The role of machine learning in the primary prevention of work-related musculoskeletal disorders: A scoping review

Applied Ergonomics, Journal Year: 2021, Volume and Issue: 98, P. 103574 - 103574

Published: Sept. 20, 2021

To determine the applications of machine learning (ML) techniques used for primary prevention work-related musculoskeletal disorders (WMSDs), a scoping review was conducted using seven literature databases. Of 4,639 initial results, 130 research studies were deemed relevant inclusion. Studies reviewed and classified as contribution to one six steps within WMSD framework by van der Beek et al. (2017). ML provided greatest contributions development interventions (48 studies), followed risk factor identification (33 underlying mechanisms (29 incidence WMSDs (14 evaluation (6 implementation effective (0 studies). Nearly quarter (23.8%) all included published in 2020. These findings provide insight into breadth can help identify areas future development.

Language: Английский

---

Wearable Sensors and Artificial Intelligence for Physical Ergonomics: A Systematic Review of Literature

Diagnostics, Journal Year: 2022, Volume and Issue: 12(12), P. 3048 - 3048

Published: Dec. 5, 2022

Physical ergonomics has established itself as a valid strategy for monitoring potential disorders related, example, to working activities. Recently, in the field of physical ergonomics, several studies have also shown improvement experimental methods ergonomic analysis, through combined use artificial intelligence, and wearable sensors. In this regard, review intends provide first account investigations carried out using these methods, considering period up 2021. The method that combines information obtained on worker sensors (IMU, accelerometer, gyroscope, etc.) or biopotential (EMG, EEG, EKG/ECG), with analysis intelligence systems (machine learning deep learning), offers interesting perspectives from both diagnostic, prognostic, preventive points view. particular, signals, recognition categorization postural biomechanical load worker, can be processed formulate algorithms applications (especially respect musculoskeletal disorders), high statistical power. For Ergonomics, but Occupational Medicine, improve knowledge limits human organism, helping definition sustainability thresholds, design environments, tools, work organization. growth prospects research area are refinement procedures detection processing signals; expansion study assisted (assistive robots, exoskeletons), categories workers suffering pathologies disabilities; well development risk assessment exceed those currently used precision agility.

Language: Английский

---

Application of wearable technology for the ergonomic risk assessment of healthcare professionals: A systematic literature review

International Journal of Industrial Ergonomics, Journal Year: 2024, Volume and Issue: 100, P. 103570 - 103570

Published: March 1, 2024

Healthcare professionals are exposed to multiple physical risk factors related the development of work-related musculoskeletal disorders (WRMSD), which significantly affect their quality life. Several ergonomic methods have been developed for identifying in workplace. Among these, wearable devices that perform direct measurements demonstrated outstanding potential recent years provide reliable, non-invasive, and continuous exposure assessment. Therefore, this systematic review aims describe use technology assessment healthcare professionals. Twenty-nine publications were selected following PRISMA guidelines based on inclusion exclusion criteria set. Most articles published last three years, confirming a growing trend research topic. devices, used isolated or combined, consist inertial sensors measure assess awkward postures sEMG sensors, measurement muscle activity parameters force applied while performing work activities. The main results respective analyses provided insights into strengths limitations using acquire data several activities performed by Future is needed widen validate applicability support interventions aimed at preventing WRMSD among

Language: Английский

---

Exposures to select risk factors can be estimated from a continuous stream of inertial sensor measurements during a variety of lifting-lowering tasks

Ergonomics, Journal Year: 2024, Volume and Issue: 67(11), P. 1596 - 1611

Published: April 22, 2024

Wearable inertial measurement units (IMUs) are used increasingly to estimate biomechanical exposures in lifting-lowering tasks. The objective of the study was develop and evaluate predictive models for estimating relative hand loads two other critical gain a comprehensive understanding work-related musculoskeletal disorders lifting. We collected 12,480 phases from 26 subjects (15 men 11 women) performing manual tasks with (0-22.7 kg) at varied workstation heights handling modes. implemented

Language: Английский

---

Manufacturing Operator Ergonomics: A Conceptual Digital Twin Approach to Detect Biomechanical Fatigue

IEEE Access, Journal Year: 2022, Volume and Issue: 10, P. 12774 - 12791

Published: Jan. 1, 2022

The primary sources of injuries in the workplace are improper manual material handling (MMH) motions, forklift collisions, slip, and fall. This research presents a Digital Twin (DT) framework to analyze fatigue humans while performing lifting MMH activity laboratory environment for purpose reducing these types injuries. proposed methodology analyzes worker's body joints detect biomechanical as factor change back, elbow, knee joint angles. Using dynamic time warping (DTW) algorithm, angles with was analyzed. variation DTW parameters evaluated using exponentially weighted moving average (EWMA) control charts further analysis. A preliminary study considering two healthy male subjects seven experiments, each under an optical motion capture system performed test model's efficiency. Our contributions twofold. First, we propose model Secondly, also shows evidence that different individuals show signs via showcases need true personalized DT operator assessment environment.

Language: Английский

---

Using Features Extracted From Upper Limb Reaching Tasks to Detect Parkinson’s Disease by Means of Machine Learning Models

IEEE Transactions on Neural Systems and Rehabilitation Engineering, Journal Year: 2023, Volume and Issue: 31, P. 1056 - 1063

Published: Jan. 1, 2023

While in the literature there is much interest investigating lower limbs gait of patients affected by neurological diseases, such as Parkinson's Disease (PD), fewer publications involving upper movements are available. In previous studies, 24 motion signals (the so-called reaching tasks) PD and Healthy Controls (HCs) were used to extract several kinematic features through a custom-made software; conversely, aim our paper investigate possibility build models - using these for distinguishing from HCs. First, binary logistic regression and, then, Machine Learning (ML) analysis was performed implementing five algorithms Knime Analytics Platform. The ML twice: first, leave-one out-cross validation applied; wrapper feature selection method implemented identify best subset that could maximize accuracy. achieved an accuracy 90.5%, demonstrating importance maximum jerk during subjects limb motion; Hosmer-Lemeshow test supported validity this model (p-value=0.408). first high evaluation metrics overcoming 95% accuracy; second perfect classification with 100% both area under curve receiver operating characteristics. top-five terms acceleration, smoothness, duration, kurtosis. investigation carried out work has proved predictive power features, extracted tasks limbs, distinguish HCs patients.

Language: Английский

---

Positive impact of short-term gait rehabilitation in Parkinson patients: a combined approach based on statistics and machine learning

Mathematical Biosciences & Engineering, Journal Year: 2021, Volume and Issue: 18(5), P. 6995 - 7009

Published: Jan. 1, 2021

<abstract> <p>Parkinson's disease is the second most common neurodegenerative disorder in world. Assumed that gait dysfunctions represent a major motor symptom for pathology, analysis can provide clinicians quantitative information about rehabilitation outcome of patients. In this scenario, wearable inertial systems be valid tool to assess functional recovery patients an automatic and way, helping decision making. Aim study evaluate impact short-term on balance with Parkinson's disease. A cohort 12 Idiopathic performed session instrumented by system analysis: Opal System, APDM Inc., spatial temporal parameters being analyzed through statistic machine learning approach. Six out fourteen motion exhibited statistically significant difference between measurements at admission discharge patients, while confirmed separability two phases terms Accuracy Area under Receiving Operating Characteristic Curve. The treatment especially improved related gait. shows positive feasibility devices, are increasingly spreading clinical practice, quantitatively improvement.</p> </abstract>

Language: Английский

---

A Combined Radiomics and Machine Learning Approach to Distinguish Clinically Significant Prostate Lesions on a Publicly Available MRI Dataset

Journal of Imaging, Journal Year: 2021, Volume and Issue: 7(10), P. 215 - 215

Published: Oct. 18, 2021

Although prostate cancer is one of the most common causes mortality and morbidity in advancing-age males, early diagnosis improves prognosis modifies therapy choice. The aim this study was evaluation a combined radiomics machine learning approach on publicly available dataset order to distinguish clinically significant from non-significant lesion. A total 299 lesions were included analysis. univariate statistical analysis performed prove goodness 60 extracted radiomic features distinguishing lesions. Then, 10-fold cross-validation used train test some models metrics calculated; finally, hold-out wrapper feature selection applied. employed algorithms Naïve bayes, K nearest neighbour tree-based ones. achieved highest metrics, with accuracies over 80%, area-under-the-curve receiver-operating characteristics below 0.80. Combined based clinical, routine, multiparametric, magnetic-resonance imaging demonstrated be useful tool stratification.

Language: Английский

---

Capability of Machine Learning Algorithms to Classify Safe and Unsafe Postures during Weight Lifting Tasks Using Inertial Sensors

Diagnostics, Journal Year: 2024, Volume and Issue: 14(6), P. 576 - 576

Published: March 8, 2024

Occupational ergonomics aims to optimize the work environment and enhance both productivity worker well-being. Work-related exposure assessment, such as lifting loads, is a crucial aspect of this discipline, it involves evaluation physical stressors their impact on workers’ health safety, in order prevent development musculoskeletal pathologies. In study, we explore feasibility machine learning (ML) algorithms, fed with time- frequency-domain features extracted from inertial signals (linear acceleration angular velocity), automatically accurately discriminate safe unsafe postures during weight tasks. The were acquired by means one measurement unit (IMU) placed sternums 15 subjects, subsequently segmented extract several features. A supervised dataset, including features, was used feed ML models assess prediction power. Interesting results terms metrics for binary safe/unsafe posture classification obtained logistic regression algorithm, which outperformed others, accuracy area under receiver operating characteristic curve values up 96% 99%, respectively. This result indicates proposed methodology—based single sensor artificial intelligence—to associated load activities. Future investigation wider study population using additional scenarios could confirm potentiality methodology, supporting its applicability occupational field.

Language: Английский

---

Combining Postural Sway Parameters and Machine Learning to Assess Biomechanical Risk Associated with Load-Lifting Activities

Diagnostics, Journal Year: 2025, Volume and Issue: 15(1), P. 105 - 105

Published: Jan. 4, 2025

Background/Objectives: Long-term work-related musculoskeletal disorders are predominantly influenced by factors such as the duration, intensity, and repetitive nature of load lifting. Although traditional ergonomic assessment tools can be effective, they often challenging complex to apply due absence a streamlined, standardized framework. Recently, integrating wearable sensors with artificial intelligence has emerged promising approach effectively monitor mitigate biomechanical risks. This study aimed evaluate potential machine learning models, trained on postural sway metrics derived from an inertial measurement unit (IMU) placed at lumbar region, classify risk levels associated lifting based Revised NIOSH Lifting Equation. Methods: To compute parameters, IMU captured acceleration data in both anteroposterior mediolateral directions, aligning closely body’s center mass. Eight participants undertook two scenarios, each involving twenty consecutive tasks. classifiers were tested utilizing validation strategies, Gradient Boost Tree algorithm achieving highest accuracy Area under ROC Curve 91.2% 94.5%, respectively. Additionally, feature importance analysis was conducted identify most influential parameters directions. Results: The results indicate that combination model offers feasible for predicting risks Conclusions: Further studies broader participant pool varied conditions could enhance applicability this method occupational ergonomics.

Language: Английский

---