XGBoost based machine learning approach to predict the risk of fall in older adults using gait outcomes.
Ontology highlight
ABSTRACT:
SUBMITTER: Noh B
PROVIDER: S-EPMC8190134 | biostudies-literature |
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:BackgroundAdverse health effects resulting from falls are a major public health concern. Although studies have identified risk factors for falls, none have examined long-term prediction of fall risk. Furthermore, recent evidence suggests that there are additional risk factors, such as psychosocial factors.ObjectiveIn this 3-year longitudinal study, we evaluated a predictive model for risk of fall among community-dwelling older adults using machine learning methods.DesignA 3-year follow-up prospective longitudinal study (from 2010 to 2013).SettingTwenty-four municipalities in nine of the 47 prefectures (provinces) of Japan.ParticipantsCommunity-dwelling individuals aged ≥65 years who were functionally independent at baseline (n = 61,883).MethodsThe baseline survey was conducted from August 2010 to January 2012, and the follow-up survey was conducted from October to December 2013. Both surveys were conducted involving self-reported questionnaires. The measured outcome at the follow-up survey was self-reported multiple falls during the previous year. The 142 variables included in the baseline survey were regarded as candidate predictors. The random-forest-based Boruta algorithm was used to select predictors, and the eXtreme Gradient Boosting algorithm with 10 repetitions of nested k-fold cross-validation was used for modeling and model evaluation. Furthermore, we used shapley additive explanations to gain insight into the behavior of the prediction model.Key resultsFourteen out of 142 candidate features were selected as predictors. Among these predictors, experience of falling as of the baseline survey was the most important feature, followed by self-rated health and age. Moreover, sense of coherence was newly identified as a risk factor for falls.ConclusionsThis study suggests that machine learning tools can be adapted to explore new associative factors, make accurate predictions, and provide actionable insights for fall prevention strategies.
| S-EPMC9411287 | biostudies-literature
Project description:Prior research has suggested that measurements of brain functioning and performance on dual tasks (tasks which require simultaneous performance) are promising candidate predictors of fall risk among older adults. However, no prior study has investigated whether brain function measurements during dual task performance could improve prediction of fall risks and whether the type of subtasks used in the dual task paradigm affects the strength of the association between fall characteristics and dual task performance. In this study, 31 cognitively normal, community-dwelling older adults provided a self-reported fall profile (number of falls and fear of falling), completed a gait dual task (spell a word backward while walking on a GaitRite mat), and completed a supine dual task (rhythmic finger tapping with one hand while completing the AX continuous performance task (AX-CPT) with the other hand) during functional magnetic resonance imaging (fMRI). Gait performance, AX-CPT reaction time and accuracy, finger tapping cadence, and brain functioning in finger-tapping-related and AX-CPT-related brain regions all showed declines in the dual task condition compared to the single task condition. Dual-task gait, AX-CPT and finger tapping performance, and brain functioning were all independent predictors of fall profile. No particular measurement domain stood out as being the most strongly associated measure with fall variables. Fall characteristics are determined by multiple factors; brain functioning, motor task, and cognitive task performance in challenging dual-task conditions all contribute to the risk of falling.
| S-EPMC7935539 | biostudies-literature
Project description:ObjectiveAmong various assessment paradigms, the cardiopulmonary exercise test (CPET) provides rich evidence as part of the cardiopulmonary endurance (CPE) assessment. However, methods and strategies for interpreting CPET results are not in agreement. The purpose of this study is to validate the possibility of using machine learning to evaluate CPET data for automatically classifying the CPE level of workers in high-latitude areas.MethodsA total of 120 eligible workers were selected for this cardiopulmonary exercise experiment, and the physiological data and completion of the experiment were recorded in the simulated high-latitude workplace, within which 84 sets of data were used for XGBOOST model training and36 were used for the model validation. The model performance was compared with Support Vector Machine and Random Forest. Furthermore, hyperparameter optimization was applied to the XGBOOST model by using a genetic algorithm.ResultsThe model was verified by the method of tenfold cross validation; the correct rate was 0.861, with a Micro-F1 Score of 0.864. Compared with RF and SVM, all data achieved a better performance.ConclusionWith a relatively small number of training samples, the GA-XGBOOST model fits well with the training set data, which can effectively evaluate the CPE level of subjects, and is expected to provide automatic CPE evaluation for selecting, training, and protecting the working population in plateau areas.
| S-EPMC9600669 | biostudies-literature
Project description:This article presents a five-part dataset for human gait analysis in a healthy older adult population (37 women and seven men; age 69.98 ± 8.57 years, body mass index 27.71 ± 4.57). Part 1 compromises demographic data for the 44 participants, along with the results of the Short Physical Performance Battery (SPPB) motor function test and the Mini-Mental State Examination (MMSE). We used the MMSE to ensure the participants could understand the experimental protocol instructions. Part 2 presents the anthropometric measurements of the participants. Part 3 shows the results for each item of the Gait component of the Performance Oriented Mobility Assessment (POMA-G). Part 4 contains five files per participant, storing motion-capture data for the lower limb in the Coordinate 3D (C3D) format. These files were generated using a Vicon motion analysis system, consisting of 24 reflective markers and seven cameras (Vantage V5) sampled at 100 Hz. Part 5 contains 26 gait parameters for each C3D file obtained using Nexus 2.9.3. The dataset is available in a Mendeley repository (Reserved DOI: 10.17632/xgw6bg3g8h.1).
| S-EPMC7701341 | biostudies-literature
Project description:Gait and physical fitness are related to cognitive function. A decrease in motor function and physical fitness can serve as an indicator of declining global cognitive function in older adults. This study aims to use machine learning (ML) to identify important features of gait and physical fitness to predict a decline in global cognitive function in older adults. A total of three hundred and six participants aged seventy-five years or older were included in the study, and their gait performance at various speeds and physical fitness were evaluated. Eight ML models were applied to data ranked by the p-value (LP) of linear regression and the importance gain (XI) of XGboost. Five optimal features were selected using elastic net on the LP data for men, and twenty optimal features were selected using support vector machine on the XI data for women. Thus, the important features for predicting a potential decline in global cognitive function in older adults were successfully identified herein. The proposed ML approach could inspire future studies on the early detection and prevention of cognitive function decline in older adults.
| S-EPMC8582857 | biostudies-literature
Project description:BackgroundAdvances in computational algorithms and the availability of large datasets with clinically relevant characteristics provide an opportunity to develop machine learning prediction models to aid in diagnosis, prognosis, and treatment of older adults. Some studies have employed machine learning methods for prediction modeling, but skepticism of these methods remains due to lack of reproducibility and difficulty in understanding the complex algorithms that underlie models. We aim to provide an overview of two common machine learning methods: decision tree and random forest. We focus on these methods because they provide a high degree of interpretability.MethodWe discuss the underlying algorithms of decision tree and random forest methods and present a tutorial for developing prediction models for serious fall injury using data from the Lifestyle Interventions and Independence for Elders (LIFE) study.ResultsDecision tree is a machine learning method that produces a model resembling a flow chart. Random forest consists of a collection of many decision trees whose results are aggregated. In the tutorial example, we discuss evaluation metrics and interpretation for these models. Illustrated using data from the LIFE study, prediction models for serious fall injury were moderate at best (area under the receiver operating curve of 0.54 for decision tree and 0.66 for random forest).ConclusionsMachine learning methods offer an alternative to traditional approaches for modeling outcomes in aging, but their use should be justified and output should be carefully described. Models should be assessed by clinical experts to ensure compatibility with clinical practice.
| S-EPMC8011704 | biostudies-literature
Project description:Predictions of patient outcomes after a given therapy are fundamental to medical practice. We employ a machine learning approach towards predicting the outcomes after stereotactic radiosurgery for cerebral arteriovenous malformations (AVMs). Using three prospective databases, a machine learning approach of feature engineering and model optimization was implemented to create the most accurate predictor of AVM outcomes. Existing prognostic systems were scored for purposes of comparison. The final predictor was secondarily validated on an independent site's dataset not utilized for initial construction. Out of 1,810 patients, 1,674 to 1,291 patients depending upon time threshold, with 23 features were included for analysis and divided into training and validation sets. The best predictor had an average area under the curve (AUC) of 0.71 compared to existing clinical systems of 0.63 across all time points. On the heldout dataset, the predictor had an accuracy of around 0.74 at across all time thresholds with a specificity and sensitivity of 62% and 85% respectively. This machine learning approach was able to provide the best possible predictions of AVM radiosurgery outcomes of any method to date, identify a novel radiobiological feature (3D surface dose), and demonstrate a paradigm for further development of prognostic tools in medical care.
| S-EPMC4746661 | biostudies-literature
Project description:The primary purpose of this study was to systematically evaluate and compare the predictive power of falls for a battery of stability indices, obtained during normal walking among community-dwelling older adults. One hundred and eighty seven community-dwelling older adults participated in the study. After walking regularly for 20 strides on a walkway, participants were subjected to an unannounced slip during gait under the protection of a safety harness. Full body kinematics and kinetics were monitored during walking using a motion capture system synchronized with force plates. Stability variables, including feasible-stability-region measurement, margin of stability, the maximum Floquet multiplier, the Lyapunov exponents (short- and long-term), and the variability of gait parameters (including the step length, step width, and step time), were calculated for each subject. Sensitivity of predicting slip outcome (fall vs. recovery) was examined for each stability variable using logistic regression. Results showed that the feasible-stability-region measurement predicted fall incidence among these subjects with the highest sensitivity (68.4%). Except for the step width (with an sensitivity of 60.2%), no other stability variables could differentiate fallers from those who did not fall for the sample included in this study. The findings from the present study could provide guidance to identify individuals at increased risk of falling using the feasible-stability-region measurement or variability of the step width.
| S-EPMC4469383 | biostudies-literature
Project description:Background: Frail older adults have an increased risk of adverse health outcomes and premature death. They also exhibit altered gait characteristics in comparison with healthy individuals. Methods: In this study, we created a Fried's frailty phenotype (FFP) labelled casual walking video set of older adults based on the West China Health and Aging Trend study. A series of hyperparameters in machine vision models were evaluated for body key point extraction (AlphaPose), silhouette segmentation (Pose2Seg, DPose2Seg, and Mask R-CNN), gait feature extraction (Gaitset, LGaitset, and DGaitset), and feature classification (AlexNet and VGG16), and were highly optimised during analysis of gait sequences of the current dataset. Results: The area under the curve (AUC) of the receiver operating characteristic (ROC) at the physical frailty state identification task for AlexNet was 0.851 (0.827-0.8747) and 0.901 (0.878-0.920) in macro and micro, respectively, and was 0.855 (0.834-0.877) and 0.905 (0.886-0.925) for VGG16 in macro and micro, respectively. Furthermore, this study presents the machine vision method equipped with better predictive performance globally than age and grip strength, as well as than 4-m-walking-time in healthy and pre-frailty classifying. Conclusion: The gait analysis method in this article is unreported and provides promising original tool for frailty and pre-frailty screening with the characteristics of convenience, objectivity, rapidity, and non-contact. These methods can be extended to any gait-related disease identification processes, as well as in-home health monitoring.
| S-EPMC8637841 | biostudies-literature
Project description:BackgroundSepsis is a significant cause of mortality in-hospital, especially in ICU patients. Early prediction of sepsis is essential, as prompt and appropriate treatment can improve survival outcomes. Machine learning methods are flexible prediction algorithms with potential advantages over conventional regression and scoring system. The aims of this study were to develop a machine learning approach using XGboost to predict the 30-days mortality for MIMIC-III Patients with sepsis-3 and to determine whether such model performs better than traditional prediction models.MethodsUsing the MIMIC-III v1.4, we identified patients with sepsis-3. The data was split into two groups based on death or survival within 30 days and variables, selected based on clinical significance and availability by stepwise analysis, were displayed and compared between groups. Three predictive models including conventional logistic regression model, SAPS-II score prediction model and XGBoost algorithm model were constructed by R software. Then, the performances of the three models were tested and compared by AUCs of the receiver operating characteristic curves and decision curve analysis. At last, nomogram and clinical impact curve were used to validate the model.ResultsA total of 4559 sepsis-3 patients are included in the study, in which, 889 patients were death and 3670 survival within 30 days, respectively. According to the results of AUCs (0.819 [95% CI 0.800-0.838], 0.797 [95% CI 0.781-0.813] and 0.857 [95% CI 0.839-0.876]) and decision curve analysis for the three models, the XGboost model performs best. The risk nomogram and clinical impact curve verify that the XGboost model possesses significant predictive value.ConclusionsUsing machine learning technique by XGboost, more significant prediction model can be built. This XGboost model may prove clinically useful and assist clinicians in tailoring precise management and therapy for the patients with sepsis-3.
| S-EPMC7720497 | biostudies-literature