Zusammenfassung
Die künstliche Intelligenz (KI) und die zugrunde liegenden Methoden des maschinellen Lernens und der neuronalen Netzwerke haben in den letzten Jahren dramatische Fortschritte gemacht und Leistungen in Domänen erreicht, die bis vor kurzem als spezifisch menschlich und für Computer nicht zugänglich galten. In diesem Überblick werden die diesen Fortschritten zugrunde liegenden methodischen Entwicklungen kurz dargestellt und in der Folge aktuelle und potenzielle Anwendungen auf die Psychiatrie in drei Bereichen diskutiert: Präzisionsmedizin und Biomarker, Verarbeitung natürlicher Sprache und KI-basierte psychotherapeutische Interventionen. Abschließend wird auf einige Risken dieser neuen Technologie hingewiesen.
Abstract
Artificial intelligence and the underlying methods of machine learning and neuronal networks (NN) have made dramatic progress in recent years and have allowed computers to reach superhuman performance in domains that used to be thought of as uniquely human. In this overview, the underlying methodological developments that made this possible are briefly delineated and then the applications to psychiatry in three domains are discussed: precision medicine and biomarkers, natural language processing and artificial intelligence-based psychotherapeutic interventions. In conclusion, some of the risks of this new technology are mentioned.
Literatur
Banerjee D, Islam K, Mei G et al (2017) A deep transfer learning approach for improved post-traumatic stress disorder diagnosis. In: Data Mining (ICDM) 2017 IEEE International Conference on. IEEE, S 11–20
Bzdok D, Meyer-Lindenberg A (2018) Machine learning for precision psychiatry: opportunities and challenges. Biol Psychiatry Cogn Neurosci Neuroimaging 3:223–230
Cao B, Zheng L, Zhang C et al (2017) Deepmood: modeling mobile phone typing dynamics for mood detection. In: Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining ACM, S 747–755
Choi H, Ha S, Im HJ et al (2017) Refining diagnosis of Parkinson’s disease with deep learning-based interpretation of dopamine transporter imaging. Neuroimage Clin 16:586–594
Cybenko G (1989) Approximation by superpositions of a sigmoidal function. Math Control Signals Syst 2:303–314
Dai D, Wang J, Hua J et al (2012) Classification of ADHD children through multimodal magnetic resonance imaging. Front Syst Neurosci 6:63
Ebner-Priemer UW, Trull TJ (2009) Ecological momentary assessment of mood disorders and mood dysregulation. Psychol Assess 21:463–475
Fodor JA, Pylyshyn ZW (1988) Connectionism and cognitive architecture: a critical analysis. Cognition 28:3–71
Frangou S, Schwarz E, Meyer-Lindenberg A et al (2016) Identifying multimodal signatures associated with symptom clusters: the example of the IMAGEMEND project. World Psychiatry 15:179–180
Frey CB, Osborne MA (2017) The future of employment: how susceptible are jobs to computerisation? Technol Forecast Soc Change 114:254–280
Heinsfeld AS (2017) Identification of autism disorder through functional MRI and deep learning. In: Pontifícia Universidade Católica do Rio Grande do Sul
Hexmoor H, Mclaughlan B, Tuli G (2009) Natural human role in supervising complex control systems. J Exp Theor Artif Intell 21:59–77
Hinton GE, Osindero S, Teh Y‑W (2006) A fast learning algorithm for deep belief nets. Neural Comput 18:1527–1554
Insel T, Cuthbert B, Garvey M et al (2010) Research domain criteria (RDoC): toward a new classification framework for research on mental disorders. Am J Psychiatry 167:748–751
Insel TR, Scolnick EM (2006) Cure therapeutics and strategic prevention: raising the bar for mental health research. Mol Psychiatry 11:11–17
Kim J, Calhoun VD, Shim E et al (2016) Deep neural network with weight sparsity control and pre-training extracts hierarchical features and enhances classification performance: Evidence from whole-brain resting-state functional connectivity patterns of schizophrenia. Neuroimage 124:127–146
Kuang D, Guo X, An X et al (2014) Discrimination of ADHD based on fMRI data with deep belief network. In: International Conference on Intelligent Computing. Springer, Berlin Heidelberg, S 225–232
Lecun Y, Bengio Y, Hinton G (2015) Deep learning. Nature 521:436–444
Li H, Habes M, Fan Y (2017) Deep ordinal ranking for multi-category diagnosis of alzheimer’s disease using hippocampal MRI data. arXiv preprint arXiv:1709.01599
Mcculloch WS, Pitts W (1943) A logical calculus of the ideas immanent in nervous activity. Bull Math Biophys 5:115–133
Mehrotra A, Hendley R, Musolesi M (2016) Towards multi-modal anticipatory monitoring of depressive states through the analysis of human-smartphone interaction. In: Proceedings of the 2016 ACM International Joint Conference on Pervasive and Ubiquitous Computing: Adjunct ACM, S 1132–1138
Miller GA (2003) The cognitive revolution: a historical perspective. Trends Cogn Sci 7:141–144
Minsky M, Papert S (1969) Perceptrons: Anlntroduction to computational geometry. MIT Press, Cambridge
Mnih V, Kavukcuoglu K, Silver D et al (2015) Human-level control through deep reinforcement learning. Nature 518:529–533
Myin-Germeys I, Klippel A, Steinhart H et al (2016) Ecological momentary interventions in psychiatry. Curr Opin Psychiatry 29:258–263
Newell A, Simon HA (1972) Human problem solving. Prentice-Hall, Englewood Cliffs
Rosenblatt F (1958) The perceptron: a probabilistic model for information storage and organization in the brain. Psychol Rev 65:386
Rosenstein M, Foltz PW, Delisi LE et al (2015) Language as a biomarker in those at high-risk for psychosis. Schizophr Res 165:249–250
Rumelhart DE, Hinton GE, Williams RJ (1986) Learning representations by back-propagating errors. Nature 323:533
Schmidhuber J (2015) Deep learning in neural networks: an overview. Neural Netw 61:85–117
Shickel B, Heesacker M, Benton S et al (2017) Hashtag Healthcare: from tweets to mental health journals using deep transfer learning. arXiv preprint arXiv:1708.01372
Silver D, Schrittwieser J, Simonyan K et al (2017) Mastering the game of go without human knowledge. Nature 550:354
Thayer JF, Ahs F, Fredrikson M et al (2012) A meta-analysis of heart rate variability and neuroimaging studies: implications for heart rate variability as a marker of stress and health. Neurosci Biobehav Rev 36:747–756
Tran T, Kavuluru R (2017) Predicting mental conditions based on “history of present illness” in psychiatric notes with deep neural networks. J Biomed Inform 75:S138–S148
Turing AM (1948) Intelligent machinery, a heretical theory. The Turing test: Verbal behavior as the hallmark of intelligence 105
Vieira S, Pinaya WH, Mechelli A (2017) Using deep learning to investigate the neuroimaging correlates of psychiatric and neurological disorders: Methods and applications. Neurosci Biobehav Rev 74(Pt A):58. https://doi.org/10.1016/j.neubiorev.2017.01.002
Wang SH, Lv YD, Sui Y et al (2017) Alcoholism detection by data augmentation and convolutional neural network with stochastic pooling. J Med Syst 42:2
Wang Y, Kosinski M (2018) Deep neural networks are more accurate than humans at detecting sexual orientation from facial images. J Pers Soc Psychol 114:246
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Interessenkonflikt
A. Meyer-Lindenberg gibt an, dass kein Interessenkonflikt besteht.
Dieser Beitrag beinhaltet keine von den Autoren durchgeführten Studien an Menschen oder Tieren.
Rights and permissions
About this article
Cite this article
Meyer-Lindenberg, A. Künstliche Intelligenz in der Psychiatrie – ein Überblick. Nervenarzt 89, 861–868 (2018). https://doi.org/10.1007/s00115-018-0557-6
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00115-018-0557-6