Background Force myography (FMG) is a non-invasive technology used to track functional movements and hand gestures by sensing volumetric changes in the limbs caused by muscle contraction. Force transmission through tissue implies that differences in tissue mechanics and/or architecture might impact FMG signal acquisition and the accuracy of gesture classifier models. The aim of this study is to identify if and how user anthropometry affects the quality of FMG signal acquisition and the performance of machine learning models trained to classify different hand and wrist gestures based on that data. Methods Wrist and forearm anthropometric measures were collected from a total of 21 volunteers aged between 22 and 82 years old. Participants performed a set of tasks while wearing a custom-designed FMG band. Primary outcome measure was the Spearman’s correlation coefficient (R) between the anthropometric measures and FMG signal quality/ML model performance. Results Results demonstrated moderate (0.3 ≤|R| < 0.67) and strong (0.67 ≤ |R|) relationships for ratio of skinfold thickness to forearm circumference, grip strength and ratio of wrist to forearm circumference. These anthropometric features contributed to 23–30% of the variability in FMG signal acquisition and as much as 50% of the variability in classification accuracy for single gestures. Conclusions Increased grip strength, larger forearm girth, and smaller skinfold-to-forearm circumference ratio improve signal quality and gesture classification accuracy.

No abstract

Knee osteotomies show efficacy in slowing knee osteoarthritis progression and delaying the need for total knee arthroplasty in younger patients. Despite evolutions in indications, techniques, and hardware that have improved outcomes, longitudinal trends demonstrate a decline in high tibial osteotomy (HTO) and distal femoral osteotomy (DFO) use. Unfortunately, knowledge of the current usage and complications associated with HTO and DFO is limited. The purpose of this study was to compare the preoperative demographics and early complication rates of HTO and DFO. We analyzed the HTOs and DFOs performed between 2006 and 2017 using the ACS-NSQIP (American College of Surgeons National Surgical Quality Improvement Program) database. We compared both groups for preoperative patient demographics (sex, age, race, body mass index [BMI]) and health status variables including functional scores, ASA (American Society of Anesthesiologists) scores, smoking status, and other comorbidities. Emergency and elective status of the patient case, length of hospital stay, operation time, and 30-day postoperative complications were also analyzed. After the exclusion criteria were applied, 321 HTO and 295 DFO patients were included in the final analysis. The HTO group had higher proportions of younger (p < 0.001) and male (p < 0.001) patients with higher BMI (p = 0.007). Racial profiles were similar between the two groups (p = 0.575). Preoperatively, those in the HTO group had more functional independence, better physical status scores, and fewer chronic conditions (p < 0.05). There were no statistically significant differences between HTO and DFO in operative time, postoperative complications, readmission, and reoperation. HTO patients, however, had shorter hospital stays (p < 0.001). Although there are differences in preoperative and operative characteristics of HTO and DFO, early postoperative complications are similar for both groups. Therefore, HTO and DFO can be considered safe and effective treatment options for younger patients with symptomatic unicompartmental knee osteoarthritis.

No abstract