Machine learning-based personalized prediction of gastric cancer incidence using the endoscopic and histologic findings at the initial endoscopy

The artificial intelligence revolution in gastric cancer management: clinical applications

Nowadays, gastric cancer has become a significant issue in the global cancer burden, and its impact cannot be ignored. The rapid development of artificial intelligence technology is attempting to address this situation, aiming to change the clinical management landscape of gastric cancer fundamentally. In this transformative change, machine learning and deep learning, as two core technologies, play a pivotal role, bringing unprecedented innovations and breakthroughs in the diagnosis, treatment, and prognosis evaluation of gastric cancer. This article comprehensively reviews the latest research status and application of artificial intelligence algorithms in gastric cancer, covering multiple dimensions such as image recognition, pathological analysis, personalized treatment, and prognosis risk assessment. These applications not only significantly improve the sensitivity of gastric cancer risk monitoring, the accuracy of diagnosis, and the precision of survival prognosis but also provide robust data support and a scientific basis for clinical decision-making. The integration of artificial intelligence, from optimizing the diagnosis process and enhancing diagnostic efficiency to promoting the practice of precision medicine, demonstrates its promising prospects for reshaping the treatment model of gastric cancer. Although most of the current AI-based models have not been widely used in clinical practice, with the continuous deepening and expansion of precision medicine, we have reason to believe that a new era of AI-driven gastric cancer care is approaching.

Recent Advancements in Localization Technologies for Wireless Capsule Endoscopy: A Technical Review

Conventional endoscopy is limited in its ability to examine the small bowel and perform long-term monitoring due to the risk of infection and tissue perforation. Wireless Capsule Endoscopy (WCE) is a painless and non-invasive method of examining the body's internal organs using a small camera that is swallowed like a pill. The existing active locomotion technologies do not have a practical localization system to control the capsule's movement within the body. A robust localization system is essential for safely guiding the WCE device through the complex gastrointestinal (GI) tract. Moreover, having access to the capsule's trajectory data is highly desirable for drug delivery and surgery, as well as for creating accurate user profiles for diagnosis and future reference. Therefore, a robust, real-time, and practical localization system is imperative to advance the field of WCE and make it desirable for clinical trials. In this work, we have identified salient features of different localization techniques and categorized studies in comprehensive tables. This study is self-contained as it offers a comprehensive overview of emerging localization techniques based on magnetic field, radio frequency (RF), video, and hybrid methods. A summary at the end of each method is provided to point out the potential gaps and give directions for future research. The main point of this work is to present an in-depth review of the most recent localization techniques published in the past five years. This will assist researchers in comprehending current techniques and pinpointing potential areas for further investigation. This review can be a significant reference and guide for future research on WCE localization.

LightGBM is an Effective Predictive Model for Postoperative Complications in Gastric Cancer: A Study Integrating Radiomics with Ensemble Learning

Postoperative complications of radical gastrectomy seriously affect postoperative recovery and require accurate risk prediction. Therefore, this study aimed to develop a prediction model specifically tailored to guide perioperative clinical decision-making for postoperative complications in patients with gastric cancer. A retrospective analysis was conducted on patients who underwent radical gastrectomy at the First Affiliated Hospital of Nanjing Medical University between April 2022 and June 2023. A total of 166 patients were enrolled. Patient demographic characteristics, laboratory examination results, and surgical pathological features were recorded. Preoperative abdominal CT scans were used to segment the visceral fat region of the patients through 3Dslicer, a 3D Convolutional Neural Network (3D-CNN) to extract image features and the LASSO regression model was employed for feature selection. Moreover, an ensemble learning strategy was adopted to train the features and predict postoperative complications of gastric cancer. The prediction performance of the LGBM (Light Gradient Boosting Machine), XGB (XGBoost), RF (Random Forest), and GBDT (Gradient Boosting Decision Tree) models was evaluated through fivefold cross-validation. This study successfully constructed a model for predicting early complications following radical gastrectomy based on the optimal algorithm, LGBM. The LGBM model yielded an AUC value of 0.9232 and an accuracy of 87.28% (95% CI, 75.61-98.95%), surpassing the performance of other models. Through ensemble learning and integration of perioperative clinical data and visceral fat radiomics, a predictive LGBM model was established. This model has the potential to facilitate individualized clinical decision-making and the early recovery of patients with gastric cancer post-surgery.

Transformative artificial intelligence in gastric cancer: Advancements in diagnostic techniques

Gastric cancer represents a significant global health challenge with elevated incidence and mortality rates, highlighting the need for advancements in diagnostic and therapeutic strategies. This review paper addresses the critical need for a thorough synthesis of the role of artificial intelligence (AI) in the management of gastric cancer. It provides an in-depth analysis of current AI applications, focusing on their contributions to early diagnosis, treatment planning, and outcome prediction. The review identifies key gaps and limitations in the existing literature by examining recent studies and technological developments. It aims to clarify the evolution of AI-driven methods and their impact on enhancing diagnostic accuracy, personalizing treatment strategies, and improving patient outcomes. The paper emphasizes the transformative potential of AI in overcoming the challenges associated with gastric cancer management and proposes future research directions to further harness AI's capabilities. Through this synthesis, the review underscores the importance of integrating AI technologies into clinical practice to revolutionize gastric cancer management.

Identification of intraoperative hypoxemia and hypoproteinemia as prognostic indicators in anastomotic leakage post-radical gastrectomy: an 8-year multicenter study utilizing machine learning techniques

Background

Complications and mortality rates following gastrectomy for gastric cancer have improved over recent years; however, complications such as anastomotic leakage (AL) continue to significantly impact both immediate and long-term prognoses. This study aimed to develop a machine learning model to identify preoperative and intraoperative high-risk factors and predict mortality in patients with AL after radical gastrectomy.

Methods

For this investigation, 906 patients diagnosed with gastric cancer were enrolled and evaluated, with a comprehensive set of 36 feature variables collected. We employed three distinct machine learning algorithms-extreme gradient boosting (XGBoost), random forest (RF), and k-nearest neighbor (KNN)-to develop our models. To ensure model robustness, we applied k-fold cross-validation for internal validation of the four models and subsequently validated them using independent datasets.

Results

In contrast to the other machine learning models employed in this study, the XGBoost algorithm exhibited superior predictive performance in identifying mortality risk factors for patients with AL across one, three, and five-year intervals. The analysis identified several common risk factors affecting mortality rates at these intervals, including advanced age, hypoproteinemia, a history of anemia and hypertension, prolonged operative time, increased intraoperative bleeding, low intraoperative percutaneous arterial oxygen saturation (SPO2) levels, T3 and T4 tumors, tumor lymph node invasion, and tumor peripheral nerve invasion (PNI).

Conclusion

Among the three machine learning models examined in this study, the XGBoost algorithm exhibited superior predictive capabilities concerning the prognosis of patients with AL following gastrectomy. Additionally, the use of machine learning models offers valuable assistance to clinicians in identifying crucial prognostic factors, thereby enhancing personalized patient monitoring and management.

Multi-bioinformatics revealed potential biomarkers and repurposed drugs for gastric adenocarcinoma-related gastric intestinal metaplasia

Biomarkers associated with the progression from gastric intestinal metaplasia (GIM) to gastric adenocarcinoma (GA), i.e., GA-related GIM, could provide valuable insights into identifying patients with increased risk for GA. The aim of this study was to utilize multi-bioinformatics to reveal potential biomarkers for the GA-related GIM and predict potential drug repurposing for GA prevention in patients. The multi-bioinformatics included gene expression matrix (GEM) by microarray gene expression (MGE), ScType (a fully automated and ultra-fast cell-type identification based solely on a given scRNA-seq data), Ingenuity Pathway Analysis, PageRank centrality, GO and MSigDB enrichments, Cytoscape, Human Protein Atlas and molecular docking analysis in combination with immunohistochemistry. To identify GA-related GIM, paired surgical biopsies were collected from 16 GIM-GA patients who underwent gastrectomy, yielding 64 samples (4 biopsies per stomach x 16 patients) for MGE. Co-analysis was performed by including scRNAseq and immunohistochemistry datasets of endoscopic biopsies of 37 patients. The results of the present study showed potential biomarkers for GA-related GIM, including GEM of individual patients, individual genes (such as RBP2 and CD44), signaling pathways, network of molecules, and network of signaling pathways with key topological nodes. Accordingly, potential treatment targets with repurposed drugs were identified including epidermal growth factor receptor, proto-oncogene tyrosine-protein kinase Src, paxillin, transcription factor Jun, breast cancer type 1 susceptibility protein, cellular tumor antigen p53, mouse double minute 2, and CD44.

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.

Risk Prediction Models for Gastric Cancer: A Scoping Review

Background

Gastric cancer is a significant contributor to the global cancer burden. Risk prediction models aim to estimate future risk based on current and past information, and can be utilized for risk stratification in population screening programs for gastric cancer. This review aims to explore the research design of existing models, as well as the methods, variables, and performance of model construction.

Methods

Six databases were searched through to November 4, 2023 to identify appropriate studies. PRISMA extension for scoping reviews and the Arksey and O'Malley framework were followed. Data sources included PubMed, Embase, Web of Science, CNKI, Wanfang, and VIP, focusing on gastric cancer risk prediction model studies.

Results

A total of 29 articles met the inclusion criteria, from which 28 original risk prediction models were identified that met the analysis criteria. The risk prediction model is screened, and the data extracted includes research characteristics, prediction variables selection, model construction methods and evaluation indicators. The area under the curve (AUC) of the models ranged from 0.560 to 0.989, while the C-statistics varied between 0.684 and 0.940. The number of predictor variables is mainly concentrated between 5 to 11. The top 5 most frequently included variables were age, helicobacter pylori (Hp), precancerous lesion, pepsinogen (PG), sex, and smoking. Age and Hp were the most consistently included variables.

Conclusion

This review enhances understanding of current gastric cancer risk prediction research and its future directions. The findings provide a strong scientific basis and technical support for developing more accurate gastric cancer risk models. We expect that these conclusions will point the way for future research and clinical practice in this area to assist in the early prevention and treatment of gastric cancer.

A machine learning model for predicting the lymph node metastasis of early gastric cancer not meeting the endoscopic curability criteria

BACKGROUND

We developed a machine learning (ML) model to predict the risk of lymph node metastasis (LNM) in patients with early gastric cancer (EGC) who did not meet the existing Japanese endoscopic curability criteria and compared its performance with that of the most common clinical risk scoring system, the eCura system.

METHODS

We used data from 4,042 consecutive patients with EGC from 21 institutions who underwent endoscopic submucosal dissection (ESD) and/or surgery between 2010 and 2021. All resected EGCs were histologically confirmed not to satisfy the current Japanese endoscopic curability criteria. Of all patients, 3,506 constituted the training cohort to develop the neural network-based ML model, and 536 constituted the validation cohort. The performance of our ML model, as measured by the area under the receiver operating characteristic curve (AUC), was compared with that of the eCura system in the validation cohort.

RESULTS

LNM rates were 14% (503/3,506) and 7% (39/536) in the training and validation cohorts, respectively. The ML model identified patients with LNM with an AUC of 0.83 (95% confidence interval, 0.76-0.89) in the validation cohort, while the eCura system identified patients with LNM with an AUC of 0.77 (95% confidence interval, 0.70-0.85) (P = 0.006, DeLong's test).

CONCLUSIONS

Our ML model performed better than the eCura system for predicting LNM risk in patients with EGC who did not meet the existing Japanese endoscopic curability criteria. We developed a neural network-based machine learning model that predicts the risk of lymph node metastasis in patients with early gastric cancer who did not meet the endoscopic curability criteria.

The role of gastric mucins and mucin-related glycans in gastric cancers

Gastric mucins serve as a protective barrier on the stomach's surface, protecting from external stimuli including gastric acid and gut microbiota. Their composition typically changes in response to the metaplastic sequence triggered by Helicobacter pylori infection. This alteration in gastric mucins is also observed in cases of gastric cancer, although the precise connection between mucin expressions and gastric carcinogenesis remains uncertain. This review first introduces the relationship between mucin expressions and gastric metaplasia or cancer observed in humans and mice. Additionally, we discuss potential pathogenic mechanisms of how aberrant mucins and their glycans affect gastric carcinogenesis. Finally, we summarize challenges to target tumor-specific glycans by utilizing lectin-drug conjugates that can bind to specific glycans. Understanding the correlation and mechanism between these mucin expressions and gastric carcinogenesis could pave the way for new strategies in gastric cancer treatment.

Data-driven rapid detection of Helicobacter pylori infection through machine learning with limited laboratory parameters in Chinese primary clinics

Background

Helicobacter pylori (H. pylori) is a significant global health concern, posing a high risk for gastric cancer. Conventional diagnostic and screening approaches are inaccessible, invasive, inaccurate, time-consuming, and expensive in primary clinics.

Objective

This study aims to apply machine learning (ML) models to detect H. pylori infection using limited laboratory parameters from routine blood tests and to investigate the association of these biomarkers with clinical outcomes in primary clinics.

Methods

A retrospective analysis with three ML and five ensemble models was conducted on 1409 adults from Hubei Provincial Hospital of Traditional Chinese Medicine. evaluating twenty-three blood test parameters and using theC 14 urea breath test as the gold standard for diagnosing H. pylori infection.

Results

In our comparative study employing three different feature selection strategies, Random Forest (RF) model exhibited superior performance over other ML and ensemble models. Multiple evaluation metrics underscored the optimal performance of the RF model (ROC = 0.951, sensitivity = 0.882, specificity = 0.906, F1 = 0.906, accuracy = 0.894, PPV = 0.908, NPV = 0.880) without feature selection. Key biomarkers identified through importance ranking and shapley additive Explanations (SHAP) analysis using the RF model without feature selection include White Blood Cell Count (WBC), Mean Platelet Volume (MPV), Hemoglobin (Hb), Red Blood Cell Count (RBC), Platelet Crit (PCT), and Platelet Count (PLC). These biomarkers were found to be significantly associated with the presence of H. pylori infection, reflecting the immune response and inflammation levels.

Conclusion

Abnormalities in key biomarkers could prompt clinical workers to consider H. pylori infection. The RF model effectively identifies H. pylori infection using routine blood tests, offering potential for clinical application in primary clinics. This ML approach can enhance diagnosis and screening, reducing medical burdens and reliance on invasive diagnostics.

Machine learning models for predicting of PD-1 treatment efficacy in Pan-cancer patients based on routine hematologic and biochemical parameters

Immune checkpoint blockade therapy targeting the programmed death-1(PD-1) pathway has shown remarkable efficacy and durable response in patients with various cancer types. Early prediction of therapeutic efficacy is important for optimizing treatment plans and avoiding potential side effects. In this work, we developed an efficient machine learning prediction method using routine hematologic and biochemical parameters to predict the efficacy of PD-1 combination treatment in Pan-Cancer patients. A total of 431 patients with nasopharyngeal carcinoma, esophageal cancer and lung cancer who underwent PD-1 checkpoint inhibitor combination therapy were included in this study. Patients were divided into two groups: progressive disease (PD) and disease control (DC) groups. Hematologic and biochemical parameters were collected before and at the third week of PD-1 therapy. Six machine learning models were developed and trained to predict the efficacy of PD-1 combination therapy at 8-12 weeks. Analysis of 57 blood biomarkers before and after three weeks of PD-1 combination therapy through statistical analysis, heatmaps, and principal component analysis did not accurately predict treatment outcome. However, with machine learning models, both the AdaBoost classifier and GBDT demonstrated high levels of prediction efficiency, with clinically acceptable AUC values exceeding 0.7. The AdaBoost classifier exhibited the highest performance among the 6 machine learning models, with a sensitivity of 0.85 and a specificity of 0.79. Our study demonstrated the potential of machine learning to predict the efficacy of PD-1 combination therapy based on changes in hematologic and biochemical parameters.

Association Between Vonoprazan and the Risk of Gastric Cancer After Helicobacter pylori Eradication

BACKGROUND & AIMS

Potassium-competitive acid blockers (PCABs) have been increasingly used to treat upper gastrointestinal disorders, replacing proton pump inhibitors (PPIs). Whereas PPIs are associated with an increased risk of gastric cancer (GC) after Helicobacter pylori (Hp) eradication, it is uncertain whether PCABs carry the same risk.

METHODS

Using a population-based claims database in Japan, we identified patients who were prescribed a clarithromycin-based first regimen of Hp eradication between 2015 and 2018. Patients who failed this regimen and those diagnosed with GC before or within 1 year after Hp eradication were excluded. We compared GC incidence between PCAB users and histamine type-2 receptor antagonist (H2RA) users, matching them on the basis of propensity scores calculated with considerations for age, sex, smoking, alcohol consumption, comorbidities, and co-administered medications. PCABs included only vonoprazan in this study.

RESULTS

Among 54,055 patients, 568 (1.05%) developed GC during the follow-up period (mean, 3.65 years). The cumulative incidence of GC was 1.64% at 3 years, 2.02% at 4 years, and 2.36% at 5 years in PCAB users and 0.71% at 3 years, 1.04% at 4 years, and 1.22% at 5 years in H2RA users. The use of PCABs was associated with a higher GC risk (matched hazard ratio, 1.92; 95% confidence interval, 1.13-3.25; P = .016). Longer PCAB use and high-dose PCAB use were significantly associated with higher incidence of GC. Sensitivity analyses showed the risk of GC incidence among PCAB users was comparable with that of PPI users.

CONCLUSIONS

The use of PCABs was associated with an increased risk of GC among Hp-eradicated patients, with duration/dose response effects.

Metabolic Factors Associated with Endoscopic Atrophy, Intestinal Metaplasia, and Gastric Neoplasms in Helicobacter pylori-Positive Patients

BACKGROUND

Previous studies demonstrate an association between metabolic factors and Helicobacter pylori-related gastric cancer. However, the association of gastric atrophy or intestinal metaplasia (IM) with these factors remains unknown.

METHODS

Data on 1603 Helicobacter pylori-positive patients who underwent esophagogastroduodenoscopy between 2001 and 2021 were evaluated. The outcome measures were endoscopic atrophy, IM grade, and the incidence of endoscopically diagnosed and pathologically confirmed gastric neoplasms. Clinical factors associated with these findings were also determined.

RESULTS

Advanced age; successful Helicobacter pylori eradication; and comorbidities including diabetes mellitus (DM), hypertension, dyslipidemia, and fib4 index were significantly associated with endoscopic gastric atrophy grade. Male sex; advanced age; and comorbidities including DM, hypertension, dyslipidemia, hyperuricemia, fatty liver, aortic calcification, and fib4 index were also significantly associated with endoscopic IM grade, whereas advanced age, successful Helicobacter pylori eradication, DM, fatty liver, and fib4 index were significantly associated with the incidence of gastric neoplasms.

CONCLUSION

Several metabolic disorders, including DM, hypertension, dyslipidemia, hyperuricemia, and fatty liver disease, are risk factors for advanced-grade gastric atrophy, intestinal metaplasia, and gastric neoplasms. Risk stratification according to these factors, particularly those with metabolic disorders, would affect EGD surveillance for Helicobacter pylori-positive patients.

The development and validation of automated machine learning models for predicting lymph node metastasis in Siewert type II T1 adenocarcinoma of the esophagogastric junction

Background

Lymph node metastasis (LNM) is considered an essential prognosis factor for adenocarcinoma of the esophagogastric junction (AEG), which also affects the treatment strategies of AEG. We aimed to evaluate automated machine learning (AutoML) algorithms for predicting LNM in Siewert type II T1 AEG.

Methods

A total of 878 patients with Siewert type II T1 AEG were selected from the Surveillance, Epidemiology, and End Results (SEER) database to develop the LNM predictive models. The patients from two hospitals in Suzhou were collected as the test set. We applied five machine learning algorithms to develop the LNM prediction models. The performance of predictive models was assessed using various metrics including accuracy, sensitivity, specificity, the area under the curve (AUC), and receiver operating characteristic (ROC) curve.

Results

Patients with LNM exhibited a higher proportion of male individuals, a poor degree of differentiation, and submucosal infiltration, with statistical differences. The deep learning (DL) model demonstrated relatively good accuracy (0.713) and sensitivity (0.868) among the five models. Moreover, the DL model achieved the highest AUC (0.781) and sensitivity (1.000) in the test set.

Conclusion

The DL model showed good predictive performance among five AutoML models, indicating the advantage of AutoML in modeling LNM prediction in patients with Siewert type II T1 AEG.

Predicting early gastric cancer risk using machine learning: A population-based retrospective study

Background

Early detection and treatment are crucial for reducing gastrointestinal tumour-related mortality. The diagnostic efficiency of the most commonly used diagnostic markers for gastric cancer (GC) is not very high. A single laboratory test cannot meet the requirements of early screening, and machine learning methods are needed to aid the early diagnosis of GC by combining multiple indicators.

Methods

Based on the XGBoost algorithm, a new model was developed to distinguish between GC and precancerous lesions in newly admitted patients between 2018 and 2023 using multiple laboratory tests. We evaluated the ability of the prediction score derived from this model to predict early GC. In addition, we investigated the efficacy of the model in correctly screening for GC given negative protein tumour marker results.

Results

The XHGC20 model constructed using the XGBoost algorithm could distinguish GC from precancerous disease well (area under the receiver operating characteristic curve [AUC] = 0.901), with a sensitivity, specificity and cut-off value of 0.830, 0.806 and 0.265, respectively. The prediction score was very effective in the diagnosis of early GC. When the cut-off value was 0.27, and the AUC was 0.888, the sensitivity and specificity were 0.797 and 0.807, respectively. The model was also effective at evaluating GC given negative conventional markers (AUC = 0.970), with the sensitivity and specificity of 0.941 and 0.906, respectively, which helped to reduce the rate of missed diagnoses.

Conclusions

The XHGC20 model established by the XGBoost algorithm integrates information from 20 clinical laboratory tests and can aid in the early screening of GC, providing a useful new method for auxiliary laboratory diagnosis.

Machine-learning-algorithms-based diagnostic model for influenza A in children

BACKGROUND

At present, nucleic acid testing is the gold standard for diagnosing influenza A, however, this method is expensive, time-consuming, and unsuitable for promotion and use in grassroots hospitals. This study aimed to establish a diagnostic model that could accurately, quickly, and simply distinguish between influenza A and influenza like diseases.

METHODS

Patients with influenza-like symptoms were recruited between December 2019 and August 2023 at the Children's Hospital Affiliated to Shandong University and basic information, nasopharyngeal swab and blood routine test data were included. Computer algorithms including random forest, GBDT, XGBoost and logistic regression (LR) were used to create the diagnostic model, and their performance was evaluated using the validation data sets.

RESULTS

A total of 4188 children with influenza-like symptoms were enrolled, of which 1992 were nucleic acid test positive and 2196 were matched negative. The diagnostic models based on the random forest, GBDT, XGBoost and logistic regression algorithms had AUC values of 0.835,0.872,0.867 and 0.784, respectively. The top 5 important features were lymphocyte (LYM) count, age, serum amyloid A (SAA), white blood cells (WBC) count and platelet-to-lymphocyte ratio (PLR). GBDT model had the best performance, the sensitivity and specificity were 77.23% and 80.29%, respectively.

CONCLUSIONS

A computer algorithm diagnosis model of influenza A in children based on blood routine test data was established, which could identify children with influenza A more accurately in the early stage, and was easy to popularize.

Application of Machine Learning Based on Structured Medical Data in Gastroenterology

The era of big data has led to the necessity of artificial intelligence models to effectively handle the vast amount of clinical data available. These data have become indispensable resources for machine learning. Among the artificial intelligence models, deep learning has gained prominence and is widely used for analyzing unstructured data. Despite the recent advancement in deep learning, traditional machine learning models still hold significant potential for enhancing healthcare efficiency, especially for structured data. In the field of medicine, machine learning models have been applied to predict diagnoses and prognoses for various diseases. However, the adoption of machine learning models in gastroenterology has been relatively limited compared to traditional statistical models or deep learning approaches. This narrative review provides an overview of the current status of machine learning adoption in gastroenterology and discusses future directions. Additionally, it briefly summarizes recent advances in large language models.

Third Eye? The Assistance of Artificial Intelligence (AI) in the Endoscopy of Gastrointestinal Neoplasms

Gastrointestinal cancers are characterized by high incidence and mortality. However, there are well-established methods of screening. The endoscopy exam provides the macroscopical image and enables harvesting the tissue samples for further histopathological diagnosis. The efficiency of endoscopies relies not only on proper patient preparation, but also on the skills of the personnel conducting the exam. In recent years, a number of reports concerning the application of artificial intelligence (AI) in medicine have arisen. Numerous studies aimed to assess the utility of deep learning/ neural network systems supporting endoscopies. In this review, we summarized the most recent reports and randomized clinical trials regarding the application of AI in screening and surveillance of gastrointestinal cancers among patients suffering from esophageal, gastric, and colorectal cancer, along with the advantages, limitations, and controversies of those novel solutions.

Bimodal artificial intelligence using TabNet for differentiating spinal cord tumors-Integration of patient background information and images

We proposed a bimodal artificial intelligence that integrates patient information with images to diagnose spinal cord tumors. Our model combines TabNet, a state-of-the-art deep learning model for tabular data for patient information, and a convolutional neural network for images. As training data, we collected 259 spinal tumor patients (158 for schwannoma and 101 for meningioma). We compared the performance of the image-only unimodal model, table-only unimodal model, bimodal model using a gradient-boosting decision tree, and bimodal model using TabNet. Our proposed bimodal model using TabNet performed best (area under the receiver-operating characteristic curve [AUROC]: 0.91) in the training data and significantly outperformed the physicians' performance. In the external validation using 62 cases from the other two facilities, our bimodal model showed an AUROC of 0.92, proving the robustness of the model. The bimodal analysis using TabNet was effective for differentiating spinal tumors.

Development of a deep learning model for early gastric cancer diagnosis using preoperative computed tomography images

Background

Gastric cancer is a highly prevalent and fatal disease. Accurate differentiation between early gastric cancer (EGC) and advanced gastric cancer (AGC) is essential for personalized treatment. Currently, the diagnostic accuracy of computerized tomography (CT) for gastric cancer staging is insufficient to meet clinical requirements. Many studies rely on manual marking of lesion areas, which is not suitable for clinical diagnosis.

Methods

In this study, we retrospectively collected data from 341 patients with gastric cancer at the First Affiliated Hospital of Wenzhou Medical University. The dataset was randomly divided into a training set (n=273) and a validation set (n=68) using an 8:2 ratio. We developed a two-stage deep learning model that enables fully automated EGC screening based on CT images. In the first stage, an unsupervised domain adaptive segmentation model was employed to automatically segment the stomach on unlabeled portal phase CT images. Subsequently, based on the results of the stomach segmentation model, the image was cropped out of the stomach area and scaled to a uniform size, and then the EGC and AGC classification models were built based on these images. The segmentation accuracy of the model was evaluated using the dice index, while the classification performance was assessed using metrics such as the area under the curve (AUC) of the receiver operating characteristic (ROC), accuracy, sensitivity, specificity, and F1 score.

Results

The segmentation model achieved an average dice accuracy of 0.94 on the hand-segmented validation set. On the training set, the EGC screening model demonstrated an AUC, accuracy, sensitivity, specificity, and F1 score of 0.98, 0.93, 0.92, 0.92, and 0.93, respectively. On the validation set, these metrics were 0.96, 0.92, 0.90, 0.89, and 0.93, respectively. After three rounds of data regrouping, the model consistently achieved an AUC above 0.9 on both the validation set and the validation set.

Conclusion

The results of this study demonstrate that the proposed method can effectively screen for EGC in portal venous CT images. Furthermore, the model exhibits stability and holds promise for future clinical applications.

Intercellular adhesion molecule 2 as a novel prospective tumor suppressor induced by ERG promotes ubiquitination-mediated radixin degradation to inhibit gastric cancer tumorigenicity and metastasis

BACKGROUND

Gastric cancer (GC) is a fatal cancer with unclear pathogenesis. In this study, we explored the function and potential mechanisms of intercellular adhesion molecule 2 (ICAM2) in the development and advancement of GC.

METHODS

Quantitative real-time polymerase chain reaction (qRT-PCR) and Western blotting were performed to quantify ICAM2 expression in harvested GC tissues and cultured cell lines. Immunohistochemical analyses were conducted on a GC tissue microarray to quantify ICAM2 expression and explore its implication on the prognosis of GC patients. In vitro experiments were carried out to reveal the biological functions of ICAM2 in GC cell lines. Further, in vivo experiments were conducted using xenograft models to assess the impact of ICAM2 on GC development and metastasis. Western blot, immunofluorescence, immunoprecipitation, luciferase assay, chromatin immunoprecipitation, and ubiquitination analysis were employed to investigate the underlying mechanisms.

RESULTS

ICAM2 expression was downregulated in GC, positively correlating with advanced T stage, distant metastasis, advanced clinical stage, vessel invasion, and shorter patient survival time. ICAM2 overexpression suppressed the proliferation, migration, invasion, metastasis of GC cells as well as their ability to form tumors, whereas ICAM2 knockdown yielded opposite results. Erythroblast transformation-specific-related gene (ERG) as a transcription factor promoted the transcription of ICAM2 by binding to the crucial response element localized within its promoter region. Further analysis revealed that ICAM2 reduced radixin (RDX) protein stability and expression. In these cells, ICAM2 bound to the RDX protein to promote the ubiquitination and degradation of RDX via NEDD4 Like E3 Ubiquitin Protein Ligase (NEDD4L), and this post-translational modification resulted in the inhibition of GC.

CONCLUSIONS

In summary, this study demonstrates that ICAM2, which is induced by ERG, suppresses GC progression by enhancing the ubiquitination and degradation of RDX in a NEDD4L-dependent manner. Therefore, these results suggest that ICAM2 is a potential prognostic marker and a therapeutic target for GC.

Application of artificial intelligence for improving early detection and prediction of therapeutic outcomes for gastric cancer in the era of precision oncology

Gastric cancer is a leading contributor to cancer incidence and mortality globally. Recently, artificial intelligence approaches, particularly machine learning and deep learning, are rapidly reshaping the full spectrum of clinical management for gastric cancer. Machine learning is formed from computers running repeated iterative models for progressively improving performance on a particular task. Deep learning is a subtype of machine learning on the basis of multilayered neural networks inspired by the human brain. This review summarizes the application of artificial intelligence algorithms to multi-dimensional data including clinical and follow-up information, conventional images (endoscope, histopathology, and computed tomography (CT)), molecular biomarkers, etc. to improve the risk surveillance of gastric cancer with established risk factors; the accuracy of diagnosis, and survival prediction among established gastric cancer patients; and the prediction of treatment outcomes for assisting clinical decision making. Therefore, artificial intelligence makes a profound impact on almost all aspects of gastric cancer from improving diagnosis to precision medicine. Despite this, most established artificial intelligence-based models are in a research-based format and often have limited value in real-world clinical practice. With the increasing adoption of artificial intelligence in clinical use, we anticipate the arrival of artificial intelligence-powered gastric cancer care.

Prognostic models for upper urinary tract urothelial carcinoma patients after radical nephroureterectomy based on a novel systemic immune-inflammation score with machine learning

PURPOSE

This study aimed to evaluate the clinical significance of a novel systemic immune-inflammation score (SIIS) to predict oncological outcomes in upper urinary tract urothelial carcinoma(UTUC) after radical nephroureterectomy(RNU).

METHOD

The clinical data of 483 patients with nonmetastatic UTUC underwent surgery in our center were analyzed. Five inflammation-related biomarkers were screened in the Lasso-Cox model and then aggregated to generate the SIIS based on the regression coefficients. Overall survival (OS) was assessed using Kaplan-Meier analyses. The Cox proportional hazards regression and random survival forest model were adopted to build the prognostic model. Then we established an effective nomogram for UTUC after RNU based on SIIS. The discrimination and calibration of the nomogram were evaluated using the concordance index (C-index), area under the time-dependent receiver operating characteristic curve (time-dependent AUC), and calibration curves. Decision curve analysis (DCA) was used to assess the net benefits of the nomogram at different threshold probabilities.

RESULT

According to the median value SIIS computed by the lasso Cox model, the high-risk group had worse OS (p<0.0001) than low risk-group. Variables with a minimum depth greater than the depth threshold or negative variable importance were excluded, and the remaining six variables were included in the model. The area under the ROC curve (AUROC) of the Cox and random survival forest models were 0.801 and 0.872 for OS at five years, respectively. Multivariate Cox analysis showed that elevated SIIS was significantly associated with poorer OS (p<0.001). In terms of predicting overall survival, a nomogram that considered the SIIS and clinical prognostic factors performed better than the AJCC staging.

CONCLUSION

The pretreatment levels of SIIS were an independent predictor of prognosis in upper urinary tract urothelial carcinoma after RNU. Therefore, incorporating SIIS into currently available clinical parameters helps predict the long-term survival of UTUC.

Non-Helicobacter pylori Gastric Microbiome Modulates Prooncogenic Responses and Is Associated With Gastric Cancer Risk

Background and Aims

Although Helicobacter pylori is the most important bacterial carcinogen in gastric cancer (GC), GC can emerge even after H. pylori eradication. Studies suggest that various constituents of the gastric microbiome may influence GC development, but the role of individual pathogens is unclear.

Methods

Human gastric mucosal samples were analyzed by 16SrRNA sequencing to investigate microbiome composition and its association with clinical parameters, including GC risk. Identified bacteria in the stomach were cocultured with gastric epithelial cells or inoculated into mice, and transcriptomic changes, DNA damage, and inflammation were analyzed. Bacterial reads in GC tissues were examined together with transcriptomic and genetic sequencing data in the cancer genome atlas dataset.

Results

Patients after Helicobacter pylori eradication formed 3 subgroups based on the microbial composition revealed by 16SrRNA sequencing. One dysbiotic group enriched with Fusobacterium and Neisseria species was associated with a significantly higher GC incidence. These species activated prooncogenic pathways in gastric epithelial cells and promoted inflammation in mouse stomachs. Sugar chains that constitute gastric mucin attenuate host-bacteria interactions. Metabolites from Fusobacterium species were genotoxic, and the presence of the bacteria was associated with an inflammatory signature and a higher tumor mutation burden.

Conclusion

Gastric microbiota in the dysbiotic stomach is associated with GC development after H. pylori eradication and plays a pathogenic role through direct host-bacteria interaction.

Cancer risk stratification system and classification of gastritis: Perspectives

Kyoto global consensus reports that the current ICD-10 classification for gastritis is obsolete. The Kyoto classification of gastritis states that severe mucosal atrophy has a high risk of gastric cancer, while mild to moderate atrophy has a low risk. The updated Kimura-Takemoto classification of atrophic gastritis considers five histological types of multifocal corpus atrophic gastritis according to stages C2 to O3. This method of morphological diagnosis of atrophic gastritis increases sensitivity by 2.4 times for severe atrophy compared to the updated Sydney system. This advantage should be considered when stratifying the high risk of gastric cancer. The updated Kimura-Takemoto classification of atrophic gastritis should be used as a reference standard (gold standard) in studies of morpho-functional relationships to identify serological markers of atrophic gastritis with evidence-based effectiveness. The use of artificial intelligence in the serological screening of atrophic gastritis makes it possible to screen a large number of the population. During serological screening of atrophic gastritis and risk stratification of gastric cancer, it is advisable to use the Kyoto classification of gastritis with updated Kimura-Takemoto classification of atrophic gastritis.

Detection and Treatment of Helicobacter pylori: Problems and Advances

Helicobacter pylori (H. pylori) infection is chronic and etiologically linked to gastric cancer (GC) derived from gastric epithelium. The potential mechanism is complex, covering chronic inflammation, epithelial senescence, NF-κB activation, the cytotoxin-associated gene A protein translocation, and related abnormal signaling pathways. In clinical practice, the test-and-treat strategy, endoscopy-based strategy, and (family-based) screen-and-treat strategy are recommended to detect H. pylori and prevent GC. It has been demonstrated that the decreasing annual incidence of GC is largely attributable to the management of H. pylori. This study reviews the current clinical practice of H. pylori on the detection and eradication, alternative treatment strategies, and related problems and advances, and hopes to contribute to the better clinical management of H. pylori.

Prediction Performance of Deep Learning for Colon Cancer Survival Prediction on SEER Data

Colon and rectal cancers are the most common kinds of cancer globally. Colon cancer is more prevalent in men than in women. Early detection increases the likelihood of survival, and treatment significantly increases the likelihood of eradicating the disease. The Surveillance, Epidemiology, and End Results (SEER) programme is an excellent source of domestic cancer statistics. SEER includes nearly 30% of the United States population, covering various races and geographic locations. The data are made public via the SEER website when a SEER limited-use data agreement form is submitted and approved. We investigate data from the SEER programme, specifically colon cancer statistics, in this study. Our objective is to create reliable colon cancer survival and conditional survival prediction algorithms. In this study, we have presented an overview of cancer diagnosis methods and the treatments used to cure cancer. This paper presents an analysis of prediction performance of multiple deep learning approaches. The performance of multiple deep learning models is thoroughly examined to discover which algorithm surpasses the others, followed by an investigation of the network's prediction accuracy. The simulation outcomes indicate that automated prediction models can predict colon cancer patient survival. Deep autoencoders displayed the best performance outcomes attaining 97% accuracy and 95% area under curve-receiver operating characteristic (AUC-ROC).

Clinicopathological Features of Gastric Cancer with Autoimmune Gastritis

Most gastric cancers develop in patients with chronic gastritis. Chronic gastritis can be classified into two major subtypes: Helicobacter pylori (H. pylori)-induced gastritis and autoimmune gastritis (AIG). Whereas H. pylori-related gastric cancers are more common and have been extensively investigated, the clinicopathological features of gastric cancer with autoimmune gastritis are unclear. Patients diagnosed with gastric cancer and hospitalized in the University Tokyo Hospital from 1998 to 2017 were enrolled. Diagnosis of autoimmune gastritis was based on positivity for serum anti-parietal cell antibody (APCA). We evaluated mucin expression and immune cell infiltration by immunohistochemical staining for MUC5AC, MUC6, PD-L1, CD3, CD11, Foxp3, and PD1. We also examined the presence of bacterial taxa that are reportedly enriched in AIG. Survival analyses of recurrence and 5-year mortality were also performed. In total, 261 patients (76 APCA-positive and 185 APCA-negative) were analyzed. Immunohistochemical staining in the matched cohort showed that AIG-related gastric cancer had higher MUC5AC expression (p = 0.0007) and MUC6 expression (p = 0.0007). Greater infiltration of CD3-positive (p = 0.001), Foxp3-positive (p < 0.001), and PD1-positive cells (p = 0.001); lesser infiltration of CD11b-positive (p = 0.005) cells; and a higher prevalence of Bacillus cereus (p = 0.006) were found in AIG-related gastric cancer patients. The cumulative incidences of gastric cancer recurrence were 2.99% at 2 years, 15.68% at 6 years, and 18.81% at 10 years in APCA-positive patients; they were 12.79% at 2 years, 21.35% at 6 years, and 31.85% at 10 years in APCA-negative patients. The cumulative incidences of mortality were 0% at 3 years and 0% at 5 years in APCA-positive patients; they were 1.52% at 3 years and 2.56% at 5 years in APCA-negative patients. We identified molecular differences between AIG and non-AIG gastric cancer. Differences in T-cell populations and the gastric microbiota may contribute to the pathogenesis of gastric cancers and potentially affect the response to immunotherapy.