Machine learning approach to diabetic foot risk classification with biomechanics data

Guiotto, A.; Bortolami, G.; Ciniglio, A.; Spolaor, F.; Guarneri, G.; Avogaro, A.; Cibin, F.; Silvestri, F.; Sawacha, Z.

doi:10.1016/j.gaitpost.2022.09.052

Cited by 5 publications

(4 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In human studies, novel IMU-based methodologies and procedures are continuously emerging to assess movement analysis and biomechanical properties of the foot [ 96 ]. In human musculoskeletal research, a combination of IMUs, OMC, machine learning gait prediction, and finite element analysis has been used for injury monitoring, treatment, and rehabilitation [ 97 , 98 ]. These techniques can also be extrapolated to animal studies, with research in this direction having recently been conducted [ 99 ].…”

Section: Discussion and Overall Conclusionmentioning

confidence: 99%

Inertial Sensor Technologies—Their Role in Equine Gait Analysis, a Review

Crecan

Peștean

2023

Sensors

View full text Add to dashboard Cite

Objective gait analysis provides valuable information about the locomotion characteristics of sound and lame horses. Due to their high accuracy and sensitivity, inertial measurement units (IMUs) have gained popularity over objective measurement techniques such as force plates and optical motion capture (OMC) systems. IMUs are wearable sensors that measure acceleration forces and angular velocities, providing the possibility of a non-invasive and continuous monitoring of horse gait during walk, trot, or canter during field conditions. The present narrative review aimed to describe the inertial sensor technologies and summarize their role in equine gait analysis. The literature was searched using general terms related to inertial sensors and their applicability, gait analysis methods, and lameness evaluation. The efficacy and performance of IMU-based methods for the assessment of normal gait, detection of lameness, analysis of horse–rider interaction, as well as the influence of sedative drugs, are discussed and compared with force plate and OMC techniques. The collected evidence indicated that IMU-based sensor systems can monitor and quantify horse locomotion with high accuracy and precision, having comparable or superior performance to objective measurement techniques. IMUs are reliable tools for the evaluation of horse–rider interactions. The observed efficacy and performance of IMU systems in equine gait analysis warrant further research in this population, with special focus on the potential implementation of novel techniques described and validated in humans.

show abstract

Section: Discussion and Overall Conclusionmentioning

confidence: 99%

Inertial Sensor Technologies—Their Role in Equine Gait Analysis, a Review

Crecan

Peștean

2023

Sensors

View full text Add to dashboard Cite

show abstract

“…The results may indicate that a subset of the tested features can be more successful in classification than using all available features. A recent study that used biomechanical data to train and test machine learning algorithms for DN diagnosis also found that using a subset of features, rather than the entire dataset, yielded greater accuracies [ 32 ]. Thus, the identification and inclusion of significant features, rather than all available features, could produce more effective and less computationally costly algorithms.…”

Section: Discussionmentioning

confidence: 99%

Prediction of Diabetes Mellitus Progression Using Supervised Machine Learning

Chauhan

Varre

Izuora

et al. 2023

Sensors

View full text Add to dashboard Cite

Diabetic peripheral neuropathy (DN) is a serious complication of diabetes mellitus (DM) that can lead to foot ulceration and eventual amputation if not treated properly. Therefore, detecting DN early is important. This study presents an approach for diagnosing various stages of the progression of DM in lower extremities using machine learning to classify individuals with prediabetes (PD; n = 19), diabetes without (D; n = 62), and diabetes with peripheral neuropathy (DN; n = 29) based on dynamic pressure distribution collected using pressure-measuring insoles. Dynamic plantar pressure measurements were recorded bilaterally (60 Hz) for several steps during the support phase of walking while participants walked at self-selected speeds over a straight path. Pressure data were grouped and divided into three plantar regions: rearfoot, midfoot, and forefoot. For each region, peak plantar pressure, peak pressure gradient, and pressure–time integral were calculated. A variety of supervised machine learning algorithms were used to assess the performance of models trained using different combinations of pressure and non-pressure features to predict diagnoses. The effects of choosing various subsets of these features on the model’s accuracy were also considered. The best performing models produced accuracies between 94–100%, showing the proposed approach can be used to augment current diagnostic methods.

show abstract

“…Such research could help identify strategies to mitigate these factors and improve patients’ well-being while they await effective treatments, as well as aiding in the selection of treatment plans [ 44 ]. In the field of orthopedics, recent studies have been conducted involving computational simulations of loads on the lower limbs for various purposes, such as defining the risk of ulceration in the diabetic foot based on foot loads during gait [ 45 ], optimising footwear to reduce plantar and metatarsal stress when running [ 46 ], and analysing mechanical stresses associated with the treatment of knee osteoarthritis patients using proximal fibular osteotomy [ 47 ], all of which show promising results.…”

Section: Discussionmentioning

confidence: 99%

Low Correlation between Gait and Quality of Life in Advanced Knee Osteoarthritis

Freijo

Navarro

Molina

et al. 2023

JFMK

View full text Add to dashboard Cite

Advanced knee osteoarthritis patients’ gait usually undergoes alterations leading to decreased mobility and lower functional performance, which can result in a worsening of their quality of life (QoL). While several authors have reported a moderate correlation between gait parameters and QoL assessed by generic questionnaires, the literature is scarce. This study aimed to explore the relationship between gait and QoL parameters assessed by a generic and a disease-specific questionnaire in patients with advanced knee osteoarthritis. In this single-centre, prospective, observational study, 129 patients with advanced knee osteoarthritis scheduled for elective total knee replacement were selected. The patients’ gait was evaluated by means of a validated wireless device while they walked 30 m at a comfortable speed. Patient function was also analysed using the Knee Society Score (KSS). QoL was measured with the EQ-5D and the Knee Injury and Osteoarthritis Outcome Score (KOOS) questionnaires. Patients showed a mean walking speed of 0.95 ± 0.19 m/s, a mean cadence of 105.6 ± 9.9 steps/min, and a mean stride length of 1.25 ± 0.17 m on both legs. They presented poor knee status (KSS < 60) and poor QoL, with an EQ-5D of 0.44 ± 0.24 and a total KOOS of 29.77 ± 13.99. Positive low correlations (r <0.5, p <0.5) were found only between the speed, propulsion and stride length of both legs, and the overall and ADLs subscale scores of the total KOOS questionnaire. In conclusion, several gait parameters have a significant low correlation with the QoL of patients with advanced knee osteoarthritis, as assessed by an osteoarthritis-specific questionnaire.

show abstract

Machine learning approach to diabetic foot risk classification with biomechanics data

Cited by 5 publications

References 0 publications

Inertial Sensor Technologies—Their Role in Equine Gait Analysis, a Review

Inertial Sensor Technologies—Their Role in Equine Gait Analysis, a Review

Prediction of Diabetes Mellitus Progression Using Supervised Machine Learning

Low Correlation between Gait and Quality of Life in Advanced Knee Osteoarthritis

Contact Info

Product

Resources

About