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.

BackgroundPatients with eating disorders are characterized by pathological eating habits and a tendency to overestimate their weight and body shape. Virtual reality shows promise for the evaluation and management of patients with eating disorders. This technology, when accepted by this population, allows immersion in virtual environments, assessment, and therapeutic approaches, by exposing users to high-calorie foods or changes in body shape.ObjectiveTo better understand the value of virtual reality, we conducted a review of the literature, including clinical studies proposing the use of virtual reality for the evaluation and management of patients with eating disorders.MethodsWe searched PubMed, PsycINFO, ScienceDirect, the Cochrane Library, Scopus, and Web of Science up to April 2017. We created the list of keywords based on two domains: virtual reality and eating disorders. We used the Preferred Reporting Items for Systematic Reviews and Meta-Analyses to identify, select, and critically appraise relevant research while minimizing bias.ResultsThe initial database searches identified 311 articles, 149 of which we removed as duplicates. We analyzed the resulting set of 26 unique studies that met the inclusion criteria. Of these, 8 studies were randomized controlled trials, 13 were nonrandomized studies, and 5 were clinical trials with only 1 participant. Most articles focused on clinical populations (19/26, 73%), with the remainder reporting case-control studies (7/26, 27%). Most of the studies used visual immersive equipment (16/26, 62%) with a head-mounted display (15/16, 94%). Two main areas of interest emerged from these studies: virtual work on patients’ body image (7/26, 27%) and exposure to virtual food stimuli (10/26, 38%).ConclusionsWe conducted a broad analysis of studies on the use of virtual reality in patients with eating disorders. This review of the literature showed that virtual reality is an acceptable and promising therapeutic tool for patients with eating disorders.

Background Sleep disorders are a major public health issue. Nearly 1 in 2 people experience sleep disturbances during their lifetime, with a potential harmful impact on well-being and physical and mental health. Objective The aim of this study was to better understand the clinical applications of wearable-based sleep monitoring; therefore, we conducted a review of the literature, including feasibility studies and clinical trials on this topic. Methods We searched PubMed, PsycINFO, ScienceDirect, the Cochrane Library, Scopus, and the Web of Science through June 2019. We created the list of keywords based on 2 domains: wearables and sleep. The primary selection criterion was the reporting of clinical trials using wearable devices for sleep recording in adults. Results The initial search identified 645 articles; 19 articles meeting the inclusion criteria were included in the final analysis. In all, 4 categories of the selected articles appeared. Of the 19 studies in this review, 58 % (11/19) were comparison studies with the gold standard, 21% (4/19) were feasibility studies, 15% (3/19) were population comparison studies, and 5% (1/19) assessed the impact of sleep disorders in the clinic. The samples were heterogeneous in size, ranging from 1 to 15,839 patients. Our review shows that mobile-health (mHealth) wearable–based sleep monitoring is feasible. However, we identified some major limitations to the reliability of wearable-based monitoring methods compared with polysomnography. Conclusions This review showed that wearables provide acceptable sleep monitoring but with poor reliability. However, wearable mHealth devices appear to be promising tools for ecological monitoring.

Background: Suicide is a major public health problem and a cause of premature mortality. With a view to prevention, a great deal of research has been devoted to the determinants of suicide, focusing mostly on individual risk factors, particularly depression. In addition to causes intrinsic to the individual, the social environment has also been widely studied, particularly social isolation. This paper examines the social dimension of suicide etiology through a review of the literature on the relationship between suicide and social isolation. Method: Medline searches via PubMed and PsycINFO were conducted. The keywords were "suicid*" AND "isolation."Results: Of the 2 684 articles initially retrieved, 46 were included in the review. Conclusion: Supported by proven theoretical foundations, mainly those developed by E. Durkheim and T.Joiner, a large majority of the articles included endorse the idea of a causal relationship between social isolation and suicide, and conversely, a protective effect of social support against suicide. Moreover, the association between suicide and social isolation is subject to variations related to age, gender, psychopathology, and specific circumstances. The social etiology of suicide has implications for intervention and future research.

No abstract

BackgroundResearch indicates that maintaining contact either via letter or postcard with at-risk adults following discharge from care services after a suicide attempt (SA) can reduce reattempt risk. Pilot studies have demonstrated that interventions using mobile health (mHealth) technologies are feasible in a suicide prevention setting.ObjectiveThe aim of this study was to report three cases of patients recruited in the Suicide Intervention Assisted by Messages (SIAM) study to describe how a mobile intervention may influence follow-up.MethodsSIAM is a 2-year, multicenter randomized controlled trial conducted by the Brest University Hospital, France. Participants in the intervention group receive SIAM text messages 48 hours after discharge, then at day 8 and day 15, and months 1, 2, 3, 4, 5, and 6. The study includes participants aged 18 years or older, who have attended a participating hospital for an SA, and have been discharged from the emergency department (ED) or a psychiatric unit (PU) for a stay of less than 7 days. Eligible participants are randomized between the SIAM intervention messages and a control group. In this study, we present three cases from the ongoing SIAM study that demonstrate the capability of a mobile-based brief contact intervention for triggering patient-initiated contact with a crisis support team at various time points throughout the mobile-based follow-up period.ResultsOut of the 244 patients recruited in the SIAM randomized controlled trial, three cases were selected to illustrate the impact of mHealth on suicide risk management. Participants initiated contact with the emergency crisis support service after receiving text messages up to 6 months following discharge from the hospital. Contact was initiated immediately following receipt of a text message or up to 6 days following a message.ConclusionsThis text message–based brief contact intervention has demonstrated the potential to reconnect suicidal individuals with crisis support services while they are experiencing suicidal ideation as well as in a period after receiving messages. As follow-up phone calls over an extended period of time may not be feasible, this intervention has the potential to offer simple technological support for individuals following discharge from the ED.Trial RegistrationClinicalTrials.gov NCT02106949; https://clinicaltrials.gov/ct2/show/NCT02106949 (Archived by WebCite at http://www.webcitation.org/6wMtAFL49)

Background and objectives: Suicide is one of the main preventable causes of death. Artificial intelligence could improve methods for assessing suicide risk. The objective of this review is to assess the potential of artificial intelligence in identifying patients who are at risk of attempting suicide.Methods: A systematic review of the literature was conducted on PubMed, EMBASE and SCOPUS databases, using relevant keywords.Results: Thanks to this research, 296 studies were identified. Seventeen studies, published between 2014 and 2020 and matching inclusion criteria, were selected as relevant. Included studies aimed at predicting individual suicide risk or identifying at-risk individuals in a specific population. The AI performance was overall good, although variable across different algorithms and application settings.Conclusion: AI appears to have high potential for identifying patients at risk of suicide. The precise use of these algorithms in clinical situations, as well as the ethical issues it raises, remain to be clarified.

Background Many mental disorders are preceded by a prodromal phase consisting of various attenuated and unspecific symptoms and functional impairment. Electronic health records are generally used to capture these symptoms during medical consultation. Internet and mobile technologies provide the opportunity to monitor symptoms emerging in patients’ environments using ecological momentary assessment techniques to support preventive therapeutic decision making. Objective The objective of this study was to assess the acceptability of a Web-based app designed to collect medical data during appointments and provide ecological momentary assessment features. Methods We recruited clinicians at 4 community psychiatry departments in France to participate. They used the app to assess patients and to collect data after viewing a video of a young patient’s emerging psychiatric consultation. We then asked them to answer a short anonymous self-administered questionnaire that evaluated their experience, the acceptability of the app, and their habit of using new technologies. Results Of 24 practitioners invited, 21 (88%) agreed to participate. Most of them were between 25 and 45 years old, and greater age was not associated with poorer acceptability. Most of the practitioners regularly used new technologies, and 95% (20/21) connected daily to the internet, with 70% (15/21) connecting 3 times a day or more. However, only 57% (12/21) reported feeling comfortable with computers. Of the clinicians, 86% (18/21) would recommend the tool to their colleagues and 67% (14/21) stated that they would be interested in daily use of the app. Most of the clinicians (16/21, 76%) found the interface easy to use and useful. However, several clinicians noted the lack of readability (8/21, 38%) and the need to improve ergonometric features (4/21, 19%), in particular to facilitate browsing through various subsections. Some participants (5/21, 24%) were concerned about the storage of medical data and most of them (11/21, 52%) seemed to be uncomfortable with this. Conclusions We describe the first step of the development of a Web app combining an electronic health record and ecological momentary assessment features. This online tool offers the possibility to assess patients and to integrate medical data easily into face-to-face conditions. The acceptability of this app supports the feasibility of its broader implementation. This app could help to standardize assessment and to build up a strong database. Used in conjunction with robust data mining analytic techniques, such a database would allow exploration of risk factors, patterns of symptom evolution, and identification of distinct risk subgroups.