RESUMEN
BACKGROUND: First episode of psychosis (FEP) is a clinical condition that usually occurs during adolescence or early adulthood and is often a sign of a future psychiatric disease. However, these symptoms are not specific, and psychosis can be caused by a physical disease in at least 5% of cases. Timely detection of these diseases, the first signs of which may appear in childhood, is of particular importance, as a curable treatment exists in most cases. However, there is no consensus in academic societies to offer recommendations for a comprehensive medical assessment to eliminate somatic causes. METHODS: We conducted a systematic literature search using a two-fold research strategy to: (1) identify physical diseases that can be differentially diagnosed for psychosis; and (2) determine the paraclinical exams allowing us to exclude these pathologies. RESULTS: We identified 85 articles describing the autoimmune, metabolic, neurologic, infectious, and genetic differential diagnoses of psychosis. Clinical presentations are described, and a complete list of laboratory and imaging features required to identify and confirm these diseases is provided. CONCLUSION: This systematic review shows that most differential diagnoses of psychosis should be considered in the case of a FEP and could be identified by providing a systematic checkup with a laboratory test that includes ammonemia, antinuclear and anti-NMDA antibodies, and HIV testing; brain magnetic resonance imaging and lumbar puncture should be considered according to the clinical presentation. Genetic research could be of interest to patients presenting with physical or developmental symptoms associated with psychiatric manifestations.
RESUMEN
BACKGROUND: Machine learning systems are part of the field of artificial intelligence that automatically learn models from data to make better decisions. Natural language processing (NLP), by using corpora and learning approaches, provides good performance in statistical tasks, such as text classification or sentiment mining. OBJECTIVE: The primary aim of this systematic review was to summarize and characterize, in methodological and technical terms, studies that used machine learning and NLP techniques for mental health. The secondary aim was to consider the potential use of these methods in mental health clinical practice. METHODS: This systematic review follows the PRISMA (Preferred Reporting Items for Systematic Review and Meta-analysis) guidelines and is registered with PROSPERO (Prospective Register of Systematic Reviews; number CRD42019107376). The search was conducted using 4 medical databases (PubMed, Scopus, ScienceDirect, and PsycINFO) with the following keywords: machine learning, data mining, psychiatry, mental health, and mental disorder. The exclusion criteria were as follows: languages other than English, anonymization process, case studies, conference papers, and reviews. No limitations on publication dates were imposed. RESULTS: A total of 327 articles were identified, of which 269 (82.3%) were excluded and 58 (17.7%) were included in the review. The results were organized through a qualitative perspective. Although studies had heterogeneous topics and methods, some themes emerged. Population studies could be grouped into 3 categories: patients included in medical databases, patients who came to the emergency room, and social media users. The main objectives were to extract symptoms, classify severity of illness, compare therapy effectiveness, provide psychopathological clues, and challenge the current nosography. Medical records and social media were the 2 major data sources. With regard to the methods used, preprocessing used the standard methods of NLP and unique identifier extraction dedicated to medical texts. Efficient classifiers were preferred rather than transparent functioning classifiers. Python was the most frequently used platform. CONCLUSIONS: Machine learning and NLP models have been highly topical issues in medicine in recent years and may be considered a new paradigm in medical research. However, these processes tend to confirm clinical hypotheses rather than developing entirely new information, and only one major category of the population (ie, social media users) is an imprecise cohort. Moreover, some language-specific features can improve the performance of NLP methods, and their extension to other languages should be more closely investigated. However, machine learning and NLP techniques provide useful information from unexplored data (ie, patients' daily habits that are usually inaccessible to care providers). Before considering It as an additional tool of mental health care, ethical issues remain and should be discussed in a timely manner. Machine learning and NLP methods may offer multiple perspectives in mental health research but should also be considered as tools to support clinical practice.
