Diabetes is a significant global health issue impacting millions. Approximately 26 million diabetics experience foot ulcers, with 20% ending up with amputations, resulting in high morbidity, mortality, and costs. Plantar pressure screening shows potential for early detection of Diabetic Foot Ulcers (DFUs). Although foot ulcers often occur due to excessive pressure on the soles during dynamic activities, most studies focus on static pressure measurements. This study’s primary objective is to apply wireless plantar pressure sensor-embedded insoles to classify and detect diabetic feet from healthy ones based on dynamic plantar pressure. The secondary objective is to compare statistical-based and Machine Learning (ML) classification methods. Data from 150 subjects were collected from the insoles during walking, revealing that diabetic feet have higher plantar pressure than healthy feet, which is consistent with prior research. The Adaptive Boosting (AdaBoost) ML model achieved the highest accuracy of 0.85, outperforming the statistical method, which had an accuracy of 0.67. These findings suggest that ML models, combined with pressure sensor-embedded insoles, can effectively classify healthy and diabetic feet using plantar pressure features. Future research will focus on using these insoles with ML to classify various stages of diabetic neuropathy, aiming for early prediction of foot ulcers in home settings.

Diabetes is a significant global health issue impacting millions. Approximately 26 million diabetics experience foot ulcers, with 20% leading to amputations, resulting in high morbidity, mortality, and costs. Plantar pressure screening shows potential for the early detection of Diabetic Foot Ulcers (DFUs). Although foot ulcers often occur due to excessive pressure on the soles during dynamic activities, most studies focus on static pressure measurements. This study’s primary objective is to apply wireless plantar pressure sensor-embedded insoles to classify and detect diabetic feet from healthy ones based on dynamic plantar pressure. The secondary objective is to compare statistical-based and Machine Learning (ML) classification methods. Data from 150 subjects were collected using the insoles during walking, revealing that diabetic feet have higher plantar pressure than healthy feet, consistent with prior research. The Adaptive Boosting (AdaBoost) ML model achieved the highest accuracy of 0.85, outperforming the statistical method, which had an accuracy of 0.67. These findings suggest that ML models, combined with pressure sensor-embedded insoles, can effectively classify healthy and diabetic feet using plantar pressure features. Future research will focus on using these insoles with ML to classify various stages of diabetic neuropathy, aiming for early prediction of foot ulcers in home settings.

Laboratory-based gait analysis using motion capture and force plates remains the gold standard for quantifying ground reaction forces (GRFs) and temporal gait parameters. However, its high cost and limited accessibility restrict routine clinical use. Wearable smart insoles offer a portable alternative, yet require rigorous validation before clinical adoption. This study evaluates the clinical and technical validity of the SuraSole® smart insole, a low-cost pressure sensor–embedded insole, by comparing its GRF and temporal gait measurements with those obtained from a laboratory force plate and 3D motion capture system. Twenty healthy adults completed five walking trials while wearing standardized footwear equipped with SuraSole insoles, with simultaneous force plate and motion capture data collection. Agreement between systems was assessed using Bland–Altman plots and intraclass correlation coefficients (ICCs). SuraSole demonstrated excellent agreement with force plates for GRF across weight acceptance, mid-stance, and push-off (ICCs 0.97–0.99), with mean differences of 15.93 ± 45.90 N, 2.38 ± 23.98 N, and 8.64 ± 40.45 N, respectively. Temporal parameters showed moderate to good reliability (ICCs 0.62–0.81), with limitations likely related to the insole's 20 Hz sampling rate. These findings indicate that SuraSole provides reliable GRF measurement and acceptable portable gait assessment, supporting its potential for use in clinical practice, rehabilitation, and community health monitoring. Future hardware improvements, particularly higher sampling frequency, may enhance temporal accuracy.