Identifying an optimal machine learning model generated circulating biomarker to predict chronic postoperative pain in patients undergoing hepatectomy

• DOI: 10.3389/fsurg.2022.1068321
• Publication Date: 2023-01-06T07:50:36Z
• Authors: Ying Hong; Yue Li; Mao Ye; Siyu Yan; Wei Yang; Chunling Jiang
• Keywords: MMP3

Chronic postsurgical pain (CPSP) after hepatectomy is highly prevalent and challenging to treat. Several risk factors have been unmasked for CPSP hepatectomy, such as acute postoperative pain. The current secondary analysis of a clinical study sought extend previous research by investigating more variables inflammatory biomarkers sifting those strongly related build reliable machine learning model predict occurring. Participants included 91 adults undergoing who was followed 3 months postoperatively. Twenty-four hours surgery, participants completed numerical rating scale (NRS) grading blood sample collecting. Three also reported whether occurred through follow-up. Random Forest Support Vector Machine models were conducted outcomes surgery. results showed that the SVM had better performance in predicting which consists (evaluated NRS) matrix metalloprotease (MMP3) level. What's more, besides traditional cytokines, several novel like C-X-C motif chemokine ligand 10 (CXCL10) MMP2 levels found be closely spectrum created. These findings demonstrate consisting MMP3 level predicts greater chronic intensity with this model, intervention administration before occurs may prevent or minimize successfully.