Endometrial cancer (EC) is the most prevalent cancer within the female reproductive system in developed countries. Despite its high incidence, there is currently no established laboratory screening test for EC, making early detection challenging. This study introduces an innovative, minimally invasive, and cost-effective method utilizing three-dimensional fluorescence analysis combined with machine learning algorithms to enhance early EC detection. Intrinsic fluorescence of blood serum samples was measured using a luminescence spectrophotometer, which captured fluorescence spectra as synchronous excitation spectra and visualized them through wavelength contour matrices. The spectral data were processed using machine learning algorithms, including Random Forest (RF), Logistic Regression (LR), Support Vector Machine (SVM), and Stochastic Gradient Descent (SGD), along with exploratory techniques such as Principal Component Analysis (PCA) and Partial Least Squares Discriminant Analysis (PLS-DA). Fluorescence ratios R300/330 and R360/490, indicative of altered tryptophan metabolism and redox state changes, were identified as fluorescent spectral markers and represent key metabolic biomarkers. These ratios demonstrated high diagnostic efficacy with AUC values of 0.88 and 0.91, respectively. Among the ML algorithms, LR and RF exhibited high sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV), showing significant promise for clinical application. After optimization, LR achieved a sensitivity of 0.94, specificity of 0.89, and an impressive AUC value of 0.94. The application of this novel approach in laboratory diagnostics has the potential to significantly enhance early detection and improve prognosis for EC patients.

Endometrial cancer is becoming increasingly common, highlighting the need for improved diagnostic methods that are both effective and non-invasive. This study investigates the use of urinary fluorescence spectroscopy as a potential diagnostic tool for endometrial cancer. Urine samples were collected from endometrial cancer patients (n = 77), patients with benign uterine tumors (n = 23), and control gynecological patients attending regular checkups or follow-ups (n = 96). These samples were analyzed using synchronous fluorescence spectroscopy to measure the total fluorescent metabolome profile, and specific fluorescence ratios were created to differentiate between control, benign, and malignant samples. These spectral markers demonstrated potential clinical applicability with AUC as high as 80%. Partial Least Squares Discriminant Analysis (PLS-DA) was employed to reduce data dimensionality and enhance class separation. Additionally, machine learning models, including Random Forest (RF), Logistic Regression (LR), Support Vector Machine (SVM), and Stochastic Gradient Descent (SGD), were utilized to distinguish between controls and endometrial cancer patients. PLS-DA achieved an overall accuracy of 79% and an AUC of 90%. These promising results indicate that urinary fluorescence spectroscopy, combined with advanced machine learning models, has the potential to revolutionize endometrial cancer diagnostics, offering a rapid, accurate, and non-invasive alternative to current methods.

Epidemiologic studies suggest an association between psoriasis and adverse reproductive outcomes. Psoriasis is a chronic inflammatory disorder, and recurrent implantation failure (RIF) is increasingly linked to dysregulated immune states in the endometrium during the implantation window. To determine whether these conditions share a conserved immunoregulatory program, RNA sequencing datasets were integrated from psoriatic lesional and non-lesional skin and from mid-secretory endometrium of fertile women and women with RIF. Differential expression analysis identified 497 genes dysregulated across tissues, including 421 coding genes. Shared genes were mapped to a protein interaction network to detect densely connected modules, followed by functional and transcription factor motif enrichment. Supervised classification models were trained using module genes and evaluated across validation schemes. Immune cell enrichment inferred from bulk profiles supported tissue-specific remodeling, with broad immune infiltration in psoriatic lesions and selective lineage shifts in RIF endometrium. Network analysis revealed a dominant 29 gene module enriched for chemokine and cytokine signaling, extracellular matrix remodeling, and immunoregulatory signaling. Increased module activity was observed in psoriatic lesions, whereas attenuated activity was detected in endometrial samples, consistent with a dysregulated immune state in RIF. Motif enrichment highlighted 13 immune-related transcriptional regulators. Module-based models supported biologically meaningful separation in both comparisons, with area under the receiver operating characteristic curve up to 0.96 in endometrium and 0.97 in skin. Together, a shared immunoregulatory network module associated with chronic cutaneous inflammation and altered endometrial receptivity was identified, providing a foundation for network-based biomarker development in RIF.

Background: Parkinsons disease (PD) has a prolonged prodromal phase, but minimally invasive molecular biomarkers distinguishing manifest PD from prodromal synucleinopathy remain insufficiently characterized. Isolated REM sleep behavior disorder (iRBD) represents a high-risk prodromal condition and provides an opportunity to investigate early blood-based transcriptional alterations. Objective: To identify peripheral blood transcriptomic signatures distinguishing healthy controls (HC), individuals with iRBD, and patients with PD, and to explore whether longitudinal iRBD samples exhibit movement toward a PD-like transcriptional state. Methods: Peripheral blood RNA-seq data were analyzed using harmonized metadata, DESeq2 differential-expression analysis, internally validated machine-learning models, PD-like projection, and integrated biomarker-panel prioritization. Independent baseline samples were used for cross-sectional differential-expression and machine-learning analyses. iRBD follow-up and post-conversion observations were excluded from baseline model development and reserved for exploratory longitudinal analyses. Results: Baseline analyses included 71 independent samples: 20 HC, 31 iRBD, and 20 PD. An additional 19 iRBD follow-up observations, including three post-conversion observations, were available for exploratory analyses. Differential-expression analysis identified 170 FDR-significant genes in PD versus HC and 85 in PD versus iRBD, compared with one FDR-significant gene in iRBD versus HC. Internal machine-learning validation showed stronger discrimination of manifest PD, with a best ROC-AUC of 0.883 for HC versus PD and 0.889 for iRBD versus PD. Discrimination between HC and iRBD was weak, with a best ROC-AUC of 0.584. PD-like projection scores were lowest in HC, highest in PD, and heterogeneous among baseline iRBD samples. Follow-up iRBD samples showed an exploratory upward shift in the mean PD-like projection score. Integrated prioritization produced a 24-gene PD candidate panel and a 24-gene exploratory iRBD panel, with genes in each panel supported by machine-learning feature-stability evidence and differential expression analysis. Conclusions: Manifest PD was associated with a distinct peripheral blood transcriptional signature, whereas iRBD-associated alterations were substantially weaker and more heterogeneous. The prioritized panels represent candidates for independent technical and external validation and should not yet be interpreted as clinically validated diagnostic or prognostic tests.