Development of a Machine Learning-Based Model to Predict Timed-Up-and-Go Test in Older Adults.

INTRODUCTION: The measurement of physical frailty in elderly patients with orthopedic impairments remains a challenge due to its subjectivity, unreliability, time-consuming nature, and limited applicability to uninjured individuals. Our study aims to address this gap by developing objective, multifactorial machine models that do not rely on mobility data and subsequently validating their predictive capacity concerning the Timed-up-and-Go test (TUG test) in orthogeriatric patients. METHODS: We utilized 67 multifactorial non-mobility parameters in a pre-processing phase, employing six feature selection algorithms. Subsequently, these parameters were used to train four distinct machine learning algorithms, including a generalized linear model, a support vector machine, a random forest algorithm, and an extreme gradient boost algorithm. The primary goal was to predict the time required for the TUG test without relying on mobility data. RESULTS: The random forest algorithm yielded the most accurate estimations of the TUG test time. The best-performing algorithm demonstrated a mean absolute error of 2.7 s, while the worst-performing algorithm exhibited an error of 7.8 s. The methodology used for variable selection appeared to exert minimal influence on the overall performance. It is essential to highlight that all the employed algorithms tended to overestimate the time for quick patients and underestimate it for slower patients. CONCLUSION: Our findings demonstrate the feasibility of predicting the TUG test time using a machine learning model that does not depend on mobility data. This establishes a basis for identifying patients at risk automatically and objectively assessing the physical capacity of currently immobilized patients. Such advancements could significantly contribute to enhancing patient care and treatment planning in orthogeriatric settings.

Evaluation of a New Treatment Strategy for Geriatric Fragility Fractures of the Posterior Pelvic Ring Using Sensor-Supported Insoles: A Proof-of-Concept Study.

The incidence of fragility fractures of the pelvis (FFPs) is currently rising. Surgical treatment, which is performed using sacroiliac screws, is complicated by compromised bone quality, oftentimes resulting in implant failure. The iFuse implant system aims to improve attachment and durability with promising results for sacroiliac dysfunction, though data for its feasibility on FFPs are rare. Consequently, this study aims to evaluate the feasibility of the iFuse for FFPs. A total of 10 patients with FFPs were treated with the iFuse in this study. Pre- and postoperatively, both mobility using an established insole force sensor for an inpatient gait analysis and general well-being and pain using questionnaires were evaluated. When comparing pre- and postoperative findings, this study demonstrated a significant increase in the average (8.14%) and maximum (9.4%) loading (p < 0.001), a reduction in pain, as measured by the visual analog scale (VAS), from 4.60 to 2.80 at rest (p = 0.011) and from 7.00 to 4.40 during movement (p = 0.008), an increase in the Barthel Index by 20 points (p < 0.001) and an increase in the Parker Mobility Score by 2.00 points (p = 0.011). All this contributes to the possibility of early postoperative mobilization and improved general well-being, ultimately preventing the late consequences of postoperative immobilization and maintaining patients autonomy and contentment.

Predictive Value of Prognostic Nutritional Index for Early Postoperative Mobility in Elderly Patients with Pertrochanteric Fracture Treated with Intramedullary Nail Osteosynthesis.

BACKGROUND: Early postoperative mobilization is essential for orthogeriatric patients. The prognostic nutritional index (PNI) is widely used to evaluate nutritional status. This study sought to investigate the predictive value of PNI for early postoperative mobility in patients with pertrochanteric femur fractures. MATERIALS AND METHODS: This study included 156 geriatric patients with pertrochanteric femur fractures treated with TFN-Advance™ (DePuy Synthes, Raynham, MA, USA). Mobility was evaluated on the third postoperative day and by discharge. Stepwise logistic regression analyses were performed to evaluate the association significance of PNI with postoperative mobility together with comorbidities. The optimal PNI cut-off value for mobility was analyzed using the receiver operating characteristic (ROC) curve. RESULTS: Three days postoperatively, PNI was an independent predictor of mobility (OR: 1.14, 95% CI: 1.07-1.23, p < 0.01). By discharge, it was found that PNI (OR: 1.18, 95% CI: 1.08-1.30, p < 0.01) and dementia (OR: 0.17, 95% CI: 0.07-0.40, p < 0.001) were significant predictors. PNI correlated weakly with age (r = -0.27, p < 0.001). The PNI cut-off value for mobility on the third postoperative day was 38.1 (specificity = 78.5%, sensitivity = 63.6%). CONCLUSIONS: Our findings indicate that PNI is an independent predictor of early postoperative mobility in geriatric patients with pertrochanteric femur fractures treated with TFNA™.

Changing patterns in the epidemiology of tibial plateau fractures: a 10-year review at a level-I trauma center.

PURPOSE: Mobility patterns of western societies have been changing due to ongoing demographic change. Therefore, continuously updated epidemiological data on fracture morphology and treatment strategies are needed. METHODS: This retrospective single-center study included all tibial plateau fractures (TPF) between January 2011 and December 2020 in a level-I trauma center in Central Europe. Epidemiology, trauma mechanism and fracture morphology were analyzed. Age- and sex-specific differences regarding fracture classification (Schatzker, AO/OTA, Moore) and changes during the study period are highlighted. RESULTS: A total of 607 patients (55.2% women, 44.8% men, mean age 52.9 years (± 17.9)) were included in the study, 462 (76.1%) thereof having undergone surgical treatment. Over the decade, an increase in mean age (+ 7.4 years; p = 0.10), incidence (+ 68%; p < 0.05) and low-energy trauma was observed, with the highest peak in elderly women. Within classifications, AO/OTA 41-B3 (24.9%), Schatzker II (26.8%) and Moore V (46.6%) fractures were the most common. CONCLUSION: Incidence (+ 68%), mean age and fractures with signs of knee dislocation of tibial plateau fracture increased over the last decade and low-energy trauma mechanism are more frequent. As the increase in incidence is mainly seen in older women, the comorbidities and need for immediate postoperative full weight-bearing have to be considered in treatment strategies.

[Influence of the COVID-19 pandemic on fracture epidemiology exemplified by tibial plateau fractures]. / Einfluss der COVID-19-Pandemie auf die Frakturepidemiologie am Beispiel der Tibiaplateaufraktur.

BACKGROUND: During the COVID-19 pandemic interventions, such as contact restrictions, lockdowns and postponement of elective surgeries were taken to ease the burden on the healthcare system. Among the population, these interventions led to changes in recreational behavior as well as personal transportation. OBJECTIVE: This paper examines the epidemiological data of tibial plateau fractures (TPF) before and during the pandemic and to what extent pandemic control measures had an impact. MATERIAL AND METHODS: In this retrospective monocentric study of a German level 1 trauma center, the intra-articular tibial plateau fractures of the years 2019 and 2020 were compared regarding incidence, demographics, cause of the accident, and treatment strategy. Fracture classification was according to Schatzker, AO/OTA, and Moore. RESULTS: Incidence showed a decrease of -8.5% as well as a shift in the age incidence curves. There was a decrease in incidence during lockdown periods but also an increase in late summer 2020 compared to 2019. Tripping accidents (+12.4%) and bicycle accidents (+6.6%) increased in the pandemic year, whereas motorized traffic accidents (-7%) and skiing accidents (-10%) decreased. In terms of fracture morphology, 2020 showed an increase in impression fractures and a decrease in complex fractures. The number of surgically treated patients decreased by 7.3%. CONCLUSION: The 12 months of pandemic resulted in only a slight incidence decrease of intra-articular tibial plateau fractures. The pandemic control measures showed effects within the calendar year and led directly and indirectly to a change in incidence, cause of the accident, fracture entities and care strategy.

Reduced Awareness for Osteoporosis in Hip Fracture Patients Compared to Elderly Patients Undergoing Elective Hip Replacement.

Background: Osteoporotic fractures are associated with a loss of quality of life, but only few patients receive an appropriate therapy. Therefore, the present study aims to investigate the awareness of musculoskeletal patients to participate in osteoporosis assessment and to evaluate whether there are significant differences between acute care patients treated for major fractures of the hip compared to elective patients treated for hip joint replacement.; Methods: From May 2015 to December 2016 patients who were undergoing surgical treatment for proximal femur fracture or total hip replacement due to osteoarthritis and were at risk for an underlying osteoporosis (female > 60 and male > 70 years) were included in the study and asked to complete a questionnaire assessing the awareness for an underlying osteoporosis. ASA Score, FRAX Score, and demographic information have also been examined. Results: In total 268 patients (female = 194 (72.0%)/male = 74 (28%)), mean age 77.7 years (±7.7) undergoing hip surgery were included. Of these, 118 were treated for fracture-related etiology and 150 underwent total hip arthroplasty in an elective care setting. Patients were interviewed about their need for osteoporosis examination during hospitalization. Overall, 76 of 150 patients receiving elective care (50.7%) considered that an examination was necessary, whereas in proximal femur fracture patients the awareness was lower, and the disease osteoporosis was assessed as threatening by significantly fewer newly fractured patients. By comparison, patients undergoing trauma surgery had a considerably greater risk of developing another osteoporotic fracture than patients undergoing elective surgery determined by the FRAX® Score (p ≤ 0.001).; Conclusions: The patients' motivation to endure additional osteoporosis diagnostic testing is notoriously low and needs to be increased. Patients who underwent acute care surgery for a fragility proximal femur fracture, although acutely affected by the potential consequences of underlying osteoporosis, showed lower awareness than the elective comparison population that was also on average 6.1 years younger. Although elective patients were younger and at a lower risk, they seemed to be much more willing to undergo further osteoporosis assessment. In order to better identify and care for patients at risk, interventions such as effective screening, early initiation of osteoporosis therapy in the inpatient setting and a fracture liaison service are important measures.

Impact of keel saw blade design and thickness on the incidence of tibial plateau fracture and tibial implant-loosening in cementless medial UKR.

BACKGROUND: Tibial plateau fractures and tibial implant- loosening are severe complications in cementless unicompartmental knee replacement (UKR). The tibial keel preparation is particularly demanding and different saw blades can be used. It was hypothesized that different blade designs and thickness have an influence on the frequency of tibial plateau fractures and implant-loosening in cementless medial UKR. METHODS: 1258 patients with cementless medial UKR were included in this retrospective study between 2013 and 2020. The tibial keel cut was performed either with a double keel saw blade (DKS; 2.8 mm) and added hand guided pick or a mono reciprocating saw blade (RKB) of different thickness (2.5 mm; 2.65 mm; 2.75 mm). Tibial plateau fracture and loosening were demonstrated by standard two-plane radiographs. Tibial implant-loosening was defined as complete radiolucency and implant migration. Fracture and loosening were combined with pain and loss of function. RESULTS: In 126 patients (10%) the tibial keel was prepared with DKS, in 407 patients (32.4%) with RKB 2.5 mm, in 330 patients (26.2%) with RKB 2.65 mm and in 395 patients (31.4%) with 2.75 mm. In 4 patients (3.17%) with DKS tibial plateau fracture occurred, in 4 patients (0.99%) with 2.5 mm RKB, in 3 patients (0.92%) with 2.65 mm RKB and in 1 patient (0.25%) with 2.75 mm RKB. Significantly fewer fractures occurred with a RKB design (p = 0.007). A negative correlation between fracture incidence and RKB saw blade thickness was found (Spearman-r = - 0.93). No difference for tibial implant-loosening was shown (p = 0.51). CONCLUSION: Different blade designs and thickness have a significant influence on the incidence of tibial plateau fractures and aseptic tibial implant-loosening. The incidence of tibial plateau fractures in cementless medial UKR can be reduced by changing the design and thickness of the tibial keel saw blade. Greater thickness of RKB leads to significantly fewer tibial plateau fractures while the incidence of implant-loosening is not increasing. TRIAL REGISTRATION: This study was retrospectively registered and ethical approval was waived by the local ethical committee (No. 2020-1174).

The grade of instability in fragility fractures of the pelvis correlates with impaired early mobilization.

PURPOSE: This study aimed to investigate whether gait patterns of patients with fragility fractures of the pelvis (FFP) comply with the grade of fracture instability, defined by radiological patterns. PATIENTS AND METHODS: This prospective, single-center, observational study included 39 patients with an FFP. Gait analysis was performed with a wearable insole force sensor (Loadsol® by Novel, Munich, Germany) 4-7 days after admission. Patients were divided in two groups: Group A included FFP type 1 fractures, which affect the anterior pelvic ring only, Group B contained FFP type 2-4 fractures with an involvement of the posterior pelvic ring. Primary outcome parameter was the FTI ratio (force-time integral (N*s)). RESULTS: The mean age was 85.08 years (SD ± 6.45), 94.9% (37/39) of the patients were female. The most common fracture type was an FFP 2b (64.1%, 25/39). Group A showed a significantly higher FTI ratio (45.12%, SD ± 4.19%) than Group B (38.45%, SD ± 5.97%, p = 0.002). Further, a significant correlation of the FTI ratio and the average (r = 0.570, p < 0.001) and maximum (r = 0.394, p = 0.013) peak force was observed. CONCLUSION: The gait pattern of patients with an FFP type 2-4 was more imbalanced than of patients with an FFP type 1 fracture. These findings match with the radiological classification of FFP, which indicates higher instability, when the posterior pelvis is affected. Gait analysis might offer earlier functional diagnostics and may accelerate the treatment decision with shorter periods of immobility in future. Especially in cross-border cases, early gait analysis could be beneficial to clarify the indication for or against surgery.

Prediction of Physical Frailty in Orthogeriatric Patients Using Sensor Insole-Based Gait Analysis and Machine Learning Algorithms: Cross-sectional Study.

BACKGROUND: Assessment of the physical frailty of older patients is of great importance in many medical disciplines to be able to implement individualized therapies. For physical tests, time is usually used as the only objective measure. To record other objective factors, modern wearables offer great potential for generating valid data and integrating the data into medical decision-making. OBJECTIVE: The aim of this study was to compare the predictive value of insole data, which were collected during the Timed-Up-and-Go (TUG) test, to the benchmark standard questionnaire for sarcopenia (SARC-F: strength, assistance with walking, rising from a chair, climbing stairs, and falls) and physical assessment (TUG test) for evaluating physical frailty, defined by the Short Physical Performance Battery (SPPB), using machine learning algorithms. METHODS: This cross-sectional study included patients aged >60 years with independent ambulation and no mental or neurological impairment. A comprehensive set of parameters associated with physical frailty were assessed, including body composition, questionnaires (European Quality of Life 5-dimension [EQ 5D 5L], SARC-F), and physical performance tests (SPPB, TUG), along with digital sensor insole gait parameters collected during the TUG test. Physical frailty was defined as an SPPB score≤8. Advanced statistics, including random forest (RF) feature selection and machine learning algorithms (K-nearest neighbor [KNN] and RF) were used to compare the diagnostic value of these parameters to identify patients with physical frailty. RESULTS: Classified by the SPPB, 23 of the 57 eligible patients were defined as having physical frailty. Several gait parameters were significantly different between the two groups (with and without physical frailty). The area under the receiver operating characteristic curve (AUROC) of the TUG test was superior to that of the SARC-F (0.862 vs 0.639). The recursive feature elimination algorithm identified 9 parameters, 8 of which were digital insole gait parameters. Both the KNN and RF algorithms trained with these parameters resulted in excellent results (AUROC of 0.801 and 0.919, respectively). CONCLUSIONS: A gait analysis based on machine learning algorithms using sensor soles is superior to the SARC-F and the TUG test to identify physical frailty in orthogeriatric patients.

Patients with complex proximal tibial fractures overestimate the prognosis of their injury.

PURPOSE: To investigate, if patients with complex proximal tibial fracture have realistic expectations on open reduction and internal fixation. METHODS: 114 patients (mean 49 years, SD ± 13) with closed AO-type B and C proximal tibial fracture were grouped (group B, respectively C). Prior to surgery expectations concerning knee function, pain, return to work/sports, and the risk for osteoarthritis was assessed with the Hospital for Special Surgery-Knee Surgery Expectations Survey (HFSS-KSE) and a non-validated ten-item survey. RESULTS: 92% of patients expected at least an almost natural knee postoperatively. All items regarding restoring knee function were ranked to be at least important in both groups. 65% in group B and 47% in group C expected at most occasional pain. 83% in group B and 67% in group C expected full return to work without any limitations. Patients with low physical work intensity expected significantly shorter incapacity to work in both groups (7.8, respectively 8.9 weeks). 71% in group B and 60% in group C expected to return to sports with at most small limitations. 33% in group B and 22% in group C assumed risk for osteoarthritis will be prevented by surgery. CONCLUSION: Expectations on surgery for complex proximal tibial fracture are high regardless of fracture type. The prognosis of many health and lifestyle domains was overestimated. The risk for osteoarthritis was underestimated. This study should sensitize surgeons to discuss realistic expectations. This may help to improve patient comprehension what leads to sensible expectations, resulting in improved patients´ satisfaction. LEVEL OF EVIDENCE: IV. TRIAL REGISTRATION NUMBER: 14104, Date of registration: 06/2015.

How relevant is lumbar bone mineral density for the stability of symphyseal implants? A biomechanical cadaver study.

PURPOSE: Osteoporotic bone tissue appears to be an important risk factor for implant loosening, compromising the stability of surgical implants. However, it is unclear whether lumbar measured bone mineral density (BMD) is of any predictive value for stability of surgical implants at the pubic symphysis. This study examines the fixation strength of cortical screws in human cadaver specimens with different BMDs. METHODS: The lumbar BMD of ten human specimens was measured using quantitative computed tomography (qCT). A cut-off BMD was set at 120 mg Ca-Ha/mL, dividing the specimens into two groups. One cortical screw was drilled into each superior pubic ramus. The screw was withdrawn in an axial direction with a steady speed and considered failed when a force decrease was detected. Required force (N) and pull-out distance (mm) were constantly tracked. RESULTS: The median peak force of group 1 was 231.88 N and 228.08 N in group 2. While BMD values differed significantly (p < 0.01), a comparison of peak forces between both groups showed no significant difference (p = 0.481). CONCLUSION: Higher lumbar BMD did not result in significantly higher pull-out forces at the symphysis. The high proportion of cortical bone near the symphyseal joint allows an increased contact of pubic screws and could explain sufficient fixation. This condition is not reflected by a compromised lumbar BMD in a qCT scan. Therefore, site-specific BMD measurement could improve individual fracture management.

Self-Assessment of Mobility of People over 65 Years of Age.

BACKGROUND AND OBJECTIVES: Nowadays, various clinical scoring systems are used in the medical care of the elderly to assess the quality of mobility. However, people often tend to under- or overestimate themselves in many aspects. Since this can have serious consequences in their treatment and care, the aim of this study was to identify differences in the self and external assessment of mobility of persons over 65 years of age. MATERIALS AND METHODS: 222 participants over 65 years of age and one external, closely-related relative or professional caregiver were interviewed by a unique study assistant using a standardized questionnaire. Participants were divided into people living in nursing homes and independent people living at home, where either the caregivers or the relatives provided the external assessment of mobility, respectively. The questionnaire included demographics, cognitive abilities (Mini Mental Status Test); fall risk (Hendrich 2 Fall Risk Model); as well as the Parker Mobility Score, Barthel Index, and EQ-5D-5L to measure mobility, activities of daily life and quality of life. In each case, the participant and the external person were asked for their assessment to the participants' mobility situation. Statistical significance of the difference between self and external assessment was calculated with a Wilcoxon rank-sum test and assumed with a p-value of ≤ 0.05. RESULTS: Self-assessment indicated a significantly higher value, when compared to an external assessment for the Parker Mobility Score for females in nursing homes (p ≤ 0.01), as well as for the Barthel Index for females (p ≤ 0.01) and males (p ≤ 0.01) in nursing homes. The EQ-5D-5L received a significantly higher self-assessment value for females (p ≤ 0.01) and males (p ≤ 0.01) living at home and females (p ≤ 0.01) and males (p ≤ 0.05) in nursing homes. CONCLUSIONS: Persons over 65 years of age tend to overestimate their level of mobility, quality of life and activities of daily life. Especially for people living in nursing homes, these scoring systems should be treated with caution due to the differences between the verbal statements. It is important to properly assess the mobility situation of elderly patients to ensure correct medical treatment and prevention of falls.

Reduced Awareness for Osteoporosis in Distal Radius Fracture Patients Compared to Patients with Proximal Femur Fractures.

PURPOSE: The present study is aiming to evaluate patients' awareness to participate in further diagnostics for osteoporosis and to find out if there are significant differences with regards to fracture site. METHODS: Patients at risk for underlying osteoporosis (female >60 and male >70 years) undergoing surgical treatment for a distal radius fracture (DRF) or a proximal femur fracture (PFF) were asked to complete a questionnaire assessing the awareness for underlying osteoporosis. Furthermore, dual-X-ray absorptiometry (DXA) scans were analyzed. RESULTS: Overall, 150 patients (w = 122/m = 28, mean age 79.9 years (±8.6)) were included, of these, 36 patients suffered a DRF and 114 patients a PFF. Of these, 68 out of the 150 patients (45.3%) considered that an examination was necessary, whereas in PFF patients the awareness was higher than in the DRF Group (41% vs. 32%). CONCLUSIONS: The patients' willingness to undergo further diagnostics for osteoporosis was generally poor. DRFs are frequently accompanied by a lower limitation of quality of life compared to PFF, which might be causative for even poorer awareness in these patients. Especially younger patients (age 60-70 years) with a distal radius fracture seemed to underestimate osteoporosis.

Inferior Outcome after Unstable Trochanteric Fracture Patterns Compared to Stable Fractures in the Elderly.

BACKGROUND: Various risk factors affecting outcome of elderly patients after proximal femur fracture have been identified. The present study aims to evaluate the impact of the fracture pattern in trochanteric fractures on postoperative mobility and complications. METHODS: Ninety-two patients with a mean age of 84 years were included. According to the revised AO/OTA classification, fractures were divided into stable (AO 31A1) and unstable (AO 31A2/3) patterns. A follow-up examination was performed 12 months after cephalomedullary fixation to assess outcome parameters for mobility/activities of daily living (Parker Mobility Score (PMS)/Barthel Index (BI)) and complications (increase in requirement of care, hospital readmission, mortality rate). RESULTS: At follow-up, patients with unstable trochanteric fracture patterns presented with lower PMS and BI compared to stable fractures (p < 0.05). Further, higher requirement of care and higher readmission rates compared to stable patterns were observed. CONCLUSION: Unstable trochanteric fractures presented inferior outcome compared to simple fracture patterns. This might be explained by the increasing surgical trauma in unstable fractures as well as by the mechanical impact of the lesser trochanter, which provides medial femoral support and is of functional relevance. Subsequent studies should assess if treatment strategies adapted to the specific fracture pattern (refixation of lesser trochanter) influence outcome in unstable trochanteric fractures.

Continuous Digital Monitoring of Walking Speed in Frail Elderly Patients: Noninterventional Validation Study and Longitudinal Clinical Trial.

BACKGROUND: Digital technologies and advanced analytics have drastically improved our ability to capture and interpret health-relevant data from patients. However, only limited data and results have been published that demonstrate accuracy in target indications, real-world feasibility, or the validity and value of these novel approaches. OBJECTIVE: This study aimed to establish accuracy, feasibility, and validity of continuous digital monitoring of walking speed in frail, elderly patients with sarcopenia and to create an open source repository of raw, derived, and reference data as a resource for the community. METHODS: Data described here were collected as a part of 2 clinical studies: an independent, noninterventional validation study and a phase 2b interventional clinical trial in older adults with sarcopenia. In both studies, participants were monitored by using a waist-worn inertial sensor. The cross-sectional, independent validation study collected data at a single site from 26 naturally slow-walking elderly subjects during a parcours course through the clinic, designed to simulate a real-world environment. In the phase 2b interventional clinical trial, 217 patients with sarcopenia were recruited across 32 sites globally, where patients were monitored over 25 weeks, both during and between visits. RESULTS: We have demonstrated that our approach can capture in-clinic gait speed in frail slow-walking adults with a residual standard error of 0.08 m per second in the independent validation study and 0.08, 0.09, and 0.07 m per second for the 4 m walk test (4mWT), 6-min walk test (6MWT), and 400 m walk test (400mWT) standard gait speed assessments, respectively, in the interventional clinical trial. We demonstrated the feasibility of our approach by capturing 9668 patient-days of real-world data from 192 patients and 32 sites, as part of the interventional clinical trial. We derived inferred contextual information describing the length of a given walking bout and uncovered positive associations between the short 4mWT gait speed assessment and gait speed in bouts between 5 and 20 steps (correlation of 0.23) and longer 6MWT and 400mWT assessments with bouts of 80 to 640 steps (correlations of 0.48 and 0.59, respectively). CONCLUSIONS: This study showed, for the first time, accurate capture of real-world gait speed in slow-walking older adults with sarcopenia. We demonstrated the feasibility of long-term digital monitoring of mobility in geriatric populations, establishing that sufficient data can be collected to allow robust monitoring of gait behaviors outside the clinic, even in the absence of feedback or incentives. Using inferred context, we demonstrated the ecological validity of in-clinic gait assessments, describing positive associations between in-clinic performance and real-world walking behavior. We make all data available as an open source resource for the community, providing a basis for further study of the relationship between standardized physical performance assessment and real-world behavior and independence.