Objective:To analyze the changes of DNA methylation in peripheral blood mononuclear cells (PBMC) of patients with hepatocellular carcinoma (HCC) and to evaluate the clinical value of a combined model based on FSIP1 gene methylation on the early diagnosis of HCC.Methods:This is a case-control study. From May 2023 to September 2024, 183 HCC patients and 155 healthy controls were collected in Qilu Hospital of Shandong University. The selected study subjects were divided into three cohorts: 14 HCC patients and 39 healthy controls formed the discovery cohort, a screening cohort consisted of 36 HCC patients and 39 healthy controls, 133 HCC patients and 77 healthy controls were included in the model construction cohort. 935k methylation chip analysis was used to identify specific differentially methylated sites in peripheral blood PBMC of the discovery cohort. The absolute value of the average methylation level difference between HCC group and healthy control group (|Δβ|) and P value were calculated. Then targeted bisulfite sequencing was used to verify the differentially methylated sites in the screening cohort. Finally, based on MethylTarget methylation sequencing technology, differential methylation sites were further verified in model construction cohort (divided into training set and validation set, training set consisted of 99 HCC patients and 57 healthy controls; validation set consisted of 34 HCC patients and 20 healthy controls). HCC early diagnosis model was constructed by random forest algorithm combined with clinical parameters and the diagnostic performance of the model was evaluated by receiver operating characteristic (ROC) curve in the validation set. Results:The total of 7 249 differentially methylated sites between HCC patients and healthy controls in discovery cohort were selected under the rule of |Δβ|≥0.06 and P<0.01. Among them, the cg02155073 site located on FSIP1 was hypermethylated in PBMC of HCC patients in the screening cohort and model cohort ( P<0.001). The AUC of HCC early diagnosis model (FmAP) based on FSIPI in the validation set was 0.967 (95% CI 0.924-1.000); sensitivity was 88%, specificity was 95%. The model had good diagnostic efficacy for patients with early HCC, stage Ⅰ-Ⅱ HCC AUC was 0.958 (95% CI 0.898-1.000). The FmAP model also had diagnostic value for tumor size <2 cm HCC and AFP negative HCC, with AUC of 0.955 (95% CI 0.898-1.000) and 0.964 (95% CI 0.934-0.994).The sensitivity were 92% and 93% and specificity both were 84%. Conclusion:The FmAP model based on FSIP1 gene methylation has good clinical value for the early diagnosis of hepatocellular carcinoma.

Objective To analyze the developmental trends and research hotspots of anoikis in cancer research from 2005 to 2024.Methods Relevant literature was retrieved from the Web of Sci-ence Core Collection.Visualization tools including CiteSpace,VOSviewer and SCImago Graphica were employed to analyze publication volume,countries,institutions,authors,journals,keywords and other bibliometric indicators.Results A total of 2,252 articles were included in this study,showing an overall upward trend in publication volume,with a notable increase after 2012.China and the United States ranked highest in terms of publication volume and citation frequency.Representative institutions included Shanghai Jiao Tong University,Chulalongkorn University and MD Anderson Cancer Center,while a representative scholar was CHANVORACHOTE Pithi.The core journal was Oncogene.Keyword and co-citation analyses revealed that research focused on genetic characteristics,cancer treatment,prognostic prediction and metabolic reprogramming,with core terms including"ex-pression""metastasis"and"anoikis".Conclusion Research interest in the field of anoikis contin-ues to rise,with future directions focusing on drug resistance mechanisms,the tumor microenvironment,immunotherapy,signaling pathways and epithelial-mesenchymal transition(EMT).

Objective:To analyze the changes of DNA methylation in peripheral blood mononuclear cells (PBMC) of patients with hepatocellular carcinoma (HCC) and to evaluate the clinical value of a combined model based on FSIP1 gene methylation on the early diagnosis of HCC.Methods:This is a case-control study. From May 2023 to September 2024, 183 HCC patients and 155 healthy controls were collected in Qilu Hospital of Shandong University. The selected study subjects were divided into three cohorts: 14 HCC patients and 39 healthy controls formed the discovery cohort, a screening cohort consisted of 36 HCC patients and 39 healthy controls, 133 HCC patients and 77 healthy controls were included in the model construction cohort. 935k methylation chip analysis was used to identify specific differentially methylated sites in peripheral blood PBMC of the discovery cohort. The absolute value of the average methylation level difference between HCC group and healthy control group (|Δβ|) and P value were calculated. Then targeted bisulfite sequencing was used to verify the differentially methylated sites in the screening cohort. Finally, based on MethylTarget methylation sequencing technology, differential methylation sites were further verified in model construction cohort (divided into training set and validation set, training set consisted of 99 HCC patients and 57 healthy controls; validation set consisted of 34 HCC patients and 20 healthy controls). HCC early diagnosis model was constructed by random forest algorithm combined with clinical parameters and the diagnostic performance of the model was evaluated by receiver operating characteristic (ROC) curve in the validation set. Results:The total of 7 249 differentially methylated sites between HCC patients and healthy controls in discovery cohort were selected under the rule of |Δβ|≥0.06 and P<0.01. Among them, the cg02155073 site located on FSIP1 was hypermethylated in PBMC of HCC patients in the screening cohort and model cohort ( P<0.001). The AUC of HCC early diagnosis model (FmAP) based on FSIPI in the validation set was 0.967 (95% CI 0.924-1.000); sensitivity was 88%, specificity was 95%. The model had good diagnostic efficacy for patients with early HCC, stage Ⅰ-Ⅱ HCC AUC was 0.958 (95% CI 0.898-1.000). The FmAP model also had diagnostic value for tumor size <2 cm HCC and AFP negative HCC, with AUC of 0.955 (95% CI 0.898-1.000) and 0.964 (95% CI 0.934-0.994).The sensitivity were 92% and 93% and specificity both were 84%. Conclusion:The FmAP model based on FSIP1 gene methylation has good clinical value for the early diagnosis of hepatocellular carcinoma.

OBJECTIVE: To use the low-cost anesthesia monitor for realizing anesthesia depth monitoring, effectively assist anesthesiologists in diagnosis and reduce the cost of anesthesia operation. METHODS: Propose a monitoring method of anesthesia depth based on artificial intelligence. The monitoring method is designed based on convolutional neural network (CNN) and long and short-term memory (LSTM) network. The input data of the model include electrocardiogram (ECG) and pulse wave photoplethysmography (PPG) recorded in the anesthesia monitor, as well as heart rate variability (HRV) calculated from ECG, The output of the model is in three states of anesthesia induction, anesthesia maintenance and anesthesia awakening. RESULTS: The accuracy of anesthesia depth monitoring model under transfer learning is 94.1%, which is better than all comparison methods. CONCLUSIONS The accuracy of this study meets the needs of perioperative anesthesia depth monitoring and the study reduces the operation cost.
Artificial Intelligence ; Neural Networks, Computer ; Heart Rate ; Electrocardiography ; Photoplethysmography/methods* ; Anesthesia

OBJECTIVE: In order to improve the accuracy of the current pulmonary nodule location detection method based on CT images, reduce the problem of missed detection or false detection, and effectively assist imaging doctors in the diagnosis of pulmonary nodules. METHODS: Propose a novel method for detecting the location of pulmonary nodules based on multiscale convolution. First, image preprocessing methods are used to eliminate the noise and artifacts in lung CT images. Second, multiple adjacent single-frame CT images are selected to be concatenate into multi-frame images, and the feature extraction is carried out through the artificial neural network model U-Net improved by multi-scale convolution to enhanced feature extraction capability for pulmonary nodules of different sizes and shapes, so as to improve the accuracy of feature extraction of pulmonary nodules. Finally, using point detection to improve the loss function of U-Net training process, the accuracy of pulmonary nodule location detection is improved. RESULTS: The accuracy of detecting pulmonary nodules equal or larger than 3 mm and smaller than 3 mm are 98.02% and 96.94% respectively. CONCLUSIONS This method can effectively improve the detection accuracy of pulmonary nodules on CT image sequence, and can better meet the diagnostic needs of pulmonary nodules.
Humans ; Lung Neoplasms/diagnostic imaging* ; Solitary Pulmonary Nodule/diagnostic imaging* ; Tomography, X-Ray Computed ; Neural Networks, Computer

Spinal cord injury is a catastrophic injury causing lifelong severe disabilities, and poses a great burden to the individuals, families and society. In order to promote the standardization in treatment of traumatic spinal cord injury, the consensus on the evaluation, treatment and rehabilitation of traumatic spinal cord injury was suggested by experts, who came from authoritative multicenter in China. The expert consensus, which formed a standardization process from the first aid clinical treatment to rehabilitation of spinal cord injury, shall give a better practical guide for clinic and rehabilitation physicians.