Abstract
Background:
Gastric cancer is one of the most common cancers. We can use AI for predictive models and help us in early detection and diagnosis.
Objective:
This study examines the use of a neural network model to classify gastric cancer based on clinical, demographic and genetic data.
Methods:
The data from the participants were divided into two subsets. 70% training data and 30% testing data. The neural network model has 12 input variables. Factors influencing a disease can be age, sex, family history, smoking, alcohol, Helicobacter pylori infection, food habits, diseases, endoscopic images, biopsy, CT scan, gene variants (TP53, KRAS, CDH1). The hyperbolic tangent activation function has four units in the hidden layer of a model. The output layer used a Softmax activation function and cross-entropy error function which predicted the presence of gastric cancer. The assessment was done on the predictors:
Results:
The training and testing datasets showed 100% accuracy predicting gastric cancer in the model outputs. Age, gender, family history, infection with Helicobacter pylori, smoking, and drinking alcohol are the biggest predictors. Information from clinical diagnosis like endoscopic images, biopsy and CT scans helped the predictive model.
Conclusion:
The neural network was able to perform well for gastric cancer predictions using multiple clinical and demographic factors, showing great utility. The outcomes for AI-based diagnostic tools look promising in cancer, however generalization needs to be confirmed using external datasets. The study shows how artificial intelligence can better precision medicine and cancer diagnosis.
Keywords: Gastric Cancer Prediction, Neural Network Classification, Artificial Intelligence in Oncology, Clinical and Genetic Predictors, Precision Medicine Tools
1. BACKGROUND
There has been significant interest in the role of artificial neural networks to predict the outcomes of disease (1). A prior study has described how such algorithms could assist with cancer prediction in a number of ways, making them of particular interest to gastric cancer, currently the leading cause of global cancer-related deaths following significant growth in incidence over recent decades (1-4). The latter has significantly improved interventions in the hope of improved healthcare systems (5-8). The potential complexity of a cancer system and the great variety of influencing factors that can determine patient outcome, has made the use of advanced biomedical and computational models desirable (9). Consequently, researchers have exploited increasingly more sophisticated techniques to explore the factors that can determine cancer outcome (10, 11).
Still, it is important to understand the significance of considering the employment of state-of-the-art computational techniques (12). Gastric cancer (stomach cancer) has over the last few decades risen to the fourth and second most common cancer in both sexes respectively, with the fifth highest global mortality rates of any gender in 2018 (4). Much of this is associated with the growing worldwide prevalence of the Helicobacter pylori infection, the reduced global burden of such a commensal bacterium historically having contributed to its top rank in cancers of the early 1990s (13). Unlike many other forms of carcinoma, it usually emerges as a rapidly progressing sub-type making early detection difficult, which is currently the only way of offering effective treatment for a lasting cure (3). Thus, gastric cancer is a concerning pathology in today’s healthcare, requiring advances in understanding and management models, for which computational techniques can be of great utility (11). Discuss the rise of computational techniques in understanding complex systems in the healthcare sector, particularly the bioinformatics of such. Such a conceptual framework is an emerging horizon, making its application an underlying gap in the current literature that could guide to unique understandings (14)..
Understanding Gastric Cancer
Gastric cancer is globally recognized as a serious health problem and the fifth most common cancer. Alarmingly, it is the third leading cause of cancer death (15). Despite the marked decrease in its global incidence, curing gastric cancer remains a challenge and it is the third common cause of cancer deaths (2). Predicting the outcome of gastric cancer after six months to one year would be of great importance for physicians and patients (16). However, the course of this cancer is difficult to predict accurately due to its heterogeneity, the complex biological behavior of tumors, and the evolving multimodal treatment strategies (17). With regard to the subject, it is essential to outline the current understanding of this cancer in terms of its epidemiological and pathophysiological aspects before focusing on the role of neural network analysis (18).
Gastric cancer is the third most common cancer and the third leading cause of cancer death worldwide (19). The highest incidence is observed in Eastern Asia, Eastern Europe, and parts of Central and South America (20). The development of gastric cancer involves a complex interplay of environmental factors, host genetic factors, and gastric microbiota with Helicobacter pylori infection (21). There is a marked variability in gastric cancer incidence depending on ethnicity and geographic location, with a male-to-female ratio from 2:1 to 3:1 in most populations (22). Gastric cancer incidence varies according to anatomical subsites (23). There are also variations in prognosis and clinical features of these tumors according to the subsite (14). Survivability drops up to 15% during the five-year period when the tumor deceases at esophagogastric junction (13). Additionally, diffuse type or undifferentiated type, Borrmann type 4 macroscopic type, venous invasion, and deep invasion were found to be the worst prognosis factors (24).
Epidemiology and Risk Factors
Gastric cancer is the fifth deadly malignancy globally (19). The existence of epidemic patterns is an opportunity for early discovery of cancer (4). Too many studies concentrated on the determinants of life stages in cancer (20). Neural network analysis can classify cancer patients from the general population by lifestyle characteristics (7). Gastric cancer has many features with covariates, making it complicated for a clinician to evaluate and certify the state of health of the patient (5). It is beneficial that a technical method can be utilized to learn from the problem and amplify it to other similar states (21). Epidemiological parameters denote the odds of affliction by a malignancy, however, there is more complicated information contained in markers of incidence and mortality of cancer (22). From objectivity, it may be obtained from cancer hazard classified markers (23). Inadequate geological studies have assessed the risk of life stages of gastric cancer (24). In this study, ecological evidence was used to classify the hazard risk of the general population for the occurrence of gastric cancer in the Golestan region, in the eastern corner of the Caspian Sea (25). The statistic of prosperity of a mechanistic model granted by the input of legends on the market is analysed for each case of demographic and lifestyle markers (26). Understanding epidemic radiation risk can provide an opening for the beginning of prevention of malignant illness (24). Recurring emergence of certain epidemiological shapes signifies the profits of machining patterns for the discovery of cancer possibilities (26).
Gastric cancer is the fifth prevalent type of cancer and the fifth reason for fatality globally (21). The most frequently recorded malignant tumor is related to the digestive system in eastern Asia and is rated as the third reason for cancer mortality (23). The regions with the highest occurrence levels are lands in eastern and southern Asia, where the number of diagnoses enlarges nearly 69% of all incidents of gastric cancer worldwide (4). A reduction in the occurrence of one-third of all cancer diagnosis may be attributed to a transformation of lifestyle (1). Diet, consumption of tobacco, chronic consumption of the excess of salt, inadequate ability to diet and preservatives have left a substantial poison on the occurrence of the malady (3). Aging also plays a role in the genesis of the affliction as stated to anemia, tetracycline, smoking, and abuse with the “na-nashi”, “illegal” and “alu-bali” drugs of the Golestan District (7). A decrease in the accident of gastric cancer can contribute to a substantial benefit for this population or it can practice to curb the occurrence development of malady using intercept health (6). Epidemiological determinants are estimations of the chance of a malignancy (26). These determinants include risk assessments of malignancy, mortality, and incidence (27). Conversely, cancer risks add a study of existence and produce an evaluation of the chance of malignancy (28).
Pathophysiology
Gastric cancer, the fifth most prevalent malignant tumor globally and the third leading cause of cancer-related deaths, represents a major public health problem (29). Despite its decreasing incidence, it is still a major contributor to global cancer mortality (23). The etiology of gastric cancer includes the interaction of various risk factors such as environmental, genetic, immunological, and infectious agents (31). Disentangling the pathophysiologic mechanisms and molecular underpinnings of this complex etiology remains an active research field in efforts toward more effective prevention, early diagnosis, and personalized intervention (8). In this regard, great strides have been made in understanding the pathophysiology of gastric cancer development (9). It has been recognized that the atrophy-metaplasia-dysplasia pathway increases the risk of tumor development (11). Moreover, numerous studies have identified molecular events and gene expression profile changes that occur during these processes 30, and central biomolecular pathways have been well described in that regard (31).
At the index level, accumulating data has demonstrated that the disrupted atrophy pathway, namely the IL-1β/IL-6, Wnt, and TGF-β pathways, are crucial in the process of atrophy and dysplasia in gastric mucosa (32). An interfered metaplasia pathway via the Notch, JAK-STAT, and Sonic Hedgehog pathways is also documented (33). Moreover, oncogenic activation of the C-MYC oncogene was found to be significantly associated with early-stage dysplasia in vivo animal studies (34). Despite increasing knowledge in this context, it remains an ongoing challenge to fully understand the pathophysiological events underlying gastric cancer development (35-37). In this perspective, the tumor microenvironment has crucial implications on the different biological mechanisms the cancer may develop (38, 39).
Neural Networks in Healthcare
In recent decades, the expanding prominence of machine learning technologies and the wide application of neural networks have transformed many fields including healthcare analytics (40). Neural networks are computational models that mimic a simplified structure of the brain’s architecture (41). They are composed of a network of simple processing units or nodes that are interlinked by weighted connections (15). Neural networks are trained to mimic basic cognitive functions of the human brain, such as learning and generalization, from data (15). Over the years, neural network structures have been expanded, and they have been used as powerful tools to handle approximate functions with a complex input-output mapping. In the healthcare domain, because of the veracity, velocity, and the diversity at which the data are generated make healthcare data analysis a complex and challenging task, this gives neural networks a marked advantage to identify the patterns and relationships in large complex datasets that traditional approaches may not (42). Neural networks have also been used in a wide range of healthcare applications and have resulted in case examples from mammography classification, ECG signal analysis, medical image analysis and computer-aided diagnostics, automating clinical diagnosis from retinal fundus photographs, and survival analysis applications (43). In the context of gastric cancer, an artificial neural network (ANN) prognostic model was proposed for predicting the overall survival of gastric cancer patients (44). The ANN methodology was applied to model the gastric cancer prognosis using 3137 gastric cancer patients who underwent surgeries between the years 1995-2004 and 2006 from a multi-centre registry in the Klang Valley of Malaysia (44). Gastric cancer is the third most common cancer type worldwide and the second leading cause of cancer-related deaths (45). The Malaysian cancer registry statistics showed the incidence of gastric cancer in Malaysians rank the second most common cancer in males and fourth most common cancer in females (46). The disease was diagnosed mostly at the advanced stages and the five-year survival rate of the Malaysian gastric cancer patients is very low (46). Gastric cancer survival outcomes are not only influenced by the well-known factors like the age of the patient, tumour stage, differentiation grade, and the lymph node (47).
Overview of Neural Networks
Neural networks have recently been integrated more widely in medical studies to analyze data from a variety of sources (41). An essential introduction to the principles behind these networks is necessary before methodologies, results, and implications are presented (44). Computational systems for neural networks are inspired by how biological systems can process information (48). The basic building block of a system based on a neural network is the neuron (49). This unit processes the data and passes the outcome of the analysis on to further neurons. In modeling terms, data is “fed” into the network at input neurons (50). A process is then set off in which the data transfers down a sequence of interconnected layers of neurons before the final output is produced (43). One of the defining characteristics of a network is the shape of these layers (40). Taken together, these layers of neurons and the connections between them constitute the architecture of a network (51). Neural analysis has seen a variety of different architectures, but two are most common in medical studies (52). Feedforward neural networks feature direct connections between consequent layers such that data only progresses in one direction. More complicated networks such as recurrent neural networks permit feedback loops in which data can pass information back to earlier layers (15). The dynamics of these models mean they are more challenging to train, but are historically more successful in learning sequential data (51). Nevertheless, applications focus primarily on feedforward networks as they are simpler constructs and simpler to develop (52). These networks have been used extensively in previous medical analyses of gastric cancer (1).
Applications in Biomedical Research
Given their ability to model complex and often poorly understood biological processes, with recent advances in hardware and machine learning algorithms, neural networks have joined the burgeoning collection of big data tools currently addressing wide-ranging questions in many areas of biomedical research (53). While the standard methods for analyzing complex, high-dimensional data often depend on very strong assumptions of data structure, the flexibility of neural networks makes them uniquely valuable for managing and analyzing data (54). These considerations are also driving interest in their expanded role in personalized medicine (55). For example, to see how an ANN has modeled the effects of over 1,500 gene mutations and drug responses altogether in leukemia patients, a task simply out of reach of conventional methods (56). With the ever-growing flood of clinical and genomic data literally exploding on the scene, the field of neuroscience has been actively exploiting the flexibility and power of ANN methodologies (15). Established applications of various ANN models to analyze patient data include, but are not limited to, discrete association analysis, survival predictions, and mapping the high-dimensional effects of gene and drug mutations (57-65). It can be reasonably anticipated that such machine-learning approaches employing ANN models will increasingly address many critical queries in biomedical research (66).
In recent years, deep learning has come to revolutionize the field of imaging analysis, a domain where traditional ANN models have struggled (67). Convolutional neural networks (CNNs) serve as the backbone of state-of-the-art image recognition algorithms (68). Furthermore, focused efforts are being made to adjust CNN models specifically for pathology slides in order to drive drug discovery and assist disease prognosis (69). Given the huge success on discrete classification problems, CNN models are increasingly being applied to address more sophisticated questions related to continuous clinical variables (70). By aggregating low-level pathological features of cancer regions with CNN models, the survival rates of patients with various types of cancer can also be better predicted (1). With this broad impact already being felt, applications of networking imaging analysis using ANN methodologies transcend a single-discipline focus, further underpinning the transformative potential of network technology in broader medical settings (71-73).
Predictive Modeling in Gastric Cancer
The vast majority of studies published in the literature concerning gastric cancer focus solely on the clinical, demographic, and biological characteristics as the subject of interest (74). However, the sheer complexity of the syndrome calls for broader studies that consider a number of potential predictors to gain a more comprehensive understanding of the disease (75). A light literature review confirms a shift towards predictive modeling rooted in mathematical and computational principles; this, in particular, might be expected to result in great progress since it uses an extensive and diverse set of patient, disease, and demographic data of diagnosed cases (76-79). In light of this, the subsequent years should show an ever-increasing pace in the development of novel methodologies given their potential to inform and improve patient outcomes in gastroenterology (80).
After the initial development, traditional modeling methods have been among the most attractive due to the ease of their interpretation (41). Most commonly utilized statistical analysis methods apply a variety of techniques to analyze patients by comparing the specified predictive features with the actual distribution of the output variable (81). In the context of gastric cancer, however, these formulation-oriented methods suffer some notable restrictions (82). In general, this is due to the focus on one or two predictive factors (83). Considering that gastric cancer patients may exhibit complex patterns in a high dimension space, it is likely there is no single or combinatorial relationship among prominent predictors (84). Furthermore, the linearity assumption made by common statistical methods is implausible when searching out the complex associations between high-dimensional features of the suspected lesions and the likelihood of gastric cancer (85). Conversely, so long as the powerful means of modeling are available, the capture of the complex relationships may prove highly beneficial for enhancing diagnostic processes (86). Given that suspected lesions will be compared with an extensive variety of features obtained from a more comprehensive set of patient, anatomical, and modality attributes of gastric cancer, these advocate the appropriateness of advanced modeling approaches (87). Broadly speaking, the so-called black-box modeling methods, and in particular neural networks (NNs), would then stand to be preferred, by allowing an interaction among the complex and nonlinear patterns embodied by diverse sources of input data, thereby generating the predicted label (88). In light of this, a model incorporating the components of pre-processing, post-processing, and the NN itself is undertaken and methods are drawn up with an ambition to improve the prognosis of gastric cancer outcomes (88). Efforts are also made to examine the impact of factors such as archiving, the measure of diversity in the data and selection criteria, and the Smote algorithm to overcome the imbalance in output distribution (90).
2. OBJECTIVE
The main objective of the present study is to use the neural network analysis to identify the predictors of gastric cancer.
material and methods
Dataset
This dataset was designed to predict gastric cancer using machine learning models. The data encompasses clinical, demographic, diagnostic, and molecular information collected from various medical sources on gastric cancer (GC) patients. The dataset comes from clinical trials, medical images, and genomics. They have a literally rich collection of features that can help in identifying patterns and predicting cancer risks like genetic, environmental and lifestyle factors etc.
The data set consists of records of gastric cancer patients including their history, diagnosis and other imaging and molecular profiles. It is really helpful for detecting and figuring out gastric cancer using AI. It is also helpful in predicting models for clinical decision making. This dataset comprises 212253 participants.
3. RESULTS AND DISCUSSION
Case processing summary
As seen in Table 1, training part included about 70% of participants, whereas testing part included about 30% of participants.
Table 1. Case Processing Summary.
| N | Percent | ||
|---|---|---|---|
| Sample | Training | 148883 | 70.1% |
| Testing | 63471 | 29.9% | |
| Valid | 212354 | 100.0% | |
| Excluded | 0 | ||
| Total | 212354 | ||
Network information
Table 2 demonstrates the network information. Input layer includes the following factors: age, gender, family history, smoking, Alcohol consumption, Helicobacter pylori (HP), dietary habits, existing conditions, endoscopic images, biopsy results, CT scan, and Target symbol (TP53, KRAS, CDH1). Hidden layers include 1 layer in which there are 4 units. The activation function is Hyperbolic tangent. The output layer comprises the dependent variable, gastric cancer of two units either gastric cancer exists or not. The activation function is Softmax, and the error function is cross entropy.
Table 2. Network information.
| Input Layer | Factors | 1 | Age |
| 2 | Gender | ||
| 3 | Family history | ||
| 4 | Smoking | ||
| 5 | Alcohol | ||
| 6 | HP | ||
| 7 | Dietary habit | ||
| 8 | Existing condemns | ||
| 9 | Endoscopic images | ||
| 10 | Biopsy results | ||
| 11 | CT scan | ||
| 12 | Target_ symbol | ||
| Number of Unitsa | 94 | ||
| Hidden Layer(s) | Number of Hidden Layers | 1 | |
| Number of Units in Hidden Layer 1a | 4 | ||
| Activation Function | Hyperbolic tangent | ||
| Output Layer | Dependent Variables | 1 | Gastic_cancer |
| Number of Units | 2 | ||
| Activation Function | Softmax | ||
| Error Function | Cross-entropy | ||
| a. Excluding the bias unit | |||
Classification of gastric cancer
As shown in Table 3, the classification of gastric cancer is given for training and testing parts. The ability of this analysis using neural network to predict gastric cancer was 100% in training and testing parts so that all cases are predicted in both sections.
Table 3. Classification of gastric cancer.
| Sample | Observed | Predicted | ||
|---|---|---|---|---|
| no | yes | Percent Correct | ||
| Training | no | 134178 | 0 | 100.0% |
| yes | 14705 | 0 | 0.0% | |
| Overall Percent | 100.0% | 0.0% | 90.1% | |
| Testing | no | 57217 | 0 | 100.0% |
| yes | 6254 | 0 | 0.0% | |
| Overall Percent | 100.0% | 0.0% | 90.1% | |
| Dependent Variable: Gastric cancer | ||||
Independent variable importance
As demonstrated in Table 4 and Figure 1, the relative importance of independent variables as predictors of gastric cancer is given. The most important predictor is age, gender, family history, smoking, alcohol, Helicobacter pylori, dietary habits, existing conditions, endoscopic images, biopsy results, CT scan, and target symbol.
Table 4. Independent Variable Importance.
| Variable | Importance | Normalized Importance |
|---|---|---|
| Age | .371 | 100.0% |
| Gender | .029 | 7.9% |
| Family history | .065 | 17.5% |
| Smoking | .055 | 14.9% |
| Alcohol | .020 | 5.4% |
| Helicobacter Pylori | .034 | 9.2% |
| Dietary habit | .046 | 12.5% |
| Existing conditions | .075 | 20.2% |
| Endoscopic images | .069 | 18.6% |
| Biopsy results | .065 | 17.7% |
| CT scan | .089 | 24.1% |
| Target symbol | .081 | 21.8% |
Figure 1. The relative importance of predictors of gastric cancer.
4. DISCUSSION
The outcome demonstrates a high predictive accuracy using neural network model to classify gastric cancer using various clinical and demographic predictors. The implications will be discussed regarding the findings. This part makes usage of predictors and consistency with the literature
Getting the Model Ready
It is a common practice for a neural network model of training a model effectively along with a robust evaluation dataset (91). To train the model 70% of data and to test the model 30% data is divided as shown in the Table 1. This halts when increasing neurons doesn’t help error reduce and can even worsen.
Network Structure and Performance
Table 2 provides important details regarding the neural network design. A model of gastric cancer risk has been developed using 12 input variables. The variables are demographic, behavioral, clinical, and genetic. Following the principle of parsimony, an architecture with four units in a hidden layer is selected.
In the output layer we use Softmax and in the hidden layers we are using hyperbolic tangent as the activation function. They are the default choices for classification tasks. The hyperbolic tangent is a nonlinear function that can represent complex relationships between the predictors (92). The Softmax model was applied to assess whether the output is positive for cancer or not, enriched with gastric cancer data. The cross-entropy error function is used for classification in a model. It examines how far apart a prediction is from an actual event. Suitable for classification of two classes (93).
Classification Accuracy
Table 3 illustrates that the model achieved 100% accuracy for both the training and test datasets. However, while the results demonstrate the neural network’s potential, they should be treated with caution as it may be overfitting. Next studies must confirm the findings with other datasets. This will show its predictive usefulness and generalizability.
Independent Variable Importance.
Predictors are important (Table 4, Figure 1). The key factors based on existing knowledge base are age, gender, family history and H. pylori infection. Having a family history of stomach cancer and being older are well-known risk factors for gastric cancer. According to WHO, infection by helicobacter pylori is carcinogenic and it will lead to gastric inflammation, which will then be cancerous (94).
The presence of smoking and drinking alcohol further supports their recognized involvement in gastric cancer pathogenesis. According to Plummer and colleagues (95). The adjustment considers food and imaging (endoscopies, biopsies, and CTs) this allows inclusion of clinical diagnostics making it realistic to apply in practice Implications. Future Directions
According to the results, a neural network can enhance gastric cancer precision medicine. The model could combine a number of predicting factors in future. So, it aids in stratifying patient by risk or for examining patients. We need to take more action to perfect the model.
For testing the model, independent datasets from various populations will be used for testing. The process of removing abilities that aren’t all that relevant may reduce the model with no loss of accuracy. When clinicians find it easy to use the model, its integration to practice may happen.
5. CONCLUSION
According to this study, neural networks are efficient tools for the prediction of gastric cancer. The model estimates risk efficiently by considering demographic, behavioral, clinical and genetic features. In the future, the studies should be validated and optimized for the clinical translation.
Author’s contribution:
The author was involved in all steps of preparation this article, including final proofreading.
Conflict of interest:
None declared.
Financial support and sponsorship:
Nil.
REFERENCES
- 1.Que SJ, Chen QY, Qing-Zhong undefined, Liu ZY, et al. Application of preoperative artificial neural network based on blood biomarkers and clinicopathological parameters for predicting long-term survival of patients with gastric cancer. 2019 doi: 10.3748/wjg.v25.i43.6451. ncbi.nlm.nih.gov. [DOI] [PMC free article] [PubMed] [Google Scholar]
- 2.Wong MC, Huang J, Chan PS, Choi P, Lao XQ, Chan SM, Teoh A, Liang P. Global incidence and mortality of gastric cancer,1980-2018. JAMA network open. 2021 Jul 1;4(7):e2118457. doi: 10.1001/jamanetworkopen.2021.18457. jamanetwork.com. [DOI] [PMC free article] [PubMed] [Google Scholar]
- 3.Morgan E, Arnold M, Camargo MC, Gini A, Kunzmann AT, Matsuda T, Meheus F, Verhoeven RH, Vignat J, Laversanne M, Ferlay J. The current and future incidence and mortality of gastric cancer in 185 countries, 2020–40: a population-based modelling study. EClinicalMedicine. 2022 May 1;47 doi: 10.1016/j.eclinm.2022.101404. thelancet.com. [DOI] [PMC free article] [PubMed] [Google Scholar]
- 4.Ilic M, Ilic I. Epidemiology of stomach cancer. World journal of gastroenterology. 2022 doi: 10.3748/wjg.v28.i12.1187. nih.gov. [DOI] [PMC free article] [PubMed] [Google Scholar]
- 5.Song Y, Liu X, Cheng W, Li H, et al. The global, regional and national burden of stomach cancer and its attributable risk factors from 1990 to 2019. Scientific Reports. 2022 doi: 10.1038/s41598-022-15839-7. nature.com. [DOI] [PMC free article] [PubMed] [Google Scholar]
- 6.Thrift AP, Wenker TN, El-Serag HB. Global burden of gastric cancer: epidemiological trends, risk factors, screening and prevention. Nature reviews Clinical oncology. 2023 doi: 10.1038/s41571-023-00747-0. ns-svc.cn. [DOI] [PubMed] [Google Scholar]
- 7.Yang WJ, Zhao HP, Yu Y, Wang JH, Guo L, Liu JY, Pu J, Lv J. Updates on global epidemiology, risk and prognostic factors of gastric cancer. World Journal of Gastroenterology. 2023 Apr 4;29(16):2452. doi: 10.3748/wjg.v29.i16.2452. nih.gov. [DOI] [PMC free article] [PubMed] [Google Scholar]
- 8.Li J, Kuang XH, Zhang Y, Hu DM, et al. Global burden of gastric cancer in adolescents and young adults: estimates from GLOBOCAN 2020. Public Health. 2022 doi: 10.1016/j.puhe.2022.06.010. [HTML] [DOI] [PubMed] [Google Scholar]
- 9.He Y, Wang Y, Luan F, Yu Z, Feng H, Chen B, Chen W. Chinese and global burdens of gastric cancer from 1990 to 2019. Cancer Medicine. 2021 May;10(10):3461–3473. doi: 10.1002/cam4.3892. wiley.com. [DOI] [PMC free article] [PubMed] [Google Scholar]
- 10.Chen M, Chen K, Hou H, Li W, Wang X, Dao Q, Wang Z. Incidence and mortality trends in gastric cancer in the United States,1992‐2019. International Journal of Cancer. 2023 May 1;152(9):1827–1836. doi: 10.1002/ijc.34415. [HTML] [DOI] [PubMed] [Google Scholar]
- 11.Cao W, Chen HD, Yu YW, Li N, et al. Changing profiles of cancer burden worldwide and in China: a secondary analysis of the global cancer statistics 2020. Chinese medical journal. 2021 doi: 10.1097/CM9.0000000000001474. mednexus.org. [DOI] [PMC free article] [PubMed] [Google Scholar]
- 12.López MJ, Carbajal J, Alfaro AL, Saravia LG, Zanabria D, Araujo JM, Quispe L, Zevallos A, Buleje JL, Cho CE, Sarmiento M. Characteristics of gastric cancer around the world. Critical Reviews in Oncology/Hematology. 2023 Jan 1;181:103841. doi: 10.1016/j.critrevonc.2022.103841. [HTML] [DOI] [PubMed] [Google Scholar]
- 13.Lin Y, Zheng Y, Wang H, Wu J. Global patterns and trends in gastric cancer incidence rates (1988–2012) and predictions to 2030. Gastroenterology. 2021 doi: 10.1053/j.gastro.2021.03.023. gastrojournal.org. [DOI] [PubMed] [Google Scholar]
- 14.Joshi SS, Badgwell BD. Current treatment and recent progress in gastric cancer. CA: a cancer journal for clinicians. 2021 doi: 10.3322/caac.21657. wiley.com. [DOI] [PMC free article] [PubMed] [Google Scholar]
- 15.Nilsaz-Dezfouli H, Rizam Abu-Bakar M, Arasan J, Bakri Adam M, et al. Improving Gastric Cancer Outcome Prediction Using Single Time-Point Artificial Neural Network Models. 2017 doi: 10.1177/1176935116686062. ncbi.nlm.nih.gov. [DOI] [PMC free article] [PubMed] [Google Scholar]
- 16.Ajani JA, D’Amico TA, Bentrem DJ, Chao J, Cooke D, Corvera C, Das P, Enzinger PC, Enzler T, Fanta P, Farjah F. Gastric cancer, version 2.2022, NCCN clinical practice guidelines in oncology. Journal of the National Comprehensive Cancer Network. 2022 Feb 1;20(2):167–192. doi: 10.6004/jnccn.2022.0008. [HTML] [DOI] [PubMed] [Google Scholar]
- 17.Xia JY, Aadam AA. Advances in screening and detection of gastric cancer. Journal of surgical oncology. 2022 doi: 10.1002/jso.26844. wiley.com. [DOI] [PMC free article] [PubMed] [Google Scholar]
- 18.Li GZ, Doherty GM, Wang J. Surgical management of gastric cancer: a review. JAMA surgery. 2022 doi: 10.1001/jamasurg.2022.0182. dermavidya.com. [DOI] [PubMed] [Google Scholar]
- 19.Reza Afrash M, Shafiee M, Kazemi-Arpanahi H. Establishing machine learning models to predict the early risk of gastric cancer based on lifestyle factors. 2023 doi: 10.1186/s12876-022-02626-x. ncbi.nlm.nih.gov. [DOI] [PMC free article] [PubMed] [Google Scholar]
- 20.Singh A. Global burden of five major types of gastrointestinal cancer. Gastroenterology Review/Przegląd Gastroenterologiczny. 2024 Jul 1;19(1) doi: 10.5114/pg.2024.141834. termedia.pl. [DOI] [PMC free article] [PubMed] [Google Scholar]
- 21.Then EO, Grantham T, Deda X, Ramachandran R, Gaduputi V. Metastatic gastric cancer to the colon. World Journal of Oncology. 2021 Aug;12(4):127. doi: 10.14740/wjon1375. nih.gov. [DOI] [PMC free article] [PubMed] [Google Scholar]
- 22.Grantham T, Ramachandran R, Parvataneni S, Budh D, Gollapalli S, Gaduputi V. Epidemiology of Gastric Cancer: Global Trends, Risk Factors and Premalignant Conditions. Journal of Community Hospital Internal Medicine Perspectives. 2023;13(6):100. doi: 10.55729/2000-9666.1252. nih.gov. [DOI] [PMC free article] [PubMed] [Google Scholar]
- 23.Yang K, Lu L, Liu H, Wang X, Gao Y, Yang L, Li Y, Su M, Jin M, Khan S. A comprehensive update on early gastric cancer: defining terms, etiology, and alarming risk factors. Expert Review of Gastroenterology & Hepatology. 2021 Mar 4;15(3):255–273. doi: 10.1080/17474124.2021.1845140. [HTML] [DOI] [PubMed] [Google Scholar]
- 24.Liu HL, Peng H, Huang CH, Zhou HY, Ge J. Mutational separation and clinical outcomes of TP53 and CDH1 in gastric cancer. World Journal of Gastrointestinal Surgery. 2023 Dec 12;15(12):2855. doi: 10.4240/wjgs.v15.i12.2855. nih.gov. [DOI] [PMC free article] [PubMed] [Google Scholar]
- 25.Syarifuddin E, Lusikooy RE, Labeda I, Sampetoding S, Dani MI, Kusuma MI, Uwuratuw JA, Faruk M. Association of clinicopathological features and gastric cancer incidence in a single institution. Asian Journal of Surgery. 2022 Jan 1;45(1):246–249. doi: 10.1016/j.asjsur.2021.05.004. sciencedirect.com. [DOI] [PubMed] [Google Scholar]
- 26.Nouri M, Zayeri F, Akbari ME, Khayamzadeh M, Moradian F. Association between gastric cancer mortality-to-incidence ratio and human development index: evidence from the global burden of disease study 2016. Archives of Iranian Medicine. 2021 Dec 1;24(12):869–75. doi: 10.34172/aim.2021.130. journalaim.com. [DOI] [PubMed] [Google Scholar]
- 27.Shin WS, Xie F, Chen B, Yu P, et al. Updated epidemiology of gastric cancer in Asia: Decreased incidence but still a big challenge. Cancers. 2023 doi: 10.3390/cancers15092639. mdpi.com. [DOI] [PMC free article] [PubMed] [Google Scholar]
- 28.Iwu CD, Iwu-Jaja CJ. Gastric cancer epidemiology: Current trend and future direction. Hygiene. 2023 mdpi.com. [Google Scholar]
- 29.Yu C, Wang J. Quantification of the Landscape for Revealing the Underlying Mechanism of Intestinal-Type Gastric Cancer. 2022 doi: 10.3389/fonc.2022.853768. ncbi.nlm.nih.gov. [DOI] [PMC free article] [PubMed] [Google Scholar]
- 30.Song WM, Lin X, Liao X, Hu D, et al. Multiscale network analysis reveals molecular mechanisms and key regulators of the tumor microenvironment in gastric cancer. 2019 doi: 10.1002/ijc.32643. ncbi.nlm.nih.gov. [DOI] [PMC free article] [PubMed] [Google Scholar]
- 31.Grad C, Grad S, Fărcaş RA, Popa S, Dumitraşcu DL. Changing trends in the epidemiology of gastric cancer. Medicine and Pharmacy Reports. 2023 Jul;96(3):229. doi: 10.15386/mpr-2538. nih.gov. [DOI] [PMC free article] [PubMed] [Google Scholar]
- 32.Goldenring JR, Mills JC. Cellular plasticity, reprogramming, and regeneration: metaplasia in the stomach and beyond. Gastroenterology. 2022 doi: 10.1053/j.gastro.2021.10.036. sciencedirect.com. [DOI] [PMC free article] [PubMed] [Google Scholar]
- 33.Jia J, Zhao H, Li F, Zheng Q, Wang G, Li D, Liu Y. Research on drug treatment and the novel signaling pathway of chronic atrophic gastritis. Biomedicine & Pharmacotherapy. 2024 Jul 1;176:116912. doi: 10.1016/j.biopha.2024.116912. sciencedirect.com. [DOI] [PubMed] [Google Scholar]
- 34.Yang H, Wei B, Hu B. Chronic inflammation and long-lasting changes in the gastric mucosa after Helicobacter pylori infection involved in gastric cancer. Inflammation Research. 2021 doi: 10.1007/s00011-021-01501-x. [HTML] [DOI] [PubMed] [Google Scholar]
- 35.Shuman JH, Lin AS, Westland MD, Bryant KN, Piazuelo MB, Reyzer ML, Judd AM, McDonald WH, McClain MS, Schey KL, Algood HM. Remodeling of the gastric environment in Helicobacter pylori-induced atrophic gastritis. Msystems. 2024 Jan 23;9(1):e01098–23. doi: 10.1128/msystems.01098-23. asm.org. [DOI] [PMC free article] [PubMed] [Google Scholar]
- 36.Cai Q, Shi P, Yuan Y, Peng J, Ou X, Zhou W, Li J, Su T, Lin L, Cai S, He Y. Inflammation-associated senescence promotes Helicobacter pylori–induced atrophic gastritis. Cellular and molecular gastroenterology and hepatology. 2021 Jan 1;11(3):857–880. doi: 10.1016/j.jcmgh.2020.10.015. sciencedirect.com. [DOI] [PMC free article] [PubMed] [Google Scholar]
- 37.Kuang W, Xu J, Xu F, Huang W, Majid M, Shi H, Yuan X, Ruan Y, Hu X. Current study of pathogenetic mechanisms and therapeutics of chronic atrophic gastritis: a comprehensive review. Frontiers in Cell and Developmental Biology. 2024 Dec 10;12:1513426. doi: 10.3389/fcell.2024.1513426. frontiersin.org. [DOI] [PMC free article] [PubMed] [Google Scholar]
- 38.Cui G, Yuan A, Li Z. Occurrences and phenotypes of RIPK3-positive gastric cells in Helicobacter pylori infected gastritis and atrophic lesions. Digestive and Liver Disease. 2022 doi: 10.1016/j.dld.2022.04.013. nord.no. [DOI] [PubMed] [Google Scholar]
- 39.He Q, Liu L, Wei J, Jiang J, Rong Z, Chen X, Zhao J, Jiang K. Roles and action mechanisms of bile acid-induced gastric intestinal metaplasia: a review. Cell Death Discovery. 2022 Apr 4;8(1):158. doi: 10.1038/s41420-022-00962-1. nature.com. [DOI] [PMC free article] [PubMed] [Google Scholar]
- 40.Wang Y, Wang YG, Hu C, Li M, Fan Y, Otter N, Sam I, Gou H, Hu Y, Kwok T, Zalcberg J. Cell graph neural networks enable the precise prediction of patient survival in gastric cancer. NPJ precision oncology. 2022 Jun 23;6(1):45. doi: 10.1038/s41698-022-00285-5. nature.com. [DOI] [PMC free article] [PubMed] [Google Scholar]
- 41.Aslam MA, Xue C, Liu M, Wang K, Cui D. Classification and Prediction of Gastric Cancer from Saliva Diagnosis using Artificial Neural Network. Engineering letters. 2021 Feb 1;29(1) engineeringletters.com. [Google Scholar]
- 42.Yan X, Wang W, Xiao M, Li Y, Gao M. Survival prediction across diverse cancer types using neural networks. In Proceedings of the 2024 7th International Conference on Machine Vision and Applications. 2024 Mar 12;:134–138. [PDF] [Google Scholar]
- 43.Alkhatib AJ, Alharoun M, Alzoubi A, Muqdadi E, Aqoulah AA. Diagnosing Brain Tumors from MRI images through a Multi-Fused CNN with Auxiliary Layers. Sustainable Machine Intelligence Journal. 2024 Mar 2;6:2–1. [Google Scholar]
- 44.Jin C, Jiang Y, Yu H, Wang W, Li B, Chen C, Yuan Q, Hu Y, Xu Y, Zhou Z, Li G. Deep learning analysis of the primary tumour and the prediction of lymph node metastases in gastric cancer. British Journal of Surgery. 2021 May 1;108(5):542–9. doi: 10.1002/bjs.11928. [HTML] [DOI] [PubMed] [Google Scholar]
- 45.Liu D, Wang X, Li L, Jiang Q, Li X, Liu M, Wang W, Shi E, Zhang C, Wang Y, Zhang Y. Machine learning-based model for the prognosis of postoperative gastric cancer. Cancer Management and Research. 2022 Jan;7:135–55. doi: 10.2147/CMAR.S342352. tandfonline.com. [DOI] [PMC free article] [PubMed] [Google Scholar]
- 46.Alkhatib AJ, Alharoun M, AlZoubi A. A Deep Learning Framework for Timely Bone Fracture Detection and Prevention. Information Sciences with Applications. 2024 Jan 31;1:52–61. [Google Scholar]
- 47.Huang B, Tian S, Zhan N, Ma J, Huang Z, Zhang C, Zhang H, Ming F, Liao F, Ji M, Zhang J. Accurate diagnosis and prognosis prediction of gastric cancer using deep learning on digital pathological images: A retrospective multicentre study. EBioMedicine. 2021 Nov 1;73 doi: 10.1016/j.ebiom.2021.103631. thelancet.com. [DOI] [PMC free article] [PubMed] [Google Scholar]
- 48.Chen PC, Lu YR, Kang YN, Chang CC. The accuracy of artificial intelligence in the endoscopic diagnosis of early gastric cancer: pooled analysis study. Journal of medical Internet research. 2022 May 16;24(5):e27694. doi: 10.2196/27694. jmir.org. [DOI] [PMC free article] [PubMed] [Google Scholar]
- 49.Ueyama H, Kato Y, Akazawa Y, Yatagai N, Komori H, Takeda T, Matsumoto K, Ueda K, Matsumoto K, Hojo M, Yao T. Application of artificial intelligence using a convolutional neural network for diagnosis of early gastric cancer based on magnifying endoscopy with narrow‐band imaging. Journal of gastroenterology and hepatology. 2021 Feb;36(2):482–489. doi: 10.1111/jgh.15190. wiley.com. [DOI] [PMC free article] [PubMed] [Google Scholar]
- 50.Bhardwaj P, Bhandari G, Kumar Y, Gupta S. An investigational approach for the prediction of gastric cancer using artificial intelligence techniques: a systematic review. Archives of Computational Methods in Engineering. 2022 Oct;29(6):4379–400. [HTML] [Google Scholar]
- 51.Cao R, Tang L, Fang M, Zhong L, Wang S, Gong L, Li J, Dong D, Tian J. Artificial intelligence in gastric cancer: applications and challenges. Gastroenterology Report. 2022 Jan 1;10:goac064. doi: 10.1093/gastro/goac064. oup.com. [DOI] [PMC free article] [PubMed] [Google Scholar]
- 52.Hu H, Gong L, Dong D, Zhu L, Wang M, He J, Shu L, Cai Y, Cai S, Su W, Zhong Y. Identifying early gastric cancer under magnifying narrow-band images with deep learning: a multicenter study. Gastrointestinal Endoscopy. 2021 Jun 1;93(6):1333–1341. doi: 10.1016/j.gie.2020.11.014. [HTML] [DOI] [PubMed] [Google Scholar]
- 53.Weiss R, Karimijafarbigloo S, Roggenbuck D, Rödiger S. Applications of neural networks in biomedical data analysis. Biomedicines. 2022 Jun 21;10(7):1469. doi: 10.3390/biomedicines10071469. mdpi.com. [DOI] [PMC free article] [PubMed] [Google Scholar]
- 54.Athanasopoulou K, Daneva GN, Adamopoulos PG, Scorilas A. Artificial intelligence: the milestone in modern biomedical research. BioMedInformatics. 2022 Dec 17;2(4):727–744. mdpi.com. [Google Scholar]
- 55.Fan Z, Kernan KF, Sriram A, Benos PV, Canna SW, Carcillo JA, Kim S, Park HJ. Deep neural networks with knockoff features identify nonlinear causal relations and estimate effect sizes in complex biological systems. GigaScience. 2023;12:giad044. doi: 10.1093/gigascience/giad044. oup.com. [DOI] [PMC free article] [PubMed] [Google Scholar]
- 56.Mirarchi A, Peláez RP, Simeon G, De Fabritiis G. AMARO: All Heavy-Atom Transferable Neural Network Potentials of Protein Thermodynamics. Journal of Chemical Theory and Computation. 2024 Nov 8;20(22):9871–9878. doi: 10.1021/acs.jctc.4c01239. nih.gov. [DOI] [PMC free article] [PubMed] [Google Scholar]
- 57.Erbas I, Pandey V, Amarnath A, Wang N, Swaminathan K, Radev ST, Intes X. Compressing recurrent neural networks for FPGA-accelerated implementation in fluorescence lifetime imaging. arXiv preprint arXiv:241000948. 2024 Oct 1; [PDF] [Google Scholar]
- 58.Hartman E, Scott AM, Karlsson C, Mohanty T, Vaara ST, Linder A, Malmström L, Malmström J. Interpreting biologically informed neural networks for enhanced proteomic biomarker discovery and pathway analysis. Nature Communications. 2023 Sep 2;14(1):5359. doi: 10.1038/s41467-023-41146-4. nature.com. [DOI] [PMC free article] [PubMed] [Google Scholar]
- 59.Wang Z, Ren Y, Peng Q, Ji D. A context-enhanced neural network model for biomedical event trigger detection. Information Sciences. 2025 [HTML] [Google Scholar]
- 60.Taghizadeh M, Khayambashi K, Hasnat MA, Alemazkoor N. Multi-fidelity graph neural networks for efficient power flow analysis under high-dimensional demand and renewable generation uncertainty. Electric Power Systems Research. 2024 Dec 1;237:111014. researchsquare.com. [Google Scholar]
- 61.Xu K, Wu Y, Xia H, Sang N, Wang B. Graph Neural Networks in Financial Markets: Modeling Volatility and Assessing Value-at-Risk. Journal of Computer Technology and Software. 2022 Apr 30;1(2) ashpress.org. [Google Scholar]
- 62.Batalov E, Haverstock P, Anderson R, Thompson W, Wolverton R. Ransomware detection via network traffic analysis using isolation forest and lstm neural networks. authorea.com. [Google Scholar]
- 63.Yang M, Lim MK, Qu Y, Li X, et al. Deep neural networks with L1 and L2 regularization for high dimensional corporate credit risk prediction. Expert Systems with Applications. 2023 gla.ac.uk. [Google Scholar]
- 64.Abbas F, Zhang F, Abbas F, Ismail M, Iqbal J, Hussain D, Khan G, Alrefaei AF, Albeshr MF. Landslide susceptibility mapping: analysis of different feature selection techniques with artificial neural network tuned by bayesian and metaheuristic algorithms. Remote Sensing. 2023 Sep 2;15(17):4330. mdpi.com. [Google Scholar]
- 65.Zhao J, Han X, Ouyang M, Burke AF. Specialized deep neural networks for battery health prognostics: Opportunities and challenges. Journal of Energy Chemistry. 2023 researchgate.net. [Google Scholar]
- 66.Lummen D, Gruber S, Schmidt A, Abramov J, Anderson C. Opcode-based ransomware detection using hybrid extreme gradient boosting and recurrent neural networks. Authorea Preprints. 2024 techrxiv.org. [Google Scholar]
- 67.Chen L, Li S, Bai Q, Yang J, et al. Review of image classification algorithms based on convolutional neural networks. Remote Sensing. 2021 mdpi.com. [Google Scholar]
- 68.Islam MM, Nooruddin S, Karray F, Muhammad G. Human activity recognition using tools of convolutional neural networks: A state of the art review, data sets, challenges, and future prospects. Computers in biology and medicine. 2022 Oct 1;149:106060. doi: 10.1016/j.compbiomed.2022.106060. [PDF] [DOI] [PubMed] [Google Scholar]
- 69.Ige AO, Sibiya M. State-of-the-art in 1D Convolutional Neural Networks: A survey. IEEE Access. 2024 ieee.org. [Google Scholar]
- 70.Taye MM. Theoretical understanding of convolutional neural network: Concepts, architectures, applications, future directions. Computation. 2023 mdpi.com. [Google Scholar]
- 71.Turay T, Vladimirova T. Toward performing image classification and object detection with convolutional neural networks in autonomous driving systems: A survey. IEEE Access. 2022 ieee.org. [Google Scholar]
- 72.Rangel G, Cuevas-Tello JC, Nunez-Varela J, Puente C, Silva-Trujillo AG. A survey on convolutional neural networks and their performance limitations in image recognition tasks. Journal of sensors. 2024;2024(1):2797320. wiley.com. [Google Scholar]
- 73.Ma N, Fan J, Wang W, Wu J, Jiang Y, Xie L, Fan R. Computer vision for road imaging and pothole detection: a state-of-the-art review of systems and algorithms. Transportation safety and Environment. 2022 Dec;4(4):tdac026. oup.com. [Google Scholar]
- 74.Alsina M, Arrazubi V, Diez M, Tabernero J. Current developments in gastric cancer: from molecular profiling to treatment strategy. Nature Reviews Gastroenterology & Hepatology. 2023 Mar;20(3):155–170. doi: 10.1038/s41575-022-00703-w. [HTML] [DOI] [PubMed] [Google Scholar]
- 75.Seeneevassen L, Bessède E, Mégraud F, Lehours P, Dubus P, Varon C. Gastric cancer: advances in carcinogenesis research and new therapeutic strategies. International journal of molecular sciences. 2021 Mar 26;22(7):3418. doi: 10.3390/ijms22073418. mdpi.com. [DOI] [PMC free article] [PubMed] [Google Scholar]
- 76.Lordick F, Carneiro F, Cascinu S, Fleitas T, Haustermans K, Piessen G, Vogel A, Smyth EC. Gastric cancer: ESMO Clinical Practice Guideline for diagnosis, treatment and follow-up☆. Annals of Oncology. 2022 Oct 1;33(10):1005–1020. doi: 10.1016/j.annonc.2022.07.004. annalsofoncology.org. [DOI] [PubMed] [Google Scholar]
- 77.Zeng Y, Jin RU. Molecular pathogenesis, targeted therapies, and future perspectives for gastric cancer. Seminars in cancer biology. 2022 doi: 10.1016/j.semcancer.2021.12.004. sciencedirect.com. [DOI] [PubMed] [Google Scholar]
- 78.Qing X, Xu W, Liu S, Chen Z, Ye C, Zhang Y. Molecular characteristics, clinical significance, and cancer immune interactions of angiogenesis-associated genes in gastric cancer. Frontiers in immunology. 2022 Feb 22;13:843077. doi: 10.3389/fimmu.2022.843077. frontiersin.org. [DOI] [PMC free article] [PubMed] [Google Scholar]
- 79.Yeoh KG, Tan P. Mapping the genomic diaspora of gastric cancer. Nature reviews cancer. 2022 doi: 10.1038/s41568-021-00412-7. [HTML] [DOI] [PubMed] [Google Scholar]
- 80.Sajjad H, Imtiaz S, Noor T, Siddiqui YH, Sajjad A, Zia M. Cancer models in preclinical research: A chronicle review of advancement in effective cancer research. Animal Models and Experimental Medicine. 2021 Jun;4(2):87–103. doi: 10.1002/ame2.12165. wiley.com. [DOI] [PMC free article] [PubMed] [Google Scholar]
- 81.Wu D, Lu J, Zheng N, Elsehrawy MG, Alfaiz FA, Zhao H, Alqahtani MS, Xu H. Utilizing nanotechnology and advanced machine learning for early detection of gastric cancer surgery. Environmental Research. 2024 Mar 15;245:117784. doi: 10.1016/j.envres.2023.117784. [HTML] [DOI] [PubMed] [Google Scholar]
- 82.Jamil D, Palaniappan S, Lokman A, Naseem M, et al. Diagnosis of gastric cancer using machine learning techniques in healthcare sector: A survey. Informatica. 2022 informatica.si. [Google Scholar]
- 83.Gogoshin G, Rodin AS. Graph neural networks in cancer and oncology research: Emerging and future trends. Cancers. 2023 doi: 10.3390/cancers15245858. mdpi.com. [DOI] [PMC free article] [PubMed] [Google Scholar]
- 84.Du H, Yang Q, Ge A, Zhao C, et al. Explainable machine learning models for early gastric cancer diagnosis. Scientific Reports. 2024 doi: 10.1038/s41598-024-67892-z. nature.com. [DOI] [PMC free article] [PubMed] [Google Scholar]
- 85.Wang Z, Liu Y, Niu X. Application of artificial intelligence for improving early detection and prediction of therapeutic outcomes for gastric cancer in the era of precision oncology. Seminars in Cancer Biology. 2023 doi: 10.1016/j.semcancer.2023.04.009. binasss.sa.cr. [DOI] [PubMed] [Google Scholar]
- 86.Sahoo AK, Chakraverty S. An unsupervised wavelet neural network model for approximating the solutions of non-linear nervous stomach model governed by tension, food and medicine. Computer Methods in Biomechanics and Biomedical Engineering. 2024 Aug 17;27(11):1538–1551. doi: 10.1080/10255842.2023.2248332. [HTML] [DOI] [PubMed] [Google Scholar]
- 87.Li C, Liu S, Zhang Q, Wan D, Shen R, Wang Z, Li Y, Hu B. Combining Raman spectroscopy and machine learning to assist early diagnosis of gastric cancer. Spectrochimica Acta Part A: Molecular and Biomolecular Spectroscopy. 2023 Feb 15;287:122049. doi: 10.1016/j.saa.2022.122049. [HTML] [DOI] [PubMed] [Google Scholar]
- 88.Wafa AA, Essa RM, Abohany AA, Abdelkader HE. Integrating deep learning for accurate gastrointestinal cancer classification: a comprehensive analysis of MSI and MSS patterns using histopathology data. Neural Computing and Applications. 2024 Aug;26:1–33. springer.com. [Google Scholar]
- 89.Mao S, Liu J. MulitDeepsurv: survival analysis of gastric cancer based on deep learning multimodal fusion models. Biomedical Optics Express. 2024 doi: 10.1364/BOE.541570. optica.org. [DOI] [PMC free article] [PubMed] [Google Scholar]
- 90.Alkhatib AJ, AlZoubi A, Alaiad A, Aqoulah AA, Alharoun M. Privacy Issues in Electronic Medical Records: A Systematic Review. Multicriteria Algorithms with Applications. 2024 Mar 13;3:32–41. [Google Scholar]
- 91.Goodfellow I, Bengio Y, Courville A. Cambridge: MIT Press; 2016. Deep Learning. [Google Scholar]
- 92.LeCun Y, Bengio Y, Hinton G. Deep learning. Nature. 2015;521(7553):436–444. doi: 10.1038/nature14539. [DOI] [PubMed] [Google Scholar]
- 93.LeCun Y, Bengio Y, Hinton G. Deep learning. Nature. 2015;521(7553):436–44. doi: 10.1038/nature14539. [DOI] [PubMed] [Google Scholar]
- 94.Correa P. Human gastric carcinogenesis: A multistep and multifactorial process. Cancer Res. 1992;52(24):6735s–40s. [PubMed] [Google Scholar]
- 95.Plummer M, Franceschi S, Vignat J, Forman D. Global burden of gastric cancer attributable to Helicobacter pylori. Int J Cancer. 2015;136(2):487–490. doi: 10.1002/ijc.28999. [DOI] [PubMed] [Google Scholar]