AAPM task group report 273: Recommendations on best practices for AI and machine learning for computer-aided diagnosis in medical imaging.

Rapid advances in artificial intelligence (AI) and machine learning, and specifically in deep learning (DL) techniques, have enabled broad application of these methods in health care. The promise of the DL approach has spurred further interest in computer-aided diagnosis (CAD) development and applications using both "traditional" machine learning methods and newer DL-based methods. We use the term CAD-AI to refer to this expanded clinical decision support environment that uses traditional and DL-based AI methods. Numerous studies have been published to date on the development of machine learning tools for computer-aided, or AI-assisted, clinical tasks. However, most of these machine learning models are not ready for clinical deployment. It is of paramount importance to ensure that a clinical decision support tool undergoes proper training and rigorous validation of its generalizability and robustness before adoption for patient care in the clinic. To address these important issues, the American Association of Physicists in Medicine (AAPM) Computer-Aided Image Analysis Subcommittee (CADSC) is charged, in part, to develop recommendations on practices and standards for the development and performance assessment of computer-aided decision support systems. The committee has previously published two opinion papers on the evaluation of CAD systems and issues associated with user training and quality assurance of these systems in the clinic. With machine learning techniques continuing to evolve and CAD applications expanding to new stages of the patient care process, the current task group report considers the broader issues common to the development of most, if not all, CAD-AI applications and their translation from the bench to the clinic. The goal is to bring attention to the proper training and validation of machine learning algorithms that may improve their generalizability and reliability and accelerate the adoption of CAD-AI systems for clinical decision support.

Risk Perception and Knowledge, Attitudes, and Practices Against COVID-19 in a Hypertensive Population From a Semi-Urban City of Ecuador.

Background: In an elderly population with hypertension, severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) is associated with a higher incidence of mortality and a protracted course of clinical symptoms. Objective: To assess the perceived risk of infection and complications due to COVID-19 in people with hypertension living in a semi-urban city of Ecuador. Methods: A cross-sectional telephone survey of adult outpatients with a previous diagnosis of hypertension in the semi-urban community of Conocoto in Quito, Ecuador was conducted from August to December 2020. Results: A total of 260 adult outpatients, aged 34-97 years, completed telephone surveys. Of total, 71.5% (n = 186) of respondents were women and 28.5% (n = 74) of respondents were men. Overall, 18.1% believe that their risk of infection is "very high," 55.4% believe that their risk of infection is "high," 21.5% believe that their risk of infection is "low," and 5% believe that their risk of infection is "very low." The perceived risk of complications, if infected by COVID-19, revealed that 21.9% believe that their risk of complication is "very high," 65.0% believe that their risk of complication is "high," 10.4% believe that their risk of complication is "low," and 2.7% believe that their risk of complication is "very low." Conclusion: Patients with hypertension are aware of the risks posed by COVID-19 infection and its impact on their health. However, the health system must educate the population on health practices and behaviors to avoid COVID-19 infection until the majority of the population of Ecuador can be vaccinated.