Diagnosis Of Early Gastric Cancer Research Articles

A prospective and comparative study on improving the diagnostic accuracy of early gastric cancer based on deep convolutional neural network real-time diagnosis system (with video).

Endoscopic diagnosis of early gastric cancer (EGC) is a challenge. It is not clear whether deep convolutional neural network (DCNN) model could improve the endoscopists' diagnostic performance. We established a DCNN-assisted system and found that accuracy of diagnosis is higher than endoscopists. We prospectively collected an independent image test set of 1289 images and a video test set of 130 patients from three endoscopic centers to compare the diagnostic efficacy of 12 endoscopists before and after DCNN model assistance. Accuracy, sensitivity, specificity, time, and AUC were the main indicators for comparison. The DCNN model discriminated EGC from the control group (including ulcers and chronic gastritis) with an AUC of 0.917, a sensitivity of 93.38% (95% CI 91.09-95.12%), and a specificity of 90.07% (95% CI 87.59-92.10%) in the image dataset. The video test dataset have an AUC of 0.930, a sensitivity of 96.92% (95% CI 88.83-99.78%), and a specificity of 89.23% (95% CI 79.11-94.98%). The diagnostic performance of novice endoscopists was comparable to those of expert endoscopists with the DCNN model's assistance (accuracy: 95.22 vs. 96.16%) in image test dataset. In the video test, the novice endoscopists, accuracy after DCNN assistance was also improved from 79.36 to 86.41%, and from 86.28 to 91.03% for expert endoscopists. The mean pairwise kappa value of endoscopists was increased significantly with the DCNN model's assistance (0.705-0.753 vs.0.767-0.890) in image testing, and (0.657-0.793 vs. 0.738-0.905) in video testing. The diagnostic duration reduced considerably with the assistance of the DCNN model from 7.09 ± 0.6s to 5.05 ± 0.55s in image test, and from 2392.17 ± 7.77s to2378.34 ± 23.51s in video test. We developed a DCNN-assisted diagnostic system. And the system can improve the diagnostic performance of endoscopists and help novice endoscopists achieve diagnostic accuracy comparable to that of expert endoscopists.

Bimodal In Situ Analyzer for Circular RNA in Extracellular Vesicles Combined with Machine Learning for Accurate Gastric Cancer Detection.

Circular RNAs in extracellular vesicles (EV-circRNAs) are gaining recognition as potential biomarkers for the diagnosis of gastric cancer (GC). Most current research is focused on identifying new biomarkers and their functional significance in disease regulation. However, the practical application of EV-circRNAs in the early diagnosis of GC is yet to be thoroughly explored due to the low accuracy of EV-circRNAs analysis. In this study, a hybridization chain reaction system based on rectangular DNA framework guidance and constructing a bimodal EV-circRNA in situ analyzer (BEISA) is developed. The analyzer can provide dual signal outputs in the fluorescence and electrochemical modes, enabling a self-correcting detection mechanism that significantly improves the accuracy of the assay. It has a broad detection range and an extremely low limit of detection. In a clinical cohort study, the BEISA used four circRNAs as biomarkers, combining them with machine learning for multiparametric analysis, which effectively differentiated between healthy donors and patients with early-stage GC. It is believed that the BEISA, in conjunction with machine learning technology, provides an efficient, sensitive, and reliable tool for EV-circRNA analysis, aiding in the early diagnosis of GC.

The Clinical Value of the Combined Detection of Systemic Immune-Inflammation Index (SII), Systemic Inflammation Response Index (SIRI), and Prognostic Nutritional Index (PNI) in Early Diagnosis of Gastric Cancer.

Gastric cancer (GC) is a common malignant tumor of the digestive tract. Accumulating studies suggest that inflammation is linked with the pathogenesis of GC. The study delves into novel hematological inflammatory markers, such as systemic immune-inflammation index (SII), systemic inflammation response index (SIRI), and prognostic nutritional index (PNI), to explore their potential applications in early diagnosis of GC. From October 2020 and August 2024, 1339 GC patients admitted to our hospital were enrolled in this study. The pre-treatment SII, SIRI, and PNI was calculated from peripheral blood samples. Univariate and multivariate logistic regression analyses were utilized to verify independent risk factors for patients, and constructed the nomograms. The correlation between hematological indicators and tumor-node-metastasis (TNM) stage was assessed through Spearman's analysis. Eligible patients and healthy controls were grouped by gender. The diagnostic ability of PNI was significantly superior to other indicators to diagnose male GC (area under the curve [AUC]=0.908, 95% CI: 0.892-0.925) and female GC (AUC=0.890, 95% CI: 0.865-0.914). Besides, the combination of hematological indicators is more effective in diagnosing GC patients, especially for male patients (AUC=0.916, 95% CI: 0.901-0.932, sensitivity: 84.98%, specificity: 84.29%). The C-statistic of Nomogram model was 0.917 for males and 0.875 for females. In both male and female cohorts, CEA, SII, and SIRI were positively correlated with TNM stage, while PNI was negatively correlated. The AUC of CEA, SII, SIRI, and PNI combined for the diagnosis in the early stage of male GC patients was 0.897 (95% CI: 0.875-0.918, sensitivity: 86.57%, specificity: 80.30%) is higher than that of in the advanced stage (AUC: 0.745, 95% CI: 0.710-0.780, sensitivity: 56.53%, specificity: 82.86%). The combined CEA, SII, PNI, and SIRI could be used as screening biomarkers in diagnosing GC, especially in the early stage of male GC patients.

Highly Sensitive Multiplexed Sensing of miRNAs in a Gastric Cancer Patient's Liquid Biopsy.

Gastric cancer (GC) is one of the leading causes of cancer mortality in the world. Most patients are in the advanced stage of the disease at the time of diagnosis because the symptoms of early gastric cancer patients are not obvious. Early diagnosis of gastric cancer is still challenging due to the high cost, invasiveness, and low accuracy of traditional diagnostic methods such as endoscopy and biopsy. Herein, we develop clinically accurate and highly sensitive detection of multiple GC miRNA biomarkers in human serum using an isothermal nucleic acid primer exchange reaction (PER). The isothermal nucleic acid primer exchange reaction demonstrates high sensitivity and robustness, exemplified by a one-pot reaction achieving a detection limit of 28.71 fM. By quantifying the levels of three miRNA biomarkers selected through bioinformatics analysis in gastric cancer serum samples, the diagnostic approach effectively distinguished between clinical gastric cancer patients (n = 25) and noncancer controls (n = 10). The performance of our three-miRNA signature in discriminating between GC and controls was as follows: area under the curve (AUC): 0.808, sensitivity: 89%, specificity: 88%, positive predictive value (PPV): 96%, and negative predictive value (NPV): 70%.

Evaluating the diagnostic performance of [18F]ALF-NOTA-FAPI-04 PET/CT in gastric cancer: a comparative study with [18F]FDG PET/CT.

To compare the diagnostic value of [18F]ALF-NOTA-FAPI-04 positron emission tomography/computed tomography (PET/CT) and 18F-fluorodeoxyglucose (FDG) PET/CT in gastric cancer. This single-center retrospective analysis included 65 patients with gastric cancer who received both [18F]FDG and [18F]ALF-NOTA-FAPI-04 PET/CT for initial staging or restaging. Histopathological manifestations, typical imaging manifestations, follow-up imaging, and comprehensive clinical assessment were used as reference criteria. The uptakes of [18F]FDG and [18F]ALF-NOTA-FAPI-04 PET were compared using the Wilcoxon signed-rank test. McNemar's test was employed to compare the diagnostic performance of the two imaging techniques. A total of 65 patients were included (26 male and 39 female; mean age, 54.03 ± 10.41 years), Among them, 10 were newly diagnosed, 46 underwent radical gastrectomy, and 9 received only chemotherapy prior to the study. Compared with [18F]FDG PET/CT, [18F]ALF-NOTA-FAPI-04 PET/CT showed higher sensitivity in primary or recurrent tumors (100% vs. 64.52%, p < 0.001)), lymph node metastases (88.89% vs. 38.89%, p = 0.006), distant metastases (91.18% vs. 50%, p < 0.001). From the semi-quantitative evaluation, the Maximum standardized uptake value (SUVmax) and target-to-background ratio of [18F]ALF-NOTA-FAPI-04 PET/CT were significantly higher than that of [18F]FDG PET/CT in primary or recurrent tumors, lymph node metastases, and distant metastases (all p < 0.001). Our study results indicate that [18F]ALF-NOTA-FAPI-04 PET/CT outperforms [18F]FDG PET/CT in the detection of primary or recurrent tumors, lymph node metastasis, and distant metastasis in gastric cancer. Question Early diagnosis and precise staging of gastric cancer are crucial for patient prognosis; however, current imaging techniques still face significant limitations. Findings [18F]ALF-NOTA-FAPI-04 PET/CT demonstrated significantly higher sensitivity than [18F]FDG PET/CT in detecting primary or recurrent tumors and metastases in patients with gastric cancer. Clinical relevance [18F]ALF-NOTA-FAPI-04 PET/CT is an advanced imaging diagnostic technique that significantly enhances the diagnostic accuracy for gastric cancer and its metastatic lesions. This technology provides robust support for clinical decision-making, thereby improving the management of patients with gastric cancer.

Identification of gastric cancer biomarkers through in-silico analysis of microarray based datasets

Gastric cancer is among the most prevalent cancers worldwide including in Pakistan. Late diagnosis of gastric cancer leads to reduced survival. The present study aimed to investigate biomarkers for early diagnosis and prognosis of gastric cancer. For this purpose, the ten microarray-based gene expression datasets (GSE54129, GSE79973, GSE161533, GSE103236, GSE33651, GSE19826, GSE118916, GSE112369, GSE13911, and GSE81948) were retrieved from GEO database and analyzed by GEO2R to identify differentially expressed genes. Datasets were arranged in subsets of different dataset combinations to identify common DEGs. The gene ontology and functional pathway enrichment analysis of common DEGs was performed by DAVID tool. Pan-cancer analysis was conducted by UALCAN database. Survival analysis of common DEGs was done by Kaplan-Meier plotter. A total of 71 common DEGs were identified in different combinations of datasets. Among them, only 5 DEGs namely ATP4B, ATP4A, CCKBR, KCNJ15, and KCNJ16 were detected to be common in all the datasets. The GO and pathway analysis represented that the identified DEGs are involved in gastric acid secretion and collecting duct acid secretion pathways. Further expression validation of these five genes using three additional datasets (GSE31811, GSE26899, and GSE26272) confirmed their differential expression in gastric cancer samples. The pan-cancer analysis also revealed aberrant expression of DEGs in various cancers. The survival analysis showed the association of these 5 DEGs with poor survival of gastric cancer patients. To conclude, this study revealed a panel of 5 genes, which can be employed as diagnostic and prognostic biomarkers of gastric cancer patients.

Preparation and identification of a fluorescent probe with CsPbBr3perovskite quantum dots and CD44v6 specific peptide for gastric cancer imaging.

Since the sensitivity and accuracy of traditional detection for early gastric cancer diagnosis are still insufficient, it is significant to continuously optimize the optical molecular imaging detection technology based on an endoscopic platform. The signal intensity and stability of traditional chemical fluorescent dyes are low, which hinders the clinical application of molecular imaging detection technology. This work developed a probe based on perovskite quantum dots (PQDs) and peptide ligands. By utilizing CsPbBr3perovskite PQDs modified by azithromycin (AZI), combined with the specific polypeptide ligand of CD44v6, a gastric cancer biomarker, the perovskite-based probe (AZI-PQDs probe) which can specifically identify gastric cancer tumor was prepared. Owing to the high photoluminescence quantum yield of CsPbBr3PQDs, the naked eye can observe the imaging under the excitation of the hand-held ultraviolet light source. AZI-PQDs probe can accurately identify gastric cancer cells, tissues, and xenograft models with experiments ofex vivoandin vivofluorescence imaging detection. It also exhibited low toxicity and immunogenicity, indicating the safety of the probe. This work provides a probe combined with cancer specificity and a reliable fluorescent signal that has the potential for application in gastric cancer optical molecular imaging.

Identification of FGG as a Biomarker in Early Gastric Cancer via Tissue Proteomics and Clinical Verification.

Early and accurate diagnosis of gastric cancer (GC) is essential for reducing mortality and improving patient well-being. However, methods for the early diagnosis of GC are still lacking. In this study, by isobaric tagging for relative and absolute quantitation (iTRAQ), we identified 336 proteins that overlapped among the upregulated differentially expressed proteins (DEPs) in early gastric cancer (EGC) versus progressive gastric cancer (PGC), upregulated DEPs in EGC versus nongastric cancer (NGC), and nonsignificant proteins in EGC versus NGC. These DEPs were involved primarily in the neutrophil-related immune response. Network analysis of proteins and pathways revealed that fibrinogen α (FGA), β (FGB), and γ (FGG) are candidates for distinguishing EGC. Furthermore, parallel reaction monitoring (PRM), immunohistochemistry (IHC), and Western blot (WB) assays of clinical samples confirmed that, compared with that in PGC and NGC, only FGG was uniquely and significantly upregulated in the gastric mucosa of EGC. Our results demonstrated that FGG in the gastric mucosa could be a novel biomarker to diagnose EGC patients via endoscopy.

Identification of plasma exosomal lncRNA as a biomarker for early diagnosis of gastric cancer.

There were about 1,090,000 gastric cancer (GC) cases in 2020 in China. The incidence and mortality rates ranked the fifth and third among all kinds of cancers in China. Early diagnosis plays an important role in the treatment and prognosis of gastric cancer. In recent years, noninvasive diagnosis, especially plasma exosome lncRNAs, has become a promissing biomarkers with high specificity and sensitivity for early diagnosis of cancers. In this study, plasma exosomes of patients with early gastric cancer were extracted efficiently by affinity membrane separation technology, including affinity adsorption, elution, affinity membrane regeneration and other steps. After identified by electron microscopy observation, particle size analysis and Western blot verification, the lncRNAs in the exosomes were extracted and were analysized by high-throughput RNA sequencing (RNA-Seq). The differentially expressed lncRNAs were verified by RT-qPCR in 93 patients with early gastric cancer and 49 normal controls. Electron microscopy, particle size analysis and Western blot showed that exosomes were successfully isolated from plasma. RNA-Seq results show that 76 lncRNAs were upregulated and 260 lncRNAs were downregulated in plasma exosomes of early gastric cancer patients compared with normal controls. RT-qPCR analysis indicated that a total of 6 lncRNAs were significantly and differentially expressed in gastric cancer patients compared to normal controls, with 2 (lncmstrg. 1319590, Lncmstrg. 2312697) highly expressed and 4 lowly expressed (lncmstr-g.1004024.1, lncmstrg. 2441832.8, lncmstrg. 315376.1, lncmstrg.907985.2,) (p < 0.05). The survival curve analysis indicated that lncmstrg.2441832.8 and lncmstrg.2312697 had higher sensitivity and specificity for the diagnosis of gastric cancer, respectively and AUC curve areas were 0.6211 and 0.631, p < 0.05, respectively, which were greater than the traditional clinical detection indexes CEA (0.61) and AFP (0.57). When combined lncmstrg.2441832.8 and lncmstrg.2312697 in gastric cancer diagnosis, AUC curve area reached 0.73, which was greater than CA199 (0.71). Lncmstrg.2441832.8 and lncmstrg.2312697 may be a potential and promissing biomarkers for early diagnosis of gastric cancer.

Correlation between White Globe Appearance and Clinicopathologic Characteristics in Early Gastric Cancer.

Magnifying endoscopy with narrow-band imaging (ME-NBI) enables the visualization of detailed microsurface (MS) and microvascular (MV) structures in the gastrointestinal tract. White globe appearance (WGA) is a small whitish lesion with a globular shape identified during ME-NBI for early gastric cancer (EGC). This study aimed to investigate the associations between WGA, clinicopathological characteristics, and other ME-NBI findings in patients with EGC. The presence or absence of WGA in 122 patients (126 lesions) with an endoscopic diagnosis of EGC who underwent ME-NBI before endoscopic or surgical resection was prospectively collected and retrospectively analyzed. During ME-NBI, the MS and MV patterns and the presence of WGA and white opaque substances (WOS) were investigated. EGC cases were categorized as differentiated or undifferentiated type, and mucosal, submucosal, or advanced. Of 126 lesions, WGA was observed in 25 (19.8%). WGA was associated with tumor size (≤2 cm [17/63, 27.0%] vs >2 cm [8/63, 12.7%]; p=0.044), histologic type (differentiated type [22/89, 24.7%] vs undifferentiated type [3/37. 8.1%]; p=0.033), and tumor location (upper third [1/11, 9.1%] vs middle third [18/58, 31.0%] and lower third [6/57, 10.5%]; p=0.017). Although WGA was observed more frequently in lesions with an oval/tubular MS pattern, a fine-network MV pattern, and the absence of WOS, the difference was not statistically significant (MS pattern, p=0.358; MV pattern, p=0.212; WOS, p=0.121, respectively). WGA was associated with small tumor size, differentiated-type histology, and middle-third tumor location, and was more frequently observed in lesions with an oval/tubular MS and fine-network MV patterns and the absence of WOS.

The importance of blood parameters in the detection of intestinal metaplasia and early diagnosis of gastric cancer

Background: We aimed to determine whether complete blood count(CBC) parameters, such as the white blood count(WBC), hemoglobin(Hb), platelet(PLT), red cell distribution width(RDW), mean platelet volume(MPV), platelet distribution width(PDW), neutrophil-to-lymphocyte ratio(NLR), platelet-to-lymphocyte ratio(PLR), and monocyte-to-lymphocyte ratio(MLR), have a predictive value in the detection of gastric cancer(GC) and intestinal metaplasia(IM). Methods: While proven GC, IM, and healthy control(HC) patients were included, patients with the comorbid disease were excluded, and univariate analyses compared three groups. The receiver operating characteristic(ROC) curve analysis was run for CBC parameters. The area under the curve(AUC) was evaluated, and a cut-off value was determined. The sensitivity and specificity of each parameter were considered. Results: The GC, IM, and HC groups consisted of 72(33%), 73(34%), and 72(33%) patients, respectively. RDW, PLT, NLR, PLR, and MLR were significant between GC and IM. The highest AUC (0.727) was obtained for the PLT yielding a 56.9% sensitivity and 79.4% specificity at a cut-off value of 151.8. The AUC of RDW was found as 0.691 and 0.626 for pairwise comparisons of GC-HC and IM-HC, respectively. At a cut-off value of 13.4, PLR yielded 70.8% sensitivity and 61.1% specificity in the detection of GC, while 64.4% sensitivity and 51.1% specificity for IM. Conclusion: CBC parameters, such as RDW, PLT, NLR, PLR, and MLR, have value in detecting GC. RDW also has diagnostic value in helping to detect IM. PLR can help to distinguish patients with GC from those with IM. These inexpensive, easily accessible parameters may help in the timely diagnosis of GC and IM. Keywords: Gastric cancer; intestinal Metaplasia; Monocyte to lymphocyte ratio; red cell distribution; hemoglobin; platelet; neutrophil-lymphocyte ratio; platelet-lymphocyte ratio; inflammation.

IGFBP7 regulates cell proliferation and migration through JAK/STAT pathway in gastric cancer and is regulated by DNA and RNA methylation.

New biomarkers for early diagnosis of gastric cancer (GC), the second leading cause of cancer-related death, are urgently needed. IGFBP7, known to play various roles in multiple tumours, is complexly regulated across diverse cancer types, as evidenced by our pancancer analysis. Bioinformatics analysis revealed that IGFBP7 expression was related to patient prognosis, tumour clinicopathological characteristics, tumour stemness, microsatellite instability and immune cell infiltration, as well as the expression of oncogenes and immune checkpoints. GSEA links IGFBP7 to several cancer-related pathways. IGFBP7 deficiency inhibited GC cell proliferation and migration invitro. Furthermore, an invivo nude mouse model revealed that IGFBP7 downregulation suppressed the tumorigenesis of GC cells. Western blotting analysis showed that the JAK1/2-specific inhibitor ruxolitinib could rescue alterations induced by IGFBP7 overexpression in GC cells. Additionally, our bioinformatics analysis and invitro assays suggested that IGFBP7 is regulated by DNA methylation at the genetic level and that the RNA m6A demethylase FTO modulates it at the posttranscriptional level. This study emphasizes the clinical relevance of IGFBP7 in GC and its influence on cell proliferation and migration via the JAK/STAT signalling pathway. This study also highlights the regulation of IGFBP7 in GC by DNA and m6A RNA methylation.

Integrated triple signal amplification strategy for ultrasensitive electrochemical detection of gastric cancer-related microRNA utilizing MoS2-based nanozyme, hybridization chain reaction, and horseradish peroxidase

Early diagnosis and treatment of gastric cancer (GC) play a vital role in improving efficacy, reducing mortality and prolonging patients’ lives. Given the importance of early detection of gastric cancer, an electrochemical biosensor was developed for the ultrasensitive detection of miR-19b-3p by integrating MoS2-based nanozymes, hybridization chain reaction (HCR) with enzyme catalyzed reaction. The as-prepared MoS2-based nanocomposites were used as substrate materials to construct nanoprobes, which can simultaneously load probe DNA and HCR initiator for signal amplification. Moreover, the MoS2-based nanocomposites are also employed as nanozymes to amplify electrochemical response. The presence of miR-19b-3p induced the assembly of MoS2-based nanoprobes on the electrode surface, which can activate in-situ HCR reaction to load a large number of horseradish peroxidase (HRP) for signal amplification. Coupling with the co-catalytic ability of HRP and MoS2-based nanozymes, the designed electrochemical biosensor can detect as low as 0.7 aM miR-19b-3p. More importantly, this biosensor can efficiently analyze miR-19b-3p in clinical samples from healthy people and gastric cancer patients due to its excellent sensitivity and selectivity, suggesting that this biosensor has a potential application in early diagnosis of disease.

Evaluation of Oxidative Stress, Anti-Oxidant, Vitamins and Co-Factor Elements in The Sera of Gastric Cancer in Iraqi Patients.

The objective of this study is to analyze oxidative stress markers Total Oxidant Status (TOS) and total Antioxidant Status (TAS), assess antioxidant levels (vitamin C, E), and evaluate co-factor element profiles zinc (Zn), copper (Cu), iron (Fe) in the serum of Iraqi gastric cancer patients. By elucidating these relationships, the research aims to enhance knowledge on oxidative stress, dietary factors, and potential therapeutic approaches for managing nutritional imbalances in this cohort. The study included 60 gastric cancer patients and 60 matched controls. Blood samples were collected and serum was extracted for analysis of TOS, TAS, Vitamin C, Vitamin E, copper, zinc, and iron levels. Measurements were conducted using spectrophotometry and ELISA kits from various companies. Statistical analysis was performed with IBM SPSS 25.0, presenting results as means ± SD, and differences between groups were assessed via independent samples t-test at p < 0.05 and p ≤ 0.01. The study results indicated statistically significant differences between gastric cancer patients and controls in various biomarkers, with all comparisons showing p-values less than 0.001. This suggests strong evidence for the observed differences between the two groups in (TOS), (TAS), vitamins C and E, Cu, Zn, and Fe levels. These relationships underscore the intricate connections among biomarkers in gastric cancer pathophysiology. The study underscores the intricate relationship between oxidative stress, antioxidant depletion, and micronutrient imbalances in gastric cancer. These findings offer valuable insights into the disease's pathophysiology, indicating potential diagnostic biomarkers. Further research is warranted to unravel underlying mechanisms and explore clinical applications for early gastric cancer diagnosis.

Ultrasensitive and multiplexed Gastric cancer biomarkers detection with an integrated electrochemical immunosensing platform

Developing immunosensing platforms capable of simultaneously detecting multiple cancer markers is crucial for clinical diagnosis and biomedical research. Here, we introduce a novel dual-mode electrochemical biosensing assay platform capable of detecting two gastric cancer biomarkers: pepsinogen I (PG I) and pepsinogen II (PG II). Methylene blue (MB) and Prussian blue (PB) were used as dual signal sources to label PG I and PG II, respectively. The platform integrates an ARM STM32F411 microcontroller and an AD5941 analog front-end, which not only facilitates cyclic voltammetry (CV) and differential pulse voltammetry (DPV) with efficacy comparable to commercial electrochemical workstations but also offers data collection and synchronous analysis capabilities, allowing simultaneous output of PG I and PGR (PG I/PG II) values. Equipped with an interactive screen for operational control and result display, the immunosensing platform provides linear detection ranges for PG I (5 pg/mL–100 ng/mL) and PG II (50 pg/mL–200 ng/mL), enabling rapid detection within 5 min. It demonstrates excellent sensitivity and selectivity when comparing serum samples from healthy individuals and gastric cancer patients. The dual-marker detection platform significantly enhances early diagnosis and screening of gastric cancer, offering substantial improvements over single-marker assays. Furthermore, this platform shows potential for detecting multiple biomarkers in various diseases, highlighting its utility for biomedical applications.

Application of Machine Learning in the Diagnosis of Early Gastric Cancer Using the Kyoto Classification Score and Clinical Features Collected from Medical Consultations.

The early detection accuracy of early gastric cancer (EGC) determines the choice of the optimal treatment strategy and the related medical expenses. We aimed to develop a simple, affordable, and time-saving diagnostic model using six machine learning (ML) algorithms for the diagnosis of EGC. It is based on the endoscopy-based Kyoto classification score obtained after the completion of endoscopy and other clinical features obtained after medical consultation. We retrospectively evaluated 1999 patients who underwent gastrointestinal endoscopy at the China Beijing Hospital. Of these, 203 subjects were diagnosed with EGC. The data were randomly divided into training and test sets (ratio 4:1). We constructed six ML models, and the developed models were evaluated on the testing set. This procedure was repeated five times. The Kolmogorov-Arnold Networks (KANs) model achieved the best performance (mean AUC value: 0.76; mean balanced accuracy: 70.96%; mean precision: 58.91%; mean recall: 70.96%; mean false positive rate: 26.11%; mean false negative rate: 31.96%; and mean F1 score value: 58.46). The endoscopy-based Kyoto classification score was the most important feature with the highest feature importance score. The results suggest that the KAN model, the optimal ML model in this study, has the potential to identify EGC patients, which may result in a reduction in both the time cost and medical expenses in clinical practice.

The Role of Biomarkers in the Early Diagnosis of Gastric Cancer: A Study on CCR5, CCL5, PDGF, and EphA7.

Despite the use of screening programs, gastric cancer (GC) diagnosis may only be possible at an advanced stage. In this study, we examined the serum levels of C-C chemokine receptor type 5 (CCR5), C-C motif chemokine ligand 5 (CCL5), platelet-derived growth factor (PDGF), and EphrinA7 (EphA7) in patients with gastric carcinoma and healthy controls to investigate the significance and usability of these potential biomarkers in the early diagnosis of GC. The study enrolled 69 GC patients and 40 healthy individuals. CCR5, CCL5, PDGF-BB, and EphA7 levels, which have been identified in the carcinogenesis of many cancers, were measured in the blood samples using the ELISA method. CCR5, CCL5, PDGF-BB, and EphA7 were all correlated with GC diagnosis (CCR5, p < 0.001, r = -0.449; CCL5, p = 0.014, r = -0.234; PDGF-BB, p < 0.001, r = -0.700; EPHA7, p < 0.001, r = -0.617). The serum CCR5, EphA7, and especially the PDGF-BB levels of the patients diagnosed with GC were discovered to be significantly higher compared to the healthy controls. PDGF-BB had the highest positive and negative predictive values when evaluated in ROC analysis to determine its diagnostic significance (cut-off value: 59.8 ng/L; AUC: 0.92 (0.87-0.97)). As far as we know, this is the first study to investigate the potential connection between GC and these four biomarkers. The fact that serum CCR5, CCL5, EphA7, and especially PDGF-BB levels in the patient group were significantly higher compared to healthy controls indicates that they can be used with high accuracy in the early diagnosis of GC. In addition, the levels of CCR5, PDGF-BB, and EphA7 can be used as important indicators to predict the biological behavior and prognosis of GC.

A novel color-aided system for diagnosis of early gastric cancer using magnifying endoscopy with narrow-band imaging.

The Pink Zone Pattern (PP) sign is a typical color alteration of early gastric cancer (EGC) under magnifying endoscopic narrow-band imaging (ME-NBI). By integrating the color changes (PP sign) with the "vessel plus surface (VS)" classification system, we developed an innovative diagnostic system for EGC and named it "Pink Microsurface Microvascular (PSV)" system. Here, we aimed to elucidate the diagnostic performance of the PSV system for EGC. We conducted a single-center prospective clinical study (before-after design) consisting of 2 cross-sectional studies at 2 separate periods. In the before phase, 184 suspected lesions were evaluated using the VS system under ME-NBI; in the after phase, 183 suspected lesions were evaluated using the PSV system. We compared the diagnostic accuracy, sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV) between the VS group and the PSV group. The accuracy, sensitivity, specificity, PPV, and NPV of the VS system for EGC were 84.6%, 87.0%, 83.6%, 67.8%, and 94.2%, respectively, and those for the PSV system were 93.0%, 92.0%, 93.4%, 85.2%, and 96.6%, respectively. The accuracy, specificity, and PPV of the PSV system were superior to those of the VS system. However, the sensitivity and NPV did not significantly differ between the VS system and the PSV system. The VS system was inconclusive for 22 lesions (12.0%) and the PSV system was inconclusive for 11 lesions (6.0%). The PSV system could identify more suspicious lesions than the VS system. We propose a new PSV diagnostic system by combining the VS system and the PP sign. Compared with the VS system, the PSV system could identify more suspected lesions and improve the diagnostic performance of EGC.

GGT5 as a promising prognostic biomarker and its effects on tumor cell progression in gastric cancer.

Gastric cancer (GC) is a gastric malignant tumor with over 1 million new cases globally each year. There are many diagnostic methods for GC, but due to the hidden early symptoms of GC, early GC is easy to be missed and misdiagnosed, which affects the follow-up treatment of patients. The early and accurate diagnosis of GC is of great significance for the treatment and survival of GC patients. Our laboratory study found that gamma-glutamyl transferase (GGT) was highly expressed in GC patients, but the mechanism of GGT family genes in the occurrence and development of GC remained to be further studied. Therefore, this study aimed to explore the mechanism of GGT family functional gene GGT5 regulating the proliferation and migration of GC cells, and provide a possible new biomarker for the early diagnosis of GC. The value of serum GGT in GC patients was first statistically analyzed. Then, The Cancer Genome Atlas (TCGA) and Gene Expression Omnibus (GEO) datasets were used to analyze the mRNA expression of GGT5 in GC, and its clinical relationship and function. Furthermore, expression of GGT5 was reduced by lentivirus RNA interference and verified by polymerase chain reaction (PCR), Cell Counting Kit-8 (CCK-8) and 5-ethynyl-2'-deoxyuridine (EdU) assays were used to detect cell proliferation after GGT5 knockdown. Scratch and Transwell assays were applied to observe cell migration after knockdown of GGT5. Finally, Western blot assays were observed to demonstrate PI3K/AKT-MAPK and MMPs expression levels after knockdown of GGT5. Serum GGT was expressed at a high level in GC patients. GGT5 was highly expressed in GC tissues, and was associated with poor prognosis and clinical stage of GC. GGT5 might be involved in the regulation of vascular development and angiogenesis, as well as in the mechanisms of cell motility and migration, and it was positively correlated with the PI3K/AKT pathway. The proliferation and migration capacity of GC cells was dampened by downregulation of GGT5. GGT5 mediated proliferation and migration of GC cells by directly targeting PI3K/AKT-MAPK-MMPs pathways. Low expression of GGT5 reduced proliferation and migration in GC cells by modulating the PI3K/AKT-MAPK-MMPs pathway, and GGT5 might be a new target for GC.

Predictive biomarkers for metachronous gastric cancer development after endoscopic resection of early gastric cancer.

We aimed to identify predictive markers for metachronous gastric cancer (MGC) in early gastric cancer (EGC) patients curatively treated with endoscopic submucosal dissection (ESD). From EGC patients who underwent ESD, bulk RNA sequencing was performed on non-cancerous gastric mucosa samples at the time of initial EGC diagnosis. This included 23 patients who developed MGC, and 23 control patients without additional gastric neoplasms for over 3 years (1:1 matched by age, sex, and Helicobacter pylori infection state). Candidate differentially-expressed genes were identified, from which biomarkers were selected using real-time quantitative polymerase chain reaction and cell viability assays using gastric cell lines. An independent validation cohort of 55 MGC patients and 125 controls was used for marker validation. We also examined the severity of gastric intestinal metaplasia, a known premalignant condition, at initial diagnosis. From the discovery cohort, 86 candidate genes were identified of which KDF1 and CDK1 were selected as markers for MGC, which were confirmed in the validation cohort. CERB5 and AKT2 isoform were identified as markers related to intestinal metaplasia and were also highly expressed in MGC patients compared to controls (p<0.01). Combining these markers with clinical data (age, sex, H. pylori and severity of intestinal metaplasia) yielded an area under the curve (AUC) of 0.91 (95% CI, 0.85-0.97) for MGC prediction. Assessing biomarkers in non-cancerous gastric mucosa may be a useful method for predicting MGC in EGC patients and identifying patients with a higher risk of developing MGC, who can benefit from rigorous surveillance.