As a form of artificial intelligence, artificial neural networks (ANNs) have the advantages of adaptability, parallel processing capabilities, and non-linear processing. They have been widely used in the early detection and diagnosis of tumors. In this article, we introduce the development, working principle, and characteristics of ANNs and review the research progress on the application of ANNs in the detection and diagnosis of gastrointestinal and liver tumors.

Background: Hepatocellular carcinoma (HCC) remains a significant therapeutic challenge due to its complex molecular mechanisms and limited effective treatments. Although the Tibetan medicine Liuwei Muxiang Pill (LWMX) has shown efficacy in gastric and colorectal cancer, no study has yet demonstrated its potential anti-HCC activity. Objective: To evaluate the therapeutic effects of LWMX on HCC. Methods: Integrating network pharmacology, high-resolution mass spectrometry, machine learning, and molecular dynamics simulations, combined with in vitro experiments for mechanism validation. Results: The study identified (Checkpoint kinase 1) CHK1 as a key target of LWMX in HCC regulation and confirmed that quercetin can form a stable complex with CHK1. In vitro experiments demonstrated that LWMX and its active component quercetin significantly inhibit the proliferation and migration of HCC cells. Conclusions: The study establishes CHK1 as a key therapeutic target, confirming the potential of LWMX and its core component quercetin in the treatment of HCC.

Objective: Rapid on-site evaluation (ROSE) of respiratory cytology specimens is a critical technique for accurate and timely diagnosis of lung cancer. However, in China, limited familiarity with the Diff-Quik staining method and a shortage of trained cytopathologists hamper utilization of ROSE. Therefore, developing an improved deep learning model to assist clinicians in promptly and accurately evaluating Diff-Quik stained cytology samples during ROSE has important clinical value. Methods: Retrospectively, 116 digital images of Diff-Quik stained cytology samples were obtained from whole slide scans. These included 6 diagnostic categories - carcinoid, normal cells, adenocarcinoma, squamous cell carcinoma, non-small cell carcinoma, and small cell carcinoma. All malignant diagnoses were confirmed by histopathology and immunohistochemistry. The test image set was presented to 3 cytopathologists from different hospitals with varying levels of experience, as well as an artificial intelligence system, as single-choice questions. Results: The diagnostic accuracy of the cytopathologists correlated with their years of practice and hospital setting. The AI model demonstrated proficiency comparable to the humans. Importantly, all combinations of AI assistance and human cytopathologist increased diagnostic efficiency to varying degrees. Conclusions: This deep learning model shows promising capability as an aid for on-site diagnosis of respiratory cytology samples. However, human expertise remains essential to the diagnostic process.

Objective: To evaluate the therapeutic potential of the curcumin analog J7 in protecting the liver and regulating glucose and lipid metabolism in rats with type 2 diabetes. Methods: Bioinformatics methods were used to identify signaling pathways linked to diabetic liver disease. Diabetic rats were treated with curcumin, low-dose J7, or high-dose J7, and liver function and fibrosis were assessed through biochemical analyses, histopathology, immunohistochemistry, and ELISA. Results: J7 administration significantly improved lisver function, reduced fibrosis, and regulated metabolic profiles in diabetic rats. J7 downregulated TGF-β 1, NF-κB p65, and BAX, while upregulating BCL-2, showing superior effects to traditional curcumin in reducing TGF-β 1 and inhibiting α-SMA expression. Conclusion: J7 demonstrates potential as a therapeutic agent for managing liver complications in type 2 diabetes, effectively attenuating liver fibrosis and regulating metabolism through the modulation of key signaling pathways and proteins. Plain Language Summary: Diabetes is a common condition that can cause serious problems in the liver, such as damage and scarring (fibrosis). These problems are linked to how the body handles sugar and fat. Right now, there are not many effective treatments for diabetes-related liver issues. Our study looked at a new drug called J7, which is based on curcumin, a natural compound found in turmeric, to see if it could help protect the liver and improve sugar and fat metabolism. We used a rat model of type 2 diabetes to test J7. Rats were given either curcumin, a low dose of J7, or a high dose of J7. We then measured how well their livers were working and examined their liver tissue under a microscope. We also looked at the levels of specific molecules in the liver that are involved in inflammation, scarring, and cell survival. We found that J7 worked better than regular curcumin. It reduced liver damage, improved how the liver handled sugar and fat, and lessened scarring. J7 achieved this by affecting certain biological pathways, like the TGF-β/Smad pathway and NF-κB signaling, which are key players in liver damage and inflammation. These results suggest that J7 could be a promising new treatment for liver problems in people with diabetes. This study highlights the potential of improving natural compounds like curcumin to make them more effective as medicines. Further research is needed to explore how J7 might help people with diabetes and liver issues.

This study examines the integration of narrative medicine (NM) into primary healthcare (PHC) settings, evaluating its role in enhancing medical humanities education within grassroots healthcare institutions. Through a comprehensive literature review and case analysis, the research investigates the current state, challenges, and practical barriers to embedding NM into PHC systems, while proposing targeted strategies for improvement. The findings suggest that NM fosters stronger doctor-patient trust, enhances healthcare quality, and promotes humanistic care. However, primary hospitals face numerous challenges in advancing medical humanities, including a lack of trust between doctors and patients, tensions arising from the commercialization of healthcare, institutional limitations, unequal distribution of resources, and issues related to physicians' professional competencies and stress management. These interrelated obstacles detract from the quality of PHC services and the overall patient experience. Drawing on successful case studies from primary hospitals, the paper outlines effective strategies for overcoming these challenges. The study provides both theoretical and practical insights for advancing medical humanities in PHC, contributing to improvements in healthcare service quality and supporting the development of high standards in the healthcare sector. Ultimately, the findings aim to promote the broader adoption and ongoing refinement of NM within PHC institutions.