Risk prediction and an injectable collagen material for intervertebral disc degeneration

Abstract

This research primarily focuses on early prediction and treatment for intervertebral disc degeneration (IVDD). In Phase 1, machine learning algorithms were evaluated to predict the risk of intervertebral disc degeneration in patients. This was done by using factors associated with IVDD and taken from patient medical history. Several classification algorithms were utilized to develop predictive models. Results demonstrated that machine learning algorithms could be used to predict IVDD risk and also the potential for developing an app from these predictive models. Phase 2 focused on the development of a collagen-based, gold nanoparticle material for intervertebral disc regeneration. Gold nanoparticles were conjugated to viscoelastic collagen using a natural crosslinker, genipin. This material was then characterized to evaluate its ability to serve as a treatment for chronic back pain caused by IVDD. Results demonstrated successful attachment of the gold nanoparticles to the collagen using the genipin crosslinker. Overall, the characterization studies of the collagen composite were successful and demonstrated potential for further application in IVDD treatment.