Machine learning-based integrated identification of predictive combined diagnostic biomarkers for endometriosis

Background: Endometriosis (EM) is a common gynecological condition in women of reproductive age, with diverse causes and a not yet fully understood pathogenesis. Traditional diagnostics rely on single diagnostic biomarkers and does not integrate a variety of different biomarkers. This study introduces multiple machine learning techniques, enhancing the accuracy of predictive models. A novel diagnostic approach that combines various biomarkers provides a new clinical perspective for improving the diagnostic efficiency of endometriosis, holding significant potential for clinical application. Methods: In this study, GSE51981 was used as a test set, and 11 machine learning algorithms (Lasso, Stepglm, glmBoost, Support Vector Machine, Ridge, Enet, plsRglm, Random Forest, LDA, XGBoost, and NaiveBayes) were employed to construct 113 predictive models for endometriosis. The optimal model was determined based on the AUC values derived from various algorithms. These genes were then evaluated using nine machine learning algorithms (Random Forest, SVM, Gradient Boosting Machine, LASSO, XGB, NNET, Generalized Linear Model, KNN, and Decision Tree) to assess significance scores and identify diagnostic genes for each algorithm. The diagnostic value of these genes was further validated in external datasets from GSE7305, GSE11691, and GSE120103. Results: Analysis of the GSE51981 dataset revealed 62 DEGs. The Stepglm [Both] and plsRglm algorithms identified 30 genes with the most potential using the AUC evaluation. Subsequently, nine machine learning algorithms were applied to select diagnostic genes, leading to the identification of five key diagnostic genes using the LASSO algorithm. The ADAT1 gene exhibited the best single-gene predictive performance, with an AUC of 0.785. A combination of genes (FOS, EPHX1, DLGAP5, PCSK5, and ADAT1) achieves an AUC of 0.836 in the test dataset. Moreover, these genes consistently exhibited an AUC exceeding 0.78 in all validation datasets, demonstrating superior predictive performance. Furthermore, correlation analysis with immune infiltration strengthened their predictive value by demonstrating the close relationship of the diagnostic genes with immune infiltrating cells. Conclusion: A combination of biomarkers consisting of FOS, EPHX1, DLGAP5, PCSK5, and ADAT1 can serve as a diagnostic tool for endometriosis, enhancing diagnostic efficiency. The association of these genes with immune infiltrating cells reveals their potential role in the pathogenesis of endometriosis, providing new insights for early detection and treatment.

Npas4-mediated dopaminergic regulation of safety memory consolidation

Amygdala circuitry encodes associations between conditioned stimuli and aversive unconditioned stimuli and also controls fear expression. However, whether and how non-threatening information for unpaired conditioned stimuli (CS^-) is discretely processed remains unknown. The fear expression toward CS^- is robust immediately after fear conditioning but then becomes negligible after memory consolidation. The synaptic plasticity of the neural pathway from the lateral to the anterior basal amygdala gates the fear expression of CS^-, depending upon neuronal PAS domain protein 4 (Npas4)-mediated dopamine receptor D4 (Drd4) synthesis, which is precluded by stress exposure or corticosterone injection. Herein, we show cellular and molecular mechanisms that regulate the non-threatening (safety) memory consolidation, supporting the fear discrimination.

Accuracy of Clinical Signs and Symptoms in the Diagnosis of Endometriosis

Endometriosis is a benign gynecological disease afffecting about 10% of all reproductive-age women which can significantly impair quality of life. As the clinical presentation is variable, with some women experiencing several severe symptoms while others remain asymptomatic, there are no sufficiently sensitive and specific signs and symptoms or diagnostic tests for the clinical diagnosis of endometriosis. The aim of this article is to review the current literature regarding the accuracy of clinical signs and symptoms in the diagnosis of endometriosis. Besides the wide spectrum of symptoms, an overlap with other causes of pelvic pain such as irritable bowel syndrome and pelvic inflammatory disease is also reported. Moreover, most of the signs and symptoms of endometriosis do not correlate with the severity (staging) of the disease. Knowledge of the characteristics of pelvic pain symptoms is important in the preoperative assessment of patients with suspected endometriosis. Pelvic tenderness, a fixed retroverted uterus, tender uterosacral ligaments or enlarged ovaries identified during a standard pelvic exam are suggestive of endometriosis. Clinical examination during menstruation apparently improves diagnostic yield. Although the clinical diagnosis of endometriosis presents low sensitivity and specificity, it should be thoroughly performed as it is the first fundamental step in the diagnostic workup. Clinical assessment helps to identify patients at high risk of endometriosis and selects those who need further testing in order to reduce diagnostic delay. Laparoscopy preferably performed in conjunction with histologic evaluation of excised lesions, however, still remains the gold standard for diagnosis as well as staging of endometriosis.