Immunohistochemical Characterization Improves the Reproducibility of the Histological Diagnosis of Ovarian Carcinoma

A multidisciplinary approach remains the best strategy to improve and strengthen the management of ovarian cancer (Review)

Ovarian cancer represents one of the most aggressive female tumors worldwide. Over the decades, the therapeutic options for the treatment of ovarian cancer have been improved significantly through the advancement of surgical techniques as well as the availability of novel effective drugs able to extend the life expectancy of patients. However, due to its clinical, biological and molecular complexity, ovarian cancer is still considered one of the most difficult tumors to manage. In this context, several studies have highlighted how a multidisciplinary approach to this pathology improves the prognosis and survival of patients with ovarian cancer. On these bases, the aim of the present review is to present recent advantages in the diagnosis, staging and treatment of ovarian cancer highlighting the benefits of a patient‑centered care approach and on the importance of a multidisciplinary team for the management of ovarian cancer.

Machine Learning Classification of Inflammatory Bowel Disease in Children Based on a Large Real-World Pediatric Cohort CEDATA-GPGE® Registry

Introduction: The rising incidence of pediatric inflammatory bowel diseases (PIBD) facilitates the need for new methods of improving diagnosis latency, quality of care and documentation. Machine learning models have shown to be applicable to classifying PIBD when using histological data or extensive serology. This study aims to evaluate the performance of algorithms based on promptly available data more suited to clinical applications.

Methods: Data of inflammatory locations of the bowels from initial and follow-up visitations is extracted from the CEDATA-GPGE registry and two follow-up sets are split off containing only input from 2017 and 2018. Pre-processing excludes patients in remission and encodes the categorical data numerically. For classification of PIBD diagnosis, a support vector machine (SVM), a random forest algorithm (RF), extreme gradient boosting (XGBoost), a dense neural network (DNN) and a convolutional neural network (CNN) are employed. As best performer, a convolutional neural network is further improved using grid optimization.

Results: The achieved accuracy of the optimized neural network reaches up to 90.57% on data inserted into the registry in 2018. Less performant methods reach 88.78% for the DNN down to 83.94% for the XGBoost. The accuracy of prediction for the 2018 follow-up dataset is higher than those for older datasets. Neural networks yield a higher standard deviation with 3.45 for the CNN compared to 0.83–0.86 of the support vector machine and ensemble methods.

Discussion: The displayed accuracy of the convolutional neural network proofs the viability of machine learning classification in PIBD diagnostics using only timely available data.