Biomedical practice is evidence-based. Peer-reviewed papers are the primary medium to present evidence and data-supported results to drive clinical practice. However, it could be argued that scientific literature does not contain data, but rather narratives about and summaries of data. Meta-analyses of published literature may produce biased conclusions due to the lack of transparency in data collection, publication bias, and inaccessibility to the data underlying a publication ('dark data'). Co-analysis of pooled data at the level of individual research participants can offer higher levels of evidence, but this requires that researchers share raw individual participant data (IPD). FAIR (findable, accessible, interoperable, and reusable) data governance principles aim to guide data lifecycle management by providing a framework for actionable data sharing. Here we discuss the implications of FAIR for data harmonization, an essential step for pooling data for IPD analysis. We describe the harmonization-information trade-off, which states that the level of granularity in harmonizing data determines the amount of information lost. Finally, we discuss a framework for managing the trade-off and the levels of harmonization. In the coming era of funder mandates for data sharing, research communities that effectively manage data harmonization will be empowered to harness big data and advanced analytics such as machine learning and artificial intelligence tools, leading to stunning new discoveries that augment our understanding of diseases and their treatments. By elevating scientific data to the status of a first-class citizen of the scientific enterprise, there is strong potential for biomedicine to transition from a narrative publication product orientation to a modern data-driven enterprise where data itself is viewed as a primary work product of biomedical research.

BACKGROUND: Recovery following total joint arthroplasty is patient-specific, yet groups of patients tend to fall into certain similar patterns of recovery. The purpose of this study was to identify and characterize recovery patterns following total hip arthroplasty (THA) and total knee arthroplasty (TKA) using patient-reported outcomes that represent distinct health domains. We hypothesized that recovery patterns could be defined and predicted using preoperative data. METHODS: Adult patients were recruited from a large, urban academic center. To model postoperative responses to THA and TKA across domains such as physical health, mental health, and joint-specific measures, we employed a longitudinal clustering algorithm that incorporates each of these health domains. The clustering algorithm from multiple health domains allows the ability to define distinct recovery trajectories, which could then be predicted from preoperative and perioperative factors using a multinomial regression. RESULTS: Four hundred forty-one of 1134 patients undergoing THA and 346 of 921 undergoing TKA met eligibility criteria and were used to define distinct patterns of recovery. The clustering algorithm was optimized for 3 distinct patterns of recovery that were observed in THA and TKA patients. Patients recovering from THA were divided into 3 groups: standard responders (50.8%), late mental responders (13.2%), and substandard responders (36.1%). Multivariable, multinomial regression suggested that these 3 groups had defined characteristics. Late mental responders tended to be obese (P = .05) and use more opioids (P = .01). Substandard responders had a larger number of comorbidities (P = .02) and used more opioids (P = .001). Patients recovering from TKA were divided among standard responders (55.8%), poor mental responders (24%), and poor physical responders (20.2%). Poor mental responders were more likely to be female (P = .04) and American Society of Anesthesiologists class III/IV (P = .004). Poor physical responders were more likely to be female (P = .03), younger (P = .04), American Society of Anesthesiologists III/IV (P = .04), use more opioids (P = .02), and be discharged to a nursing facility (P = .001). The THA and TKA models demonstrated areas under the curve of 0.67 and 0.72. CONCLUSIONS: This multidomain, longitudinal clustering analysis defines 3 distinct patterns in the recovery of THA and TKA patients, with most patients in both cohorts experiencing robust improvement, while others had equally well defined yet less optimal recovery trajectories that were either delayed in recovery or failed to achieve a desired outcome. Patients in the delayed recovery and poor outcome groups were slightly different between THA and TKA. These groups of patients with similar recovery patterns were defined by patient characteristics that include potentially modifiable comorbid factors. This research suggests that there are multiple defined recovery trajectories after THA and TKA, which provides a new perspective on THA and TKA recovery. LEVEL OF EVIDENCE: III.

Traumatic brain injury (TBI) affects how the brain functions in the short and long term. Resulting patient outcomes across physical, cognitive, and psychological domains are complex and often difficult to predict. Major challenges to developing personalized treatment for TBI include distilling large quantities of complex data and increasing the precision with which patient outcome prediction (prognoses) can be rendered. We developed and applied interpretable machine learning methods to TBI patient data. We show that complex data describing TBI patients intake characteristics and outcome phenotypes can be distilled to smaller sets of clinically interpretable latent factors. We demonstrate that 19 clusters of TBI outcomes can be predicted from intake data, a ~ 6× improvement in precision over clinical standards. Finally, we show that 36% of the outcome variance across patients can be predicted. These results demonstrate the importance of interpretable machine learning applied to deeply characterized patients for data-driven distillation and precision prognosis.

Background

Tools, such as the STarTBack Screening Tool (SBT), have been developed to identify risks of progressing to chronic disability in low back pain (LBP) patients in the primary care population. However, less is known about predictors of change in function after treatment in the specialty care population.

Objective

We pursued a retrospective observational cohort study involving LBP patients seen in a multidisciplinary specialty clinic to assess which features can predict change in function at follow-up.

Methods

The SBT was administered at initial visit, and a variety of patient characteristics were available in the chart including the presence of chronic overlapping pain conditions (COPCs). Patient Reported Outcomes Measurement Information System-10 (PROMIS-10) global physical health (PH) and global mental health (MH) were measured at baseline and at pragmatic time points during follow-up. Linear regression was used to estimate adjusted associations between available features and changes in PROMIS scores.

Results

241 patients were followed for a mean of 17.0 ± 7.5 months. Mean baseline pain was 6.7 (SD 2.1), PROMIS-10 global MH score was 44.8 (SD 9.3), and PH score was 39.4 (SD 8.6). 29.7% were low-risk on the SBT, 41.8% were medium-risk, and 28.5% were high-risk. Mean change in MH and PH scores from baseline to the follow-up questionnaire were 0.86 (SD 8.11) and 2.39 (SD 7.52), respectively. Compared to low-risk patients, high-risk patients had a mean 4.35 points greater improvement in their MH score (p= 0.004) and a mean 3.54 points greater improvement in PH score (p= 0.006). Fewer COPCs also predicted greater improvement in MH and PH.

Conclusions

SBT and the presence of COPC, which can be assessed at initial presentation to a specialty clinic, can predict change in PROMIS following treatment. Effort is needed to identify other factors that can help predict change in function after treatment in the specialty care setting.

Background

Paraspinal muscle fat infiltration is associated with spinal degeneration and low back pain, however, quantifying muscle fat using clinical magnetic resonance imaging (MRI) techniques continues to be a challenge. Advanced MRI techniques, including chemical-shift encoding (CSE) based water-fat MRI, enable accurate measurement of muscle fat, but such techniques are not widely available in routine clinical practice.

Methods

To facilitate assessment of paraspinal muscle fat using clinical imaging, we compared four thresholding approaches for estimating muscle fat fraction (FF) using T1- and T2-weighted images, with measurements from water-fat MRI as the ground truth: Gaussian thresholding, Otsu's method, K-mean clustering, and quadratic discriminant analysis. Pearson's correlation coefficients (r), mean absolute errors, and mean bias errors were calculated for FF estimates from T1- and T2-weighted MRI with water-fat MRI for the lumbar multifidus (MF), erector spinae (ES), quadratus lumborum (QL), and psoas (PS), and for all muscles combined.

Results

We found that for all muscles combined, FF measurements from T1- and T2-weighted images were strongly positively correlated with measurements from the water-fat images for all thresholding techniques (r = 0.70-0.86, p < 0.0001) and that variations in inter-muscle correlation strength were much greater than variations in inter-method correlation strength.

Conclusion

We conclude that muscle FF can be quantified using thresholded T1- and T2-weighted MRI images with relatively low bias and absolute error in relation to water-fat MRI, particularly in the MF and ES, and the choice of thresholding technique should depend on the muscle and clinical MRI sequence of interest.

Meta-analyses suggest that the published literature represents only a small minority of the total data collected in biomedical research, with most becoming 'dark data' unreported in the literature. Dark data is due to publication bias toward novel results that confirm investigator hypotheses and omission of data that do not. Publication bias contributes to scientific irreproducibility and failures in bench-to-bedside translation. Sharing dark data by making it Findable, Accessible, Interoperable, and Reusable (FAIR) may reduce the burden of irreproducible science by increasing transparency and support data-driven discoveries beyond the lifecycle of the original study. We illustrate feasibility of dark data sharing by recovering original raw data from the Multicenter Animal Spinal Cord Injury Study (MASCIS), an NIH-funded multi-site preclinical drug trial conducted in the 1990s that tested efficacy of several therapies after a spinal cord injury (SCI). The original drug treatments did not produce clear positive results and MASCIS data were stored in boxes for more than two decades. The goal of the present study was to independently confirm published machine learning findings that perioperative blood pressure is a major predictor of SCI neuromotor outcome (Nielson et al., 2015). We recovered, digitized, and curated the data from 1125 rats from MASCIS. Analyses indicated that high perioperative blood pressure at the time of SCI is associated with poorer health and worse neuromotor outcomes in more severe SCI, whereas low perioperative blood pressure is associated with poorer health and worse neuromotor outcome in moderate SCI. These findings confirm and expand prior results that a narrow window of blood-pressure control optimizes outcome, and demonstrate the value of recovering dark data for assessing reproducibility of findings with implications for precision therapeutic approaches.

Purpose

The paraspinal muscles (PSM) are a key feature potentially related to low back pain (LBP), and their structure and composition can be quantified using MRI. Most commonly, quantifying PSM measures across individual muscles and individual spinal levels renders numerous separate metrics that are analyzed in isolation. However, comprehensive multivariate approaches would be more appropriate for analyzing the PSM within an individual. To establish and test these methods, we hypothesized that multivariate summaries of PSM MRI measures would associate with the presence of LBP symptoms (i.e., pain intensity).

Methods

We applied hierarchical multiple factor analysis (hMFA), an unsupervised integrative method, to clinical PSM MRI data from unique cohort datasets including a longitudinal cohort of astronauts with pre- and post-spaceflight data and a cohort of chronic LBP subjects and asymptomatic controls. Three specific use cases were investigated: (1) predicting longitudinal changes in pain using combinations of baseline PSM measures; (2) integrating baseline and post-spaceflight MRI to assess longitudinal change in PSM and how it relates to pain; and (3) integrating PSM quality and adjacent spinal pathology between LBP patients and controls.

Results

Overall, we found distinct complex relationships with pain intensity between particular muscles and spinal levels. Subjects with high asymmetry between left and right lean muscle composition and differences between spinal segments PSM quality and structure are more likely to increase in pain reported outcome after prolonged time in microgravity. Moreover, changes in PSM quality and structure between pre and post-spaceflight relate to increase in pain after prolonged microgravity. Finally, we show how unsupervised hMFA recapitulates previous research on the association of CEP damage and LBP diagnostic.

Conclusion

Our analysis considers the spine as a multi-segmental unit as opposed to a series of discrete and isolated spine segments. Integrative and multivariate approaches can be used to distill large and complex imaging datasets thereby improving the clinical utility of MRI-based biomarkers, and providing metrics for further analytical goals, including phenotyping.

Background #OrthoTwitter has evolved to disseminate findings and engage the public. However, the academic impact of Twitter utilization in orthopaedic surgery is unknown. Questions/purposes The purpose of the study was to evaluate relationships between the author and manuscript Twitter activity and citations. Methods Manuscripts in 17 orthopaedic journals from 2018 were identified. Citations, online mentions, impact factors, and subspecialties were obtained. H-index and Twitter account details for authors were obtained for a subset of manuscripts. Relationships between Twitter activity and citations were evaluated. Results 2,473/4,224 (58.5%) manuscripts were mentioned on Twitter (n=29,958 mentions), with Twitter manuscripts cited more frequently (median 10 vs. 7, p<0.0001). Twitter mentions, impact factors, non-open-access status, and subspecialties were associated with citation counts. Articles mentioned in 10, 100, and 1,000 Tweets were observed to have a 1.1-fold, 1.7-fold, and 245-fold increase in citations. In author-level analyses, 156 (20.0%) first and 216 (27.7%) senior authors had Twitter accounts. Citation count was associated with increasing senior author H-index (β _est=0.13, p<0.05), Twitter mentions (β _est=0.0043, p<0.0001), impact factors (β _est=0.13, p<0.0001), and having a first (β _est=0.20, p<0.05) or senior author (β _est=0.17, p<0.05) on Twitter. Articles published in arthroplasty (β _est=0.49, p<0.05), general interest (β _est=0.55, p<0.01), sports (β _est=0.63, p<0.01), and non-open access journals (β _est=0.41, p<0.001) were cited more. H-index correlated with followers for first (rho=0.31, p<0.0001) and senior authors (rho=0.44, p<0.0001). Conclusion Author Twitter utilization is independently associated with manuscript citations. Authors should be aware of the potential association between social media utilization and traditional academic impact. Understanding the relationship between social media utilization and academic impact is necessary to effectively disseminate research.

Interplanetary space travel poses many hazards to the human body. To protect astronaut health and performance on critical missions, there is first a need to understand the effects of deep space hazards, including ionizing radiation, confinement, and altered gravity. Previous studies of rodents exposed to a single such stressor document significant deficits, but our study is the first to investigate possible cumulative and synergistic impacts of simultaneous ionizing radiation, confinement, and altered gravity on behavior and cognition. Our cohort was divided between 6-month-old female and male mice in group, social isolation, or hindlimb unloading housing, exposed to 0 or 50 cGy of 5 ion simplified simulated galactic cosmic radiation (GCRsim). We report interactions and independent effects of GCRsim exposure and housing conditions on behavioral and cognitive performance. Exposure to GCRsim drove changes in immune cell populations in peripheral blood collected early after irradiation, while housing conditions drove changes in blood collected at a later point. Female mice were largely resilient to deficits observed in male mice. Finally, we used principal component analysis to represent total deficits as principal component scores, which were predicted by general linear models using GCR exposure, housing condition, and early blood biomarkers.

Western blot is a popular biomolecular analysis method for measuring the relative quantities of independent proteins in complex biological samples. However, variability in quantitative western blot data analysis poses a challenge in designing reproducible experiments. The lack of rigorous quantitative approaches in current western blot statistical methodology may result in irreproducible inferences. Here we describe best practices for the design and analysis of western blot experiments, with examples and demonstrations of how different analytical approaches can lead to widely varying outcomes. To facilitate best practices, we have developed the blotRig tool for designing and analyzing western blot experiments to improve their rigor and reproducibility. The blotRig application includes functions for counterbalancing experimental design by lane position, batch management across gels, and analytics with covariates and random effects.