Sandra Amador¹, ANA MARIA LUCAS OCHOA², Raquel Gómez de León Zapata², José Luis Fernández Alemán³, David Gil⁴, Colleen Norris⁵, Valeria Raparelli⁶, Alexandra Kautzky-Willer⁷, Karolina Kublickiene⁸, Louise Pilote⁹, Maria Trinidad Herrero Ezquerro²

(1) Clinical and Experimental Neuroscience (NiCE-IMIB), University of Murcia, España (Región de Murcia)
(2) NEUROCIENCIA CLÍNICA Y EXPERIMENTAL, IMIB-Arrixaca, España
(3) School of Medicine, School of Informatics, University of Murcia, España (Región de Murcia)
(4) Informatics and Technology, University of Alicante, España (Comunidad Valenciana)
(5) Faculty of Nursing, University of Alberta, Edmonton, Alta, Cardiovascular and Stroke Strategic Clinical Network, Alberta Health Services, Edmonton, Alta, Canadá
(6) Department of Experimental Medicine, Sapienza University of Rome, Rome, Italia
(7) Division of Endocrinology and Metabolism, Department of Medicine III, Medical University of Vienna, Vienna, Austria
(8) Department of Renal Medicine, Institution for Clinical Science, Intervention and Technology, Karolinska Institute, Stockholm, Suecia
(9) Research Institute of McGill University Health Centre, Division of Clinical Epidemiology McGill University, Montréal, Que, Canadá

It is well known that sex and gender differences are important and contribute to differential health outcomes, however, there is still gender inequality in health research. Predictive medicine, using machine learning techniques, takes into account gender and sex differences and can predict health outcomes, so this will contribute to a better quality of people’s life. Due to that, the aim of this mapping study was to identify and analyse the articles that apply machine learning techniques in the nervous system diseases (psychiatric and neurological) considering gender and social aspects. Mapping studies are ideal to provide a general idea of an investigation area by using the research questions such as where the study took place, the journal it was published or came from, etc.

A mapping study was applied to answer the research questions. Once they were stablished, an exhaustive search chain was applied for the nervous system diseases, using the International Statistical Classification of Diseases and Related Health Problems 10th Revision (ICD-10), 2019 version, in Group V (Mental and behavioural disorder) and VI (Nervous system diseases), taking into account the inclusion and exclusion criteria.

49 articles for the psychiatric and 20 articles for the neurological diseases were classified in relation to gender, social factors and machine learning techniques. Depression for the psychiatric disorders and Alzheimer’s disease for the neurological diseases were the diseases with more articles being published but if the variables were taken into account individually this changed; for the psychiatric diseases, considering only gender or machine learning techniques, Stress was the most common disease with more articles being published. By applying social factors, Depression was the most common disease. On the other hand, for the neurological diseases, taken the variables individually or all together, Alzheimer's disease was the common disease with more articles being published. The number of studies in relation to machine learning techniques, social factors and gender is growing up every year. At present, United States and China were the countries with more publications in this area.

Even if there are thousands of research published in the nervous system diseases field (psychiatric and neurological), when the search string was done in relation to gender, social factors and machine learning techniques the number of articles decreased to just 69, so this underlines the need of investigation in those areas. It is worthy to say that in the last few years, it has been an increase of these research topics. In addition, this mapping study concludes that it is compulsory to include gender and machine learning in the agendas in order to get new data and knowledge about social factors related to health and disease for all populations allowing to make more accurate predictions and to improve health outcomes.