techniques to obtain quantitative image measurements of the extent of a particular disease. Such measurements provide more accurate information that can be used to better study the associations between anatomical changes and clinical findings. Unfortunately, even with the use of quantitative image features, the correlations between anatomical changes and clinical findings are often not apparent and definite conclusions are difficult to reach. This paper uses nonparametric exploration techniques to demonstrate that even when the associations between two-variables seems weak, advanced properties of the associations can be studied and used to better understand the relationships between individual measurements. This paper uses quantitative imaging findings and clinical measurements of 85 patients with pulmonary fibrosis to demonstrate the advantages of non-linear dependency analysis. Results show that even when the correlation coefficients between imaging and clinical findings seem small, statistical measurements such as the maximum asymmetry score (MAS) and maximum edge value (MEV) can be used to better understand the hidden associations between the variables.

Monitoring pulmonary fibrosis by fusing clinical, physiological, and computed tomography features.

Advances in medical imaging and screening tests have made possible the detection and diagnosis of many diseases in their early stages. Those advances have enabled more effective planning, execution, and monitoring of a treatment plan. However, early detection has also resulted in an increase of the number of longitudinal radiographs requested for most patients, thus increasing the risk for potential long-term effects of ionizing radiation exposure and increasing the cost associated with a specific treatment plan. The aim of this paper is to study the associations between clinical measurements and quantitative image features in patients with pulmonary fibrosis. The association between these multi-modal features could be used to more accurately determine the state of the disease and could potentially be used to predict many of the longitudinal image features when CT images are not available. Our results show how textural image features are highly correlated with the severity of fibrosis, how clinical variables can be combined to monitor progression, and how simple blood features can be used to predict statistical image attributes of the lungs.

Texture-based transfer functions for direct volume rendering.

Visualization of volumetric data faces the difficult task of finding effective parameters for the transfer functions. Those parameters can determine the effectiveness and accuracy of the visualization. Frequently, volumetric data includes multiple structures and features that need to be differentiated. However, if those features have the same intensity and gradient values, existing transfer functions are limited at effectively illustrating those similar features with different rendering properties. We introduce texture-based transfer functions for direct volume rendering. In our approach, the voxel's resulting opacity and color are based on local textural properties rather than individual intensity values. For example, if the intensity values of the vessels are similar to those on the boundary of the lungs, our texture-based transfer function will analyze the textural properties in those regions and color them differently even though they have the same intensity values in the volume. The use of texture-based transfer functions has several benefits. First, structures and features with the same intensity and gradient values can be automatically visualized with different rendering properties. Second, segmentation or prior knowledge of the specific features within the volume is not required for classifying these features differently. Third, textural metrics can be combined and/or maximized to capture and better differentiate similar structures. We demonstrate our texture-based transfer function for direct volume rendering with synthetic and real-world medical data to show the strength of our technique.

Rapid development of medical imaging tools with open-source libraries.

Rapid prototyping is an important element in researching new imaging analysis techniques and developing custom medical applications. In the last ten years, the open source community and the number of open source libraries and freely available frameworks for biomedical research have grown significantly. What they offer are now considered standards in medical image analysis, computer-aided diagnosis, and medical visualization. A cursory review of the peer-reviewed literature in imaging informatics (indeed, in almost any information technology-dependent scientific discipline) indicates the current reliance on open source libraries to accelerate development and validation of processes and techniques. In this survey paper, we review and compare a few of the most successful open source libraries and frameworks for medical application development. Our dual intentions are to provide evidence that these approaches already constitute a vital and essential part of medical image analysis, diagnosis, and visualization and to motivate the reader to use open source libraries and software for rapid prototyping of medical applications and tools.

Reconstruction and enhancement in monocular laparoscopic imagery.

Constrained minimally-invasive surgical environments create a number of challenges for the surgeon and for automated tools designed to aid in the performance and analysis of complex procedures. The 3D reconstruction of the operative field opens up a number of possibilities for immersive presentation, automated analysis, and post-operative evaluation of surgical procedures. This paper presents a method for estimating complete 3D information about scope and instrument positioning from monocular imagery. These measurements can be used as the basis for deriving and presenting additional cues during procedures, and can also be used for post-procedure analysis such as objective estimates of high-level performance measures like economy of motion and ergonomic metrics.