Basic gait pattern and impact of fall risk factors on gait among older adults in India

Kulkarni, Snehal; Nagarkar, Aarti

doi:10.1016/j.gaitpost.2021.04.043

Cited by 6 publications

(4 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The RTLS variables, particularly the daily total distance, represent the total amount of patient movement in a day. Contrastingly, the daily speed represents an average daily measure of the gait speed, a well-known factor associated with falls that is emphasized in conventional methods 13,[20][21][22] . The daily top 50% active movement ratio, which indicates the proportion of time spent on moving at a faster pace, serves as an indirect measure of physical activity, another key factor in determining fall risk 11,23 .…”

Section: Discussionmentioning

confidence: 99%

Integrating Real-Time Location Systems with Electronic Medical Records: A Machine Learning Approach for In-Hospital Fall Risk Prediction

Kim,

Seo,

Kwon

et al. 2024

Preprint

View full text Add to dashboard Cite

Hospital falls are the most prevalent adverse event in healthcare, posing significant risks to patient health outcomes and institutional care quality. The effectiveness of several fall prediction models currently in use is limited by various clinical factors. This study explored the efficacy of merging real-time location system (RTLS) data with clinical information to enhance the accuracy of in-hospital fall predictions. The model performances were compared based on the clinical data, RTLS data, and a hybrid approach using various evaluation metrics. The RTLS and integrated clinical data were obtained from 22,201 patients between March 2020 and June 2022. From the initial cohort, 118 patients with falls and 443 patients without falls were included. Predictive models were developed using the XGBoost algorithm across three distinct frameworks: clinical model, RTLS model, and clinical + RTLS model. The model performance was evaluated using metrics, such as AUROC, AUPRC, accuracy, PPV, sensitivity, specificity, and F1 score. Shapley additive explanation values were used to enhance the model interpretability. The clinical model yielded an AUROC of 0.813 and AUPRC of 0.407. The RTLS model demonstrated superior fall prediction capabilities, with an AUROC of 0.842 and AUPRC of 0.480. The clinical + RTLS model excelled further, achieving an AUROC of 0.853 and AUPRC of 0.497. Feature importance analysis revealed that movement patterns of patients on the last day of their stay were significantly associated with falls, together with elevated RDW levels, sedative administration, age. This study underscored the advantages of combining RTLS data with clinical information to predict in-hospital falls more accurately. This innovative technology-driven approach may enhance early fall risk detection during hospitalization, potentially preventing falls, improving patient safety, and contributing to more efficient healthcare delivery.

show abstract

Section: Discussionmentioning

confidence: 99%

Integrating Real-Time Location Systems with Electronic Medical Records: A Machine Learning Approach for In-Hospital Fall Risk Prediction

Kim,

Seo,

Kwon

et al. 2024

Preprint

View full text Add to dashboard Cite

show abstract

“…Gait characteristics, which are easily assessed using wearable sensors (i.e., IMU sensors), have a significant correlation with physical function, muscle power, and dynamic ability [ 12 , 13 , 14 , 15 ]. Our previous studies have revealed that gait characteristics could predict slip-related fall risk in both heathy older adults and stroke patients [ 16 , 17 ], and many studies have proposed that gait characteristics could also be used as a predictor(s) to forecast the fall risk following a trip perturbation, such as foot clearance [ 18 , 19 ], step length, gait speed, trunk flexion angle, and velocity [ 20 ].…”

Section: Introductionmentioning

confidence: 99%

Trip-Related Fall Risk Prediction Based on Gait Pattern in Healthy Older Adults: A Machine-Learning Approach

Wang

Nguyen

Bhatt

2023

Sensors

View full text Add to dashboard Cite

Trip perturbations are proposed to be a leading cause of falls in older adults. To prevent trip-falls, trip-related fall risk should be assessed and subsequent task-specific interventions improving recovery skills from forward balance loss should be provided to the individuals at risk of trip-fall. Therefore, this study aimed to develop trip-related fall risk prediction models from one’s regular gait pattern using machine-learning approaches. A total of 298 older adults (≥60 years) who experienced a novel obstacle-induced trip perturbation in the laboratory were included in this study. Their trip outcomes were classified into three classes: no-falls (n = 192), falls with lowering strategy (L-fall, n = 84), and falls with elevating strategy (E-fall, n = 22). A total of 40 gait characteristics, which could potentially affect trip outcomes, were calculated in the regular walking trial before the trip trial. The top 50% of features (n = 20) were selected to train the prediction models using a relief-based feature selection algorithm, and an ensemble classification model was selected and trained with different numbers of features (1–20). A ten-times five-fold stratified method was utilized for cross-validation. Our results suggested that the trained models with different feature numbers showed an overall accuracy between 67% and 89% at the default cutoff and between 70% and 94% at the optimal cutoff. The prediction accuracy roughly increased along with the number of features. Among all the models, the one with 17 features could be considered the best model with the highest AUC of 0.96, and the model with 8 features could be considered the optimal model, which had a comparable AUC of 0.93 and fewer features. This study revealed that gait characteristics in regular walking could accurately predict the trip-related fall risk for healthy older adults, and the developed models could be a helpful assessment tool to identify the individuals at risk of trip-falls.

show abstract

“…Ren et al [ 6 ] further studied the kinematics and dynamics of patients with ACLD with meniscus injuries when waking horizontally. However, due to the difficulty in directly measuring the force, most studies of the knee have been limited to kinematics analysis, for example by measuring kinematics to investigate basic gait patterns in adolescents with autism spectrum disorder [ 7 ], children with Achondroplasia [ 8 ], and the older adults [ 9 ]. Only a few studies [ 10 – 12 ] have focused on the changes of dynamics in patients with ACLD during jogging.…”

Section: Introductionmentioning

confidence: 99%

Muscle dynamics analysis by clustered categories during jogging in patients with anterior cruciate ligament deficiency

Li,

Huang,

Zhang

et al. 2023

BMC Musculoskelet Disord

View full text Add to dashboard Cite

Background Patients with anterior cruciate ligament (ACL) deficiency (ACLD) tend to have altered lower extremity dynamics. Little is known about the changes in dynamic function and activation during jogging in patients with ACLD. Methods Twenty patients with an injured ACL before ACL reconstruction (ACLD group) and nine healthy male volunteers (control group) were recruited. Each volunteer repeated the jogging experiment five times. Based on the experimental data measured, a musculoskeletal multibody dynamics model was employed to simulate the tibiofemoral joint dynamics during jogging. Eighteen muscles were used for analysis. The obtained dynamics data were used for clustering and curve difference analysis. Results The 18 muscles studied were divided into 3 categories. All the quadriceps, the soleus, the gastrocnemius, and the popliteus were classified as label 1. All the hamstrings were classified as label 2, and the sartorius muscles were classified as label 3. Among them, the classification of the short head of the biceps femoris was significantly different between the two groups (P < 0.001). The force curves of all 18 muscles and the between-group differences were studied according to clustered categories. Most muscle force in label 1 was approaching zero in the terminal stance phase, which was significantly lower than that in the control group (P < 0.05). The muscle force in label 2 had areas with significant differences in the stance phase. Muscle force in label 3 was significantly lower than that in the control group in the pre-swing phase. Conclusions This study showed that there are various changes of muscle function and activation in patients with ACLD. Through clustering and curve analysis, the joint reactions and changes of different muscle forces in the gait cycle between the ACLD and control groups could be further clarified.

show abstract

Basic gait pattern and impact of fall risk factors on gait among older adults in India

Cited by 6 publications

References 32 publications

Integrating Real-Time Location Systems with Electronic Medical Records: A Machine Learning Approach for In-Hospital Fall Risk Prediction

Integrating Real-Time Location Systems with Electronic Medical Records: A Machine Learning Approach for In-Hospital Fall Risk Prediction

Trip-Related Fall Risk Prediction Based on Gait Pattern in Healthy Older Adults: A Machine-Learning Approach

Muscle dynamics analysis by clustered categories during jogging in patients with anterior cruciate ligament deficiency

Contact Info

Product

Resources

About