Design, Simulations and Tests of a Novel Force and Moments Sensor for Instrumented Knee Implants.

OBJECTIVES: Early identification of mechanical complications of total knee arthroplasties is of great importance to minimize the complexity and iatrogenicity of revision surgeries. There is therefore a critical need to use smart knee implants during intra or postoperative phases. Nevertheless, these devices are absent from commercialized orthopaedic implants, mainly due to their manufacturing complexity. We report the design, simulations and tests of a force and moments sensor integrated inside the tibial tray of a knee implant. METHODS: By means of a "tray-pillar-membrane" arrangement, strain gauges and metal additive technology, our device facilitates the manufacturing and assembly steps of the complete system. We used finite element simulations to optimize the sensor and we compared the simulation results to mechanical measurements performed on a real instrumented tibial tray. RESULTS: With a low power acquisition electronics, the measurements corroborate with simulations for low vertical input forces. Additionally, we performed ISO fatigue testings and high force measurements, with a good agreement compared to simulations but high non-linearities for positions far from the tray centre. In order to estimate the center of pressure coordinates and the normal force applied on the tray, we also implemented a small-size artificial neural network. CONCLUSION: This work shows that relevant mechanical components acting on a tibial tray of a knee implant can be measured in an easy to assemble, leak-proof and mechanically robust design while offering relevant data usable by clinicians during the surgical or rehabilitation procedures. SIGNIFICANCE: This work contributes to increase the technological readiness of smart orthopaedic implants.

Analysis of Graphomotor Tests with Machine Learning Algorithms for an Early and Universal Pre-Diagnosis of Dysgraphia.

Five to ten percent of school-aged children display dysgraphia, a neuro-motor disorder that causes difficulties in handwriting, which becomes a handicap in the daily life of these children. Yet, the diagnosis of dysgraphia remains tedious, subjective and dependent to the language besides stepping in late in the schooling. We propose a pre-diagnosis tool for dysgraphia using drawings called graphomotor tests. These tests are recorded using graphical tablets. We evaluate several machine-learning models and compare them to build this tool. A database comprising 305 children from the region of Grenoble, including 43 children with dysgraphia, has been established and diagnosed by specialists using the BHK test, which is the gold standard for the diagnosis of dysgraphia in France. We performed tests of classification by extracting, correcting and selecting features from the raw data collected with the tablets and achieved a maximum accuracy of 73% with cross-validation for three models. These promising results highlight the relevance of graphomotor tests to diagnose dysgraphia earlier and more broadly.