Machine learning in mental health: A systematic scoping review of methods and applications

Abstract

ObjectiveThis paper aims to synthesise the literature on machine learning (ML) and big data applications for mental health, highlighting current research and applications in practice. Materials and MethodsEight health and information technology research databases were searched using the terms "big data" or "machine learning" and "mental health". Articles were assessed by two reviewers, and data were extracted on the article's mental health application, ML technique, data type and size, and study results. Articles were then synthesised via narrative review. ResultsThree hundred papers focusing on the application of ML to mental health were identified. Four main application domains emerged in the literature, including: (i) detection and diagnosis; (ii) prognosis, treatment and support; (iii) public health; and, (iv) research and clinical administration. The most common mental health conditions addressed included depression, schizophrenia, and Alzheimer's Disease. ML techniques used included support vector machines, decision trees, neural networks, latent dirichlet allocation, and clustering. Discussion and ConclusionOverall, the application of ML to mental health has demonstrated a range of benefits across the areas of diagnosis, treatment and support, research, and clinical administration.With the majority of studies identified focusing on the detection and diagnosis of mental health conditions, it is evident that there is significant room for the application of ML to improve other areas of psychological functioning. The challenges of using ML techniques are discussed, as well as opportunities to improve and advance the field. BACKGROUND AND SIGNIFICANCE

Predicting Symptoms of Depression and Anxiety Using Smartphone and Wearable Data

“…Notwithstanding these limitations, the current study provides promising indications of digital phenotyping data derived from consumer wearable devices for the identification of individuals suffering from or at risk of developing a mental health condition. Future research would benefit from assessing how data from additional sensors [e.g., speech and voice (77), keyboard interactions (78), bio-sensing (79), and smartphone app usage (80)], combined with machine learning models may be used to further improve predictive accuracy (81)(82)(83)(84)(85). Given the issues quantifying explained variance in multilevel models (86,87), future research would also benefit from understanding the amount of variance explained in symptomatology by smartphone and wearable sensing data.…”

Study of the Computer-Based Interventions for Adolescents in the Prevention and Treatment of Depression and Anxiety

“…HCI has more scope in an effective online or computer/mobile assisted intervention. Figure 3 shows the different techniques, application programs and questionnaires used in manual and computer assisted intervention programs Online Interventions mainly use CBT for depression and anxiety with or without randomized control trial, and therapist assistance [36]. CBT has much more efficacy but has some of the limitation with use in online interventions.…”

Künstliche Intelligenz für die Sprachanalyse in der Psychotherapie – Chancen und Risiken

“…Die Kombination mit weiteren Modalitäten und Datenquellen (z. B. Smartphonenutzung, Mimik, Biophysiologie) kann die Interpretations- und Vorhersageleistung komplexer Analysen steigern, in denen Sprache bisher noch unterrepräsentiert ist 10 . Durch die Implementierung in E-Mental-Health Applikationen, z.…”