Predicting Fall Probability Based on a Validated Balance Scale

Masalha, Alaa; Eichler, Nadav; Raz, Shmuel; Toledano-Shubi, Adi; Niv, Daphna; Shimshoni, Ilan; Hel‐Or, Hagit

doi:10.1109/cvprw50498.2020.00159

Cited by 8 publications

(7 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Results indicated that SVM and KNN outperformed CNN and LSTM, delivering superior performance on the collected data. [28] utilized a 3D vision sensor to capture 3D skeletons, from which features were extracted to train Random Forest and Support Vector Machine models for estimating the Berg Balance Scale (BBS) and assessing fall risk. A pilot test demonstrated high rates of fall risk prediction and a notable correlation with physiotherapists' BBS scores on individual motion tasks.…”

Section: B Fall Predictionmentioning

confidence: 99%

Computer Vision Based Transfer Learning-Aided Transformer Model for Fall Detection and Prediction

McCall,

Kolawole,

Naz

et al. 2024

IEEE Access

View full text Add to dashboard Cite

Falls bring about significant risks to individuals' well-being and independence, prompting widespread public health concerns. Swift detection and even predicting the risk of falls are crucial for implementing effective measures to alleviate the adverse consequences associated with such incidents. This study presents a new framework for identifying and forecasting fall risks. Our approach utilizes a novel transformer model trained on 2D poses extracted through an off-the-shelf pose extractor, incorporating transfer learning techniques. Initially, the transformer is trained on a large dataset containing 2D poses of general actions. Subsequently, we freeze the majority of its layers and fine-tune only the last few layers using relatively smaller datasets for fall detection and prediction tasks. Experimental results indicate that our proposed method outperforms traditional machine learning (e.g., SVM, Decision Tree, etc.) and deep learning approaches (e.g., LSTM, CNN, ST-GCN, PoseC3D, etc.) in both fall detection and prediction tasks across various datasets.

show abstract

Section: B Fall Predictionmentioning

confidence: 99%

Computer Vision Based Transfer Learning-Aided Transformer Model for Fall Detection and Prediction

McCall,

Kolawole,

Naz

et al. 2024

IEEE Access

View full text Add to dashboard Cite

show abstract

“…The first two components compute the 14 BBS scores by tracking the subject's motion and using machine learning to predict the scores. This work, which was presented in [9], is reviewed in Sections 3 and 4. Section 4 also reviews the machine learning model used to predict the level of risk from the 14 previously predicted BBS scores either as a final score (from 0-56) or as one of three levels of risk (high, medium, or low risk of fall).…”

Section: Automated Fall Risk Assessment Systemmentioning

confidence: 99%

“…The predicted scores were shown to correlate well with the scores assessed by the physiotherapists. More details can be found in [9].…”

Section: Predicting Bbs Scores Using Machine Learningmentioning

confidence: 99%

“…Feature selection was also guided by recommendations from the physiotherapists as to the most predictive parts of the body and its features. Feature selection resulted in different features per each BBS task, ranging from 100-200 features (for examples, see [9,71]).…”

Section: Feature Extractionmentioning

confidence: 99%

“…In the following sections, we review the automated system and introduce the E-BBS. We present a description of the full system including a review of the previously presented study in [9] with additional statistical analysis. We show the results of a pilot study, run on 130 patients in a major hospital, including the accuracy and statistical evaluations.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Automatic and Efficient Fall Risk Assessment Based on Machine Learning

Eichler

Raz

Toledano-Shubi³

et al. 2022

Sensors

Self Cite

View full text Add to dashboard Cite

Automating fall risk assessment, in an efficient, non-invasive manner, specifically in the elderly population, serves as an efficient means for implementing wide screening of individuals for fall risk and determining their need for participation in fall prevention programs. We present an automated and efficient system for fall risk assessment based on a multi-depth camera human motion tracking system, which captures patients performing the well-known and validated Berg Balance Scale (BBS). Trained machine learning classifiers predict the patient’s 14 scores of the BBS by extracting spatio-temporal features from the captured human motion records. Additionally, we used machine learning tools to develop fall risk predictors that enable reducing the number of BBS tasks required to assess fall risk, from 14 to 4–6 tasks, without compromising the quality and accuracy of the BBS assessment. The reduced battery, termed Efficient-BBS (E-BBS), can be performed by physiotherapists in a traditional setting or deployed using our automated system, allowing an efficient and effective BBS evaluation. We report on a pilot study, run in a major hospital, including accuracy and statistical evaluations. We show the accuracy and confidence levels of the E-BBS, as well as the average number of BBS tasks required to reach the accuracy thresholds. The trained E-BBS system was shown to reduce the number of tasks in the BBS test by approximately 50% while maintaining 97% accuracy. The presented approach enables a wide screening of individuals for fall risk in a manner that does not require significant time or resources from the medical community. Furthermore, the technology and machine learning algorithms can be implemented on other batteries of medical tests and evaluations.

show abstract