Recently, several smartphone applications (apps) have been developed and validated for ankle ROM measurement tools like the universal goniometer. This is the first innovative study introduces a new smartphone application to measure ankle joint ROM as a remote solution. This study aimed to assess the correlation between smartphone ROM and universal goniometer measurements, and also report the evaluation of the DijiA app by users. The study included 22 healthy university students (14F/8M; 20.68±1.72 years) admitted to Yeditepe University. Fourty four feet was measured by both the universal goniometer (UG) and DijiA app. The datas were analyzed through using the intraclass correlation coefficient (ICC). The DijiA app was evaluated by usability testing with representative users. Pearson correlation coefficient test showed moderate correlation between the DijiA and UG for dorsiflexion (DF) and plantar flexion (PF) measurements (Pearson correlation coefficient: r=0.323, for DF; r=0.435 for PF 95% confidence interval). The application usability was found as high with 76.5 average score and users liked it. The DijiA app may be a more convenient and easy way to measure ankle DF and PF-ROM than UG. It can be used to evaluate ROM in clinical practice or home using as a personal smartphone

The Step Holter is a software and mobile application that can be used to easily study gait analysis. The application can be downloaded for free on the App Store and Google Play Store for iOS and Android devices. The software can detect with an easy calibration the three planes to detect the movement of the gait. Before proceeding with the calibration, the smartphone can be placed and fixed with a band or stowed into a long sock with its top edge at the height of the joint line, in the medial side of the tibia. The calibration consists in bending the knee about 20 to 30 degrees and then making a rotation movement, leaving the heel fixed to the ground as a rotation fulcrum. After calibration, the program records data related to lateral flexion, rotation, and bending of the leg. This data can be viewed directly from the smartphone screen or transmitted via a web link to the Step Holter web page . www.stepholter.com. by scanning a personal QR code. The web page allows the users to monitor the test during its execution or view data for tests done previously. By pressing the play button, it is possible to see a simulation of the patient's leg and its movement. With the analyze button, the program is capable of calculating the swing and stance phase of every single step, providing a plot with time and percentages. Finally, with the Get Excel button, test data can be conveniently exported for more in-depth research. The advantage of this application is not only to reduce the costs of a machine for the study of gait analysis but also being able to perform tests quickly, without expensive hardware or software and be used in specific spaces, without specialized personnel. Furthermore, the application can collect important data concerning rotation that cannot be highlighted with the classic gait analysis. The versatility of a smartphone allows tests to be carried out not only during walking but also by climbing or descending stairs or sitting down or getting up from a chair. This software offers the possibility to easily study any kind of patients; Older patients, reluctant to leave their homes for a gait analysis can be tested at home or during an office control visit. Step Holter could be one small step for patients, one giant leap for gait study simplicity. For any figures or tables, please contact authors directly

INTRODUCTION. The magnitude of knee flexion angle is a relevant information during clinical examination of the knee, and this item is a significant part of every knee scoring system. It is generally performed by visual analysis or with manual goniometers, but these techniques may be neither precise nor accurate. More sophisticated techniques are only possible in experimental studies. Smartphone technology might offer a new way to perform this measurement with increased accuracy. MATERIAL. 20 patients operated on for unicompartmental or total knee replacement with help of a navigation system participated to the study. There were 13 women and 7 men with a mean age of 72.1 years. METHODS. All patients were operated on for unicompartmental or total knee replacement. All patients were operated on with help of a non-image based navigation system. The navigation system is able to measure very accurately the knee flexion angle. The Smartphone application allows measuring this angle in two steps 1) recording the reference position by putting the Smartphone on the operating table, 2) recording the knee flexion angle by putting the Smartphone against the tibial crest. Two observers participated to the study. The first observer performed three independent navigated measurements followed by three independent Smartphone measurements while positioning the knee under visual control in full extension, at 0°, 30°, 60°, 90° of knee flexion and at maximal flexion; the second observer performed only one set of measurements. The intra- and inter-observer variability was assessed by calculation of the intra-class correlation coefficient. Navigated and Smartphone data were compared by a paired Wilcoxon test and calculation of the Spearman coefficient of correlation at a 5% level of significance. RESULTS. There was no significant difference between paired navigated and Smartphone measurements at any degree of knee flexion. There was a strong correlation between the two data sets. The intra- and inter-observer reproducibility was high. DISCUSSION-CONCLUSION. There was a high agreement between the navigated measurements considered as the reference and the Smartphone measurements. This new technology is easy to use and extensively available. It allows improving significantly the precision and the accuracy of the measurement of the knee flexion angle without technical difficulties. This technique might allow a self-control by the patient of the progression of the post-operative rehabilitation. SUMMARY. The Smartphone application allows improving significantly the precision and the accuracy of the measurement of the knee flexion angle without technical difficulties

INTRODUCTION. Measurement of range of motion is a critical item of any knee scoring system. Conventional measurements used in the clinical settings are not as precise as required. Smartphone technology using either inclinometer application or photographic technology may be more precise with virtually no additional cost when compared to more sophisticated techniques such as gait analysis or image analysis. No comparative analysis between these two techniques has been previously performed. The goal of the study was to compare these two technologies to the navigated measurement considered as the gold standard. MATERIAL. Ten patients were consecutively included. Inclusion criterion was implantation of a TKA with a navigation system. METHODS. Two free angle measurement applications were downloaded to the Smartphone: one using inclinometer technology, the other using camera technology. After navigation assisted TKA and just before wound closure, the operated knee was positioned at full extension, 30±2°, 60±2°, 90±2° and 120±2° according to the navigated measurement. At each step, the knee flexion angle was measured with both Smartphone applications: inclinometer application (figure 1) and camera application (figure 2). For each of the ten patients, 5 navigated, 5 inclinometer and 5 camera measurements were obtained for each patient, giving three sets of 50 repeat measurements. The sample size was calculated to get a significance level of 0.05 and a power of 0.8 to detect a 10° difference. The difference between the three sets of measurements was analyzed with an ANOVA test for repeat measurements, with post-hoc comparisons with a paired Wilcoxon test. The correlation between the three sets of measurements was analyzed with a Kendall test, with post-hoc comparisons with a Spearman test. All tests were performed at a 0.05 level of significance, and post-hoc comparisons were performed at a 0.01 level of significance. RESULTS. The mean paired difference between navigated and camera measurements was 0.7° (SD 1.5°), with one difference greater than 3°. The mean paired difference between navigated and inclinometer measurements was 7.5° (SD 5.3°), with 16 differences greater than 10°. The mean paired difference between inclinometer and camera measurements was −6.8° (SD5.2°), with 7 differences greater than 10°. The ANOVA test for repeat measurements showed a significant difference between the three sets of measurements (p<0.001). The results of post-hoc paired comparisons with the Wilcoxon test are reported in table 2. The Kendall test showed that the distribution of the three sets of measurements was no different. The post-hoc paired correlations with the Spearman test showed a good coherence between all pairs of measurements (R² between 0.02 and 0.12). No pre-operative criteria showed a significant influence on the differences observed. DISCUSSION. Measuring the knee flexion angle with the camera of a smartphone is effective in a routine clinical practice. Accuracy can be better than other conventional measurement techniques. All applications of a smartphone do not have the same precision and must be validated before clinical use. CONCLUSION. Smartphone technology enables a more accurate assessment of the knee range of motion after TKA than conventional measurement techniques. To view tables/figures, please contact authors directly

Background. Smartphones are now a ubiquitous presence within the modern healthcare setting. Uses such as internet, database software and storage of medical textbooks, all contribute to the clinical value of the devices. Within orthopaedics, transmission of digital images via smartphones is now routinely used to obtain instant second opinions of trauma radiographs. However questions remain as to whether smartphone image quality is sufficient for primary diagnosis and secondary consultation. Aim. To assess the accuracy of diagnosis made when radiographs are viewed on a smartphone screen in comparison with a standard digital monitor. Also to assess the diagnostic confidence, diagnostic difficulty, subjective image quality and formulation of management plan. Method. 30 orthopaedic registrars viewed a total of 900 radiographs–450 radiographs were viewed on a 3.5inch, 640×960 PPI smartphone screen and 450 on a standard digital monitor. Likert scales were used to assess the diagnostic accuracy, confidence and difficulty along with image quality and management plan. Initially images were viewed on the smartphone screen and after one week the same images were viewed on the digital monitor. Results were then compared. Results. There was no difference in diagnostic accuracy between smartphone and digital monitors although participants tended to be more confident in their diagnosis when made on the larger screen of the digital monitor. Diagnostic difficulty was higher in the smartphone group and image quality was lower. However there was a high correlation between management plans made after viewing images in both modalities. Discussion. This study demonstrates that although participants found the image quality poorer and found it marginally more difficult to make a diagnosis the same diagnosis was arrived at and the same management plan formulated using a smartphone compared to a standard digital monitor. Therefore smartphone based teleradiology appears to have a valid use in orthopaedic trauma

Introduction. With advances in mobile application, digital health is being increasingly used for remote and personalised care. Patient education, self-management and tele communication is a crucial factor in optimising outcomes. Aims. We explore the use of a smartphone app based orthopaedic care management system to deliver personalised surgical experience, monitor patient engagement and functional outcomes of patients undergoing knee arthroplasty. Results. Over a 12-month period, 124 patients listed for knee arthroplasty were offered access to the app. Average patient age was 65.4 years (range 49 to 86). 13(10.4%) patients were over 80 years. Compliance with app usage was 86.4%. Compliance with post-operative exercises increased following a message through the app. The mean Oxford knee score improved from a pre-op value of 17 to 35 at a mean follow-up of 6 months. Mean numeric rating scale pain score reduced from 7 pre-operatively to 3 at the latest follow-up. 58 patients (46.7%) used the communication feature on the app (text messages, photos, video consultations), reducing telephone calls and patient foot fall in the hospital. Patient satisfaction with the app was very high. Conclusion. We found the virtual care system to be effective in providing patient education, prehabilitation and post-operative rehabilitation along with being an effective channel of communication between patients and the hospital team. Patient satisfaction and compliance was very high

Aim. Smartphone applications have a great scope for revolutionising the medical field and are becoming increasingly utilised in clinical practice. They are advantageous as they are timesaving and readily available at the touch of a button. We reviewed all the T&O clinically relevant applications available for doctors on Apple's ‘App Store’. Methods. A search was performed using the following terms: Trauma, Orthopaedics, Ortho, Musculoskeletal and Fracture. Applications that were in any language other than English were excluded. The applications were subsequently categorised into: ‘clinical’, ‘learning and reference’, ‘hospital guidelines’ and ‘patient education’. Results. 136 of the 575 were relevant to T&O from the search conducted using the above terms. 18 of these applications were aimed at patient education and 118 were designed for use by doctors. 91 applications were for learning and referencing purposes, 4 were local hospital guidelines and only 23 were designed for use in clinical practice. 2/23 clinical applications were validated by official bodies and only 1/23 was rated by users. Conclusion. It is clear that smartphone use is becoming more popular in clinical practice; however there is a need for developers to create more validated applications of higher quality for T&O surgeons

Acetabular cup placement in total hip replacement surgery is often difficult to assess, especially in the lateral position and using the posterior approach. On table control X-Rays are not always accessible, especially in the government sector. Conventional techniques and computer assisted surgery (CAS), are currently the two most popular methods for proper placement of the acetabular cup in Lewinnek's safe zone of orientation (anteversion 15°–10° and lateral inclination 40°±10°). We developed a simple way to get accurate cup placement using Smartphone technology. Methods:. A spirit level application was downloaded to the Smartphone. The acetabulum inclination was measured on the pre-operative X-Rays. The phone is placed in a sterile bag and then used intra-operatively, to measure and set our acetabular cup orientation to our pre-operative measurements. The inclination level was measured before and after final placement of the acetabular cup. This was compared to the acetabular cup inclination in our post-operative X-Rays. Results:. In our series of 50 cup placements we found high accuracy. The results show less than 5° deviation between our pre-, intra- and post-operative measurements. Conclusions:. Smartphone technology proves to be good alternative to conventional methods and CAS, to improve Acetabular Cup placement in Total Hip Arthroplasty

Introduction. Gait analysis systems have enjoyed increasing usage and have been validated to provide highly accurate assessments for range of motion. Size, cost, need for marker placement and need for complex data processing have remained limiting factors in uptake outside of what remains predominantly large research institutions. Progress and advances in deep neural networks, trained on millions of clinically labelled datasets, have allowed the development of a computer vision system which enables assessment using a handheld smartphone with no markers and accurate range of motion for knee during flexion and extension. This allows clinicians and therapists to objectively track progress without the need for complex and expensive equipment or time-consuming analysis, which was concluded to be lacking during a recent systematic review of existing applications. Method. A smartphone based computer vision system was assessed for accuracy with a gold standard comparison using a validated ‘traditional’ infra-red motion capture system which had a defined calibrated accuracy of 0.1degrees. A total of 22 subjects were assessed simultaneously using both the computer vision smartphone application and the standard motion capture system. Assessment of the handheld system was made by comparison to the motion capture system for knee flexion and extension angles through a range of motion with a simulated fixed-flexion deformity which prevented full extension to assess the accuracy of the system, repeating movements ten times. The peak extension angles and also numerous discrete angle measurements were compared between the two systems. Repeatability was assessed by comparing several sequential cycles of flexion/extension and comparison of the maximum range of motion in normal knees and in those with a simulated fixed-flexion deformity. In addition, discrete angles were also measured on both legs of three cadavers with both skin and then bone implanted fiducial markers for ground truth reliability accounting for skin movement. Data was processed quickly through an automated secure cloud system. Results. The smartphone application was found to be accurate to 1.47±1.05 degrees through a full range of motion and 1.75±1.56 degrees when only peak extension angles were compared, demonstrating excellent reliability and repeatability. The cadaveric studies despite limitations which will be discussed still showed excellent accuracy with average errors as low as 0.29 degrees for individual angles and 4.09 degrees for an average error in several measurement. Conclusion. This novel solution offers for the first time a way to objectively measure knee range of motion using a markerless handheld device and enables tracking through a range of assessments with proven accuracy and reliability even accounting for traditional issues with the previous marker based systems. Repeatability for both computer vision and motion capture have greater extrinsic than intrinsic error, particularly with marker placement - another benefit of a markerless system. Clinical applications include pre-operative assessment and post-operative follow-up, paired with surgical planning (including with robots) and remote monitoring after knee surgery, with outcomes guiding treatment and rehabilitation and leading to reduced need for manipulation under anaesthesia and greater satisfaction

Aims. The purpose of this study is to evaluate early outcomes with the use of a smartphone-based exercise and educational care management system after total hip arthroplasty (THA) and demonstrate decreased use of in-person physiotherapy (PT). Methods. A multicentre, prospective randomized controlled trial was conducted to evaluate a smartphone-based care platform for primary THA. Patients randomized to the control group (198) received the institution’s standard of care. Those randomized to the treatment group (167) were provided with a smartwatch and smartphone application. PT use, THA complications, readmissions, emergency department/urgent care visits, and physician office visits were evaluated. Outcome scores include the Hip disability and Osteoarthritis Outcome Score (HOOS, JR), health-related quality-of-life EuroQol five-dimension five-level score (EQ-5D-5L), single leg stance (SLS) test, and the Timed Up and Go (TUG) test. Results. The control group was significantly younger by a mean 3.0 years (SD 9.8 for control, 10.4 for treatment group; p = 0.007), but there were no significant differences between groups in BMI, sex, or preoperative diagnosis. Postoperative PT use was significantly lower in the treatment group (34%) than in the control group (55.4%; p = 0.001). There were no statistically significant differences in complications, readmissions, or outpatient visits. The 90-day outcomes showed no significant differences in mean hip flexion between controls (101° (SD 10.8)) and treatment (100° (SD 11.3); p = 0.507) groups. The HOOS, JR scores were not significantly different between control group (73 points (SD 13.8)) and treatment group (73.6 points (SD 13); p = 0.660). Mean 30-day SLS time was 22.9 seconds (SD 19.8) in the control group and 20.7 seconds (SD 19.5) in the treatment group (p = 0.342). Mean TUG time was 11.8 seconds (SD 5.1) for the control group and 11.9 (SD 5) seconds for the treatment group (p = 0.859). Conclusion. The use of the smartphone care management system demonstrated similar early outcomes to those achieved using traditional care models, along with a significant decrease in PT use. Noninferiority was demonstrated with regard to complications, readmissions, and ED and urgent care visits. This technology allows patients to rehabilitate on a more flexible schedule and avoid unnecessary healthcare visits, as well as potentially reducing overall healthcare costs. Cite this article: Bone Joint J 2021;103-B(7 Supple B):91–97

Aims. The purpose is to determine the non-inferiority of a smartphone-based exercise educational care management system after primary knee arthroplasty compared with a traditional in-person physiotherapy rehabilitation model. Methods. A multicentre prospective randomized controlled trial was conducted evaluating the use of a smartphone-based care management system for primary total knee arthroplasty (TKA) and partial knee arthroplasty (PKA). Patients in the control group (n = 244) received the respective institution’s standard of care with formal physiotherapy. The treatment group (n = 208) were provided a smartwatch and smartphone application. Early outcomes assessed included 90-day knee range of movement, EuroQoL five-dimension five-level score, Knee Injury and Osteoarthritis Outcome Score for Joint Replacement (KOOS JR) score, 30-day single leg stance (SLS) time, Time up and Go (TUG) time, and need for manipulation under anaesthesia (MUA). Results. Overall, 90-day mean flexion was not significantly different between the control (121° (SD 11.7°)) and treatment groups (121. o. ; p = 0.559); 90-day mean SLS was 22.7 seconds (SD 9.8) in controls and 24.3 seconds (SD 20.8) in treatment (p = 0.519); 90-day mean TUG times were 10.1 seconds (SD 4.8) in control and 9.3 seconds (SD 3.3) in treatment (p = 0.139). Mean KOOS JR scores were significantly different between control group (73.6 (SD 13.4)) and treatment group (70.4 (SD 12.6); p = 0.026). MUAs were performed in nine (3.7%) patients in the control group and four (1.9%) in the treatment group (p = 0.398). Physiotherapy was performed by 230 (94.4%) of control group and 123 (59.3%) of treatment group (p < 0.001). There were no significant differences between groups in postoperative urgent care visits, or readmissions within 90 days, with significantly fewer emergency department visits in the treatment group (16 (8.2%) vs five (2.5%), p = 0.014). Conclusion. The use of the smartwatch/smartphone care platform demonstrated non-inferiority of clinically significant outcomes to traditional care models, while requiring significantly less postoperative physiotherapy and fewer emergency department visits. This platform could aid in decreasing postoperative costs, while improving patient engagement and communication with the healthcare team. Cite this article: Bone Joint J 2021;103-B(6 Supple A):3–12

Smartphones are often equipped with inertial sensors capable of measuring individuals' physical activities. Their role in monitoring the patients' physical activities in telemedicine, however, needs to be explored. The main objective of this study was to explore the correlation between a participant's daily step counts and the daily step counts reported by their smartphone. This prospective observational study was conducted on patients undergoing lower limb orthopedic surgery and a group of non-patients. The data collection period was from 2 weeks before until four weeks after the surgery for the patients and two weeks for the non-patients. The participants' daily steps were recorded by physical activity trackers employed 24/7, and an application recorded the number of daily steps registered by the participants' smartphones. We compared the cross-correlation between the daily steps time-series taken from the smartphones and physical activity trackers in different groups of participants. We also employed mixed modeling to estimate the total number of steps. Overall, 1067 days of data were collected from 21 patients (11 females) and 10 non-patients (6 females). The cross-correlation coefficient between the smartphone and physical activity tracker was 0.70 [0.53–0.83]. The correlation in the non-patients was slightly higher than in the patients (0.74 [0.60–0.90] and 0.69 [0.52–0.81], respectively). Considering the ubiquity, convenience, and practicality of smartphones, the high correlation between the smartphones and the total daily step time-series highlights the potential usefulness of smartphones in detecting the change in the step counts in remote monitoring of the patient's physical activity

Access to health care, including physiotherapy, is increasingly occurring through virtual formats. At-home adherence to physical therapy programs is often poor and few tools exist to objectively measure low back physiotherapy exercise participation without the direct supervision of a medical professional. The aim of this study was to develop and evaluate the potential for performing automatic, unsupervised video-based monitoring of at-home low back physiotherapy exercises using a single mobile phone camera. 24 healthy adult subjects performed seven exercises based on the McKenzie low back physiotherapy program while being filmed with two smartphone cameras. Joint locations were automatically extracted using an open-source pose estimation framework. Engineered features were extracted from the joint location time series and used to train a support vector machine classifier (SVC). A convolutional neural network (CNN) was trained directly on the joint location time series data to classify exercises based on a recording from a single camera. The models were evaluated using a 5-fold cross validation approach, stratified by subject, with the class-balanced accuracy used as the performance metric. Optimal performance was achieved when using a total of 12 pose estimation landmarks from the upper and lower body, with the SVC model achieving a classification accuracy of 96±4% and the CNN model an accuracy of 97±2%. This study demonstrates the feasibility of using a smartphone camera and a supervised machine learning model to effectively assess at-home low back physiotherapy adherence. This approach could provide a low-cost, scalable method for tracking adherence to physical therapy exercise programs in a variety of settings

Advances in algorithms developed with sensor data from smart phones demonstrates the capacity to passively collect qualitative gait metrics. The purpose of this feasibility study was to assess the recovery of these metrics following joint reconstruction. A secondary data analysis of an ethics approved global, multicenter, prospective longitudinal study evaluating gait quality data before and after primary total knee arthroplasty (TKA, n=476), partial knee arthroplasty (PKA, n=139), and total hip arthroplasty (THA, n=395). A minimum 24 week follow-up was required (mean 45±12, range 24 - 78). Gait bouts and gait quality metrics (walking speed, step length, timing asymmetry, and double support percentage) were collected from a standardized smartphone operating system. Pre- and post-operative values were compared using paired-samples t-tests (p<0.05). A total of 595 females and 415 males with a mean age of 61.9±9.3 years and mean BMI of 30.2±6.1 kg/m. 2. were reviewed. Walking speeds were lowest at post-operative week two (all, p<.001). Speeds exceeded pre-operative means consistently by week 21 (p=0.015) for PKA, and week 13 (p=0.007) for THA. The average weekly step length was lowest in post-operative week two (all, p<0.001). PKA and THA cases achieved pre-operative step lengths by week seven (p=0.064) and week 9 (p=0.081), respectively. The average weekly gait asymmetry peaked at week two post-operatively (all, p <0.001). Return to pre-operative baseline asymmetry was achieved by week 11 (p=0.371) for TKA, week six (p=0.541) for PKA, and week eight (p=.886) for THA. Double limb support percentages peaked at week two (all, p<0.001) and returned to pre-operative levels by week 24 (p=0.089) for TKA, week 12 (p=0.156) for PKA, and week 10 (p=0.143) for THA. Monitoring gait quality in real-world settings following joint reconstruction using smartphones is feasible, and may provide the advantage of removing the Hawthorne effect related to typical gait assessments and in-clinic observations

Aims. Disorders of bone integrity carry a high global disease burden, frequently requiring intervention, but there is a paucity of methods capable of noninvasive real-time assessment. Here we show that miniaturized handheld near-infrared spectroscopy (NIRS) scans, operated via a smartphone, can assess structural human bone properties in under three seconds. Methods. A hand-held NIR spectrometer was used to scan bone samples from 20 patients and predict: bone volume fraction (BV/TV); and trabecular (Tb) and cortical (Ct) thickness (Th), porosity (Po), and spacing (Sp). Results. NIRS scans on both the inner (trabecular) surface or outer (cortical) surface accurately identified variations in bone collagen, water, mineral, and fat content, which then accurately predicted bone volume fraction (BV/TV, inner R. 2. = 0.91, outer R. 2. = 0.83), thickness (Tb.Th, inner R. 2. = 0.9, outer R. 2. = 0.79), and cortical thickness (Ct.Th, inner and outer both R. 2. = 0.90). NIRS scans also had 100% classification accuracy in grading the quartile of bone thickness and quality. Conclusion. We believe this is a fundamental step forward in creating an instrument capable of intraoperative real-time use. Cite this article: Bone Jt Open 2023;4(4):250–261

Artificial Intelligence (AI) is becoming more powerful but is barely used to counter the growth in health care burden. AI applications to increase efficiency in orthopedics are rare. We questioned if (1) we could train machine learning (ML) algorithms, based on answers from digitalized history taking questionnaires, to predict treatment of hip osteoartritis (either conservative or surgical); (2) such an algorithm could streamline clinical consultation. Multiple ML models were trained on 600 annotated (80% training, 20% test) digital history taking questionnaires, acquired before consultation. Best performing models, based on balanced accuracy and optimized automated hyperparameter tuning, were build into our daily clinical orthopedic practice. Fifty patients with hip complaints (>45 years) were prospectively predicted and planned (partly blinded, partly unblinded) for consultation with the physician assistant (conservative) or orthopedic surgeon (operative). Tailored patient information based on the prediction was automatically sent to a smartphone app. Level of evidence: IV. Random Forest and BernoulliNB were the most accurate ML models (0.75 balanced accuracy). Treatment prediction was correct in 45 out of 50 consultations (90%), p<0.0001 (sign and binomial test). Specialized consultations where conservatively predicted patients were seen by the physician assistant and surgical patients by the orthopedic surgeon were highly appreciated and effective. Treatment strategy of hip osteoartritis based on answers from digital history taking questionnaires was accurately predicted before patients entered the hospital. This can make outpatient consultation scheduling more efficient and tailor pre-consultation patient education

In absence of available quantitative measures, the assessment of fracture healing based on clinical examination and X-rays remains a subjective matter. Lacking reliable information on the state of healing, rehabilitation is hardly individualized and mostly follows non evidence-based protocols building on common guidelines and personal experience. Measurement of fracture stiffness has been demonstrated as a valid outcome measure for the maturity of the repair tissue but so far has not found its way to clinical application outside the research space. However, with the recent technological advancements and trends towards digital health care, this seems about to change with new generations of instrumented implants – often unfortunately termed “smart implants” – being developed as medical devices. The AO Fracture Monitor is a novel, active, implantable sensor system designed to provide an objective measure for the assessment of fracture healing progression (1). It consists of an implantable sensor that is attached to conventional locking plates and continuously measures implant load during physiological weight bearing. Data is recorded and processed in real-time on the implant, from where it is wirelessly transmitted to a cloud application via the patient's smartphone. Thus, the system allows for timely, remote and X-ray free provision of feedback upon the mechanical competence of the repair tissue to support therapeutic decision making and individualized aftercare. The device has been developed according to medical device standards and underwent extensive verification and validation, including an in-vivo study in an ovine tibial osteotomy model, that confirmed the device's capability to depict the course of fracture healing as well as its long-term technical performance. Currently a multi-center clinical investigation is underway to demonstrate clinical safety of the novel implant system. Rendering the progression of bone fracture healing assessable, the AO Fracture Monitor carries potential to enhance today's postoperative care of fracture patients

Smartphone-based apps that measure step-count and patient reported outcomes (PROMs) are being increasingly used to quantify recovery in total hip arthroplasty (THA). However, optimum patient-specific activity level before and during THA early-recovery is not well characterised. This study investigated 1) correlations between step-count and PROMs and 2) how patient demographics impact step-count preoperatively and during early postoperative recovery. Smartphone step-count and PROM data from 554 THA patients was retrospectively reviewed. Mean age was 64±10yr, BMI was 29±13kg/m2, 56% were female. Mean daily step count was calculated over three time-windows: 60 days prior to surgery (preop), 5–6 weeks postop (6wk), and 11–12 weeks postop (12wk). Linear correlations between step-count and HOOS12 Function and UCLA activity scores were performed. Patients were separated into three step-count levels: low (<2500steps/day), medium (2500-5500steps/day), and high (>5500steps/day). Age >65years, BMI >30, and sex were used for demographic comparisons. Student's t-tests determined significant differences in mean step-counts between demographic groups and in mean PROMs between step-count groups. UCLA correlated with step-count at all time-windows (p<0.01). HOOS12 Function correlated with step-count preoperatively and at 6wk (p<0.01). High vs low step count individuals had improved UCLA scores preoperatively (∆1.8,p<0.001), at 6wk (∆1.1,p<0.05), and 12wk (∆1.6,p<0.01), and improved HOOS12 Function scores preoperatively (∆8.4,p<0.05) and at 6wk (∆8.8,p<0.001). Younger patients had greater step-count preoperatively (4.1±3.0k vs 3.0±2.5k, p<0.01) and at 12wk (5.1±3.3k vs 3.6±2.9k, p<0.01). Males had greater step-count preoperatively (4.1±3.0k vs. 3.0±2.7k, p<0.001), at 6wk (4.5±3.2k vs 2.6±2.5k, p<0.001), and at 12wk (5.2±3.6k vs. 3.4±2.5k, p<0.001). Low BMI patients had greater step-count at 6wk (4.3±3.3k vs. 2.6±2.7k, p<0.01) and 12wk (5.0±3.6k vs. 3.6±2.6k, p<0.05). Daily step-count is significantly impacted by patient demographics and correlates with PROMs, where patients with high step count exhibit improved PROMs. Generic recovery profiles may therefore not be appropriate for benchmarking across diverse populations

Passive smartphone-based apps are becoming more common for measuring patient progress after total knee arthroplasty (TKA). Optimum activity levels during early TKA recovery haven't been well documented. This study investigated correlations between step-count and patient reported outcome measures (PROMs) and how demographics impact step-count preoperatively and during early post-operative recovery. Smartphone capture step-count data from 357 TKA patients was retrospectively reviewed. Mean age was 68±8years. 61% were female. Mean BMI was 31±6kg/m2. Mean daily step count was calculated over three time-windows: 60 days prior to surgery (preop), 5-6 weeks postop (6wk), and 11-12 weeks postop (12wk). Linear correlations between step-count and KOOS12-function and UCLA activity scores were performed. Patients were separated into three step-count levels: low (<1500steps/day), medium (1500-4000steps/day), and high (>4000steps/day). Age >65years, BMI >30kg/m2, and sex were used for demographic comparisons. Student's t-tests determined significant differences in mean step-counts between demographic groups, and in mean PROMs between step-count groups. UCLA correlated with step-count at all time-windows (p<0.01). KOOS12-Function correlated with step-count at 6wk and 12wk (p<0.05). High step-count individuals had improved PROMs compared to low step-count individuals preoperatively (UCLA: ∆1.4 [p<0.001], KOOS12-Function: ∆7.3 [p<0.05]), at 6wk (UCLA: ∆1 [p<0.01], KOOS12-Function: ∆7 [p<0.05]), and at 12wk (UCLA: ∆0.8 [p<0.05], KOOS12-Function: ∆6.5 [p<0.05]). Younger patients had greater step-count preoperatively (3.8±3.0k vs. 2.5±2.3k, p<0.01), at 6wk (3.1±2.9k vs. 2.2±2.3k, p<0.05) and at 12wk (3.9±2.6k vs. 2.8±2.6k, p<0.01). Males had greater step-count preoperatively (3.7±2.6k vs. 2.5±2.6k, p<0.001), at 6wk (3.6±2.6k vs. 1.9±2.4k, p<0.001), and at 12wk (3.9±2.3 vs. 2.8±2.8k, p<0.01). No differences in step-count were observed between low and high BMI patients at any timepoint. High step count led to improved PROMs scores compared to low step-count. Early post-operative step-count was significantly impacted by age and sex. Generic recovery profiles may not be appropriate across a diverse population

Abstract. Patient Reported Outcome Measures (PROMs) can be completed using paper and postal services (pPROMS) or via computer, tablet or smartphone (ePROMs). We have investigated whether there are differences in scores depending on the method of PROMs acquisition for the Oxford Knee (OKS) and the EQ-5D scores, at one and two years post operatively. Patient demographics, mode of preferred data collection and pre-and post-operative PROMs for Total Knee Replacements (TKRs) performed between 1st January 2018 and 31st December 2018 were collected. During the study period, 1573 patients underwent TKRs. The average OHS and EQ-5D pre-operatively scores was 19.47 and 0.40 respectively. 71.46% opted to undertake post-operative questionnaires using ePROMs. The remaining 28.54% opted for pPROMS. The one and two-year OHS for ePROMS patients increased to 37.64 and 39.76 while the OHS scores for pPROMS patients were 35.71 and 36.83. At the one and two-year post-operative time intervals, a Mann-Whitney test showed statistical significance between the modes of administration for OHS (P-Value = 0.044 and 0.01 respectively). The one and two-year EQ-5D for ePROMS patients increased to 0.76 and 0.78 while the EQ-5D scores for pPROMS patients were 0.73 and 0.76. The P-Value for Mann-Whitney tests comparing the modes of administration for EQ-5D were 0.04 and 0.07 respectively. There is no agreed mode of PROMs data acquisition for the OKS and EQ-5D Scores. While we have demonstrated an apparent difference in scores depending on the mode of administration, further work is required to establish the influence of potentially confounding factors