The prevalence of diabetes has been increasing in recent years, and previous research has found that machine-learning models are good diabetes prediction tools. The purpose of this study was to compare the efficacy of five different machine-learning models for diabetes prediction using lifestyle data from the National Health and Nutrition Examination Survey (NHANES) database. The 1999–2020 NHANES database yielded data on 17,833 individuals data based on demographic characteristics and lifestyle-related variables. To screen training data for machine models, the Akaike Information Criterion (AIC) forward propagation algorithm was utilized. For predicting diabetes, five machine-learning models (CATBoost, XGBoost, Random Forest (RF), Logistic Regression (LR), and Support Vector Machine (SVM)) were developed. Model performance was evaluated using accuracy, sensitivity, specificity, precision, F1 score, and receiver operating characteristic (ROC) curve. Among the five machine-learning models, the dietary intake levels of energy, carbohydrate, and fat, contributed the most to the prediction of diabetes patients. In terms of model performance, CATBoost ranks higher than RF, LG, XGBoost, and SVM. The best-performing machine-learning model among the five is CATBoost, which achieves an accuracy of 82.1% and an AUC of 0.83. Machine-learning models based on NHANES data can assist medical institutions in identifying diabetes patients.

Arch structure is a crucial interface between the human body and the ground during landing tasks, but the biomechanical effects of arch support stiffness remain insufficiently explored. This study examines the effects of arch supports with different stiffnesses on lower-limb biomechanics during landing. Twelve male participants (six normal arches, six flat feet) performed a single-leg drop landing from a 45 cm height under four arch support conditions: no arch support pad (NAP), soft-stiffness arch support pad (SAP), medium-stiffness arch support pad (MAP), and high-stiffness arch support pad (HAP). Dominant lower-limb joint angles and moments in the sagittal plane and vertical ground reaction force (vGRF)-related parameters—time to peak vGRF, peak vGRF, and max loading rate—were recorded using a motion capture system and force plate. Data were analyzed using one-way repeated measures analysis of variance (ANOVA). Arch pad stiffness significantly affected ankle and knee kinematics. The NAP condition exhibited significantly higher ankle plantarflexion at initial contact (p ≤ 0.01), as well as larger range of motion (ROM) of the knee (p = 0.03) and hip (p < 0.01), compared to the use of a SAP or MAP. The use of a HAP resulted in a significantly lower peak ankle dorsiflexion moment and larger peak knee flexion angle than the other conditions (p ≤ 0.04). The peak knee extension moment was the highest when using a NAP, and was significantly higher than that shown with the use of a MAP or HAP (p ≤ 0.02). No significant differences were observed in hip joint moments or vGRF-related parameters across conditions (p ≥ 0.52). These results indicate that hard-stiffness arch support pads modulate lower-limb mechanics during landing, potentially enhancing shock absorption and reducing knee loading.

This study explores the biomechanical impact of an elliptical leaf spring (ELS) foot on individuals with unilateral below-knee amputation. The ELS-foot, constructed with carbon fiber leaf springs and an ethylene-vinyl acetate rocker bottom sole, aims to balance energy storge and dissipation for effective cushioning and energy management. Six participants were recruited and visited the laboratory twice within a 3-to-5-day interval. The ELS-foot is compared with their own prosthesis through various mobility and balance tests, including the Timed Up and Go test, Four Square Step Test, 10 m walk test, Berg Balance Test, eyes-closed standing test, Tandem Test, jumping and walking test, and a subjective evaluation. Passive-reflective markers are placed on the participants according to the plug-in full body model. An eight-camera motion capture system synced with two force plates mounted under a walkway is used for the gait analysis. The results show that participants move faster during the Four Square Step Test and demonstrate better balance during the eyes-closed standing test and Tandem Test and jump higher with the ELS-foot. The unique ELS-foot design mechanism and rocker bottom sole facilitates better energy transfer and stability, thus enhancing the postural stability. These findings offer valuable insights for future prosthetic technology advancements.

This study aimed to investigate the effects of different saddle height setting methods and fatigue on lower limb kinematics during indoor cycling in recreational cyclists. Twelve recreational male cyclists completed indoor cycling randomly using three saddle height setting methods—trochanteric length method (TLM), LeMond method (LMM) and knee angle method (KAM)—performed a fatigue protocol. Sagittal-plane ankle, knee and hip kinematic data were collected. Extracted ankle, knee and hip angles at top dead center (TDC), bottom dead center (BDC) and range of motion (ROM) for data analysis. A two-way repeated-measures ANOVA was conducted to examine the main effects of saddle height, fatigue and their interaction. This study found that saddle height setting methods significantly influenced ankle and knee kinematics. Compared with KAM and LMM, TLM resulted in greater ankle ( p = 0.01) and knee ( p = 0.01) ROM, as well as reduced knee flexion at TDC ( p = 0.01) and reduced knee extension at BDC ( p = 0.01). Fatigue significantly reduced ankle ( p = 0.02) and hip ( p = 0.01) angles at TDC but did not affect knee kinematics. A significant saddle height × fatigue interaction was observed only for hip range of motion ( p = 0.04), with a post-fatigue increase occurring exclusively under LMM condition. Saddle height setting methods substantially influence lower-limb kinematics during cycling, while fatigue induces joint-specific adaptations. Recreational cyclists should consider that different setting methods produce distinct effective heights that influence joint responses to fatigue.