Background
In 2019, 1 in every 8 people, or 970 million people around the world were living with a mental disorder, with anxiety and depressive disorders being the most common. [6] In 2020, the number of people living with anxiety and depressive disorders rose significantly because of the COVID-19 pandemic. [7] Additionally, the prevalence of mental health and addiction disorders exhibits a nearly equal distribution across genders, emphasizing the widespread nature of the issue. [8]
The use of AI in mental health aims to support responsive and sustainable interventions against the global challenge posed by mental health disorders. Some issues common to the mental health industry are provider shortages, inefficient diagnoses, and ineffective treatments. The Global market for AI-driven mental health applications is projected to grow significantly, with estimates suggesting an increase from 0.92 billion USD in 2023 to $14.89 billion USD by 2033. [9] This growth indicates a growing interest in AI's ability to address critical challenges in mental healthcare provision through the development and implementation of innovative solutions. [10]
AI-driven approaches
There are several components of AI that are currently widely available for multiple applications, such as machine learning (ML), natural language processing (NLP), deep learning (DL), and computer vision (CV). These technologies enable early detection of mental health conditions, personalized treatment recommendations, and real-time monitoring of patient well-being.
Machine learning
Machine learning is an AI technique that enables computers to identify patterns in large datasets and make predictions based on those patterns. Unlike traditional medical research, which begins with a hypothesis, ML models analyze existing data to uncover correlations and develop predictive algorithms. [10] ML in psychiatry is limited by data availability and quality. Many psychiatric diagnoses rely on subjective assessments, interviews, and behavioral observations, making structured data collection difficult. [10] Researchers are addressing these challenges using transfer learning, a technique that adapts ML models trained in other fields for use in mental health applications. [11]
Natural language processing
Natural Language Processing allows AI systems to analyze and interpret human language, including speech, text, and tone of voice. In mental health, NLP is used to extract meaningful insights from conversations, clinical notes, and patient-reported symptoms. NLP can assess sentiment, speech patterns, and linguistic cues to detect signs of mental distress. This is crucial because many of the diagnoses and DSM-5 mental health disorders are diagnosed via speech in doctor-patient interviews, utilizing the clinician's skill for behavioral pattern recognition and translating it into medically relevant information to be documented and used for diagnoses. As research continues, NLP models must address ethical concerns related to patient privacy, consent, and potential biases in language interpretation. [12]
Deep Learning
Deep learning, a subset of ML, involves neural networks that mimic the human brain to analyze complex data. It is particularly useful for identifying subtle patterns in speech, imaging, and physiological data. [13] Deep learning is used in neuroimaging analysis, helping researchers detect abnormalities in brain scans associated with conditions such as schizophrenia, depression, and PTSD. [14] However, deep learning models require extensive, high-quality datasets to function effectively. The limited availability of large, diverse mental health datasets poses a challenge, as patient privacy regulations restrict access to medical records. Additionally, deep learning models often operate as "black boxes", meaning their decision-making processes are not easily interpretable by clinicians, raising concerns about transparency and clinical trust. [15]
Computer Vision
Computer vision enables AI to analyze visual data, such as facial expressions, body language, and micro expressions, to assess emotional and psychological states. This technology is increasingly used in mental health research to detect signs of depression, anxiety, and PTSD through facial analysis. [16] CV can detect subtle nonverbal cues, such as hesitation or changes in eye contact, which may indicate emotional distress. Despite its potential, computer vision in mental health raises ethical and accuracy concerns. Facial recognition algorithms can be influenced by cultural and racial biases, leading to potential misinterpretations of emotional expressions. [17] Additionally, concerns about informed consent and data privacy must be addressed before widespread clinical adoption.
Current AI trends in mental health
As of 2020, the Food and Drug Administration (FDA) had not approved any artificial intelligence-based tools for use in Psychiatry. [22] However, in 2022, the FDA granted authorization for the initial testing of an AI-driven mental health assessment tool known as the AI-Generated Clinical Outcome Assessment (AI-COA). This system employs multimodal behavioral signal processing and machine learning to track mental health symptoms and assess the severity of anxiety and depression. AI-COA was integrated into a pilot program to evaluate its clinical effectiveness, though it has not yet received full regulatory approval. [23]
Mental health tech startups continue to lead investment activity in digital health despite the ongoing impacts of macroeconomic factors like inflation, supply chain disruptions, and interest rates. [24]
According to CB Insights, State of Mental Health Tech 2021 Report, mental health tech companies raised $5.5 billion worldwide (324 deals), a 139% increase from the previous year that recorded 258 deals.
A number of startups that are using AI in mental healthcare have closed notable deals in 2022 as well. Among them is the AI chatbot Wysa (20$ million in funding), BlueSkeye that is working on improving early diagnosis (£3.4 million), the Upheal smart notebook for mental health professionals (€1.068 million), and the AI-based mental health companion clare&me (€1 million).
An analysis of the investment landscape and ongoing research suggests that we are likely to see the emergence of more emotionally intelligent AI bots and new mental health applications driven by AI prediction and detection capabilities.
For instance, researchers at Vanderbilt University Medical Center in Tennessee, US, have developed an ML algorithm that uses a person’s hospital admission data, including age, gender, and past medical diagnoses, to make an 80% accurate prediction of whether this individual is likely to take their own life. [25] And researchers at the University of Florida are about to test their new AI platform aimed at making an accurate diagnosis in patients with early Parkinson’s disease. [26] Research is also underway to develop a tool combining explainable AI and deep learning to prescribe personalized treatment plans for children with schizophrenia. [27]
AI systems could predict and plan treatments accurately and effectively for all fields of medicine at levels similar to that of physicians and general clinical practices. For example, one AI model diagnosed depression and post-traumatic stress disorder with precision that exceeded that of general practitioners based solely on their assessments. [28]
AI systems studying social media data are being developed to help spot mental health risks sooner and in more locations and for less money. Ethical concerns include uneven performance between digital services, the possibility that biases could affect decision-making, and trust, privacy, and doctor-patient relationship issues. [29]
In January of 2024, Cedars-Sinai physician-scientists developed a first-of-its-kind program that uses immersive virtual reality and generative artificial intelligence to provide mental health support. The program is called XAIA which employs a large language model programmed to resemble a human therapist.
The University of Southern California is researching the effectiveness of a virtual therapist named Ellie. Through a webcam and microphone, this AI is able to process and analyze the emotional cues derived from the patient's face and the variation in expressions and tone of voice.
A team of Stanford Psychologists and AI experts created "Woebot". Woebot is an app that makes therapy sessions available 24/7. WoeBot tracks its users' mood through brief daily chat conversations and offers curated videos or word games to assist users in managing their mental health. A Scandinavian team of software engineers and a clinical psychologist created "Heartfelt Services". Heartfelt Services is an application meant to simulate conventional talk therapy with an AI therapist. [30]
