Build Prediction Models Research Articles

Prediction models for physical function in COVID-19 survivors

BackgroundThe burden of caring for patients who have survived COVID-19 will be enormous in the coming years, especially with respect to physical function. Physical function has been routinely assessed using the Post-COVID-19 Functional Status (PCFS) scale. AimThis study built prediction models for the PCFS scale using sociodemographic data, clinical findings, lung function, and muscle strength. MethodTwo hundred and one patients with post-COVID-19 syndrome (PCS) completed the PCFS scale to assess physical function. Their levels of general fatigue were also assessed using the Functional Assessment of Chronic Illness Therapy-Fatigue (FACIT-F) scale, handgrip strength (HGS), and spirometry. ResultsThe number of participants who scored 0 (none), 1 (negligible), 2 (slight), 3 (moderate), and 4 (severe) on the PCFS scale was 25 (12%), 40 (20%), 39 (19%), 49 (24%), and 48 (24%), respectively. The PCFS scale was significantly correlated with the following variables: FACIT-F score (r = −0.424, P < 0.001), HGS (r = −0.339, P < 0.001), previous hospitalization (r = 0.226, P = 0.001), body mass index (r = 0.163, P = 0.021), and sex (r = −0.153, P = 0.030). The regression model with the highest coefficient of regression (R = 0.559) included the following variables: age, sex, body mass index, FACIT-F, HGS, and previous hospitalization. ConclusionsWorse general fatigue and HGS are associated with more severe physical function impairments in PCS patients. Furthermore, a history of prior hospitalization results in worse physical function. Thus, prediction models for the PCFS scale that incorporate objective measures enable a better assessment of the physical function of these patients, thus helping in the selection of candidates for a program of physical reconditioning.

Model for Predicting the Risk of Bronchopleural Fistula After Pneumonectomy for Destructive Pulmonary Tuberculosis

Introduction: Predicting various events based on influencing factors is important for statistical analysis in medical research. Unfortunately, mathematical models are rarely built on the identified factors.Objective: To develop a model to predict the risk of bronchopleural fistula after pneumonectomy for destructive pulmonary tuberculosis.Materials and methods: We analyzed medical records of 198 patients who underwent pneumonectomy. Of them 6 patients (3%) developed a bronchopleural fistula. We used machine learning algorithms such as ridge regression, support vector machine, random forest, and CatBoost, the Jupyter open­source development environment, and Python 3.6 to build prediction models. ROC analysis was used to evaluate the quality of the binary classification.Results: We built 4 models to predict the risk of bronchopleural fistula. Their ROC AUC were as follows: ridge regression – 0.88, support vector machine – 0.87, CatBoost – 0.75, and random forest – 0.74. The model based on the ridge regression showed the best ROC AUC. Based on the coordinates of the ROC curve, the threshold value of 1.9% provides the maximum total sensitivity and specificity (100% and 68.8%, respectively).Conclusions: The developed model has a high predictive ability, which allows focusing on the patient group with an increased risk of bronchopleural fistula and justifying the need for preventive measures.

Predicting micropapillary or solid pattern of lung adenocarcinoma with CT-based radiomics, conventional radiographic and clinical features

BackgroundTo build prediction models with radiomics features, clinical/conventional radiographic signs and combined scores for the discrimination of micropapillary or solid subtypes (high-risk subtypes) of lung adenocarcinoma.MethodsThis retrospective study enrolled 351 patients with and without high-risk subtypes. Least Absolute Shrinkage and Selection Operator (LASSO) regression with cross-validation was performed to determine the optimal features of radiomics model. Missing clinical data were imputed by Multiple Imputation with Chain Equations (MICE). Clinical model with radiographic signs was built and scores of both models were integrated to establish combined model. Receiver operating characteristics (ROC) curves, area under ROC curves and decision curve analysis (DCA) were plotted to evaluate the model performance and clinical application.ResultsStratified splitting allocated 246 patients into training set. MICE for missing values obtained complete and unbiased data for the following analysis. Ninety radiomic features and four clinical/conventional radiographic signs were used to predict the high-risk subtypes. The radiomic model, clinical model and combined model achieved AUCs of 0.863 (95%CI: 0.817–0.909), 0.771 (95%CI: 0.713–0.713) and 0.872 (95%CI: 0.829–0.916) in the training set, and 0.849 (95%CI: 0.774–0.924), 0.778 (95%CI: 0.687–0.868) and 0.853 (95%CI: 0.782–0.925) in the test set. Decision curve showed that the radiomic and combined models were more clinically useful when the threshold reached 37.5%.ConclusionsRadiomics features could facilitate the prediction of subtypes of lung adenocarcinoma. A simple combination of radiomics and clinical scores generated a robust model with high performance for the discrimination of micropapillary or solid subtype of lung adenocarcinoma.

Acute renal injury after aortic arch reconstruction with cardiopulmonary bypass for children: prediction models by machine learning of a retrospective cohort study

BackgroundAcute renal injury (AKI) after aortic arch reconstruction with cardiopulmonary bypass leads to injury of multiple organs and increases perioperative mortality. The study was performed to explore risk factors for AKI. We aim to develop a prediction model that can be used to accurately predict AKI through machine learning (ML).MethodsA retrospective analysis was performed on 134 patients with aortic arch reconstruction with cardiopulmonary bypass who were treated at our hospital from January 2002 to January 2022. Risk factors for AKI were compositive and were evaluated with comprehensive analyses. Six artificial intelligence (AI) models were used for machine learning to build prediction models and to screen out the best model to predict AKI.ResultsWeight, eGFR, cyanosis, PDA, newborn birth and duration of renal ischemia were closely related to AKI. By integrating the results of the training cohort and validation cohort, we finally confirmed that the logistic regression model was the most stable model among all the models, and the logistic regression model showed good discrimination, calibration and clinical practicability. Based on 6 independent factors, the dynamic nomogram can be used as a predictive tool for clinical application.ConclusionsDHCA could be considered in aortic arch reconstruction if additional perfusion of lower body were not performed especially when renal ischemia is greater than 30 min. Machine Learning models should be developed for early recognition of AKI.Trial Registration: ChiCTR, ChiCTR2200060552. Registered 4 june 2022. Graphical

A Novel COVID-19 Diagnosis Approach Utilizing a Comprehensive Set of Diagnostic Information (CSDI)

The aim of the study was to develop a computerized method for distinguishing COVID-19-affected cases from cases of pneumonia. This task continues to be a real challenge in the practice of diagnosing COVID-19 disease. In the study, a new approach was proposed, using a comprehensive set of diagnostic information (CSDI) including, among other things, medical history, demographic data, signs and symptoms of the disease, and laboratory results. These data have the advantage of being much more reliable compared with data based on a single source of information, such as radiological imaging. On this basis, a comprehensive process of building predictive models was carried out, including such steps as data preprocessing, feature selection, training, and evaluation of classification models. During the study, 9 different methods for feature selection were used, while the grid search method and 12 popular classification algorithms were employed to build classification models. The most effective model achieved a classification accuracy (ACC) of 85%, a sensitivity (TPR) equal to 83%, and a specificity (TNR) of 88%. The model was built using the random forest method with 15 features selected using the recursive feature elimination selection method. The results provide an opportunity to build a computer system to assist the physician in the diagnosis of the COVID-19 disease.

A CT-based radiomics classification model for the prediction of histological type and tumour grade in retroperitoneal sarcoma (RADSARC-R): a retrospective multicohort analysis

Retroperitoneal sarcomas are tumours with a poor prognosis. Upfront characterisation of the tumour is difficult, and under-grading is common. Radiomics has the potential to non-invasively characterise the so-called radiological phenotype of tumours. We aimed to develop and independently validate a CT-based radiomics classification model for the prediction of histological type and grade in retroperitoneal leiomyosarcoma and liposarcoma. A retrospective discovery cohort was collated at our centre (Royal Marsden Hospital, London, UK) and an independent validation cohort comprising patients recruited in the phase 3 STRASS study of neoadjuvant radiotherapy in retroperitoneal sarcoma. Patients aged older than 18 years with confirmed primary leiomyosarcoma or liposarcoma proceeding to surgical resection with available contrast-enhanced CT scans were included. Using the discovery dataset, a CT-based radiomics workflow was developed, including manual delineation, sub-segmentation, feature extraction, and predictive model building. Separate probabilistic classifiers for the prediction of histological type and low versus intermediate or high grade tumour types were built and tested. Independent validation was then performed. The primary objective of the study was to develop radiomic classification models for the prediction of retroperitoneal leiomyosarcoma and liposarcoma type and histological grade. 170 patients recruited between Oct 30, 2016, and Dec 23, 2020, were eligible in the discovery cohort and 89 patients recruited between Jan 18, 2012, and April 10, 2017, were eligible in the validation cohort. In the discovery cohort, the median age was 63 years (range 27-89), with 83 (49%) female and 87 (51%) male patients. In the validation cohort, median age was 59 years (range 33-77), with 46 (52%) female and 43 (48%) male patients. The highest performing model for the prediction of histological type had an area under the receiver operator curve (AUROC) of 0·928 on validation, based on a feature set of radiomics and approximate radiomic volume fraction. The highest performing model for the prediction of histological grade had an AUROC of 0·882 on validation, based on a radiomics feature set. Our validated radiomics model can predict the histological type and grade of retroperitoneal sarcomas with excellent performance. This could have important implications for improving diagnosis and risk stratification in retroperitoneal sarcomas. Wellcome Trust, European Organisation for Research and Treatment of Cancer-Soft Tissue and Bone Sarcoma Group, the National Institutes for Health, and the National Institute for Health and Care Research Biomedical Research Centre at The Royal Marsden NHS Foundation Trust and The Institute of Cancer Research.

Prediction of individual brain age using movie and resting-state fMRI.

Brain age is a promising biomarker for predicting chronological age based on brain imaging data. Although movie and resting-state functional MRI techniques have attracted much research interest for the investigation of brain function, whether the 2 different imaging paradigms show similarities and differences in terms of their capabilities and properties for predicting brain age remains largely unexplored. Here, we used movie and resting-state functional MRI data from 528 participants aged from 18 to 87years old in the Cambridge Centre for Ageing and Neuroscience data set for functional network construction and further used elastic net for age prediction model building. The connectivity properties of movie and resting-state functional MRI were evaluated based on the connections supporting predictive model building. We found comparable predictive abilities of movie and resting-state connectivity in estimating brain age of individuals, as evidenced by correlation coefficients of 0.868 and 0.862 between actual and predicted age, respectively. Despite some similarities, notable differences in connectivity properties were observed between the predictive models using movie and resting-state functional MRI data, primarily involving components of the default mode network. Our results highlight that both movie and resting-state functional MRI are effective and promising techniques for predicting brain age. Leveraging its data acquisition advantages, such as improved child and patient compliance resulting in reduced motion artifacts, movie functional MRI is emerging as an important paradigm for studying brain function in pediatric and clinical populations.

Kernel Cox partially linear regression: Building predictive models for cancer patients' survival.

Wide heterogeneity exists in cancer patients' survival, ranging from a few months to several decades. To accurately predict clinical outcomes, it is vital to build an accurate predictive model that relates the patients' molecular profiles with the patients' survival. With complex relationships between survival and high-dimensional molecular predictors, it is challenging to conduct nonparametric modeling and irrelevant predictors removing simultaneously. In this article, we build a kernel Cox proportional hazards semi-parametric model and propose a novel regularized garrotized kernel machine (RegGKM) method to fit the model. We use the kernel machine method to describe the complex relationship between survival and predictors, while automatically removing irrelevant parametric and nonparametric predictors through a LASSO penalty. An efficient high-dimensional algorithm is developed for the proposed method. Comparison with other competing methods in simulation shows that the proposed method always has better predictive accuracy. We apply this method to analyze a multiple myeloma dataset and predict the patients' death burden based on their gene expressions. Our results can help classify patients into groups with different death risks, facilitating treatment for better clinical outcomes.

Machine learning-based predictive model for the differential diagnosis of ≤ 5 cm gastric stromal tumor and gastric schwannoma based on CT images

The clinical symptoms of ≤ 5 cm gastric stromal tumor (GST) and gastric schwannoma (GS) are similar, but the treatment regimens are different. This study explored the value of computed tomography (CT) combined with machine learning (ML) algorithms to find the best model to discriminate them. A total of 126 patients with GST ≤ 5 cm and 35 patients with GS ≤ 5 during 2013–2022 were included. CT imaging features included qualitative data (tumor location, growth pattern, lobulation, surface ulcer status, necrosis, calcification, and surrounding lymph nodes) and quantitative data [long diameter (LD); short diameter (SD); LD/SD ratio; degree of enhancement (DE); heterogeneous degree (HD)]. Patients were randomly divided into a training set (n = 112) and test set (n = 49) using 7:3 stratified sampling. The univariate and multivariate logistic regression analysis were used to identify independent risk factors. Five ML algorithms were used to build prediction models: Support Vector Machine, k-Nearest Neighbor, Random Forest, Extra Trees, and Extreme Gradient Boosting Machine. The analysis identified that HDv, lobulation, and tumor growth site were independent risk factors (P < 0.05). We should focus on these three imaging features of tumors, which are relatively easy to obtain. The area under the curve for the SVM, KNN, RF, ET, and XGBoost prediction models were, respectively, 0.790, 0.895, 0.978, 0.988, and 0.946 for the training set, and were, respectively, 0.848, 0.892, 0.887, 0.912, and 0.867 for the test set. The CT combined with ML algorithms generated predictive models to improve the differential diagnosis of ≤ 5 cm GST and GS which has important clinical practical value. The Extra Trees algorithm resulted in the optimal model.

Machine learning-based evaluation of application value of traditional Chinese medicine clinical index and pulse wave parameters in the diagnosis of polycystic ovary syndrome

IntroductionPolycystic ovary syndrome (PCOS) is a prevalent endocrine disorder in women that often leads to ovulatory infertility. This study aims to establish and validate an effective predictive model for PCOS and to explore the correlation of features between patients with irregular menstruation and those with PCOS, using pulse wave parameters and traditional Chinese medicine (TCM) clinical indices. MethodsFrom August 2018 to January 2022, women with irregular menstruation were enrolled in this study. Subjects who met the inclusion criteria were categorized into PCOS and non-PCOS groups based on diagnostic criteria. Pulse wave parameters and TCM clinical indices were collected by two medical professionals. After data cleaning, recursive feature elimination with cross-validation (RFECV) was used for feature selection. Four supervised machine learning classifiers were used to build PCOS prediction models, including Extra Trees (ET), Random Forest (RF), Extreme Gradient Boosting (XGB/XGBoost), and Support Vector Machine (SVM). The SHapley Additive exPlanation (SHAP) values based on the optimal model were visualized for further feature explanation. ResultsA total of 450 women with irregular periods were enrolled in the study, consisting of 294 patients with PCOS and 156 without PCOS. Based on RFECV, 31 features, including 12 pulse parameters and 19 TCM clinical indices, were selected for building prediction models. Using pulse and TCM clinical index was superior to using pulse parameters or TCM clinical index alone in prediction. SVM achieved the best PCOS prediction results (accuracy=0.837, AUC=0.878, F1 score=0.878). For pulse parameters, lower values of right As, right h4, left h1, left h3, left h5, left w/t, and higher right t5 showed an obvious positive PCOS predictive effect. Women with PCOS were more likely to experience delayed menstruation, negative emotions, a slightly jelly-like menstrual texture, higher BMI, and a TCM assessment of greasy tongue coating. ConclusionA PCOS prediction model based on the SVM algorithm was established and verified as the best model for distinguishing between patients with PCOS and patients without PCOS with irregular menstruation. The new prediction model that uses pulse wave parameters and TCM clinical indices offers a non-invasive and cost-effective way to diagnose PCOS, and the model provides objective evidence for TCM diagnosis.

Prediction of Wordle report distribution results based on PSO-LBGM prediction model

Accurate prediction of Wordle report headcount distribution is an important reference for Wordle's later word difficulty setting to expand the number of players. In order to increase the number of purchased products, the prediction model of the number of people distribution results is constructed by using Lightweight Gradient Boosting Machine (LightGBM), and PSO is used to optimize the hyperparameters of the LightGBM model. The historical data were preprocessed and the word attributes were extracted using unique thermal coding to build prediction models based on PSO-LightGBM, LightGBM and LSTM. The results show that the mean absolute percentage (MAPE) of the training and test sets predicted by PSO-LightGBM for (1, 2, 3, 4, 5, 6, X) is 0.531%, 0.410%, respectively. and the model was more accurate in predicting the number distribution results than LightGBM and LSTM models.

Prediction of symptomatic anastomotic leak after rectal cancer surgery: A machine learning approach.

Anastomotic leakage (AL) remains the most dreaded and unpredictable major complication after low anterior resection for mid-low rectal cancer. The aim of this study is to identify patients with high risk for AL based on the machine learning method. Patients with mid-low rectal cancer undergoing low anterior resection were enrolled from West China Hospital between January 2008 and October 2019 and were split by time into training cohort and validation cohort. The least absolute shrinkage and selection operator (LASSO) method and stepwise method were applied for variable selection and predictive model building in the training cohort. The area under the receiver operating characteristic curve (AUC) and calibration curves were used to evaluate the performance of the models. The rate of AL was 5.8% (38/652) and 7.2% (15/208) in the training cohort and validation cohort, respectively. The LASSO-logistic model selected almost the same variables (hypertension, operating time, cT4, tumor location, intraoperative blood loss) compared to the stepwise logistic model except for tumor size (the LASSO-logistic model) and AmericanSociety of Anesthesiologists score (the stepwise logistic model). The predictive performance of the LASSO-logistics model was better than the stepwise-logistics model (AUC: 0.790 vs. 0.759). Calibration curves showed mean absolute error of 0.006 and 0.013 for the LASSO-logistics model and stepwise-logistics model, respectively. Our study developed a feasible predictive model with a machine-learning algorithm to classify patients with a high risk of AL, which would assist surgical decision-making and reduce unnecessary stoma diversion. The involved machine learning algorithms provide clinicians with an innovative alternative to enhance clinical management.

Prediction of Cancer Metastasis Using Correlations Between miRNAs and Competing Endogenous RNAs.

Cancer metastasis is a complex process which involves the spread of tumor cells from the primary site to other parts of the body. Metastasis is the major cause of cancer mortality, accounting for about 90% of cancer deaths. Metastasis is primarily diagnosed by clinical examinations and imaging techniques, but such a diagnosis is made after metastasis has occurred. Prediction or early detection of metastasis is important for treatment planning since it has an impact on the survival of patients. Recently a few methods have been developed to predict lymph node metastasis, but few methods are available for predicting distant metastasis. Motivated by a gene regulation mechanism involving miRNAs, we have developed a new method for predicting both lymph node metastasis and distant metastasis. We have derived differential correlations of miRNAs and their target RNAs in cancer, and built prediction models using the differential correlations. Testing the method on several types of cancer showed that differential correlations of miRNAs and target RNAs are much more powerful and stable than expressions of known metastasis predictive genes in predicting distant metastasis as well as lymph node metastasis. The method developed in this study will be useful in predicting metastasis and thereby in determining treatment options for cancer patients.

스마트도시의 안전성 향상을 위한 스마트기술 적용방안에 관한 연구

In order to propose ways to apply smart technology to improve the safety of smart cities, this study aims to propose smart technologies that are highly related to safety management in the areas of transportation, medical care, environment, nature, and crime prevention in smart cities, such as AR, BIM, big data, and cloud. , IoT, VR, robot automation, drones, and 3D printing were analyzed. For the study, the applicability of smart technology in each field was investigated by safety management experts using a matrix evaluation method, and the results can be summarized as follows. In the transportation field, big data technology for collecting and processing traffic information through GPS, GIS and smart phone apps, drone technology that monitors real-time traffic information and utilizes sensors such as vehicles, roads and signal devices, and various collected information The safety of smart cities can be secured by applying IoT technology that builds prediction models based on traffic patterns. In the medical field, robot automation technology that sets up predictive models for telemedicine, health management, drug processing and infectious diseases, drone technology that utilizes the movement of patients and medical staff, attachment of monitoring devices, and securing public health response data, etc. It is predicted that it will be possible to secure the safety of smart cities through 3D printing technology that can manufacture medical instruments, auxiliary devices, and various artificial bodies, as well as various medical models and educational tools. In the environmental field, drone technology enables real-time monitoring of water quality, air, and various environmental factors, robotic automation technology that uses robots in places to collect environmental data within the city, and environmental infrastructure that installs and collects buildings, vehicles, and various infrastructure facilities. IoT technology can be applied to improve the safety of smart cities. In the natural field, drone technology is capable of collecting and utilizing various data by attaching video, thermal images, LiDAR scans, radars and sensors, and integrated management linked to a central system focused on the installation of houses, buildings and various infrastructure facilities and environmental changes. The safety of smart cities can be improved by utilizing possible IoT technology, BIM technology that can establish response plans for storm and flood damage, cold waves, heatstroke, and earthquakes through 3D models, and big data technology that collects, integrates, and builds platforms for safety-related data. It can be promoted. In the crime prevention field, drone technology that can detect the occurrence of abnormal signals such as sound, heat, and optical sensors and link with the local police station, IoT technology that can collect and analyze voice recognition technology, and AI that strengthens facial and vehicle recognition in intelligent CCTV. The safety of smart cities can be secured through robot automation technology that combines the deployment of basic robots and collaboration with drones and IoT technologies.

IMDAC: A robust intelligent software defect prediction model via multi‐objective optimization and end‐to‐end hybrid deep learning networks

AbstractSoftware defect prediction (SDP) aims to build an effective prediction model for historical defect data from software repositories by some specialized techniques or algorithms, and predict the defect proneness of new software modules. Nevertheless, the complex internal intrinsic structure hidden behind the defect data makes it challenging for the built prediction model to capture the most expressive defect feature representations, and largely limits the SDP performance. Fortunately, artificial intelligence is interacting closely with humans and provides powerful intelligent technical support for addressing these SDP issues. In this article, we propose a robust intelligent SDP model called IMDAC based on deep learning and soft computing techniques. This model has three main advantages: (1) an effective deep generative network—InfoGAN (information maximizing GANs) is employed to conduct data augmentation, namely generating sufficient defect instances and achieving defect class balance simultaneously. (2) Select the fewest representative feature subset for the minimum error via an advanced multi‐objective optimization approach—MSEA (multi‐stage evolutionary algorithm). (3) Build a powerful end‐to‐end deep defect predictor by hybrid deep learning techniques—DAE (Denoising AutoEncoder) and CNN (convolutional neural network), which can not only reconstruct a clean “repaired” input with strong robustness and generalization capabilities via DAE, but also learn the abstract deep semantic features with strong discriminating capability via CNN. Experimental results verify the superiority and robustness of the IMDAC model across 15 software projects.

Implementing a Novel Machine Learning System for Nutrition Education in Diabetes Mellitus Nutritional Clinic: Predicting 1-Year Blood Glucose Control.

(1) Background: Persistent hyperglycemia in diabetes mellitus (DM) increases the risk of death and causes cardiovascular disease (CVD), resulting in significant social and economic costs. This study used a machine learning (ML) technique to build prediction models with the factors of lifestyle, medication compliance, and self-control in eating habits and then implemented a predictive system based on the best model to forecast whether blood glucose can be well-controlled within 1 year in diabetic patients attending a DM nutritional clinic. (2) Methods: Data were collected from outpatients aged 20 years or older with type 2 DM who received nutrition education in Chi Mei Medical Center. Multiple ML algorithms were used to build the predictive models. (3) Results: The predictive models achieved accuracies ranging from 0.611 to 0.690. The XGBoost model with the highest area under the curve (AUC) of 0.738 was regarded as the best and used for the predictive system implementation. SHAP analysis was performed to interpret the feature importance in the best model. The predictive system, evaluated by dietitians, received positive feedback as a beneficial tool for diabetes nutrition consultations. (4) Conclusions: The ML prediction model provides a promising approach for diabetes nutrition consultations to maintain good long-term blood glucose control, reduce diabetes-related complications, and enhance the quality of medical care.

Development and temporal validation of clinical prediction models for 1-year disability and pain after lumbar decompressive surgery. The Norwich Lumbar Surgery Predictor (development version).

To identify clinical predictors and build prediction models for 1-year patient-reported outcomes measures (PROMs) after lumbar decompressive surgery for disc herniation or spinal stenosis. The study included 1835 cases, with or without additional single-level fusion, from a single centre from 2008 through 2020. General linear models imputed with 37 clinical variables identified 18 significant 1-year PROM predictors for retention in development models. Interaction of surgical indication with each predictor was tested. Temporal validation was conducted at the same centre on cases through 2021. R2 was used to measure goodness-of-fit, and area under curve (AUC) used to measure classification to a satisfactory symptom state (Oswestry Disability Index (ODI) ≤ 22; back or leg pain ≤ 30 out of 100). A total 1228 (67%) had complete data for inclusion in model development. Predictors of ODI were baseline PROMs (ODI, back pain, leg pain), work status, condition duration, previous lumbar operation, multiple-joint osteoarthritis, female, diabetes, current smoker, rheumatic disorder, lower limb arthroplasty, mobility aided, provider status, facet cyst, scoliosis, and age, with BMI significantly associated with stenosis. Temporal validation (n = 188) found the ODI model R2 was 0.29 (95% confidence intervals (CI) 0.18-0.40) and AUC was 0.74 (95% CI 0.67-0.81). Back and leg pain models had lower R2 (0.12-0.14) and AUC (0.68-0.69) values. Important PROM predictors are baseline PROMs, specific co-morbidities, work status, condition duration, previous lumbar operation, female, and smoking status. The ODI model predicted the likelihood of achieving a satisfactory state of both disability and pain.

Design of a Sensor-Technology-Augmented Gait and Balance Monitoring System for Community-Dwelling Older Adults in Hong Kong: A Pilot Feasibility Study.

Routine assessments of gait and balance have been recognized as an effective approach for preventing falls by issuing early warnings and implementing appropriate interventions. However, current limited public healthcare resources cannot meet the demand for continuous monitoring of deteriorations in gait and balance. The objective of this study was to develop and evaluate the feasibility of a prototype surrogate system driven by sensor technology and multi-sourced heterogeneous data analytics, for gait and balance assessment and monitoring. The system was designed to analyze users' multi-mode data streams collected via inertial sensors and a depth camera while performing a 3-m timed up and go test, a five-times-sit-to-stand test, and a Romberg test, for predicting scores on clinical measurements by physiotherapists. Generalized regression of sensor data was conducted to build prediction models for gait and balance estimations. Demographic correlations with user acceptance behaviors were analyzed using ordinal logistic regression. Forty-four older adults (38 females) were recruited in this pilot study (mean age = 78.5 years, standard deviation [SD] = 6.2 years). The participants perceived that using the system for their gait and balance monitoring was a good idea (mean = 5.45, SD = 0.76) and easy (mean = 4.95, SD = 1.09), and that the system is useful in improving their health (mean = 5.32, SD = 0.83), is trustworthy (mean = 5.04, SD = 0.88), and has a good fit between task and technology (mean = 4.97, SD = 0.84). In general, the participants showed a positive intention to use the proposed system in their gait and balance management (mean = 5.22, SD = 1.10). Demographic correlations with user acceptance are discussed. This study provides preliminary evidence supporting the feasibility of using a sensor-technology-augmented system to manage the gait and balance of community-dwelling older adults. The intervention is validated as being acceptable, viable, and valuable.

A novel method of neural network model predictive control integrated process monitoring and applications to hot rolling process

The stable control of product quality when abnormal working conditions occur in the industrial production process is essential to improve product quality and economic efficiency. However, the process industry suffers from multivariate, nonlinear, uncertainty, long time delays and frequent failures, making its modeling and control difficult. In this paper, a novel method of neural network model predictive control integrated process monitoring (PM-NNMPC) is proposed. First, the combination of gated recurrent unit and convolutional neural network (GRU-CNN) is used to extract the features from the time and the space separately to build prediction models for different working conditions of the process. Then, a process monitoring and fault diagnosis method of principal component analysis combined with deep neural network and XGBoost (PCA-DNN-XGBoost) is designed to monitor the working conditions in real-time and diagnose accurately when faults occur. Finally, a new operation control framework integrating process monitoring and fault diagnosis into the model prediction control is designed to solve the problem that equipment operation failure, which makes the product quality fluctuation because of the model mismatch and the system runaway. The experimental results of hot rolling process show that PM-NNMPC can effectively control the system under normal working conditions and in case of the system failure to ensure the stable product quality.

Research on learning behavior patterns from the perspective of educational data mining: Evaluation, prediction and visualization

The rapid growth of educational data creates the requirement to mine useful information from learning behavior patterns. The development of data mining technology makes educational data mining possible. The paper intends to use a public educational data set to study learning behavior patterns from the perspective of educational data mining, so as to promote the innovation of educational management. Firstly, in order to reduce the dimension of data analysis that facilitates the improvement in efficiency, principal component analysis is carried out to reduce the number of attributes in the data set. The significant attributes in the rotating principal component matrix rather than principal components which are not closely related to learning behavior patterns are extracted as the research variables. Then, a pseudo statistic is proposed to determine the number of clusters and the preprocessed data set is clustered according to the extracted attributes. The clustering results are applied to add class labels to the data, which is convenient for the later data training. Finally, six classification algorithms J48, K-Nearest Neighbor, Bayes Net, Random Forest, Support Vector Machine and Logit Boost are used to train the data with labels and build prediction models. At the same time, the performance and applicable conditions of six classifiers in terms of accuracy, efficiency, error, and so on are discussed and compared. It is found that the performance of the integrated algorithm is better than that of a single classifier. In the integrated algorithm, compared with Random Forest, the running time of Logit Boost is shorter.