Application of Natural Language Processing (NLP) in Detecting and Preventing Suicide Ideation: A Systematic Review

Abstract

(1) Introduction: Around a million people are reported to die by suicide every year, and due to the stigma associated with the nature of the death, this figure is usually assumed to be an underestimate. Machine learning and artificial intelligence such as natural language processing has the potential to become a major technique for the detection, diagnosis, and treatment of people. (2) Methods: PubMed, EMBASE, MEDLINE, PsycInfo, and Global Health databases were searched for studies that reported use of NLP for suicide ideation or self-harm. (3) Result: The preliminary search of 5 databases generated 387 results. Removal of duplicates resulted in 158 potentially suitable studies. Twenty papers were finally included in this review. (4) Discussion: Studies show that combining structured and unstructured data in NLP data modelling yielded more accurate results than utilizing either alone. Additionally, to reduce suicides, people with mental problems must be continuously and passively monitored. (5) Conclusions: The use of AI&ML opens new avenues for considerably guiding risk prediction and advancing suicide prevention frameworks. The review’s analysis of the included research revealed that the use of NLP may result in low-cost and effective alternatives to existing resource-intensive methods of suicide prevention.

The now and future of ChatGPT and GPT in psychiatry

“…Although ChatGPT's moderate performance in suicide assessment is described above, a recent study reported initial success for an AI model designed to detect cognitive distortions in text messages as accurately as clinically trained human raters 40 . Previous research on NLP detection and prevention of suicide ideation is also yielding promise for more technological advances in AI's emotional quotient 41 …”

“…40 Previous research on NLP detection and prevention of suicide ideation is also yielding promise for more technological advances in AI's emotional quotient. 41 When GPT technology is equipped with the ability to empathize, recognize emotion, assess personality, and detect mental health warning signs, we envision a future with GPT in psychiatric clinics. With full informed consent, patients can willingly provide their social media content or conversations for assessment by GPT-based medical apps.…”

Suicide Risk Assessment and Prevention Tools in the UK: Current Landscape and Future Directions

“…Also worth mentioning are the Reasons for Living scales [86,87], Screening for Depression and Thoughts of Suicide scale [88], Suicidal Imagery Questionnaire [89], Depressive Symptom Inventory-Suicidality Subscale [90], Suicide Risk Scale for Medical Inpatients [91], etc. For a comprehensive review on the various tools available for assessment of suicidal ideation and suicide, please see [92,93].…”

“…In recent years, machine learning and artificial intelligence have been used extensively in suicide research and prevention especially in terms of data generation through algorithms such as natural language processing (NLP), that use existing data from physical clinical records and electronic health records (EHRs) for the identification of people at a higher risk of suicide. Indeed, computational algorithms based on NLP can provide a low-cost and resource-efficient alternative to more expensive methods according to a recent systematic review [93]. Machine learning (ML) is a branch of artificial intelligence (AI) that describes various algorithms, associated with the efficient handling of data (especially big data) to perform various human tasks in a logical and reproducible manner [94,95].…”

Teen-adult interactions during the co-design of data literacy activities for the public library: insights from a natural language processing analysis of linguistic patterns

“…It has the advantage of being able to quickly and efficiently (once the data is cleaned) extract broad statistically significant trends from data sets that might, otherwise, be too labor intensive to analyze. This has had a wide range of research applications in recent years, from using NLP models to analyze survey data relating to job satisfaction (Speer et al , 2022) to the detection of suicidal ideation (Arowosegbe and Oyelade, 2023) and early signs of Alzheimer’s (Diaz-Asper et al , 2022).…”