Development and pilot evaluation of the Children's Masking Questionnaire.

According to the World Health Organization (WHO) [], the Human Immunodeficiency Virus (HIV) remains a global public health problem. This retrovirus primarily targets CD4-positive T lymphocytes, which its progressive depletion drives the development of immunodeficiency in people living with HIV (PLWH). If not treated properly, this infection can lead to Acquired Immunodeficiency Syndrome (AIDS) and death, so early diagnosis and prompt initiation of effective Antiretroviral Treatment (ART) are essential. Currently, ART has made it possible to turn HIV into a manageable chronic infection, stopping or reverting the progression of the disease to AIDS, as well as the appearance of other pathologies. Beyond its individual clinical benefits, effective antiretroviral therapy confers substantial public health advantages. Sustained viral suppression eliminates the risk of sexual HIV transmission and prevents mother-to-child transmission. Together, these effects form the basis of the Treatment as Prevention (TasP) strategy and reinforce broader prevention approaches, including pre-exposure prophylaxis (PrEP). However, new clinical challenges have emerged, such as Low Level Viremia (LLV) [, ] or some non-AIDS defining comorbidities, which require additional tools to facilitate the management of more complex cases. In recent years, there has been a constant growth in the volume of data, both structured (e.g., longitudinal clinical variables, biomarkers, or genomic information) and unstructured (e.g., clinical notes). The complexity of heterogeneous data, characterized by non-linear relationships or high dimensionality [], makes that, in many scenarios, classical statistical techniques are unable to adequately capture the necessary information for analysis and management of the clinical progression of PLWH. In this sense, Artificial Intelligence (AI) techniques emerge as key tools to deal with complex data []. Both machine learning and deep learning techniques are able to model complex relationships and identify patterns in the data, thus facilitating the different clinical domains of the disease: prevention, diagnosis, treatment, progression and comorbidities. In order to properly address the diversity of techniques, data and clinical applications, it is necessary to contextualize the use of these techniques in the HIV field in a structured way.