An individualized gait pattern prediction model based on the least absolute shrinkage and selection operator regression

Novel Methods for Personalized Gait Assistance: Three-Dimensional Trajectory Prediction Based on Regression and LSTM Models

Enhancing human-robot interaction has been a primary focus in robotic gait assistance, with a thorough understanding of human motion being crucial for personalizing gait assistance. Traditional gait trajectory references from Clinical Gait Analysis (CGA) face limitations due to their inability to account for individual variability. Recent advancements in gait pattern generators, integrating regression models and Artificial Neural Network (ANN) techniques, have aimed at providing more personalized and dynamically adaptable solutions. This article introduces a novel approach that expands regression and ANN applications beyond mere angular estimations to include three-dimensional spatial predictions. Unlike previous methods, our approach provides comprehensive spatial trajectories for hip, knee and ankle tailored to individual kinematics, significantly enhancing end-effector rehabilitation robotic devices. Our models achieve state-of-the-art accuracy: overall RMSE of 13.40 mm and a correlation coefficient of 0.92 for the regression model, and RMSE of 12.57 mm and a correlation of 0.99 for the Long Short-Term Memory (LSTM) model. These advancements underscore the potential of these models to offer more personalized gait trajectory assistance, improving human-robot interactions.

Establishment of a risk prediction model for residual low back pain in thoracolumbar osteoporotic vertebral compression fractures after percutaneous kyphoplasty

OBJECTIVE

This study aims to identify potential independent risk factors for residual low back pain (LBP) in patients with thoracolumbar osteoporotic vertebral compression fractures (OVCFs) following percutaneous kyphoplasty (PKP) treatment. Additionally, we aim to develop a nomogram that can accurately predict the occurrence of residual LBP.

METHODS

We conducted a retrospective review of the medical records of thoracolumbar OVCFs patients who underwent PKP treatment at our hospital between July 2021 and December 2022. Residual LBP was defined as the presence of moderate or greater pain (VAS score ≥ 4) in the low back one day after surgery, and patients were divided into two groups: the LBP group and the non-LBP group. These patients were then randomly allocated to either a training or a validation set in the ratio of 7:3. To identify potential risk factors for residual LBP, we employed lasso regression for multivariate analysis, and from this, we constructed a nomogram. Subsequently, the predictive accuracy and practical clinical application of the nomogram were evaluated through a receiver operating characteristic (ROC) curve, a calibration curve, and a decision curve analysis (DCA).

RESULTS

Our predictive model revealed that five variables-posterior fascial oedema, intravertebral vacuum cleft, time from fracture to surgery, sarcopenia, and interspinous ligament degeneration-were correlated with the presence of residual LBP. In the training set, the area under the ROC was 0.844 (95% CI 0.772-0.917), and in the validation set, it was 0.842 (95% CI 0.744-0.940), indicating that the model demonstrated strong discriminative performance. Furthermore, the predictions closely matched actual observations in both the training and validation sets. The decision curve analysis (DCA) curve suggested that the model provides a substantial net clinical benefit.

CONCLUSIONS

We have created a novel numerical model capable of accurately predicting the potential risk factors associated with the occurrence of residual LBP following PKP in thoracolumbar OVCFs patients. This model serves as a valuable tool for guiding specific clinical decisions for patients with OVCFs.

Individualized Three-Dimensional Gait Pattern Generator for Lower Limbs Rehabilitation Robots

In the field of robotic gait rehabilitation, controlling robotic devices to follow specific human-like trajectories is often required. In recent years, various gait generator models have been proposed, providing customized gait patterns adjustable to a range of heights and gait speeds. However, these models were developed with a focus on gait rehabilitation devices designed to control the angular trajectories of the subject's joints, e.g. exoskeletons. Similar devices, e.g. end-effector robots, control the orientation and also the 3D position of the subject's joints and cannot easily implement these models. In this study, it is proposed a new individualized three-dimensional gait pattern generator for gait rehabilitation robots. The generator employs multi-variable regression models to predict the joint angular trajectories of the pelvis, hip, and ankle along the gait cycle. The 3D joints positions are then reconstructed by applying the predicted angular trajectories over a human model inspired on the inverted pendulum analogy using inverse kinematics. The generator's performance was statistically evaluated against real gait patterns from 42 participants walking at 8 different velocities. The predicted trajectories matched the measured ones with an average Root Mean Squared Error of 25.73 mm for all joints at all Cartesian axes, with better results between 3.3 - 5.4 km/h. Suggesting to be a good solution to be applied in end-effector gait robotic rehabilitation devices.

Developing a nomogram-based scoring model to estimate the risk of pulmonary embolism in respiratory department patients suspected of pulmonary embolisms

Objective

Pulmonary embolisms (PE) are clinically challenging because of their high morbidity and mortality. This study aimed to create a nomogram to accurately predict the risk of PE in respiratory department patients in order to enhance their medical treatment and management.

Methods

This study utilized a retrospective method to collect information on medical history, complications, specific clinical characteristics, and laboratory biomarker results of suspected PE patients who were admitted to the respiratory department at Affiliated Dongyang Hospital of Wenzhou Medical University between January 2012 and December 2021. This study involved a total of 3,511 patients who were randomly divided into a training group (six parts) and a validation group (four parts) based on a 6:4 ratio. The LASSO regression and multivariate logistic regression were used to develop a scoring model using a nomogram. The performance of the model was evaluated using receiver operating characteristic curve (AUC), calibration curve, and clinical decision curve.

Results

Our research included more than 50 features from 3,511 patients. The nomogram-based scoring model was established using six predictive features including age, smoke, temperature, systolic pressure, D-dimer, and fibrinogen, which achieved AUC values of 0.746 in the training cohort (95% CI 0.720-0.765) and 0.724 in the validation cohort (95% CI 0.695-0.753). The results of the calibration curve revealed a strong consistency between probability predicted by the nomogram and actual probability. The decision curve analysis (DCA) also demonstrated that the nomogram-based scoring model produced a favorable net clinical benefit.

Conclusion

In this study, we successfully developed a novel numerical model that can predict the risk of PE in respiratory department patients suspected of PE, which can not only appropriately select PE prevention strategies but also decrease unnecessary computed tomographic pulmonary angiography (CTPA) scans and their adverse effects.

A nomogram for predicting the risk of pulmonary embolism in neurology department suspected PE patients: A 10-year retrospective analysis

Objective

The purpose of this retrospective study was to establish a numerical model for predicting the risk of pulmonary embolism (PE) in neurology department patients.

Methods

A total of 1,578 subjects with suspected PE at the neurology department from January 2012 to December 2021 were considered for enrollment in our retrospective study. The patients were randomly divided into the training cohort and the validation cohort in the ratio of 7:3. The least absolute shrinkage and selection operator regression were used to select the optimal predictive features. Multivariate logistic regression was used to establish the numerical model, and this model was visualized by a nomogram. The model performance was assessed and validated by discrimination, calibration, and clinical utility.

Results

Our predictive model indicated that eight variables, namely, age, pulse, systolic pressure, hemoglobin, neutrophil count, low-density lipoprotein, D-dimer, and partial pressure of oxygen, were associated with PE. The area under the receiver operating characteristic curve of the model was 0.750 [95% confidence interval (CI): 0.721–0.783] in the training cohort and 0.742 (95% CI: 0.689–0.787) in the validation cohort, indicating that the model showed a good differential performance. A good consistency between the prediction and the real observation was presented in the training and validation cohorts. The decision curve analysis in the training and validation cohorts showed that the numerical model had a good net clinical benefit.

Conclusion

We established a novel numerical model to predict the risk factors for PE in neurology department suspected PE patients. Our findings may help doctors to develop individualized treatment plans and PE prevention strategies.

An inflammation-related gene landscape predicts prognosis and response to immunotherapy in virus-associated hepatocellular carcinoma

Background

Due to the viral infection, chronic inflammation significantly increases the likelihood of hepatocellular carcinoma (HCC) development. Nevertheless, an inflammation-based signature aimed to predict the prognosis and therapeutic effect in virus-related HCC has rarely been established.

Method

Based on the integrated analysis, inflammation-associated genes (IRGs) were systematically assessed. We comprehensively investigated the correlation between inflammation and transcriptional profiles, prognosis, and immune cell infiltration. Then, an inflammation-related risk model (IRM) to predict the overall survival (OS) and response to treatment for virus-related HCC patients was constructed and verified. Also, the potential association between IRGs and tumor microenvironment (TME) was investigated. Ultimately, hub genes were validated in plasma samples and cell lines via qRT-PCR. After transfection with shCCL20 combined with overSLC7A2, morphological change of SMMC7721 and huh7 cells was observed. Tumorigenicity model in nude mouse was established.

Results

An inflammatory response-related gene signature model, containing MEP1A, CCL20, ADORA2B, TNFSF9, ICAM4, and SLC7A2, was constructed by conjoint analysis of least absolute shrinkage and selection operator (LASSO) Cox regression and gaussian finite mixture model (GMM). Besides, survival analysis attested that higher IRG scores were positively relevant to worse survival outcomes in virus-related HCC patients, which was testified by external validation cohorts (the ICGC cohort and GSE84337 dataset). Univariate and multivariate Cox regression analyses commonly proved that the IRG was an independent prognostic factor for virus-related HCC patients. Thus, a nomogram with clinical factors and IRG was also constructed to superiorly predict the prognosis of patients. Featured with microsatellite instability-high, mutation burden, and immune activation, lower IRG score verified a superior OS for sufferers. Additionally, IRG score was remarkedly correlated with the cancer stem cell index and drug susceptibility. The measurement of plasma samples further validated that CCL20 upexpression and SLC7A2 downexpression were positively related with virus-related HCC patients, which was in accord with the results in cell lines. Furthermore, CCL20 knockdown combined with SLC7A2 overexpression availably weakened the tumor growth in vivo.

Conclusions

Collectively, IRG score, serving as a potential candidate, accurately and stably predicted the prognosis and response to immunotherapy in virus-related HCC patients, which could guide individualized treatment decision-making for the sufferers.

Establishment and Verification of a Predictive Nomogram for New Vertebral Compression Fracture Occurring after Bone Cement Injection in Middle-Aged and Elderly Patients with Vertebral Compression Fracture

OBJECTIVE

New vertebral compression fracture (NVCF) occurring after bone cement injection in middle-aged and elderly patients with vertebral compression fracture is very common. Preoperative baseline characteristics and surgical treatment parameters have been widely studied as a risk factor, but the importance of the patients' laboratory indicators has not been thoroughly explored. We aimed to explore the relationship between laboratory indicators and NVCF, and attempt to construct a clinical prediction model of NVCF together with other risk factors.

METHODS

Retrospective analysis was performed for 200 patients who underwent bone cement injection (percutaneous kyphoplasty or vertebroplasty) for vertebral compression fractures between January 2019 and January 2020. We consulted the relevant literature and collated the factors affecting the occurrence of NVCF. Feature selection of patients with NVCF was optimized using the least absolute shrinkage and selection operator regression model, which was used to conduct multivariable logistic regression analysis, to create a predictive model incorporating the selected features. The discrimination, calibration, and clinical feasibility of the predictive model were assessed using the concordance index (C-index), calibration plots, and decision curve analysis. Internal validation was performed using Bootstrap resampling verification.

RESULTS

Time from injury to surgery exceeding 7 days, low osteocalcin levels, elevated homocysteine levels, osteoporosis, mode of operation (percutaneous vertebroplasty), lack of postoperative anti-osteoporosis treatment, and poor diffusion of bone cement were independent risk factors for NVCF in middle-aged and elderly patients with vertebral compression fracture after bone cement injection. The C-index of the nomogram constructed using these seven factors was 0.895, indicating good discriminatory ability. The calibration plot showed that the model was well calibrated. Bootstrap resampling verification yielded a significant C-index of 0.866. Decision curve analysis demonstrated that the greatest clinical net benefit for predicting NVCF after bone cement injection could be achieved with a threshold of 1%-91%.

CONCLUSION

This nomogram can effectively predict NVCF incidence after bone cement injection in middle-aged and elderly patients with vertebral compression fracture, thus aiding clinical decision-making and postoperative management, promoting effective postoperative rehabilitation, and improving the quality of life.

Predictive factors and nomogram to evaluate the risk of below-ankle re-amputation in patients with diabetic foot

BACKGROUND

Diabetes mellitus, as the most common metabolic disease, is common worldwide and represents a crucial global health concern. The purpose of this research was to investigate the related risk factors and to develop a re-amputation risk nomogram in diabetic patients who have undergone an amputation.

METHODS

A observational analysis was performed on 459 patients who have underwent amputation for diabetic foot from January 2014 through December 2019 at the First Affiliated Hospital of Wenzhou Medical University. The least absolute shrinkage and selection operator regression and stepwise regression methods were implemented to determine risk selection for the re-amputation risk model, and the predictive nomogram was established with these features. Calibration curve, receiver operating characteristic curve, and decision curve analysis of this re-amputation nomogram were assessed.

RESULTS

Predictors contained in this predictive model included smoking, glycated hemoglobin A1c (HbA1c), ankle-brachial index (ABI) and C-reactive protein (CRP). Good discrimination with a C-index of 0.725 (95% CI, 0.6624-0.7876) and good calibration were displayed with this predictive model. The decision curve analysis showed that this re-amputation nomogram predicting risk adds more benefit than none strategy if the threshold probability of a patient was >6% and <59%.

CONCLUSIONS

This novel re-amputation nomogram incorporating smoking, glycated hemoglobin A1c (HbA1c), ankle-brachial index (ABI), C-reactive protein (CRP), and smoking could be easily used to predict individual re-amputation risk prediction in diabetic foot patients who have undergone an amputation. In the future, further analysis and external testing will be needed as much as possible to reconfirm that this new Nomogram can accurately predict the risk of toe re-amputation.

Versatile in silico modeling of XAD-air partition coefficients for POPs based on abraham descriptor and temperature

The concentration of persistent organic pollutants (POPs) makes remarkable difference to environmental fate. In the field of passive sampling, the partition coefficients between polystyrene-divinylbenzene resin (XAD) and air (i.e., K_XAD-A) are indispensable to obtain POPs concentration, and the K_XAD-A is generally thought to be governed by temperature and molecular structure of POPs. However, experimental determination of K_XAD-A is unrealistic for countless and novel chemicals. Herein, the Abraham solute descriptors of poly parameter linear free energy relationship (pp-LFER) and temperature were utilized to develop models, namely pp-LFER-T, for predicting K_XAD-A values. Two linear (MLR and LASSO) and four nonlinear (ANN, SVM, kNN and RF) machine learning algorithms were employed to develop models based on a data set of 307 sample points. For the aforementioned six models, R²_adj and Q²_ext were both beyond 0.90, indicating distinguished goodness-of-fit and robust generalization ability. By comparing the established models, the best model was observed as the RF model with R²_adj = 0.991, Q²_ext = 0.935, RMSE_tra = 0.271 and RMSE_ext = 0.868. The mechanism interpretation revealed that the temperature, size of molecules and dipole-type interactions were the predominant factors affecting K_XAD-A values. Concurrently, the developed models with the broad applicability domain provide available tools to fill the experimental data gap for untested chemicals. In addition, the developed models were helpful to preliminarily evaluate the environmental ecological risk and understand the adsorption behavior of POPs between XAD membrane and air.

A Soft Robotic Intervention for Gait Enhancement in Older Adults

Falls continue to be a major safety and health concern for older adults. Researchers reported that increased gait variability was associated with increased fall risks. In the present study, we proposed a novel wearable soft robotic intervention and examined its effects on improving gait variability in older adults. The robotic system used customized pneumatic artificial muscles (PAMs) to provide assistive torque for ankle dorsiflexion during walking. Twelve older adults with low fall risks and twelve with medium-high fall risks participated in an experiment. The participants were asked to walk on a treadmill under no soft robotic intervention, inactive soft robotic intervention, and active soft robotic intervention, and their gait variability during treadmill walking was measured. The results showed that the proposed soft robotic intervention could reduce step length variability for elderly people with medium-high fall risks. These findings provide supporting evidence that the proposed soft robotic intervention could potentially serve as an effective solution to fall prevention for older adults.

Validation and Comparison of Instrumented Mouthguards for Measuring Head Kinematics and Assessing Brain Deformation in Football Impacts

Because of the rigid coupling between the upper dentition and the skull, instrumented mouthguards have been shown to be a viable way of measuring head impact kinematics for assisting in understanding the underlying biomechanics of concussions. This has led various companies and institutions to further develop instrumented mouthguards. However, their use as a research tool for understanding concussive impacts makes quantification of their accuracy critical, especially given the conflicting results from various recent studies. Here we present a study that uses a pneumatic impactor to deliver impacts characteristic to football to a Hybrid III headform, in order to validate and compare five of the most commonly used instrumented mouthguards. We found that all tested mouthguards gave accurate measurements for the peak angular acceleration, the peak angular velocity, brain injury criteria values (mean average errors < 13, 8, 13%, respectively), and the mouthguards with long enough sampling time windows are suitable for a convolutional neural network-based brain model to calculate the brain strain (mean average errors < 9%). Finally, we found that the accuracy of the measurement varies with the impact locations yet is not sensitive to the impact velocity for the most part.