Machine Learning and Natural Language Processing in Mental Health: Systematic Review

Abstract

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.

Artificial intelligence, machine learning, and deep learning for clinical outcome prediction

“…In Supplementary Table S1 , we have complied recent review articles detailing emerging examples of how statistical and ML methods are being utilized for clinical outcome prediction in major medical specialities. Applications are found in the fields of Anesthesiology [ 32 , 33 , 34 ], Dermatology [ 35 , 36 , 37 ], Emergency Medicine [ 38 , 39 ], Family Medicine [ 40 , 40 ], Internal Medicine [ 41 , 42 , 43 ], Interventional Radiology [ 44 , 45 ], Medical Genetics [ 46 ], Neurological Surgery [ 47 ], Neurology [ 48 , 49 , 50 ], Obstetrics and Gynecology [ 51 , 52 ], Ophthalmology [ 53 , 54 , 55 ], Orthopaedic Surgery [ 56 ], Otorhinolaryngology [ 57 , 58 ], Pathology [ 59 , 60 , 61 ], Pediatrics [ 62 ], Physical Medicine and Rehabilitation [ 63 , 64 ], Plastic and Reconstructive Surgery [ 65 , 66 ], Psychiatry [ 67 , 68 ], Radiation Oncology [ 69 , 70 ], Radiology [ 71 , 72 ], General Surgery [ 73 , 74 ], Cardiothoracic Surgery [ 75 , 76 ], Urology [ 77 , 78 ], Vascular Surgery [ 79 , 80 ]. These papers introduce terms describing ML models as ‘supervised’ or ‘unsupervised’.…”

Natural Language Processing Of Helpline Chat Data Before And During The Pandemic Revealed Significant Decrease In Self-image Appreciation And Changes In Other Traits

“…For instance, researchers have found that liberals tend to self-report less happiness than conservatives but display more in their actual behavior [15]. Lately, computer-based tools, such as Natural Language Processing (NLP) and Machine Learning (ML), have increasingly been adopted to study mental health [16]. Using large amounts of text from either patient records, emergency room data or even social media, researchers have been able to extract symptoms, classify the severity and identify psycho-pathological clues [16].…”

“…Lately, computer-based tools, such as Natural Language Processing (NLP) and Machine Learning (ML), have increasingly been adopted to study mental health [16]. Using large amounts of text from either patient records, emergency room data or even social media, researchers have been able to extract symptoms, classify the severity and identify psycho-pathological clues [16]. NLP has even been used to design chat-bots for complementary mental health treatment [17].…”

Listening to Mental Health Crisis Needs at Scale: Using Natural Language Processing to Understand and Evaluate a Mental Health Crisis Text Messaging Service

“…The data from non-traditional digital mental health support services offers a unique window into mental health needs and experiences of distress, and provides an opportunity to evaluate personalised support approaches. In particular, big data analysis techniques, such as natural language processing (NLP) and machine learning, allow us to examine, at scale, expressions of distress and user interactions with mental health services ( 6 ). To date, the challenges involved in accessing relevant data sets have partly prevented a full exploration of the value of such techniques for mental health insights and service evaluation [see ( 7 ) for a notable exception].…”

“…In the context of mental health, NLP has also been used for predicting suicidal ideation ( 17 , 18 ), analysing post-traumatic stress disorder ( 19 ), predicting psychosis ( 20 ) and other disorders ( 21 ), generating artificial mental health records ( 22 ), and for motivational interviewing ( 23 ). For a more complete review of NLP in mental health, see ( 6 ). However, NLP models have been rarely applied to digital mental health resources such as crisis text line services ( 7 ), and to date no published studies analyse the Shout data set.…”