The diagnostic accuracy of serum and plasma microRNAs in detection of cervical intraepithelial neoplasia and cervical cancer: A systematic review and -analysis. | LitMetric
Studies suggest a need for new diagnostic approaches for cervical cancer including microRNA technology. In this review, we assessed the diagnostic accuracy of microRNAs in detecting cervical cancer and Cervical Intraepithelial Neoplasia (CIN). We performed a systematic review following the Preferred Reporting Items for Systematic Review and Meta-Analysis guideline for protocols (PRISMA-P). We searched for all articles in online databases and grey literature from 01st January 2012 to 16th August 2022. We used the quality assessment of diagnostic accuracy studies tool (QUADAS-2) to assess the risk of bias of included studies and then conducted a Random Effects Meta-analysis. We identified 297 articles and eventually extracted data from 24 studies. Serum/plasma concentration miR-205, miR-21, miR-192, and miR-9 showed highest diagnostic accuracy (AUC of 0.750, 0.689, 0.980, and 0.900, respectively) for detecting CIN from healthy controls. MicroRNA panels (miR-21, miR-125b and miR-370) and (miR-9, miR-10a, miR-20a and miR-196a and miR-16-2) had AUC values of 0.897 and 0.886 respectively for detecting CIN from healthy controls. For detection of cervical cancer from healthy controls, the most promising microRNAs were miR-21, miR-205, miR-192 and miR-9 (AUC values of 0.723, 0.960, 1.00, and 0.99 respectively). We report higher diagnostic accuracy of upregulated microRNAs, especially miR-205, miR-9, miR-192, and miR-21. This highlights their potential as stand-alone screening or diagnostic tests, either with others, in a new algorithm, or together with other biomarkers for purposes of detecting cervical lesions. Future studies could standardize quantification methods, and also study microRNAs in higher prevalence populations like in sub-Saharan Africa and South Asia. Our review protocol was registered in PROSPERO (CRD42022313275).
Purpose: To evaluate the diagnostic ability and methodological quality of ML models in detecting Pancreatic Ductal Adenocarcinoma (PDAC) in Contrast CT images.
Method: Included studies assessed adults diagnosed with PDAC, confirmed by histopathology. Metrics of tests were interpreted by ML algorithms.
Background/aims: Alzheimer's Disease (AD) is a progressive neurodegenerative disorder that severely affects cognitive functions and memory. Early detection is crucial for timely intervention and improved patient outcomes. However, traditional diagnostic tools, such as MRI and PET scans, are costly and less accessible.
This study aims to investigate the diagnostic values of fine needle aspiration cytology (FNAC) and frozen section (FS) in evaluating parotid gland masses subjected to parotidectomy. A retrospective analysis of data from 274 patients who underwent parotidectomy for parotid gland masses was performed at the Department of Otolaryngology of the University Hospital between 2013 and 2019. We compared the preoperative FNAC and intraoperative FS records with the definitive histopathological diagnoses obtained from the surgical resection specimens.
Missing Alzheimer's disease (AD) data is prevalent and poses significant challenges for AD diagnosis. Previous studies have explored various data imputation approaches on AD data, but the systematic evaluation of deep learning algorithms for imputing heterogeneous and comprehensive AD data is limited. This study investigates the efficacy of denoising autoencoder-based imputation of missing key features of heterogeneous data that comprised tau-PET, MRI, cognitive and functional assessments, genotype, sociodemographic, and medical history.
This paper develops a method for cancer classification from microRNA data using a convolutional neural network (CNN)-based model optimized by genetic algorithm. The convolutional neural network has performed well in various recognition and perception tasks. This paper contributes to the cancer classification using a union of two CNNs.
