BACKGROUND:Basic research demonstrated that type Ⅰ collagen exhibited prominent effect on osteogenesis,bone mass and bone fracture,which also participated in the bone fusion.However,few reports concerning the polymorphism of type Ⅰ collagen gene and spinal fusion.OBJECTIVE:To investigate the polymorphism of type Ⅰ collagen and to explore its relationship with the spinal fusion rate following metal implant or autogenous bone transplantation.METHODS:A total of 200 volunteers who need to receive spinal fusion in the Affiliated Hospital of Qingdao University Medical College were selected,including 102 cases received anterior cervical subcorpectomy combined with lilac bone implantation fusion following decompression,and 98 cases received posterior laminectomy for decompression combined with intertransverse process fusion.Meantime,223 normal adults were served as the control group.The peripheral blood was drawn-off and genomic DNA was extracted from white blood cells.The specific fragment which includes the objective gene was amplified by polymerase chain reaction (PCR),with length of 293 bp.The genotypes of Pcol2 site in type Ⅰ collagen were detected by PCR-restriction fragment length polymorphism (PCR-RFLP) method.The PCR product was digested with restriction endonuclease Eco311 and the result was observed by agarose gel electrophoresis.The G gene represented for the presence of the restriction endonuclease site,while the T gene for the absence of the restriction endonuclease site.The fusion rate of the bone graft was evaluated by x-ray film prior to and at months 3,6 and 12 after operation,and the results were compared by stages including quick (＜3 months),middle (3-6 months) and slow (6-12 months).RESULT AND CONCLUSION:There were the-1997G/T polymorphisms of the type Ⅰ collagen gene in 423 cases,including 166cases with GG,232 cases with GT,and 25 cases with TT,in addition,there was some correlation between the GG genotype and the lilac bone implantation fusion (P =0.004).The GG genotype accounted for 50% in the fast group,which was obviously greater than that of the middle and slow groups (33.3% and 16.7%,respectively).However,the-1997G/T polymorphisms had no correlation with the bone graft fusions inter transverse process of lumbar vertebra (P=0.831).The GG genotype in the-1997G/T polymophsim of the type Ⅰ collagen gene may be the essential factor which can promote the C-spine auto-ilium graft fusion.

Objective To construct a model of heart failure risk prediction based on four machine learning algo-rithms in order to support early diagnosis and intervention.Methods After reviewing the heart failure dataset pub-lished on the Kaggle community,feature selection was used to select relevant factors related to heart failure as pre-dictive indicators.Four machine learning algorithms,namely logistic regression,support vector machine,random forest,and XGBoost were selected to establish predictive models.Compared and analyzed its accuracy,precision,recall,F1 score and area under the ROC curve(AUC)to verify the performance of the model.Results The study analyzed 11 features of 918 patients with heart failure and selected 10 feature factors for modeling.After optimizing the hyper-parameters through grid search,the XGBoost model performed the best,with accuracy,precision,recall,and f1_score and AUC values were 87.5%,90.38%,89.71%,90.04%and 0.93,respectively.In addition,data analysis showed that exercise ST slope,chest pain type,and exercise induced angina were main influencing factors for heart failure.Conclusions The XG Boost model has the best predictive tool for heart failure,and machine learning algorithms may support early prevention,early diagnosis as well as control of heart failure.