Due to the necessity for flexibility without compromising the Li-ion battery (LIB) state of health (SOH), LIB is a critical challenge for flexible hybrid electronic (FHE) devices. A thin form factor-based LIB with a thickness of less than 1 mm is regarded as the candidate material to suit such demands since it can be folded, bent, and twisted with minimal performance loss. Furthermore, LIB has high specific power (W/Kg) and specific energy (Wh/Kg), as well as a smaller memory effect, making it more appealing for wearable applications. While much research has been done on the chemo-physical effects of repeated charging and discharging LIB, such as solid electrolyte interphase (SEI) development, material deterioration, and so on, but such impacts owing to repeated flexure LIB have not been much studied. The deterioration of the reliability of thin-flexible power sources was investigated in this work under twist, flexing, and flex-to-install to simulate stresses of daily motions of the human body by utilizing motion-control setups in a lab setting. Furthermore, an AI-based regression model has been developed to forecast the SOH of the battery based on many variables such as physical, atmospheric, and chemo-mechanical experimental circumstances that may be difficult to address by manpower. Based on the various variables and their interactions, the generated models are expected to be used to predict battery life and assess the acceleration factors between test circumstances and usage conditions for a range of test scenarios.