Producción Científica

This review aims to explore the growing impact of machine learning and deep learning algorithms in the medical field, with a specific focus on the critical issues of explainability and interpretability associated with black-box algorithms. While machine learning algorithms are increasingly employed for medical analysis and diagnosis, their complexity underscores the importance of understanding how these algorithms explain and interpret data to take informed decisions. This review comprehensively analyzes challenges and solutions presented in the literature, offering an overview of the most recent techniques utilized in this field. It also provides precise definitions of interpretability and explainability, aiming to clarify the distinctions between these concepts and their implications for the decision-making process. Our analysis, based on 448 articles and addressing seven research questions, reveals an exponential growth in this field over the last decade. The psychological dimensions of public perception underscore the necessity for effective communication regarding the capabilities and limitations of artificial intelligence. Researchers are actively developing techniques to enhance interpretability, employing visualization methods and reducing model complexity. However, the persistent challenge lies in finding the delicate balance between achieving high performance and maintaining interpretability. Acknowledging the growing significance of artificial intelligence in aiding medical diagnosis and therapy, and the creation of interpretable artificial intelligence models is considered essential. In this dynamic context, an unwavering commitment to transparency, ethical considerations, and interdisciplinary collaboration is imperative to ensure the responsible use of artificial intelligence. This collective commitment is vital for establishing enduring trust between clinicians and patients, addressing emerging challenges, and facilitating the informed adoption of these advanced technologies in medicine.

Purpose To explore gender distribution in authorship and citation parameters of articles published in five optometry journals included in the Ophthalmology category of Journal Citation Reports. Methods The Scopus database was used to retrieve all citable articles published in 2011 and 2021 in Optometry and Vision Science, Ophthalmic and Physiological Optics, Clinical Experimental Optometry, Contact Lens and Anterior Eye, and Eye and Contact Lens. Gender of the first, last and single authors of all articles, and citation parameters of articles published in 2011 up to May 2023 were determined. Gender of the editor-in-chief and members of the editorial board of these journals was investigated (May 2023). Results Only one journal had a female editor-in-chief and three journals had more males than females in their editorial board. In 2011 and 2021, respectively, 40.1% and 48.0% of articles had female as the first authors, and 32.7% and 39.6% had female as the last authors. Gender parity was observed in one journal for the first author and none for the last author in 2011, and in three journals for the first author and one for the last author in 2021. Regarding combinations of male (M) and female (F) first and last authorship positions, the authors of articles in 2011 were MM (44.5%), FM (22.8%), FF (17.3%) and MF (15.4%), and MM (34.6%), FM (25.8%), FF (22.1%) and MF (17.5%) in 2021. Differences between 2011 and 2021 were statistically significant. The proportion of authorship combinations did not show statistically significant differences among journals in 2011 or in 2021. Neither citation nor self-citation were influenced by gender. Conclusions Gender disparities persist in optometry journals, with females being under-represented in senior and leadership positions. Increasing the awareness of gender disparity in authorship is a necessary step towards ensuring fairness in science in general, and optometry in particular.