Oral squamous cell carcinoma recognition presents a challenge due to late diagnosis and costly data acquisition. A cost-efficient, computerized screening system is crucial for early disease detection, minimizing the need for expert intervention and expensive analysis. Besides, transparency is essential to align these systems with critical sector applications. Explainable Artificial Intelligence (XAI) provides techniques for understanding models. However, current XAI is mostly data-driven and focused on addressing developers' requirements of improving models rather than clinical users' demands for expressing relevant insights. Among different XAI strategies, we propose a solution composed of Case-Based Reasoning paradigm to provide visual output explanations and Informed Deep Learning (IDL) to integrate medical knowledge within the system. A key aspect of our solution lies in its capability to handle data imperfections, including labeling inaccuracies and artifacts, thanks to an ensemble architecture on top of the deep learning (DL) workflow. We conducted several experimental benchmarks on a dataset collected in collaboration with medical centers. Our findings reveal that employing the IDL approach yields an accuracy of 85%, surpassing the 77% accuracy achieved by DL alone. Furthermore, we measured the human-centered explainability of the two approaches and IDL generates explanations more congruent with the clinical user demands.

Medication-related osteonecrosis of the jaw (MRONJ) is a serious adverse reaction, mainly due to bone-modifying agents (BMA), and it is a potentially painful and debilitating condition. To date, the literature has reported a 90% rate of successful outcomes for MRONJ patients undergoing surgical treatment. Particularly for patients with advanced disease stages who are unsuitable for surgery, prolonged medical treatment is required, with a consequent risk of the overuse of antibiotics and antibiotic resistance. The aim of this study is to evaluate the efficiency and safety of ozone, via oral mucosal infiltrations, in seven cancer patients with MRONJ, who are not eligible for surgery. The protocol (OZOPROMAF) consists of intratissue injections of an oxygen ozone (O₂O₃) mixture, which is applied until formation of a sequestrum and clinical healing. Follow-up was scheduled to confirm the healing of MRONJ and radiological evaluations by CBCT were planned. In order to assess the level of pain, a questionnaire including the Numeric Rating Scale for Pain (NRS Pain) was administered on the first visit, one day after treatment, and one week after treatment. After an application of OZOPROMAF, all patients reported discomfort for some hours, probably due to soft tissue pressure around the infiltration site. Thereafter, the discomfort subsided within 6–8 h. Complete mucosal healing of MRONJ occurred within a number of cycles ranging from 7 to 16. Complete resolution with an improvement in bone condition was observed in all patients. The MRONJ lesions of all patients healed after 18–24 months. The authors of this study contend that these preliminary results suggest the efficiency and safety of the O₂O₃ mixture. However, further research is required to confirm the efficacy of the O₂O₃ mixtures in MRONJ treatment, at least for patients who are unsuitable for surgery.

Objective: Oral diseases, specifically malignant lesions, are serious global health concerns requiring early diagnosis for effective treatment. In recent years, deep learning (DL) has emerged as a powerful tool for the automated detection and classification of oral lesions. This research, by conducting a scoping review and meta‐analysis, aims to provide an overview of the progress and achievements in the field of automated detection of oral lesions using DL.Materials and Methods: A scoping review was conducted to identify relevant studies published in the last 5 years (2018–2023). A comprehensive search was conducted using several electronic databases, including PubMed, Web of Science, and Scopus.Two reviewers independently assessed the studies for eligibility and extracted data using a standardized form, and a meta‐analysis was conducted to synthesize the findings.Results: Fourteen studies utilizing various DL algorithms were identified and included for the detection and classification of oral lesions from clinical images. Among these, three were included in the meta‐analysis. The estimated pooled sensitivity and specificity were 0.86 (95% confidence interval [CI] = 0.80–0.91) and 0.67 (95% CI = 0.58–0.75), respectively.Conclusions: The results of meta‐analysis indicate that DL algorithms improve the diagnosis of oral lesions. Future research should develop validated algorithms for automated diagnosis.Trial Registration: Open Science Framework (https://osf.io/4n8sm)

The use of digital health technologies, including telemedicine and teledentistry, has become a necessity in healthcare due to the SARS-CoV-19 pandemic. These technologies allow for the reduction of the workload of healthcare providers and the improvement of patient outcomes in cases of remote monitoring, diagnosis, and communication. While there are no doubtful benefits, there are some counterparts, such as concerns about clinical risks, data security, and privacy protection. This paper aims to review the regulations regarding the use of digital health apps and software in healthcare. This scoping review followed the PRISMA-ScR guidelines and the five-step framework of Arksey and O’Malley. Study selection was based on eligibility criteria that were defined using the population-exposure framework. The review of the articles selected (n = 24) found that the majority focused on data security policies in the healthcare industry, highlighting the need for comprehensive regulations and app control systems to protect patient data. The articles also emphasized the requirement for more appropriate research and policy initiatives to improve data security practices and better address privacy and safety challenges related to health-related apps. The review recognized that papers did not report consistent standards in professional obligation and informed consent in online medical consultations, with potential risks for data privacy, medical liabilities, and ethical issues. Digital health has already revolutionized medical service delivery through technology but faces some challenges, including the lack of standardized protocols for handling sensitive patient data and the absence of common legislative provisions, raising concerns about confidentiality and security. To address these issues and deficiencies, regulatory compliance is crucial to clarify and harmonize regulations and provide guidelines for doctors and the health system. In conclusion, regulating patient data, clarifying provisions, and addressing informed patients are critical and urgent steps in maximizing usage and successful implementation of telemedicine.

Obstructive sleep apnoea syndrome (OSAS) is the most severe condition on the spectrum of sleep-related breathing disorders (SRBDs). The Paediatric Sleep Questionnaire (PSQ) is one of the most used and validated screening tools, but it lacks the comprehensive assessment of some determinants of OSAS, specifically anamnestic assessment and sleep quality. This study aims to assess the accuracy of some specific items added to the original PSQ, particularly related to the patient’s anamnestic history and to the quality of sleep, for the screening of OSAS in a paediatric population living in Sicily (Italy). Fifteen specific items, divided into “anamnestic” and “related to sleep quality” were added to the original PSQ. The whole questionnaire was administered via a digital form to the parents of children at 4 schools (age range: 3–13 years). For each item, sensitivity and specificity, positive and negative predictive values, and positive and negative likelihood ratios were calculated. The highest sensitivity (80.0, 95% CI: 28.4; 99.5), in combination with the highest specificity (61.1, 95% CI: 35.7; 82.7), was found for the Item 32 (“assumption of bizarre or abnormal positions during sleep”). This item was found statistically significant for predicting the occurrence of OSAS in children (p-value ≤0.003). The study demonstrates the accuracy of specific items related to sleep quality disturbance for the preliminary assessment of the disease. Although these results should be validated on a larger sample of subjects, they suggest that including the factors discriminating sleep quality could further increase the efficiency and accuracy of PSQ.

Oral potentially malignant disorders can be defined as mucosal lesions and conditions with an increased risk of malignant transformation. Oral potentially malignant disorders are a significant health burden, and they are often diagnosed late due to scant attention to routine dental practice and the low number of specialized oral medicine centres. This report summarizes the DoctOral experience, a research initiative, providing a free smartphone-based decision support tool for the general medical/dental practitioner; the tool is based on the clinical appearance of oral lesions. Captured, oral pictures can be immediately examined via interactive decision trees and constructed on the smartphone. Such decision trees are expressed in standard formats, and they are readily accessible for facilitating the completion of a hypothetical diagnostic path. Since October 2017 the DoctOral mobile app has been downloaded by 10K + users, achieving a score of 4.8 out of 5. DoctOral also supports an unfolding joint initiative, called DoctOralAI: this involves selecting reference images, with which to create an open-source model, and perform a Case-Based Reasoning method, both of which are combined with machine learning. The DoctOral mobile app has revolutionized oral pathology by providing dental students and professionals with an interactive platform for recognizing and diagnosing oral lesions.