A feasibility study on utilizing machine learning technology to reduce the costs of gastric cancer screening in Taizhou, China.

Aim: To optimize gastric cancer screening score and reduce screening costs using machine learning models. Methods: This study included 228,634 patients from the Taizhou Gastric Cancer Screening Program. We used three machine learning models to optimize Li's gastric cancer screening score: Gradient Boosting Machine (GBM), Distributed Random Forest (DRF), and Deep Learning (DL). The performance of the binary classification models was evaluated using the area under the curve (AUC) and area under the precision-recall curve (AUCPR). Results: In the binary classification model used to distinguish low-risk and moderate- to high-risk patients, the AUC in the GBM, DRF, and DL full models were 0.9994, 0.9982, and 0.9974, respectively, and the AUCPR was 0.9982, 0.9949, and 0.9918, respectively. Excluding Helicobacter pylori IgG antibody, pepsinogen I, and pepsinogen II, the AUC in the GBM, DRF, and DL models were 0.9932, 0.9879, and 0.9900, respectively, and the AUCPR was 0.9835, 0.9716, and 0.9752, respectively. Remodel after removing variables IgG, PGI, PGII, and G-17, the AUC in GBM, DRF, and DL was 0.8524, 0.8482, 0.8477, and AUCPR was 0.6068, 0.6008, and 0.5890, respectively. When constructing a tri-classification model, we discovered that none of the three machine learning models could effectively distinguish between patients at intermediate and high risk for gastric cancer (F1 scores in the GBM model for the low, medium and high risk: 0.9750, 0.9193, 0.5334, respectively; F1 scores in the DRF model for low, medium, and high risks: 0.9888, 0.9479, 0.6694, respectively; F1 scores in the DL model for low, medium, and high risks: 0.9812, 0.9216, 0.6394, respectively). Conclusion: We concluded that gastric cancer screening indicators could be optimized when distinguishing low-risk and moderate to high-risk populations, and detecting gastrin-17 alone can achieve a good discriminative effect, thus saving huge expenditures.

Case Report: Keratoacanthoma and type I diabetes secondary to treatment with PM8001, a bifunctional fusion protein targeting TGF-ß and PD-L1.

Immune-related adverse reactions primarily involve the skin and the endocrine, digestive, and respiratory systems. In the endocrine system, these adverse effects mainly include hypophysitis, thyroiditis, hypoadrenalism, and rarely, diabetes mellitus. The most common symptoms in the skin are pruritus, rash, and infrequently, eruptive keratoacanthoma. Here, we report a case of a 67-year-old woman who developed eruptive keratoacanthoma of the skin 6 weeks after beginning treatment with a bispecific antibody (PM8001), targeting both programmed cell death receptor 1 and transforming growth factor ß, as well as type I diabetes mellitus-induced ketoacidosis after 13 weeks. The type I diabetes appeared to stabilize after insulin treatment, and the keratoacanthoma gradually resolved after drug discontinuation. This case report describes a case of the effects of PM8001 immunotherapy on the endocrine glands and skin, together with a review of the relevant literature, and summarizes the different clinical characteristics of rare immune-related adverse events resulting from PM8001 immunotherapy to provide a reference for their early detection, diagnosis, and treatment.

Efficacy and safety of re-challenging 160 mg furmonertinib for advanced NSCLC after resistance to third-generation EGFR-TKIs targeted agents: A real-world study.

BACKGROUND: Third-generation epidermal growth factor receptor tyrosine kinase inhibitors (EGFR-TKI) show good selectivity for classical EGFR mutated and EGFR T790M mutated non-small cell lung cancer (NSCLC). However, resistance inevitably occurs to third-generation EGFR-TKI. This study describes the real-world characteristics, efficacy, and safety of treating post-progression NSCLC with 160 mg of furmonertinib (in combination with or without anti-angiogenic agents and chemotherapy) with third-generation EGFR-TKIs. METHODS: EGFR-mutated NSCLC patients with intracranial progression pattern cohort (IP cohort) or extracranial progression pattern cohort (EP cohort) were retrospectively analyzed following progression to third-generation EGFR-TKIs receiving furmonertinib 160 mg daily as second-line or later treatment in combination with or without anti-angiogenic agents and chemotherapy. RESULTS: Thirty-nine patients were included and categorized into two groups according to the progression pattern. Then, 22 patients in the IP cohort and 17 patients in the EP cohort, most of whom were in poor physical condition, were included and 84.6% had central nervous system metastases. In the IP cohort, the median PFS was 5.5 months (95% CI 4.67-8.72), and the median OS was 9.8 months (95% CI 7.25-11.20) for single-agent furmonertinib or combination therapy. In the EP cohort, the median PFS was 3.2 months (95% CI 2.18-4.70), and the median OS was 6.7 months (95% CI 4.99-8.75). Univariate analysis showed the association between the presence of a prior T790M mutation and a history of combined radiotherapy with longer PFS with furmonertinib (p = 0.048, p = 0.004). Overall, adverse events (AEs) of any grade occurred in 84.6% of patients (33/39), with the majority having grade 2 or lower AEs. CONCLUSION: Furmonertinib 160 mg is an optional regimen for patients with advanced NSCLC who develop resistance after treatment with third-generation EGFR-TKIs, especially those developing resistance due to the progression of intracranial lesions, with good efficacy and an acceptable safety profile that warrants further exploration.

Current status and challenges of immunotherapy in ALK rearranged NSCLC.

Rearrangements of the anaplastic lymphoma kinase (ALK) gene account for 5-6% in non-small cell lung cancer (NSCLC). ALK rearranged NSCLC is sensitive to ALK tyrosine kinase inhibitors (TKIs) but prone to drug resistance. Meanwhile, ALK rearranged NSCLC has poor response to single immunotherapy. Here we mainly describe the immune escape mechanisms of ALK mutated NSCLC and the role of related biomarkers. Additionally, we collate and evaluate preclinical and clinical studies of novel immune combination regimens, and describe the prospects and perspectives for the in vivo application of novel immune technologies in patients with ALK rearranged NSCLC.

Characterization With KRAS Mutant Is a Critical Determinant in Immunotherapy and Other Multiple Therapies for Non-Small Cell Lung Cancer.

Non-small cell lung cancer (NSCLC) is a frequent type of cancer, which is mainly characterized clinically by high aggressiveness and high mortality. KRAS oncoprotein is the most common molecular protein detected in NSCLC, accounting for 25% of all oncogenic mutations. Constitutive activation of the KRAS oncoprotein triggers an intracellular cascade in cancer cells, leading to uncontrolled cell proliferation of cancer cells and aberrant cell survival states. The results of multiple clinical trials have shown that different KRAS mutation subtypes exhibit different sensitivities to different chemotherapy regimens. Meanwhile, anti-angiogenic drugs have shown differential efficacy for different subtypes of KRAS mutated lung cancer. It was explored to find if the specificity of the KRAS mutation subtype would affect PD-L1 expression, so immunotherapy would be of potential clinical value for the treatment of some types of KRAS mutations. It was discovered that the specificity of the KRAS mutation affected PD-L1, which opened up immunotherapy as a potential clinical treatment option. After several breakthrough studies, the preliminary test data of many early clinical trials showed that it is possible to directly inhibit KRAS G12C mutation, which has been proved to be a targeted treatment that is suitable for about 10%-12% of patients with advanced NSCLC, having a significant impact on the prolongation of their survival and the improvement of their quality of life. This article reviews the latest progress of treatments for NSCLC with KRAS mutation, in order to gain insight into the biological diversity of lung cancer cells and their potential clinical implications, thereby enabling individualized treatment for patients with KRAS-mutant NSCLC.