The aim of this research is to create a medical expert system based on Bayes theorem to diagnose level of disc hernia based on real foot force measurement signals obtained using sensors and implement the whole system on field programable gate array (FPGA). We have created a database of attributes based on recorded foot force values of 33 patients pre-diagnosed with herniated disc on levels L4/L5 or L5/S1 on the left or right side. The results obtained by software (Matlab) and hardware (FPGA simulation) are matching well, achieving high accuracy, which shows that VHDL implementation of Naïve Bayes theorem for disc hernia diagnostics is adequate. The output on FPGA is easy to understand for any user, as it is implemented as four-bit output where the position of bit value 1 indicates the level of disc herniation. The system is able to distinguish between the healthy subjects and subjects with disc herniation and is able to detect if improvement in stability is present after surgery or physical therapy. Our proposed measurement platform can be coupled with FPGA to create a portable and not expensive tool for real time signal acquisition, processing and decision support system in disc hernia diagnosis and post-surgical recovery.

本研究的目的是创建一个基于贝叶斯定理的医学专家系统，根据传感器获得的真实足力测量信号来诊断椎间盘突出的程度，并将整个系统实现在现场可编程门阵列（FPGA）上。我们根据 33 名预先诊断为左侧或右侧 L4/L5 或 L5/S1 水平椎间盘突出症的患者记录的足力值创建了一个属性数据库。软件（Matlab）和硬件（FPGA仿真）得到的结果匹配良好，精度高，这表明朴素贝叶斯定理的VHDL实现对椎间盘突出症的诊断是足够的。FPGA 上的输出对于任何用户来说都很容易理解，因为它被实现为四位输出，其中位值 1 的位置表示椎间盘突出的程度。该系统能够区分健康受试者和椎间盘突出症受试者，并能够检测手术或物理治疗后稳定性是否有所改善。我们提出的测量平台可以与 FPGA 相结合，为椎间盘突出症诊断和术后恢复中的实时信号采集、处理和决策支持系统创建一个便携式且不昂贵的工具。