A deep learning approach for lower back-pain risk prediction during manual lifting.
Ontology highlight
ABSTRACT:
SUBMITTER: Snyder K
PROVIDER: S-EPMC7894914 | biostudies-literature | 2021
REPOSITORIES: biostudies-literature
Publications
A deep learning approach for lower back-pain risk prediction during manual lifting.
Snyder Kristian K Thomas Brennan B Lu Ming-Lun ML Jha Rashmi R Barim Menekse S MS Hayden Marie M Werren Dwight D
PloS one 20210219 2
Occupationally-induced back pain is a leading cause of reduced productivity in industry. Detecting when a worker is lifting incorrectly and at increased risk of back injury presents significant possible benefits. These include increased quality of life for the worker due to lower rates of back injury and fewer workers' compensation claims and missed time for the employer. However, recognizing lifting risk provides a challenge due to typically small datasets and subtle underlying features in acce ...[more]
Similar Datasets
Project description:ObjectivesTo determine whether advice and training on working techniques and lifting equipment prevent back pain in jobs that involve heavy lifting.Data sourcesMedline, Embase, CENTRAL, Cochrane Back Group's specialised register, CINAHL, Nioshtic, CISdoc, Science Citation Index, and PsychLIT were searched up to September-November 2005.Review methodsThe primary search focused on randomised controlled trials and the secondary search on cohort studies with a concurrent control group. Interventions aimed to modify techniques for lifting and handling heavy objects or patients and including measurements for back pain, consequent disability, or sick leave as the main outcome were considered for the review. Two authors independently assessed eligibility of the studies and methodological quality of those included. For data synthesis, we summarised the results of studies comparing similar interventions. We used odds ratios and effect sizes to combine the results in a meta-analysis. Finally, we compared the conclusions of the primary and secondary analyses.ResultsSix randomised trials and five cohort studies met the inclusion criteria. Two randomised trials and all cohort studies were labelled as high quality. Eight studies looked at lifting and moving patients, and three studies were conducted among baggage handlers or postal workers. Those in control groups received no intervention or minimal training, physical exercise, or use of back belts. None of the comparisons in randomised trials (17,720 participants) yielded significant differences. In the secondary analysis, none of the cohort studies (772 participants) had significant results, which supports the results of the randomised trials.ConclusionsThere is no evidence to support use of advice or training in working techniques with or without lifting equipment for preventing back pain or consequent disability. The findings challenge current widespread practice of advising workers on correct lifting technique.
| S-EPMC2249682 | biostudies-literature
Project description:BackgroundTrunk co-contraction during lifting may reflect a guarded motor response to a threatening task. This work estimated the impact of pain catastrophizing on trunk co-contraction during lifting, in people with and without low back pain.MethodsAdults with high pain catastrophizing (back pain: n = 29, healthy: n = 7) and low pain catastrophizing (back pain: n = 20, healthy: n = 11), performed 10 repetitions of a lifting task. Electromyography data of rectus abdominis, erector spinae and external oblique muscles were collected, bilaterally. Co-contraction indices were determined for rectus abdominis/erector spinae and external oblique/erector spinae pairings, bilaterally. Pain catastrophizing was measured using the pain catastrophizing scale and task-specific fear using the Photograph series of daily activities scale. Three-way mixed ANOVAs tested the effects of group (back pain vs. healthy), pain catastrophizing (high vs. low), lifting phase (lifting vs. replacing) and their interactions.ResultsThere were no main effects of pain catastrophizing, lifting phase, nor any interactions (p > 0.05). Group effects revealed greater co-contraction for bilateral erector spinae/rectus abdominis pairings (but not erector spinae-external oblique pairings) in people with back pain, compared to healthy participants, independent of pain catastrophizing and lifting phase (p < 0.05). Spearman correlations associated greater task-specific fear and greater erector spinae-left external oblique co-contraction, only in people with back pain (p < 0.05).ConclusionsGreater co-contraction in the back pain group occurred independent of pain catastrophizing, as measured with a general questionnaire. A task-specific measure of threat may be more sensitive to detecting relationships between threat and co-contraction.Significance statementThis work contributes evidence that people with back pain commonly exhibit trunk co-contraction when lifting. The lack of a relationship between pain catastrophizing and trunk co-contraction, however, challenges evidence linking psychological factors and guarded motor behaviour in this group. Together, this suggests that other factors may be stronger determinants of co-contraction in people with LBP or that a general construct like pain catastrophizing may not accurately represent this relationship.
| S-EPMC11671318 | biostudies-literature
Project description:Chronic low back pain (LBP) is a very common health problem worldwide and a major cause of disability. Yet, the lack of quantifiable metrics on which to base clinical decisions leads to imprecise treatments, unnecessary surgery and reduced patient outcomes. Although, the focus of LBP has largely focused on the spine, the literature demonstrates a robust reorganization of the human brain in the setting of LBP. Brain neuroimaging holds promise for the discovery of biomarkers that will improve the treatment of chronic LBP. In this study, we report on morphological changes in cerebral cortical thickness (CT) and resting-state functional connectivity (rsFC) measures as potential brain biomarkers for LBP. Structural MRI scans, resting state functional MRI scans and self-reported clinical scores were collected from 24 LBP patients and 27 age-matched healthy controls (HC). The results suggest widespread differences in CT in LBP patients relative to HC. These differences in CT are correlated with self-reported clinical summary scores, the Physical Component Summary and Mental Component Summary scores. The primary visual, secondary visual and default mode networks showed significant age-corrected increases in connectivity with multiple networks in LBP patients. Cortical regions classified as hubs based on their eigenvector centrality (EC) showed differences in their topology within motor and visual processing regions. Finally, a support vector machine trained using CT to classify LBP subjects from HC achieved an average classification accuracy of 74.51%, AUC = 0.787 (95% CI: 0.66-0.91). The findings from this study suggest widespread changes in CT and rsFC in patients with LBP while a machine learning algorithm trained using CT can predict patient group. Taken together, these findings suggest that CT and rsFC may act as potential biomarkers for LBP to guide therapy.
| S-EPMC7750450 | biostudies-literature
Project description:BackgroundFor the purpose to examine lower limb melanoma (LLM) and its long-term survival rate, we used data from the Surveillance, Epidemiology and End Results (SEER) database. To estimate the prognosis of LLM patients and assess its efficacy, we used a powerful deep learning and neural network approach called DeepSurv.MethodsWe gathered data on those who had an LLM diagnosis between 2000 and 2019 from the SEER database. We divided the people into training and testing cohorts at a 7:3 ratio using a random selection technique. To assess the likelihood that LLM patients would survive, we compared the results of the DeepSurv model with those of the Cox proportional-hazards (CoxPH) model. Calibration curves, the time-dependent area under the receiver operating characteristic curve (AUC), and the concordance index (C-index) were all used to assess how accurate the predictions were.ResultsIn this study, a total of 26,243 LLM patients were enrolled, with 7873 serving as the testing cohort and 18,370 as the training cohort. Significant correlations with age, gender, AJCC stage, chemotherapy status, surgery status, regional lymph node removal and the survival outcomes of LLM patients were found by the CoxPH model. The CoxPH model's C-index was 0.766, which signifies a good degree of predicted accuracy. Additionally, we created the DeepSurv model using the training cohort data, which had a higher C-index of 0.852. In addition to calculating the 3-, 5-, and 8-year AUC values, the predictive performance of both models was evaluated. The equivalent AUC values for the CoxPH model were 0.795, 0.767, and 0.847, respectively. The DeepSurv model, in comparison, had better AUC values of 0.872, 0.858, and 0.847. In comparison to the CoxPH model, the DeepSurv model demonstrated greater prediction performance for LLM patients, as shown by the AUC values and the calibration curve.ConclusionWe created the DeepSurv model using LLM patient data from the SEER database, which performed better than the CoxPH model in predicting the survival time of LLM patients.
| S-EPMC10686915 | biostudies-literature
Project description:Protein Blocks (PBs) are a widely used structural alphabet describing local protein backbone conformation in terms of 16 possible conformational states, adopted by five consecutive amino acids. The representation of complex protein 3D structures as 1D PB sequences was previously successfully applied to protein structure alignment and protein structure prediction. In the current study, we present a new model, PYTHIA (predicting any conformation at high accuracy), for the prediction of the protein local conformations in terms of PBs directly from the amino acid sequence. PYTHIA is based on a deep residual inception-inside-inception neural network with convolutional block attention modules, predicting 1 of 16 PB classes from evolutionary information combined to physicochemical properties of individual amino acids. PYTHIA clearly outperforms the LOCUSTRA reference method for all PB classes and demonstrates great performance for PB prediction on particularly challenging proteins from the CASP14 free modelling category.
| S-EPMC8396346 | biostudies-literature
Project description:Study designRetrospective observational study.ObjectivesThere is no consensus to predict improvement of lower back pain (LBP) in lumbar spinal stenosis after decompression surgery. The aim of this study was to evaluate the improvement of LBP and analyze the preoperative predicting factors for residual LBP.MethodsWe retrospectively reviewed 119 patients who underwent lumbar decompression surgery without fusion and had a minimum follow-up of 1 year. LBP was evaluated using the numerical rating scale (NRS), Japanese Orthopaedic Association Back Pain Evaluation Questionnaire (JOABPEQ) LBP score, and Roland-Morris Disability Questionnaire (RMDQ). All patients were divided into LBP improved group (group I) and LBP residual group (group R) according to the NRS score. Radiographic images were examined preoperatively and at the final follow-up. We evaluated spinopelvic radiological parameters and analyzed the differences between group I and group R.ResultsLBP was significantly improved after decompression surgery (LBP NRS, 5.7 vs 2.6, P < .001; JOABPEQ LBP score, 41.3 vs 79.6, P < .001; RMDQ, 10.3 vs 3.6, P < .001). Of 119 patients, 94 patients were allocated to group I and 25 was allocated to group R. There was significant difference in preoperative thoracolumbar kyphosis between group I and group R.ConclusionsMost cases of LBP in lumbar spinal stenosis were improved after decompression surgery without fusion. Preoperative thoracolumbar kyphosis predicted residual LBP after decompression surgery.
| S-EPMC7882817 | biostudies-literature
Project description:ObjectiveTo develop and evaluate deep learning (DL) risk assessment models for predicting pain progression in subjects with or at risk of knee osteoarthritis (OA).Materials and methodsThe incidence and progression cohorts of the Osteoarthritis Initiative, a multi-center longitudinal study involving 9348 knees in 4674 subjects with or at risk of knee OA that began in 2004 and is ongoing, were used to conduct this retrospective analysis. A subset of knees without and with pain progression (defined as a 9-point or greater increase in pain score between baseline and two or more follow-up time points over the first 48 months) was randomly stratified into training (4200 knees with a mean age of 61.0 years and 60% female) and hold-out testing (500 knees with a mean age of 60.8 years and 60% female) datasets. A DL model was developed to predict pain progression using baseline knee radiographs. An artificial neural network was used to develop a traditional risk assessment model to predict pain progression using demographic, clinical, and radiographic risk factors. A combined model was developed to combine demographic, clinical, and radiographic risk factors with DL analysis of baseline knee radiographs. Area under the curve (AUC) analysis was performed using the hold-out testing dataset to evaluate model performance.ResultsThe traditional model had an AUC of 0.692 (66.9% sensitivity and 64.1% specificity). The DL model had an AUC of 0.770 (76.7% sensitivity and 70.5% specificity), which was significantly higher (p < 0.001) than the traditional model. The combined model had an AUC of 0.807 (72.3% sensitivity and 80.9% specificity), which was significantly higher (p < 0.05) than the traditional and DL models.ConclusionsDL models using baseline knee radiographs had higher diagnostic performance for predicting pain progression than traditional models using demographic, clinical, and radiographic risk factors.
| S-EPMC9232386 | biostudies-literature
Project description:Computational prediction of Protein-Ligand Interaction (PLI) is an important step in the modern drug discovery pipeline as it mitigates the cost, time, and resources required to screen novel therapeutics. Deep Neural Networks (DNN) have recently shown excellent performance in PLI prediction. However, the performance is highly dependent on protein and ligand features utilized for the DNN model. Moreover, in current models, the deciphering of how protein features determine the underlying principles that govern PLI is not trivial. In this work, we developed a DNN framework named SSnet that utilizes secondary structure information of proteins extracted as the curvature and torsion of the protein backbone to predict PLI. We demonstrate the performance of SSnet by comparing against a variety of currently popular machine and non-Machine Learning (ML) models using various metrics. We visualize the intermediate layers of SSnet to show a potential latent space for proteins, in particular to extract structural elements in a protein that the model finds influential for ligand binding, which is one of the key features of SSnet. We observed in our study that SSnet learns information about locations in a protein where a ligand can bind, including binding sites, allosteric sites and cryptic sites, regardless of the conformation used. We further observed that SSnet is not biased to any specific molecular interaction and extracts the protein fold information critical for PLI prediction. Our work forms an important gateway to the general exploration of secondary structure-based Deep Learning (DL), which is not just confined to protein-ligand interactions, and as such will have a large impact on protein research, while being readily accessible for de novo drug designers as a standalone package.
| S-EPMC7869013 | biostudies-literature
Project description:Several experimental evidences have shown that the human endogenous hormones can interact with drugs in many ways and affect drug efficacy. The hormone drug interactions (HDI) are essential for drug treatment and precision medicine; therefore, it is essential to understand the hormone-drug associations. Here, we present HormoNet to predict the HDI pairs and their risk level by integrating features derived from hormone and drug target proteins. To the best of our knowledge, this is one of the first attempts to employ deep learning approach for prediction of HDI prediction. Amino acid composition and pseudo amino acid composition were applied to represent target information using 30 physicochemical and conformational properties of the proteins. To handle the imbalance problem in the data, we applied synthetic minority over-sampling technique technique. Additionally, we constructed novel datasets for HDI prediction and the risk level of their interaction. HormoNet achieved high performance on our constructed hormone-drug benchmark datasets. The results provide insights into the understanding of the relationship between hormone and a drug, and indicate the potential benefit of reducing risk levels of interactions in designing more effective therapies for patients in drug treatments. Our benchmark datasets and the source codes for HormoNet are available in: https://github.com/EmamiNeda/HormoNet .
| S-EPMC10903040 | biostudies-literature
Project description:BackgroundThe handling of unknown weights, which is common in daily routines either at work or during leisure time, is suspected to be highly associated with the incidence of low back pain (LBP).ObjectivesTo investigate the effects of knowledge and magnitude of a load (to be lifted) on brain responses, autonomic nervous activity, and trapezius and erector spinae muscle activity.MethodsA randomized, within-subjects experiment involving manual lifting was conducted, wherein 10 participants lifted three different weights (1.1, 5, and 15 kg) under two conditions: either having or not having prior knowledge of the weight to be lifted.ResultsThe results revealed that the lifting of unknown weights caused increased average heart rate and percentage of maximum voluntary contraction (%MVC) but decreased average inter-beat interval, very-low-frequency power, low-frequency power, and low-frequency/high-frequency ratio. Regardless of the weight magnitude, lifting of unknown weights was associated with smaller theta activities in the power spectrum density (PSD) of the central region, smaller alpha activities in the PSD of the frontal region, and smaller beta activities in the PSDs of both the frontal and central regions. Moreover, smaller alpha and beta activities in the PSD of the parietal region were associated only with lifting of unknown lightweights.ConclusionsUncertainty regarding the weight to be lifted could be considered as a stress-adding variable that may increase the required physical demand to be sustained during manual lifting tasks. The findings of this study stress the importance of eliminating uncertainty associated with handling unknown weights, such as in the cases of handling patients and dispatching luggage. This can be achieved through preliminary self-sensing of the load to be lifted, or the cautious disclosure of the actual weight of manually lifted objects, for example, through clear labeling and/or a coding system.
| S-EPMC7909684 | biostudies-literature