Description:
Reference #: 1680
The University of South Carolina is offering licensing opportunities for Predicting biomaterial-implant surgical outcome using medical record and blood-cytokine data.
Background:
Pelvic organ prolapse (POP), defined as symptomatic descent of the vagina and surrounding pelvic organs, affects approximately 50% of parous women and 6% of nonparous women between ages 20 and 59 years, with almost 300,000 POP surgeries performed per year. To reduce anatomical recurrence, surgical treatment may include the insertion of polypropylene mesh into the vaginal wall to provide mechanical support and reinforcement of the prolapsed organs. Unfortunately, postsurgical mesh complication, predominantly mesh exposure through the vaginal wall, occurs with some frequency and results in decreased quality of life, leaving patients with costly residual symptoms and emotional distress. These complications are marked by inflammatory responses associated with abnormal levels of mesh-induced cytokine response. While some degree of mesh-induced cytokine response is necessary for successful implantation, excess or unattenuated cytokine response could result in chronic inflammation and implant rejection. The balance between proinflammatory and anti-inflammatory agents is critical in achieving successful mesh implantation, and this balance may be influenced by the individual's response to the implant material. Thus, leveraging a patient’s immune response to the biomaterial could facilitate the prediction of postsurgical outcomes. Leveraging a patient-specific, multifaceted immune response for the prediction of postsurgical complications is an ideal problem for the application of principal component analysis (PCA) and supervised machine learning models.
Invention Description:
This invention is a method for evaluating post-surgical success in relation to mesh-induced complications by comparing a patient’s cytokine patters along with patient medical record data using Principal Component Analysis (PCA) and Supervised Machine Learning Models. This approach provides information about whether a patient might have an adverse surgical outcome.
Potential Applications:
Surgical analysis, prognosis analysis, prediction of desired outcomes involving in relation to surgical procedures.
Advantages and Benefits:
This innovation provides a not yet available means by which to minimize risk of adverse outcomes following biomaterial implant surgery, including but not limited to surgery to correct pelvic organ prolapse (POP).