Comparison of two fluorescence detectors in flow cytometry to predict malignant transformation of oral leukoplakia from cell cycle fractions.

Objective: The objective of this paper was to compare the accuracy of predicting malignant transformation of oral leukoplakia using the 585-620 nm detector when compared with data obtained with the 661-683 nm detector.

Study Design: This was a single-factor retrospective longitudinal experimental study, whose factor will be DNA content (DNA ploidy) at 4 levels, G1 phase, S phase, mitosis phase (G2), and DNA excess (4cER). The sample is a cohort of individuals diagnosed with oral leukoplakia (N = 97) where 18 cases evolved into cancer and 79 did not.

Effects of ozone therapy on postoperative pain, swelling, and trismus caused by surgical extraction of unerupted lower third molars: a double-blinded split-mouth randomized controlled trial.

Background: Third molar extraction surgery is a common procedure, but it results in pain, swelling, and trismus. Ozone therapy (Oz) has emerged as a viable option for pain control and as an option to limit bacterial growth, improving the wound healing. Then, this randomized controlled trial aimed to evaluate the effectiveness of adjunctive use of ozone therapy (OzT) in managing pain, swelling, and trismus after lower third molar removal.

A comparative analysis of DNA content and cell cycle phases in pleomorphic adenoma and carcinoma ex pleomorphic adenoma.

Objective: This study aimed to analyze the DNA ploidy profile of pleomorphic adenoma (PA) using flow cytometry, with a particular focus on its malignant transformation.

Study Design: Tissue samples were obtained from normal glands, primary and recurrent PA, and carcinoma ex PA (CXPA) (residual PA and malignant areas) for analysis. The data were analyzed using dedicated software and relevant increased literature resources.

Artificial intelligence in healthcare applications targeting cancer diagnosis-part II: interpreting the model outputs and spotlighting the performance metrics.

Background: The lack of standardized performance assessment metrics and the inconsistent reporting of results can lead to the presentation of overly optimistic outcomes that fail to accurately represent key aspects of the Machine Learning framework and may not align with real-world clinical needs.

Methods: This conceptual review of the literature compiled the theoretical basis for performance analysis of binary and multiclass models.

Results: Accuracy and error rates are straightforward but not ideal if dataset is imbalanced.

Artificial intelligence in healthcare applications targeting cancer diagnosis-part I: data structure, preprocessing and data organization.

Background: Machine learning techniques hold significant potential to support the diagnosis and prognosis of diseases. However, the success of these approaches is heavily dependent on rigorous data acquisition, preprocessing and data organization.

Methods: This article reviews the literature to evaluate key factors in dataset construction, focusing on data structure, preprocessing, and data organization, particularly in the context of imaging data.