Reviews

Issue 1 - March 2024

Artificial intelligence applications in mental health: the state of the art

Authors

Key words: artificial intelligence, deep learning, machine learning, natural language processing, mental health, severe mental illness
Publication Date: 2024-05-20

Abstract

Objectives. This review aims to examine the current use of artificial intelligence (AI) in mental health. The first step involves categorising AI algorithms into three subtypes: natural language processing (NLP), machine learning (ML), and deep learning (DL). Next, we evaluated their application in mental health and the instrumental methods used to collect valid and sufficient quantitative data. 
Results. Evidence suggests that AI algorithms are being used, particularly in the diagnosis or differential diagnosis of mental illness. The most commonly used instrumental techniques were neuroimaging, particularly magnetic resonance imaging (MRI), and neurophysiology, specifically electroencephalography (EEG). 
Conclusions. This review is the first to analyse these three algorithms in the field of mental health, without any limitations on method or population type. Further studies are necessary to better understand the validity of these algorithms in clinical practice. It is important to anticipate both useful innovations and potential difficulties.

INTRODUCTION

Artificial intelligence

Recent years have seen significant advances in technology, leading to what is commonly referred to as the “Fourth Industrial Revolution” or “Industry 4.0” 1. Simultaneously, there has been a progression in digital technology, commonly known as the “Digital Revolution” 2. This revolution is impacting all areas of society, including healthcare. With the advent of the COVID-19 pandemic, healthcare professionals and patients alike are increasingly using technological devices that were previously under-utilised but have now become commonplace 3.

Mental health services have undergone a transformation towards digitised medicine, utilising technology at various levels, from diagnosis and related care to service delivery 4. One of the most controversial technological innovations is artificial intelligence (AI), which has brought about numerous changes and raised ethical questions 5.

The birth of AI dates back to 1950 when mathematician Alan Turing published his article “Computing machinery and intelligence” in the journal “Mind” 6. Turing questioned the possibility of building a machine that could think like humans, but defining human thought is a complex task that limits the answer to this question. Therefore, he later decided to shift his focus from abstract concepts to something more concrete: specifically, he began to hypothesise the creation of a machine that could act in a certain way to satisfy the demands placed upon it. The term “artificial intelligence” was later coined by John McCarthy in 1956, who defined it as “the science and engineering of making machines intelligent” 7.

Over the years, several algorithms have been developed for various purposes. Some were initially created for recreational use, such as IBM Deep Blue 8, IBM Watson 9, and DeepMind AlphaGo 10; others, like ChatGPT (GPT: Generative Pre-trained Transformer) 11,12, have become more widely used.

Defining AI is a complex task as there are multiple definitions available 13. However, they can be simplified into four categories 14: i) systems that think like humans; ii) systems that act like humans; iii) systems that think rationally; and iv) systems that act rationally.

Currently, the three most widely used types of AI are natural language processing (NLP), machine learning (ML), and deep learning (DL). It is important to note that these algorithms are often combined.

Natural language processing

NLP originated in the 1950s from the integration of computer science, linguistics, and mathematics. It is an analytical technique that uses computers to decode and automatically understand human language 15. NLP can be divided into two categories: natural language understanding (NLU) is the process of translating human language into a machine-understandable format 16; and natural language generation (NLG) is the process of producing human language output from digital data 17, including text-to-text 18, text-to-speech 19, and other-to-text 20. NLU and NLG are important components of speech technology.

The process of NLP can be divided into four parts: text pre-processing, text representation, model training, and model evaluation. The first part involves simplifying and correcting the text by removing meaningless symbols and correcting spelling mistakes to achieve better accuracy and efficiency in subsequent steps. The text is then converted (“represented”) into numerical vectors and matrices, on which algorithms are applied to train a model. Finally, the model is evaluated to confirm its generalisability and efficiency in the real world 21.

In recent years, there has been exponential development in NLP 22, particularly in machine translation 23, pattern matching 24, sentiment analysis 25, and voice recognition 26. The advancement of technology has facilitated the development of intelligent devices such as Siri and Cortana, simultaneous translations like Google Translator or Microsoft Translator, and voice recognition software such as Windows Voice Recognition. Additionally, algorithms have been created to predict the financial market based on sentiment analysis of Twitter.

Machine learning

ML algorithms gather information about their surroundings by hypothesising a law that they will then use later. The machine “learns” through observation. The process is simple, with input and output variables, and the machine’s task is to find a connection between the two, without creating a universal law 27.

There are three modes of learning 28: supervised learning (SL), reinforcement learning (RL), and unsupervised learning (UL). In SL, the machine is provided with all the data, which is divided into input and output, and creates a function that explains the phenomenon. Later, it can use this function to predict outputs from new input data 29,30. In RL, the machine is given data sequentially, and from time to time, it evaluates what action is best to take to approach a known function. RL involves a “reward” for each action based on its functionality in achieving the goal 31. In UL, the machine has access to all input and output data, but without subdivisions, it seeks to identify an underlying function for future observations. In this case, since the data is not split, the machine will have no constraints and the number of possibilities will be greater. As a result, groupings between data are usually created based on a similarity or proximity criterion, known as clustering 32.

In addition to these three types, there are also systems known as semi-supervised learning 33, which is a combination of SL and UL, and DL.

Deep learning

DL is a type of ML that utilises neural networks for learning through training. “Deep neural networks” are so named because they are composed of interconnected layers of “artificial neurons” (also known as Artificial Neural Networks or ANNs). This structure typically includes three or more layers, and in some of the latest algorithms, there can be hundreds of layers. In DL algorithms, as in our nervous system, learning occurs by changing the “weight” of connections between neurons. Functional connections are given higher priority 34. Artificial Neural Networks process input data in a non-linear manner, similar to brain neurons, and only activate if they reach a threshold potential determined by the weighted sum of inputs, resulting in an output 35. This method is ideal for integrating and extracting information from multimodal data, which is collected through several complementary modalities such as behavioural measurements, electroencephalography (EEG), and magnetic resonance imaging (MRI). The layers in this method establish a hierarchy, with the first layers extracting basic features specific to each modality, and the subsequent layers serving for abstract concepts that can be shared between the modalities.

The difference with ML is the type of data processed: DL works on raw, unlabelled data, as opposed to ML, that works on extrapolated and selected data, chosen by the programmer. In DL, it is the algorithm itself that processes and extrapolates the data it will later need to respond to the queries made. The data that can be used can be structured data with a high sample size (e.g. EEG, MRI).

AIMS

This study aims to investigate the performance of the most commonly used AI algorithms in the field of mental health. Additionally, we will analyse the most frequently used methods for collecting data to train these algorithms. Finally, we will examine the most commonly used recruitment settings. The ultimate objective is to establish a basis for comprehending the potential development and application of AI in the future.

RESULTS

In recent years, there have been several reviews and meta-analyses exploring the use of AI in the field of mental health 36,37. This review includes AI studies without a focus on a specific algorithm or on a single mental disorder. On the contrary, previous studies have focused on specific algorithms (e.g. ML 38, DL 39) or specific instrumental methods (e.g. MRI 40, EEG 41), or specific psychiatric disorders (e.g. anxiety and depression 42, schizophrenia) 43.

The studies’ individual outcomes differ and cover four main research areas: neurobiological correlates; investigation on clinical characterization; diagnostic ability improvement; and prognosis prediction.

The study of neurobiological correlates involves the identification of brain areas and circuits that may be pathognomonic 44-46, as well as the investigation of patients’ brain age and the aging trajectory of the nervous system 47,48.

The investigation of clinical characterisation involves the correlation of specific data with various aspects of the patient’s clinical and biological profile, including psychopathology 49, physical comorbidities 50, self-harm, suicidal 51 and aggressive behaviours 52, objective and subjective psychosocial functioning, quality of life, and the use of services 53-55. In the field of diagnostics, there are ongoing efforts to develop innovative AI algorithms that can assist clinicians in distinguishing between healthy individuals and those with a disorder 56,57, as well as in making differential diagnoses among various psychiatric disorders 58-61.

Finally, prognostic prediction 62 involves the study of the evolution of a patient’s condition in relation to the treatment they receive, including pharmacological and psychotherapeutic treatments, as well as their adherence to the treatment plan 63-66. An increasingly analysed topic is the discovery of the trajectory of individuals at risk to develop mental disorders, within a primary prevention perspective 67-69.

To function optimally, AI requires a large amount of data, so studies typically make use of neurobiological measurements, audio/video recordings, biological samples, and special measurements.

Neuroimaging (structural and functional MRI 70,71, magnetoencephalography 72, positron emission tomography [PET] 73, etc.) and neurophysiology (EEG) 74 methods provide most of the neurobiological measurements.

Interviews or tests involve audio or video recordings to extract information not only from language (such as syntax and tone) 75, but also from non-verbal cues (such as facial expressions and movements) 76.

Biological samples, including blood and saliva, were collected for genetic analyses and evaluation of various aspects, such as the inflammatory system, kidney and liver function, and lipid balance in some studies 77,78.

Other studies have also included measurements of somatic parameters, such as height, weight, and body mass index (BMI) 79, as well as movement parameters like eye, head, and limb movements 80. Data was collected using mobile device applications 81, which enabled the detection of reaction times and subject movements using gyroscopes and GPS tracking.

Finally, some authors have chosen to use only socio-demographic variables and psychopathological evaluations as data to be included in the algorithms, without employing instrumental methods 82,83.

The data used in the algorithms was mainly obtained from subject recruitment conducted in clinical and/or university settings. However, the researchers also used open-access databases as a data source 84,85. This allowed them to collect the necessary amount of data to train the algorithms and then recruit a small sample of real-life subjects to test the validity of the algorithms.

A summary of the current AI applications in mental health is shown in Table I.

DISCUSSION

In recent years, there has been a growing interest in AI to the extent that some Journals have introduced a dedicated section on the topic, such as The New England Journal of Medicine 86. As with any innovation, doubts and perplexities have arisen regarding the integration of AI in the medical and mental health fields 87,88.

The safety and reliability of each algorithm is the first aspect to be assessed. This parameter is evaluated using the technology readiness level (TRL) scale, a 9-level assessment invented by the National Aeronautics and Space Administration (NASA) in the 1970s 89. To date, no AI method has passed all the levels, making them suitable only for experimental and academic fields, not for use in clinical practice 90.

The reliability of an AI algorithm is largely dependent on the quality of the data used to develop it 91. If databases not specifically created for this purpose are used, there may be errors, shortcomings or simplifications that reduce the accuracy of the AI. In order to compensate for the considerable amount of data required, existing datasets are often used. It is also important to ensure that the data collected from recruited subjects is comparable to the pool on which the AI will be used clinically, a process commonly known as “database shift”. The data must be numerous, heterogeneous but also specific. Therefore, data collection is typically carried out using instrumental methods that provide a significant amount of information even with small recruitment samples. Conversely, if instrumental methods are not available, large samples of subjects are necessary.

This review shows that current research is primarily focused on discovering new methods for diagnosing disorders and linking neurobiological changes with psychopathological dimensions. Currently, in the absence of pathognomonic biological markers, psychiatric disorders are diagnosed using arbitrary criteria, which can be inherently subjective, so it is important to exclude subjective assessments unless clearly defined. New classification systems are emerging to be more objective by making diagnoses based on biological correlates. An example of this is the Research Domain Criteria (RDoC) system created in 2009 by the National Institute of Mental Health (NIMH) 92. A more objective diagnosis is required, not only due to new classification systems, but also the need for new technological aids to support it. These aids are often unfamiliar to clinicians, which can lead to a sense of distrust 88.

DL is an algorithm that is playing an increasingly important role and has gained considerable interest in recent years because it allows large amounts of data from instrumental methods to be analysed without the need for pre-processing 35, enabling increasingly complex and articulated functions to be performed. The availability of powerful chips at affordable prices can also drive this shift towards more sophisticated and effective algorithms.

However, the use of AI in the clinical field still presents issues beyond the development of efficient and reliable algorithms. These include the attribution of responsibility and the possibility of hacking. Currently, there is a lack of adequate legislation, and in the event of an AI error, it is uncertain who should be held responsible: the psychiatrist who validated the result, the patient who accepted it, the developers of the algorithm, the health system that implemented it, or no one at all. In addition, by collecting sensitive data and tracking daily activities, the studies face the risk of hacking, which threatens the privacy of the subjects.

AI could be a valuable tool for clinicians to implement new classification systems based on objective biological data. However, this is not yet possible due to the need for increasingly efficient, safe, and cost-effective algorithms, dedicated databases, impenetrable security systems, and training for clinicians in the use and interpretation of results. Additionally, an information campaign directed at the general population and the development of ethical and legislative issues are necessary.

To our knowledge, this is the first literature review that attempts to analyse multiple types of AI in mental health, regardless of method and data source. In addition, subcategories were created to achieve better categorisation when analysing all variables. Although several encouraging findings were observed, this review has some limitations. At a methodological level, this is a qualitative analysis of the current literature, and it would be desirable to carry out a systematic review in order to obtain objective data. In addition, this review only includes the most well-known methods, such as ML, DL and NLP, while more unusual and less well-known algorithms have been excluded due to the lack of sufficient literature for an objective and scientifically accepted categorisation.

CONCLUSIONS

In conclusion, currently there are no algorithms that can be implemented in clinical practice for all the aforementioned problems. However, the number of studies on this topic is increasing, indicating a growing interest in the field of applying AI in mental health. This study is just the beginning. The first step is to conduct one or more systematic reviews on the subject to determine the most useful algorithm and method for clinical practice, and to identify variables to create open-access databases that can be used to train future algorithms.

Conflict of interest statement

The authors declare no conflict of interest.

Funding

The authors declare that they have received compensation from third parties for the creation of this article.

Authors’ contributions

A.Z.: conceptualization, data curation, investigation, methodology, writing – original draft, writing – review & editing. G.N.: data curation, investigation, methodology, writing – review & editing. L.A.: data curation, investigation, methodology. L.B.: data curation, investigation, methodology. I.C.-P.: Data curation, investigation, methodology. E.I.: data curation, investigation, methodology. N.N.: data curation, investigation, methodology. C.C.: data curation, investigation, methodology. L.P.: data curation, investigation, methodology. V.B.: data curation, investigation, methodology. J.L.: data curation, investigation, methodology. G.D.: data curation, investigation, methodology. S.B.: methodology, supervision, writing – review & editing. A.V.: methodology, supervision, writing – review & editing.

Ethical consideration

Not applicable to this study design.

Figures and tables

Type of algorithm Psychiatric disorder Outcome Instrumental techniques
Natural language processing Schizophrenia spectrum disorders Neurobiological correlates Neurobiological measurements
Machine learning Bipolar Disorder Identification of brain areas and circuits Neuroimaging (eg., MRI)
Deep learning Major depression disorder Brain age Neurophysiology (eg., EEG)
Obsessive compulsive disorder Clinical characterisation Audio/video recordings
Anxiety disorders Psychopathological aspects Biological samples
Personality disorders Physical comorbidities Genetic analysis
Self-harming dimension Other analysis
Hetero-aggressive behaviour dimension Other
Use of Services Somatic and physiological measurements
Perception of quality of life Motion sensors
Diagnostics APP on mobile devices
Prognosis Other techniques
Prognosis in patients
Response and adherence to therapy
Prediction transition
EEG: electroencephalography; MRI: magnetic resonance imaging.
TABLE I. Artificial Intelligence applications in mental health.

References

Lasi H, Fettke P, Kemper H. Industry 4.0. <i>Bus Inf Syst Eng</i>. 2014;6:239-242. doi:https://doi.org/10.1007/s12599-014-0334-4
Hodson R. Digital revolution. <i>Nature</i>. 2018;563. doi:https://doi.org/10.1038/d41586-018-07500-z
Hantrais L, Allin P, Kritikos M. Covid-19 and the digital revolution. <i>Contemp Soc Sci</i>. 2021;16:256-270. doi:https://doi.org/10.1080/21582041.2020.1833234
Bucci S, Schwannauer M, Berry N. The digital revolution and its impact on mental health care. <i>Psychol Psychother Theory Res Pract</i>. 2019;92:277-297. doi:https://doi.org/10.1111/papt.12222
Brem A, Giones F, Werle M. The AI Digital Revolution in Innovation: A Conceptual Framework of Artificial Intelligence Technologies for the Management of Innovation. <i>IEEE Trans Eng Manag</i>. 2023;70:770-776. doi:https://doi.org/10.1109/TEM.2021.3109983
Turing A. I.—Computing Machinery And Intelligence. <i>Mind</i>. 1950;LIX:433-460. doi:https://doi.org/10.1093/mind/LIX.236.433
McCarthy J. <i>Philosophical Logic and Artificial Intelligence</i>. (Thomason R, ed.). Springer Netherlands; 1989. doi:https://doi.org/10.1007/978-94-009-2448-2_6
Wikipedia; 2021.
IBM Watson.
Wikipedia; 2023.
ChatGPT.
Wikipedia; 2023.
Simmons A, Chappell S. Artificial intelligence-definition and practice. <i>IEEE J Ocean Eng</i>. 1988;13:14-42. doi:https://doi.org/10.1109/48.551
Russell S, Norvig P, Davis E. Prentice Hall; 2010.
Manning C, Schütze H. MIT Press; 1999.
Schank R. Conceptual dependency: A theory of natural language understanding. <i>Cognit Psychol</i>. 1972;3:552-631. doi:https://doi.org/10.1016/0010-0285(72)90022-9
Paris C, Swartout W, Mann W, eds. Springer US; 1991. doi:https://doi.org/10.1007/978-1-4757-5945-7
Genest P, Lapalme G. <i>Proceedings of the Workshop on Monolingual Text-To-Text Generation</i>. Association for Computational Linguistics; 2011.
Xu T, Zhang P, Huang Q. AttnGAN: Fine-Grained Text to Image Generation with Attentional Generative Adversarial Networks. <i>Published online</i>. Published online 2017. doi:https://doi.org/10.48550/ARXIV.1711.10485
Rohrbach M, Qiu W, Titov I, Thater S, Pinkal M, Schiele B. Translating Video Content to Natural Language Descriptions. <i>2013 IEEE International Conference on Computer Vision</i>. Published online 2013:433-440. doi:https://doi.org/10.1109/ICCV.2013.61
Kang Y, Cai Z, Tan C, Huang Q, Liu H. Natural language processing (NLP) in management research: A literature review. <i>J Manag Anal</i>. 2020;7:139-172. doi:https://doi.org/10.1080/23270012.2020.1756939
Lu Y. Artificial intelligence: a survey on evolution, models, applications and future trends. <i>J Manag Anal</i>. 2019;6:1-29. doi:https://doi.org/10.1080/23270012.2019.1570365
Och F. Minimum error rate training in statistical machine translation. <i>Proceedings of the 41st Annual Meeting on Association for Computational Linguistics - ACL ’03</i>. 2003;1:160-167. doi:https://doi.org/10.3115/1075096.1075117
Califf M, Mooney R. Computational Natural Language Learning; 1997.
Liu B. Springer International Publishing; 2012. doi:https://doi.org/10.1007/978-3-031-02145-9
Weber D. Object interactive user interface using speech recognition and natural language processing. <i>J Acoust Soc Am</i>. 2003;114. doi:https://doi.org/10.1121/1.1601094
Jordan M, Mitchell T. Machine learning: Trends, perspectives, and prospects. <i>Science</i>. 2015;349:255-260. doi:https://doi.org/10.1126/science.aaa8415
D’Acquisto G. G. Giappichelli Editore; 2021.
Bzdok D, Krzywinski M, Altman N. Machine learning: supervised methods. <i>Nat Methods</i>. 2018;15:5-6. doi:https://doi.org/10.1038/nmeth.4551
Nasteski V. An overview of the supervised machine learning methods. <i>HORIZONSB</i>. 2017;4:51-62. doi:https://doi.org/10.20544/HORIZONS.B.04.1.17.P05
Gottesman O, Johansson F, Komorowski M. Guidelines for reinforcement learning in healthcare. <i>Nat Med</i>. 2019;25:16-18. doi:https://doi.org/10.1038/s41591-018-0310-5
Yao J, Mao Q, Goodison S. Feature selection for unsupervised learning through local learning. <i>Pattern Recognit Lett</i>. 2015;53:100-107. doi:https://doi.org/10.1016/j.patrec.2014.11.006
Ding S, Zhu Z, Zhang X. An overview on semi-supervised support vector machine. <i>Neural Comput Appl</i>. 2017;28:969-978. doi:https://doi.org/10.1007/s00521-015-2113-7
LeCun Y, Bengio Y, Hinton G. Deep learning. <i>Nature</i>. 2015;521:436-444. doi:https://doi.org/10.1038/nature14539
Cortes-Briones J, Tapia-Rivas N, D’Souza D. Going deep into schizophrenia with artificial intelligence. <i>Schizophr Res</i>. 2022;245:122-140. doi:https://doi.org/10.1016/j.schRes2021.05.018
Le Glaz A, Haralambous Y, Kim-Dufor D. Machine Learning and Natural Language Processing in Mental Health: Systematic Review. <i>J Med Internet Res</i>. 2021;23. doi:https://doi.org/10.2196/15708
Sajjadian M, Lam R, Milev R. Machine learning in the prediction of depression treatment outcomes: a systematic review and meta-analysis. <i>Psychol Med</i>. 2021;51:2742-2751. doi:https://doi.org/10.1017/S0033291721003871
Graham S, Depp C, Lee E. Artificial Intelligence for Mental Health and Mental Illnesses: an Overview. <i>Curr Psychiatry Rep</i>. 2019;21. doi:https://doi.org/10.1007/s11920-019-1094-0
Su C, Xu Z, Pathak J. Deep learning in mental health outcome research: a scoping review. <i>Transl Psychiatry</i>. 2020;10. doi:https://doi.org/10.1038/s41398-020-0780-3
Zhang Z, Li G, Xu Y. Application of Artificial Intelligence in the MRI Classification Task of Human Brain Neurological and Psychiatric Diseases: A Scoping Review. <i>Diagnostics</i>. 2021;11. doi:https://doi.org/10.3390/diagnostics11081402
Liu Y, Pu C, Xia S. Machine learning approaches for diagnosing depression using EEG: A review. <i>Transl Neurosci</i>. 2022;13:224-235. doi:https://doi.org/10.1515/tnsci-2022-0234
Abd-alrazaq A, AlSaad R, Aziz S. Wearable Artificial Intelligence for Anxiety and Depression: Scoping Review. <i>J Med Internet Res</i>. 2023;25. doi:https://doi.org/10.2196/42672
Sadeghi D, Shoeibi A, Ghassemi N. An overview of artificial intelligence techniques for diagnosis of Schizophrenia based on magnetic resonance imaging modalities: Methods, challenges, and future works. <i>Comput Biol Med</i>. 2022;146. doi:https://doi.org/10.1016/j.compbioMed2022.105554
Bashyam V, Erus G, Doshi J. MRI signatures of brain age and disease over the lifespan based on a deep brain network and 14 468 individuals worldwide. <i>Brain</i>. 2020;143:2312-2324. doi:https://doi.org/10.1093/brain/awaa160
Sui J, Qi S, Van Erp T. Multimodal neuromarkers in schizophrenia via cognition-guided MRI fusion. <i>Nat Commun</i>. 2018;9. doi:https://doi.org/10.1038/s41467-018-05432-w
Provenza N, Sheth S, Dastin-van Rijn E. Long-term ecological assessment of intracranial electrophysiology synchronized to behavioral markers in obsessive-compulsive disorder. <i>Nat Med</i>. 2021;27:2154-2164. doi:https://doi.org/10.1038/s41591-021-01550-z
Chung Y, Addington J, Bearden C. Use of Machine Learning to Determine Deviance in Neuroanatomical Maturity Associated With Future Psychosis in Youths at Clinically High Risk. <i>JAMA Psychiatry</i>. 2018;75:960-968. doi:https://doi.org/10.1001/jamapsychiatry.2018.1543
McWhinney S, Kolenic M, Franke K. Obesity as a Risk Factor for Accelerated Brain Ageing in First-Episode Psychosis – A Longitudinal Study. <i>Schizophr Bull</i>. 2021;47:1772-1781. doi:https://doi.org/10.1093/schbul/sbab064
Chen J, Patil K, Weis S. Neurobiological Divergence of the Positive and Negative Schizophrenia Subtypes Identified on a New Factor Structure of Psychopathology Using Non-negative Factorization: An International Machine Learning Study. <i>Biol Psychiatry</i>. 2020;87:282-293. doi:https://doi.org/10.1016/j.biopsych.2019.08.031
Shamsutdinova D, Das-Munshi J, Ashworth M. Predicting type 2 diabetes prevalence for people with severe mental illness in a multi-ethnic East London population. <i>Int J Med Inf</i>. 2023;172. doi:https://doi.org/10.1016/j.ijmedinf.2023.105019
Edgcomb J, Shaddox T, Hellemann G. Predicting suicidal behavior and self-harm after general hospitalization of adults with serious mental illness. <i>J Psychiatr Res</i>. 2021;136:515-521. doi:https://doi.org/10.1016/j.jpsychiRes2020.10.024
Gou N, Xiang Y, Zhou J. Identification of violent patients with schizophrenia using a hybrid machine learning approach at the individual level. <i>Psychiatry Res</i>. 2021;306. doi:https://doi.org/10.1016/j.psychRes2021.114294
Kwakernaak S, Van Mens K, Cahn W. Using machine learning to predict mental healthcare consumption in non-affective psychosis. <i>Schizophr Res</i>. 2020;218:166-172. doi:https://doi.org/10.1016/j.schRes2020.01.008
Cowan T, Rodriguez Z, Granrud O. Talking about Health: A Topic Analysis of Narratives from Individuals with Schizophrenia and Other Serious Mental Illnesses. <i>Behav Sci</i>. 2022;12. doi:https://doi.org/10.3390/bs12080286
Palacios-Ariza M, Morales-Mendoza E, Murcia J. Prediction of patient admission and readmission in adults from a Colombian cohort with bipolar disorder using artificial intelligence. <i>Front Psychiatry</i>. 2023;14. doi:https://doi.org/10.3389/fpsyt.2023.1266548
Wang T, Bezerianos A, Cichocki A. Multikernel Capsule Network for Schizophrenia Identification. <i>IEEE Trans Cybern</i>. 2022;52:4741-4750. doi:https://doi.org/10.1109/TCYB.2020.3035282
Sánchez-Morla E, Fuentes J, Miguel-Jiménez J. Automatic Diagnosis of Bipolar Disorder Using Optical Coherence Tomography Data and Artificial Intelligence. <i>J Pers Med</i>. 2021;11. doi:https://doi.org/10.3390/jpm11080803
Yoshihara Y, Lisi G, Yahata N. Overlapping but Asymmetrical Relationships Between Schizophrenia and Autism Revealed by Brain Connectivity. <i>Schizophr Bull</i>. 2020;46:1210-1218. doi:https://doi.org/10.1093/schbul/sbaa021
Li Z, Li W, Wei Y. Deep learning based automatic diagnosis of first-episode psychosis, bipolar disorder and healthy controls. <i>Comput Med Imaging Graph</i>. 2021;89. doi:https://doi.org/10.1016/j.compmedimag.2021.101882
Han K, De Berardis D, Fornaro M. Differentiating between bipolar and unipolar depression in functional and structural MRI studies. <i>Prog Neuropsychopharmacol Biol Psychiatry</i>. 2019;91:20-27. doi:https://doi.org/10.1016/j.pnpbp.2018.03.022
Bayes A, Spoelma M, Parker G. Comorbid bipolar disorder and borderline personality disorder: Diagnosis using machine learning. <i>J Psychiatr Res</i>. 2022;152:1-6. doi:https://doi.org/10.1016/j.jpsychiRes2022.05.032
Garriga R, Mas J, Abraha S. Machine learning model to predict mental health crises from electronic health records. <i>Nat Med</i>. 2022;28:1240-1248. doi:https://doi.org/10.1038/s41591-022-01811-5
Wu C, Luedtke A, Sadikova E. Development and Validation of a Machine Learning Individualized Treatment Rule in First-Episode Schizophrenia. <i>JAMA Netw Open</i>. 2020;3. doi:https://doi.org/10.1001/jamanetworkopen.2019.21660
Góngora AS, Herrera MI, Ayala J. Machine Learning Models to Predict Readmission Risk of Patients with Schizophrenia in a Spanish Region. <i>Int J Ment Health Addict</i>. doi:https://doi.org/10.1007/s11469-022-01001-x
Gao S, Calhoun V, Sui J. Machine learning in major depression: From classification to treatment outcome prediction. <i>CNS Neurosci Ther</i>. 2018;24:1037-1052. doi:https://doi.org/10.1111/cns.13048
Salomoni G, Grassi M, Mosini P. Artificial Neural Network Model for the Prediction of Obsessive-Compulsive Disorder Treatment Response. <i>J Clin Psychopharmacol</i>. 2009;29:343-349. doi:https://doi.org/10.1097/JCP.0b013e3181aba68f
Corcoran C, Carrillo F, Fernández-Slezak D. Prediction of psychosis across protocols and risk cohorts using automated language analysis. <i>World Psychiatry</i>. 2018;17:67-75. doi:https://doi.org/10.1002/wps.20491
Worthington M, Addington J, Bearden C. Individualized Prediction of Prodromal Symptom Remission for Youth at Clinical High Risk for Psychosis. <i>Schizophr Bull</i>. 2022;48:395-404. doi:https://doi.org/10.1093/schbul/sbab115
Ucuz I, Ari A, Ozcan O. Estimation of the Development of Depression and PTSD in Children Exposed to Sexual Abuse and Development of Decision Support Systems by Using Artificial Intelligence. <i>J Child Sex Abuse</i>. 2022;31:73-85. doi:https://doi.org/10.1080/10538712.2020.1841350
Li H, Srinivasan D, Zhuo C. Computing personalized brain functional networks from fMRI using self-supervised deep learning. <i>Med Image Anal</i>. 2023;85. doi:https://doi.org/10.1016/j.media.2023.102756
Huang F, Yang X, Luo J. Functional and structural MRI based obsessive-compulsive disorder diagnosis using machine learning methods. <i>BMC Psychiatry</i>. 2023;23. doi:https://doi.org/10.1186/s12888-023-05299-2
Phalen H, Coffman B, Ghuman A. Non-negative Matrix Factorization Reveals Resting-State Cortical Alpha Network Abnormalities in the First-Episode Schizophrenia Spectrum. <i>Biol Psychiatry Cogn Neurosci Neuroimaging</i>. 2020;5:961-970. doi:https://doi.org/10.1016/j.bpsc.2019.06.010
Josin G, Liddle P. Neural network analysis of the pattern of functional connectivity between cerebral areas in schizophrenia. <i>Biol Cybern</i>. 2001;84:117-122. doi:https://doi.org/10.1007/s004220000197
Lillo E, Mora M, Lucero B. Automated diagnosis of schizophrenia using EEG microstates and Deep Convolutional Neural Network. <i>Expert Syst Appl</i>. 2022;209. doi:https://doi.org/10.1016/j.eswa.2022.118236
Voppel A, De Boer J, Brederoo S. Semantic and Acoustic Markers in Schizophrenia-Spectrum Disorders: A Combinatory Machine Learning Approach. <i>Schizophr Bull</i>. 2023;49:163-171. doi:https://doi.org/10.1093/schbul/sbac142
Huang J, Zhao Y, Qu W. Automatic recognition of schizophrenia from facial videos using 3D convolutional neural network. <i>Asian J Psychiatry</i>. 2022;77. doi:https://doi.org/10.1016/j.ajp.2022.103263
Susai S, Mongan D, Healy C. Machine learning based prediction and the influence of complement – Coagulation pathway proteins on clinical outcome: Results from the NEURAPRO trial. <i>Brain Behav Immun</i>. 2022;103:50-60. doi:https://doi.org/10.1016/j.bbi.2022.03.013
Chen S, Chen G, Li Y. Predicting the diagnosis of various mental disorders in a mixed cohort using blood-based multi-protein model: a machine learning approach. <i>Eur Arch Psychiatry Clin Neurosci</i>. 2023;273:1267-1277. doi:https://doi.org/10.1007/s00406-022-01540-3
Sivakumar J, Ahmed S, Begdache L. Prediction of Mental Illness in Heart Disease Patients: Association of Comorbidities, Dietary Supplements, and Antibiotics as Risk Factors. <i>J Pers Med</i>. 2020;10. doi:https://doi.org/10.3390/jpm10040214
Price G, Heinz M, Zhao D. An unsupervised machine learning approach using passive movement data to understand depression and schizophrenia. <i>J Affect Disord</i>. 2022;316:132-139. doi:https://doi.org/10.1016/j.jad.2022.08.013
Bain E, Shafner L, Walling D. Use of a Novel Artificial Intelligence Platform on Mobile Devices to Assess Dosing Compliance in a Phase 2 Clinical Trial in Subjects With Schizophrenia. <i>JMIR MHealth UHealth</i>. 2017;5. doi:https://doi.org/10.2196/mhealth.7030
Lefort-Besnard J, Varoquaux G, Derntl B. Patterns of schizophrenia symptoms: hidden structure in the PANSS questionnaire. <i>Transl Psychiatry</i>. 2018;8. doi:https://doi.org/10.1038/s41398-018-0294-4
Lee D, Kim C, Lee S. Psychosis Relapse Prediction Leveraging Electronic Health Records Data and Natural Language Processing Enrichment Methods. <i>Front Psychiatry</i>. 2022;13. doi:https://doi.org/10.3389/fpsyt.2022.844442
Allesøe R, Thompson W, Bybjerg-Grauholm J. Deep Learning for Cross-Diagnostic Prediction of Mental Disorder Diagnosis and Prognosis Using Danish Nationwide Register and Genetic Data. <i>JAMA Psychiatry</i>. 2023;80. doi:https://doi.org/10.1001/jamapsychiatry.2022.4076
Lin Q, Niu Y, Sui J. SSPNet: An interpretable 3D-CNN for classification of schizophrenia using phase maps of resting-state complex-valued fMRI data. <i>Med Image Anal</i>. 2022;79. doi:https://doi.org/10.1016/j.media.2022.102430
Beam A, Drazen J, Kohane I. Artificial Intelligence in Medicine. <i>N Engl J Med</i>. 2023;388:1220-1221. doi:https://doi.org/10.1056/NEJMe2206291
Rocheteau E. On the role of artificial intelligence in psychiatry. <i>Br J Psychiatry</i>. 2023;222:54-57. doi:https://doi.org/10.1192/bjp.2022.132
Monteith S, Glenn T, Geddes J. Expectations for Artificial Intelligence (AI) in Psychiatry. <i>Curr Psychiatry Rep</i>. 2022;24:709-721. doi:https://doi.org/10.1007/s11920-022-01378-5
Lavin A, Gilligan-Lee C, Visnjic A. Technology readiness levels for machine learning systems. <i>Nat Commun</i>. 2022;13. doi:https://doi.org/10.1038/s41467-022-33128-9
Mankins J. TECHNOLOGY READINESS LEVELS.
Matheny M, Israni S, Ahmed M, Whicher D, eds. The National Academies Press; 2019. doi:https://doi.org/10.17226/27111
Cuthbert B, Insel T. Toward the future of psychiatric diagnosis: the seven pillars of RDoC. <i>BMC Med</i>. 2013;11. doi:https://doi.org/10.1186/1741-7015-11-126

Downloads

Authors

Andrea Zucchetti - Department of Mental Health and Addiction Services, ASST Spedali Civili of Brescia, Brescia, Italy; Department of Clinical and Experimental Sciences, University of Brescia, Brescia, Italy

Gabriele Nibbio - Department of Clinical and Experimental Sciences, University of Brescia, Brescia, Ital

Luca Altieri - Department of Clinical and Experimental Sciences, University of Brescia, Brescia, Ital

Lorenzo Bertorni - Department of Clinical and Experimental Sciences, University of Brescia, Brescia, Ital

Irene Calzavara-Pinton - Department of Mental Health and Addiction Services, ASST Spedali Civili of Brescia, Brescia, Italy;  Department of Molecular and Translational Medicine, University of Brescia, Brescia, Italy

Elena Invernizzi - Department of Clinical and Experimental Sciences, University of Brescia, Brescia, Italy

Nicola Necchini - Department of Clinical and Experimental Sciences, University of Brescia, Brescia, Italy

Caterina Cerati - Department of Clinical and Experimental Sciences, University of Brescia, Brescia, Italy

Laura Poddighe - Department of Mental Health and Addiction Services, ASST Spedali Civili of Brescia, Brescia, Italy

Viola Bulgari - Department of Clinical and Experimental Sciences, University of Brescia, Brescia, Italy

Jacopo Lisoni - Department of Mental Health and Addiction Services, ASST Spedali Civili of Brescia, Brescia, Italy

Giacomo Deste - Department of Clinical and Experimental Sciences, University of Brescia, Brescia, Italy; Psychiatric Unit, ASST Valcamonica, Italy

Stefano Barlati - Department of Mental Health and Addiction Services, ASST Spedali Civili of Brescia, Brescia, Italy; Department of Clinical and Experimental Sciences, University of Brescia, Brescia, Italy

Antonio Vita - Department of Mental Health and Addiction Services, ASST Spedali Civili of Brescia, Brescia, Italy; Department of Clinical and Experimental Sciences, University of Brescia, Brescia, Ita

How to Cite
Zucchetti, A., Nibbio, G., Altieri, L., Bertorni, L., Calzavara-Pinton, I. ., Invernizzi, E. ., Necchini, N., Cerati, C., Poddighe, L., Bulgari, V., Lisoni, J., Deste, G., Barlati, S., & Vita, A. (2024). Artificial intelligence applications in mental health: the state of the art. Italian Journal of Psychiatry, 10(1). https://doi.org/10.36180/2421-4469-2024-5
  • Abstract viewed - 104 times
  • PDF downloaded - 36 times