Study on Automatic Multi-Classification of Spine Based on Deep Learning and Postoperative Infection Screening.

Area of Science:

• Neurosurgery
• Pain Management
• Medical Imaging

Background:

• Accurate preoperative diagnosis of intervertebral foramen stenosis is crucial for effective pain management and recovery after spinal fusion.
• Current diagnostic methods lack sufficient research and effective tools for clinicians.
• Computer-aided diagnosis can improve accuracy and efficiency in identifying spinal stenosis.

Purpose of the Study:

• To propose a deep learning algorithm for automatic grading of intervertebral foramen stenosis from MRI images.
• To evaluate the effectiveness of multimodal analgesia nursing in controlling postoperative pain after spinal fusion.
• To compare patient satisfaction with pain control between multimodal and routine analgesic nursing.

Main Methods:

• A deep learning algorithm was developed to grade intervertebral foramen stenosis using MRI images.
• Eighty-six patients undergoing spinal fusion were randomized into control (routine nursing) and multimodal groups.
• Pain levels (VAS) and satisfaction scores were assessed post-operatively.

Main Results:

• The multimodal analgesia nursing group showed significantly lower VAS scores compared to the control group (P < 0.05).
• Patient satisfaction with pain control was significantly higher in the multimodal group (P < 0.05).
• The deep learning algorithm aimed to improve diagnostic accuracy for spinal stenosis.

Conclusions:

• Multimodal analgesia nursing is effective in reducing postoperative pain after spinal fusion.
• This nursing approach enhances patient satisfaction with pain management.
• The study highlights the potential of deep learning in diagnosing spinal stenosis and the benefits of multimodal pain management strategies.