BACKGROUND: Epidermal growth factor receptor (EGFR) sensitive mutation is one of the effective targets of targeted therapy for non-small cell lung cancer (NSCLC). However, due to the difficulty of obtaining some primary tissues and the economic factors in some underdeveloped areas, some patients cannot undergo traditional genetic testing. The aim of this study is to establish a machine learning (ML) model using non-invasive peripheral blood markers to explore the biomarkers closely related to EGFR mutation status in NSCLC and evaluate their potential prognostic value. METHODS: 2642 lung cancer patients who visited Jiangsu Cancer Hospital from November 2016 to May 2023 were retrospectively enrolled and finally 175 NSCLC patients with complete follow-up data were included in the study. The ML model was constructed based on peripheral blood indicators and divided into training set and test set according to the ratio of 8:2. Unsupervised learning algorithms were used for clustering blood features and mutual information method for feature selection, and an ensemble learning algorithm based on Shapley value was designed to calculate the contribution of each feature to the model prediction result. The receiver operating characteristic (ROC) curve was used to evaluate the predictive ability of the model. RESULTS: Through the feature extraction and contribution analysis of the predictive results of the interpretable ML model based on the Shapley value, the top ten indicators with the highest contribution were: pathological type, phosphorus, eosinophils, monocyte count, activated partial thromboplastin time, potassium, total bilirubin, sodium, eosinophil percentage, and total cholesterol. The area under the curve (AUC) of the model was 0.80. In addition, patients with hyponatremia and squamous cell carcinoma group had a poor prognosis (P<0.05). CONCLUSIONS The interpretable model constructed in this study provides a new approach for the prediction of EGFR mutation status in NSCLC patients, which provides a scientific basis for the diagnosis and treatment of patients who cannot undergo genetic testing.
Humans ; Carcinoma, Non-Small-Cell Lung/diagnosis* ; Machine Learning ; Lung Neoplasms/diagnosis* ; Male ; Female ; Mutation ; Middle Aged ; ErbB Receptors/genetics* ; Prognosis ; Aged ; Retrospective Studies ; Adult ; Biomarkers, Tumor/genetics*

Interpreting genes of interest is essential for identifying molecular mechanisms, but acquiring such information typically involves tedious manual retrieval. To streamline this process, the fanyi package offers tools to retrieve gene information from sources like National Center for Biotechnology Information (NCBI), significantly enhancing accessibility. Additionally, understanding the latest research advancements and sharing achievements are crucial for junior researchers. However, language barriers often restrict knowledge absorption and career development. To address these challenges, we developed the fanyi package, which leverages artificial intelligence (AI)-driven online translation services to accurately translate among multiple languages. This dual functionality allows researchers to quickly capture and comprehend information, promotes a multilingual environment, and fosters innovation in academic community. Meanwhile, the translation functions are versatile and applicable beyond biomedicine research to other domains as well. The fanyi package is freely available at https://github.com/YuLab-SMU/fanyi.

BACKGROUND: Lung cancer is the leading cause of cancer-related death, of which non-small cell lung cancer (NSCLC) is the most common type. Immune checkpoint inhibitors (ICIs) have now become one of the main treatments for advanced NSCLC. This paper retrospectively investigated the effect of peripheral blood inflammatory indexes on the efficacy of immunotherapy and survival of patients with advanced non-small cell lung cancer, in order to find strategies to guide immunotherapy in NSCLC. METHODS: Patients with advanced non-small cell lung cancer who were hospitalized in The Affiliated Cancer Hospital of Nanjing Medical University from October 2018 to August 2019 were selected to receive anti-PD-1 (pembrolizumab, sintilimab or toripalimab) monotherapy or combination regimens. And were followed up until 10 December 2020, and the efficacy was evaluated according to RECIST1.1 criteria. Progression-free survival (PFS) and overall survival (OS) were followed up for survival analysis. A clinical prediction model was constructed to analyze the predictive value of neutrophil-to-lymphocyte ratio (NLR) based on NLR data at three different time points: before treatment, 6 weeks after treatment and 12 weeks after treatment (0w, 6w and 12w), and the accuracy of the model was verified. RESULTS: 173 patients were finally included, all of whom received the above treatment regimen, were followed up for a median of 19.7 months. The objective response rate (ORR) was 27.7% (48/173), the disease control rate (DCR) was 89.6% (155/173), the median PFS was 8.3 months (7.491-9.109) and the median OS was 15.5 months (14.087-16.913). The chi-square test and logistic multi-factor analysis showed that NLR6w was associated with ORR and NLR12w was associated with ORR and DCR. Further Cox regression analysis showed that NLR6w and NLR12w affected PFS and NLR0w, NLR6w and NLR12w were associated with OS. CONCLUSIONS In patients with advanced non-small cell lung cancer, NLR values at different time points are valid predictors of response to immunotherapy, and NLR <3 is often associated with a good prognosis.
Aged ; Antibodies, Monoclonal, Humanized/therapeutic use* ; Antineoplastic Agents, Immunological/therapeutic use* ; Biomarkers/blood* ; Carcinoma, Non-Small-Cell Lung/pathology* ; Female ; Humans ; Immunotherapy/methods* ; Inflammation/blood* ; Leukocyte Count ; Lung Neoplasms/pathology* ; Lymphocytes ; Male ; Middle Aged ; Neutrophils ; Predictive Value of Tests ; Prognosis ; Retrospective Studies ; Survival Analysis ; Treatment Outcome