Random forest algorithms to classify frailty and falling history in seniors using plantar pressure measurement insoles: a large-scale feasibility study

Fall Risk Prediction Using Instrumented Footwear in Institutionalized Older Adults

This study presents a novel framework that utilizes instrumented footwear to predict fall risk in institutionalized older adults by leveraging stride-to-stride gait data. The older adults are categorized into fallers and non-fallers using three distinct criteria: retrospective fall history, prospective fall occurrence, and a combination of both retrospective and prospective data. Three types of data collected from N=95 institutionalized older adults are analyzed: traditional timed mobility tests, gait data collected from a validated electronic walkway, and gait data collected with instrumented footwear developed by our team. The importance of each type of data is assessed using a brute-force search method, through which the optimal features are selected. AdaBoost algorithms are then utilized to develop predictive models based on the selected features. The models are evaluated using leave-one-out cross-validation and 10-fold cross-validation. The results show that models using gait data from the instrumented footwear outperformed those based on traditional tests and walkway data, with area under the receiver operating characteristic curve (AUC) values for predicting prospective falls being 0.47, 0.66, and 0.80, respectively. The sensitivity of the models increases when they are trained using both past and future falls data, rather than relying solely on past or future falls data. This study demonstrates the potential of instrumented footwear for fall risk assessment in elderly individuals. The findings provide valuable insights for fall prevention and care, highlighting the superior predictive capabilities of the developed system compared to traditional methods.

Physical Frailty Prediction Using Cane Usage Characteristics during Walking

This study aimed to determine the characteristics of accelerations and angular velocities obtained by an inertial measurement unit (IMU) attached to a cane between older people with and without physical frailty. Community-dwelling older people walked at a comfortable speed using a cane with a built-in IMU. Physical frailty was assessed using exercise-related items extracted from the Kihon Check List. The efficacy of five machine learning models in distinguishing older people with physical frailty was investigated. This study included 48 older people, of which 24 were frail and 24 were not. Compared with the non-frail participants, the older people with physical frailty had a small root mean square value in the vertical and anteroposterior directions and angular velocity in the anteroposterior direction (p < 0.001, r = 0.36; p < 0.001, r = 0.29; p < 0.001, r = 0.30, respectively) and a large mean power frequency value in the vertical direction (p = 0.042, r = 0.18). The decision tree model could most effectively classify physical frailty, with an accuracy, F1 score, and area under the curve of 78.6%, 91.8%, and 0.81, respectively. The characteristics of IMU-attached cane usage by older adults with physical frailty can be utilized to effectively evaluate and determine physical frailty in their usual environments.

Using Flexible-Printed Piezoelectric Sensor Arrays to Measure Plantar Pressure during Walking for Sarcopenia Screening

Sarcopenia is an age-related syndrome characterized by the loss of skeletal muscle mass and function. Community screening, commonly used in early diagnosis, usually lacks features such as real-time monitoring, low cost, and convenience. This study introduces a promising approach to sarcopenia screening by dynamic plantar pressure monitoring. We propose a wearable flexible-printed piezoelectric sensing array incorporating barium titanate thin films. Utilizing a flexible printer, we fabricate the array with enhanced compressive strength and measurement range. Signal conversion circuits convert charge signals of the sensors into voltage signals, which are transmitted to a mobile phone via Bluetooth after processing. Through cyclic loading, we obtain the average voltage sensitivity (4.844 mV/kPa) of the sensing array. During a 6 m walk, the dynamic plantar pressure features of 51 recruited participants are extracted, including peak pressures for both sarcopenic and control participants before and after weight calibration. Statistical analysis discerns feature significance between groups, and five machine learning models are employed to screen for sarcopenia with the collected features. The results show that the features of dynamic plantar pressure have great potential in early screening of sarcopenia, and the Support Vector Machine model after feature selection achieves a high accuracy of 93.65%. By combining wearable sensors with machine learning techniques, this study aims to provide more convenient and effective sarcopenia screening methods for the elderly.

In-Shoe Sensor Measures of Loading Asymmetry during Gait as a Predictor of Frailty Development in Community-Dwelling Older Adults

Clinical walk tests may not predict the development of frailty in healthy older adults. With advancements in wearable technology, it may be possible to predict the development of frailty using loading asymmetry parameters during clinical walk tests. This prospective cohort study aimed to test the hypothesis that increased limb loading asymmetry predicts frailty risk in community-living older adults. Sixty-three independently ambulant community-living adults aged ≥ 65 years were recruited, and forty-seven subjects completed the ten-month follow-up after baseline. Loading asymmetry index of net and regional (forefoot, midfoot, and rearfoot) plantar forces were collected using force sensing insoles during a 10 m walk test with their maximum speed. Development of frailty was defined if the participant progressed from baseline at least one grading group of frailty at the follow-up period using the Kihon Checklist. Fourteen subjects developed frailty during the follow-up period. Increased risk of frailty was associated with each 1% increase in loading asymmetry of net impulse (Odds ratio 1.153, 95%CI 1.001 to 1.329). Net impulse asymmetry significantly correlated with asymmetry of peak force in midfoot force. These results indicate the feasibility of measuring plantar forces of gait during clinical walking tests and underscore the potential of using load asymmetry as a tool to augment frailty risk assessment in community-dwelling older adults.

Advancements in diabetic foot insoles: a comprehensive review of design, manufacturing, and performance evaluation

The escalating prevalence of diabetes has accentuated the significance of addressing the associated diabetic foot problem as a major public health concern. Effectively offloading plantar pressure stands out as a crucial factor in preventing diabetic foot complications. This review comprehensively examines the design, manufacturing, and evaluation strategies employed in the development of diabetic foot insoles. Furthermore, it offers innovative insights and guidance for enhancing their performance and facilitating clinical applications. Insoles designed with total contact customization, utilizing softer and highly absorbent materials, as well as incorporating elliptical porous structures or triply periodic minimal surface structures, prove to be more adept at preventing diabetic foot complications. Fused Deposition Modeling is commonly employed for manufacturing; however, due to limitations in printing complex structures, Selective Laser Sintering is recommended for intricate insole designs. Preceding clinical implementation, in silico and in vitro testing methodologies play a crucial role in thoroughly evaluating the pressure-offloading efficacy of these insoles. Future research directions include advancing inverse design through machine learning, exploring topology optimization for lightweight solutions, integrating flexible sensor configurations, and innovating new skin-like materials tailored for diabetic foot insoles. These endeavors aim to further propel the development and effectiveness of diabetic foot management strategies. Future research avenues should explore inverse design methodologies based on machine learning, topology optimization for lightweight structures, the integration of flexible sensors, and the development of novel skin-like materials specifically tailored for diabetic foot insoles. Advancements in these areas hold promise for further enhancing the effectiveness and applicability of diabetic foot prevention measures.

Cross-subject EEG-based emotion recognition through dynamic optimization of random forest with sparrow search algorithm

The objective of EEG-based emotion recognition is to classify emotions by decoding signals, with potential applications in the fields of artificial intelligence and bioinformatics. Cross-subject emotion recognition is more difficult than intra-subject emotion recognition. The poor adaptability of classification model parameters is a significant factor of low accuracy in cross-subject emotion recognition. We propose a model of a dynamically optimized Random Forest based on the Sparrow Search Algorithm (SSA-RF). The decision trees number (DTN) and the leave minimum number (LMN) of the RF are dynamically optimized by the SSA. 12 features are used to construct feature combinations for selecting the optimal feature combination. DEAP and SEED datasets are employed for testing the performance of SSA-RF. The experimental results show that the accuracy of binary classification is 76.81% on DEAP, and the accuracy of triple classification is 75.96% on SEED based on SSA-RF, which are both higher than that of traditional RF. This study provides new insights for the development of cross-subject emotion recognition, and has significant theoretical value.

Machine Learning Applications in Sarcopenia Detection and Management: A Comprehensive Survey

This extensive review examines sarcopenia, a condition characterized by a loss of muscle mass, stamina, and physical performance, with a particular emphasis on its detection and management using contemporary technologies. It highlights the lack of global agreement or standardization regarding the definition of sarcopenia and the various techniques used to measure muscle mass, stamina, and physical performance. The distinctive criteria employed by the European Working Group on Sarcopenia in Older People (EWGSOP) and the Asian Working Group for Sarcopenia (AWGSOP) for diagnosing sarcopenia are examined, emphasizing potential obstacles in comparing research results across studies. The paper delves into the use of machine learning techniques in sarcopenia detection and diagnosis, noting challenges such as data accessibility, data imbalance, and feature selection. It suggests that wearable devices, like activity trackers and smartwatches, could offer valuable insights into sarcopenia progression and aid individuals in monitoring and managing their condition. Additionally, the paper investigates the potential of blockchain technology and edge computing in healthcare data storage, discussing models and systems that leverage these technologies to secure patient data privacy and enhance personal health information management. However, it acknowledges the limitations of these models and systems, including inefficiencies in handling large volumes of medical data and the lack of dynamic selection capability. In conclusion, the paper provides a comprehensive summary of current sarcopenia research, emphasizing the potential of modern technologies in enhancing the detection and management of the condition while also highlighting the need for further research to address challenges in standardization, data management, and effective technology use.

Physical ability, cervical function, and walking plantar pressure in frail and pre-frail older adults: An attentional focus approach

Aging and increased vulnerability define the clinical condition of frailty. However, while the cervical function is recognized as a determinant of balance and walking performance, no study simultaneously physical ability, cervical function, balance, and plantar pressure distribution in walking in nursing house population. Thus, the present study aimed to compare these parameters between Frail and Pre-Frail aged people. Thirty-one (12 men and 19 women) institutionalized participants (age: 89.45 ± 5.27 years, weight: 61.54 ± 9.99 kg, height: 160.34 ± 7.93 cm) were recruited and divided into Pre-Frail and Frail groups according to SPPB (Short Physical Performance Battery) score (Frail <6, Pre-Frail ≥6). Participants performed the Timed Up and Go Test (TUGT) and a static balance evaluation. The cervical range of motion (COM), knee extensor strength, and walking plantar pressure distribution have been measured. The Pre-Frail group showed a higher gait speed (ES = 0.78, p ≤ 0.001) and a better TUGT, as well as higher knee extensor strength (ES = 0.4, p = 0.04). Furthermore, the Pre-Frail group presented a center of pressure (COP) displacement velocity on the sagittal axis (ES = 0.43, p = 0.02) and a more COP projection on this axis (ES = 0.43, p = 0.02). No significant difference has been observed between the two groups concerning the total contact time and most of the plantar pressure parameters except for the rear foot relative contact time which was lower in the Pre-Frail group. The Pre-Frail group also showed better cervical tilt mobility (ES = 0.35, p = 0.04). This study highlights the influence of some new parameters on frailty in older people, such as cervical mobility and plantar pressure distribution in walking.