Myography – the measurement and recording of muscular activity – finds applications across diverse fields, such as biomechanics, clinical neurophysiology or electrodiagnostic medicine, rehabilitation, sports science, and human-machine interaction.1 Non-invasive myography methods include surface EMG (sEMG, where electrodes are placed on the skin to measure electrical signals during muscle actuation) and force myography (FMG). While sEMG is more broadly explored than FMG, it suffers from limited resolution, signal crosstalk, and skin impedance issues.2 sEMG requires proper skin preparation and electrode placement in order to reduce skin impedance and collect accurate data, making it difficult for home use by general public.3 Furthermore, if one is interested in translating the sEMG signal to muscle forces applied or actions done, as most applications are, the signal needs to be of high quality collected at high sampling rates and needs to be heavily processed.4 On the other hand, FMG measures the position or movement of a limb based on changes in stiffness of the corresponding musculotendinous complex against the default state.5 It offers an attractive alternative to sEMG due to direct measurement of force, user-friendly and less sensitivity to skin impedance, reduced cross talk and robustness in dynamic environments, and high compatibility with prosthetics and exoskeletons.6 While there has been significant progress in FMG devices, existing platforms are still bulky and restrictive to the user.5 A highly flexible and skin conformal sensor system is needed to improve the system's wearability and its integration into other components such as prosthetics. To achieve skin conformality in wearable devices, laser induced graphene (LIG) has emerged as a suitable material owing to its ease of fabrication, cost-effective materials, and tunable properties.7 To the best of our knowledge, skin conformal FMG sensors, especially based on LIG have not been explored. In this work, we developed a skin conformal FMG wearable device based on LIG, capable of continuous strain measurement across the circumference of the forearm for gesture recognition. LIG writing parameters are optimized to obtain a 100-micron highly fibrous film enabling easier transfer. After creating LIG on polyimide, it is transferred onto medical grade polyurethane (MPU) to obtain highly skin conformal and stretchable devices. The sensor system consists of an array of nine individual strain sensors, designed to be placed along the circumference of the forearm. Each strain sensor is connected to an integrated wireless readout system which constantly measures their resistance. Different gestures are performed by the user with the sensor system worn on the forearm. Gestures include individual finger flexions, wrist movements, wrist clenches, and forearm pronation/supination. Upon muscle actuation, each sensor experiences a different strain profile depending on its location with respect to the actuated muscle group. The temporal data associated with each action is analyzed to extract features for training a machine learning (ML)-based classifier. Using the ML model, the system can successfully distinguish among various gestures with a high accuracy (> 97%). Further performance improvement can be achieved by increasing the density of sensors and integrating other piezoresistive materials with LIG to enhance the strain sensitivity. Future work also includes integration with other wearable sensors for simultaneous recording of temperature, pH, and metabolites to achieve a multisensory system for improved health monitoring. References 1 D. F. Stegeman, J. H. Blok, H. J. Hermens and K. Roeleveld, Journal of Electromyography and Kinesiology, 2000, 10, 313–326.2 A. Ranavolo, M. Serrao and F. Draicchio, Front Neurol, 2020, 11, 572069.3 M. L. Delva, K. Lajoie, M. Khoshnam and C. Menon, Biomed Eng Online, 2020, 19, 1–18.4 D. Staudenmann, K. Roeleveld, D. F. Stegeman and J. H. van Dieen, Journal of Electromyography and Kinesiology, 2010, 20, 375–387.5 Z. G. Xiao and C. Menon, Sensors 2019, Vol. 19, Page 4557, 2019, 19, 4557.6 A. Radmand, E. Scheme and K. Englehart, 2016, 53, 443–456.7 R. Ye, D. K. James and J. M. Tour, , DOI:10.1021/acs.accounts.8b00084.