Machine learning prediction model for gray-level co-occurrence matrix features of synchronous liver metastasis in colorectal cancer

BACKGROUND Synchronous liver metastasis(SLM)is a significant contributor to morbidity in colorectal cancer(CRC).There are no effective predictive device integration algorithms to predict adverse SLM events during the diagnosis of CRC.AIM To explore the risk factors for SLM in CRC and construct a visual prediction model based on gray-level co-occurrence matrix(GLCM)features collected from magnetic resonance imaging(MRI).METHODS Our study retrospectively enrolled 392 patients with CRC from Yichang Central People’s Hospital from January 2015 to May 2023.Patients were randomly divided into a training and validation group(3:7).The clinical parameters and GLCM features extracted from MRI were included as candidate variables.The prediction model was constructed using a generalized linear regression model,random forest model(RFM),and artificial neural network model.Receiver operating characteristic curves and decision curves were used to evaluate the prediction model.RESULTS Among the 392 patients,48 had SLM(12.24%).We obtained fourteen GLCM imaging data for variable screening of SLM prediction models.Inverse difference,mean sum,sum entropy,sum variance,sum of squares,energy,and difference variance were listed as candidate variables,and the prediction efficiency(area under the curve)of the subsequent RFM in the training set and internal validation set was 0.917[95%confidence interval(95%CI):0.866-0.968]and 0.09(95%CI:0.858-0.960),respectively.CONCLUSION A predictive model combining GLCM image features with machine learning can predict SLM in CRC.This model can assist clinicians in making timely and personalized clinical decisions.

Paeoniflorin inhibits human gastric carcinoma cell proliferation through up-regulation of microRNA-124 and suppression of PI3K/Akt and STAT3 signaling

AIM: To examine the potential anti-tumor activity of paeoniflorin in the human gastric carcinoma cell line MGC-803.METHODS: Cell viability and cytotoxic effects in MGC-803 cells were analyzed using a 3-(4,5-dimethylthiazol-2-yl)-2,5-diphenyltetrazolium bromide and lactate dehydrogenase assay, respectively. Cell apoptosis of MGC-803 cells was measured using flow cytometry,DAPI staining assay and caspase-3 activity assay.Quantitative reverse transcription-polymerase chain reaction(RT-PCR) was used to measure the expression of microRNA-124(miR-124) in response to paeoniflorin.The expression of phosphatidylinositol 3-kinase(PI3K),protein kinase B(Akt), phospho-Akt(p-Akt) and phospho-signal transducer and activator of transcription3(p-STAT3) were also measured by quantitative RTPCR and Western blot analysis in normal, miR-124 and anti-miR-124 over-expressing MGC-803 cells, treated with paeoniflorin.RESULTS: Paeoniflorin was found to inhibit MGC-803 cell viability in a dose-dependent manner. Paeoniflorin treatment was associated with the induction of apoptosis and caspase-3 activity in MGC-803 cells. Paeoniflorin treatment significantly increased miR-124 levels and inhibited the expression of PI3 K, Akt, p-Akt and p-STAT3 in MGC-803 cells. Interestingly, the over-expression of miR-124 inhibits PI3K/Akt and phospho-STAT3 expressions in MGC-803 cells. PI3 K agonist(IGF-1, 1μg/10 μL) or over-expression of STAT3 reversed the effect of paeoniflorin on the proliferation of MGC-803 cells. Over-expression of anti-miR-124 in MGC-803 cells reversed paeoniflorin-induced up-regulation.CONCLUSION: In summary, the in vitro data suggest that paeoniflorin is a potential novel therapeutic agent against gastric carcinoma, which inhibits cell viability and induces apoptosis through the up-regulation of miR-124 and suppression of PI3K/Akt and STAT3 signaling.

miR-132 inhibits colorectal cancer invasion and metastasis via directly targeting ZEB2

AIM:To investigate the biological role and underlying mechanism of miR-132 in colorectal cancer(CRC)progression and invasion.METHODS:Quantitative RT-PCR analysis was used to examine the expression levels of miR-132 in five CRC cell lines(SW480,SW620,HCT116,HT29 and LoVo)and a normal colonic cell line NCM460,as well as in tumor tissues with or without metastases.The KaplanMeier method was used to analyze the prognostic significance of miR-132 in CRC patients.The biological effects of miR-132 were assessed in CRC cell lines using the transwell assay.Quantitative RT-PCR and western blot analyses were employed to evaluate the expression of miR-132 targets.The regulation of ZEB2 by miR-132was confirmed using the luciferase activity assay.RESULTS:miR-132 was significantly down-regulated in the CRC cell lines compared with the normal colonic cell line(P<0.05),as well as in the CRC tissues withdistant metastases compared with the tissues without metastases(10.52±4.69 vs 23.11±7.84)(P<0.001).Down-regulation of miR-132 was associated with tumor size(P=0.016),distant metastasis(P=0.002),and TNM stage(P=0.020)in CRC patients.Kaplan-Meier survival curve analysis indicated that patients with low expression of miR-132 tended to have worse diseasefree survival than patients with high expression of miR-132(P<0.001).Moreover,ectopic expression of miR-132 markedly inhibited cell invasion(P<0.05)and the epithelial-mesenchymal transition(EMT)in CRC cell lines.Further investigation revealed ZEB2,an EMT regulator,was a downstream target of miR-132.CONCLUSION:Our study indicated that miR-132 plays an important role in the invasion and metastasis of CRC.