Background and Objectives: Thyroid nodules are lumps of solid or liquid-filled tumors that form inside the thyroid gland, which can be malignant or benign. Our aim was to test whether the described features of the Thyroid Imaging Reporting and Data System (TI-RADS) could improve radiologists’ decision making when integrated into a computer system. In this study, we developed a computer-aided diagnosis system integrated into multiple-instance learning (MIL) that would focus on benign–malignant classification. Data were available from the Universidad Nacional de Colombia. Materials and Methods: There were 99 cases (33 Benign and 66 malignant). In this study, the median filter and image binarization were used for image pre-processing and segmentation. The grey level co-occurrence matrix (GLCM) was used to extract seven ultrasound image features. These data were divided into 87% training and 13% validation sets. We compared the support vector machine (SVM) and artificial neural network (ANN) classification algorithms based on their accuracy score, sensitivity, and specificity. The outcome measure was whether the thyroid nodule was benign or malignant. We also developed a graphic user interface (GUI) to display the image features that would help radiologists with decision making. Results: ANN and SVM achieved an accuracy of 75% and 96% respectively. SVM outperformed all the other models on all performance metrics, achieving higher accuracy, sensitivity, and specificity score. Conclusions: Our study suggests promising results from MIL in thyroid cancer detection. Further testing with external data is required before our classification model can be employed in practice.

Background: Digital contact tracing apps have the potential to augment contact tracing systems and disrupt COVID-19 transmission by rapidly identifying secondary cases prior to the onset of infectiousness and linking them into a system of quarantine, testing, and health care worker case management. The international experience of digital contact tracing apps during the COVID-19 pandemic demonstrates how challenging their design and deployment are. Objective: This study aims to derive and summarize best practice guidance for the design of the ideal digital contact tracing app. Methods: A collaborative cross-disciplinary approach was used to derive best practice guidance for designing the ideal digital contact tracing app. A search of the indexed and gray literature was conducted to identify articles describing or evaluating digital contact tracing apps. MEDLINE was searched using a combination of free-text terms and Medical Subject Headings search terms. Gray literature sources searched were the World Health Organization Institutional Repository for Information Sharing, the European Centre for Disease Prevention and Control publications library, and Google, including the websites of many health protection authorities. Articles that were acceptable for inclusion in this evidence synthesis were peer-reviewed publications, cohort studies, randomized trials, modeling studies, technical reports, white papers, and media reports related to digital contact tracing. Results: Ethical, user experience, privacy and data protection, technical, clinical and societal, and evaluation considerations were identified from the literature. The ideal digital contact tracing app should be voluntary and should be equitably available and accessible. User engagement could be enhanced by small financial incentives, enabling users to tailor aspects of the app to their particular needs and integrating digital contact tracing apps into the wider public health information campaign. Adherence to the principles of good data protection and privacy by design is important to convince target populations to download and use digital contact tracing apps. Bluetooth Low Energy is recommended for a digital contact tracing app's contact event detection, but combining it with ultrasound technology may improve a digital contact tracing app's accuracy. A decentralized privacy-preserving protocol should be followed to enable digital contact tracing app users to exchange and record temporary contact numbers during contact events. The ideal digital contact tracing app should define and risk-stratify contact events according to proximity, duration of contact, and the infectiousness of the case at the time of contact. Evaluating digital contact tracing apps requires data to quantify app downloads, use among COVID-19 cases, successful contact alert generation, contact alert receivers, contact alert receivers that adhere to quarantine and testing recommendations, and the number of contact alert receivers who subsequently are tested positive for COVID-19. The outcomes of digital contact tracing apps' evaluations should be openly reported to allow for the wider public to review the evaluation of the app. Conclusions: In conclusion, key considerations and best practice guidance for the design of the ideal digital contact tracing app were derived from the literature.

Ireland is a country with a low incidence of tuberculosis (TB) (5.6 cases per 100,000 population in 2019) that should be aiming for TB elimination (fewer than 1 case per million of population). To achieve TB elimination in low-incidence countries, programmatic latent tuberculosis infection (LTBI) management is important. This requires high-quality latent tuberculosis infection (LTBI) screening. Aim: To assess the quality of LTBI screening in a tertiary centre in Ireland using a framework. Methods: A retrospective review of the health care records of patients screened for TB in a tertiary centre in Ireland using an interferon-gamma release assay (IGRA) between 2016 and 2018 was performed. Three domains from the Institute of Medicine framework for health care quality, effectiveness, efficiency, and equity, were applied to measure the quality of LTBI screening. Results: Forty patients had LTBI and an indication for treatment, of whom 20% (8/40) were not offered treatment by the health care provider, 2.5% (1/40) did not accept treatment, and 10% (4/40) did not complete treatment. Seventy-five percent (6/8) of patients not offered treatment were non-Irish. The cost of screening per LTBI case identified was EUR 2048. Conclusions: This study evaluated the quality of LTBI screening using a framework and identified that LTBI screening in this tertiary centre needs to be scaled and expanded, and that treatment initiation needs to be improved, particularly among non-Irish nationals.