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*

Objective:To evaluate the pregnancy outcomes of fetal tethered cord (TC) prenatally diagnosed by MRI.Methods:Clinical data of 38 fetuses diagnosed as having TC by MRI, including 36 singletons and two fetuses who were both one of dichorionic diamniotic twins, were retrospectively collected and analyzed in the Obstetrics and Gynecology Hospital of Fudan University from January 2015 to August 2019. According to whether conus medullaris was located above the bladder or reached the lower edge of the bladder, all cases were divided into high or low groups. Pregnancy outcomes were compared between the two groups using Fisher's exact test and Student's t-test. Results:(1) The gestational age at MRI was (25.5±4.7) weeks. Among the 38 cases, 14 (36.8%) were isolated TC, 24 (63.2%) were complicated by other anomalies. The meningocele was responsible for the most (39.5%, n=15). The results of the ultrasound were consistent with those of MRI in 24 cases (63.2%). While in the other 14 cases (36.8%), the ultrasound only showed vertebral body's abnormal morphology, after which further MRI examination revealed a tethered cord. (2) Twenty-nine women (76.3%) chose to terminate the pregnancy. One patient (2.6%) underwent fetal reduction at 23 gestational weeks (one normal twin was delivered prematurely), and one (2.6%) was lost to follow-up. Seven (18.4%) cases continued the pregnancies to delivery. The postnatal follow-up period was 8.1 months (4.0 to 54.9 months). Two infants without comorbidities showed normal growth and development. Another three cases underwent surgeries after birth, and two cases died in the neonatal period. (3) The average width of the medullary cone was (2.5±0.8) cm. There was no significant difference in the spinal cord width between the high [(2.5±0.8) cm, n=34] and low group [(2.7±1.1) cm, n=4]. Six pregnancies (17.6%) in the high group was continued to delivery, and one of the neonates died of severe hydrocephalus. One patient in the low group (1/4) was delivered, while the baby died of neonatal asphyxia. Conclusions:Fetuses with isolated TC are prone to have a good prognosis. Further study should focus on the relation between the high or low position of the conus medullaris and pregnancy outcomes.