Modern views of machine learning for precision psychiatry
Open accessThe DOI matches its Crossref record; 95 of the 95 references it cites were found in a registry or an index.
Abstract
In light of the National Institute of Mental Health (NIMH)'s Research Domain Criteria (RDoC), the advent of functional neuroimaging, novel technologies and methods provide new opportunities to develop precise and personalized prognosis and diagnosis of mental disorders. Machine learning (ML) and artificial intelligence (AI) technologies are playing an increasingly critical role in the new era of precision psychiatry. Combining ML/AI with neuromodulation technologies can potentially provide explainable solutions in clinical practice and effective therapeutic treatment. Advanced wearable and mobile technologies also call for the new role of ML/AI for digital phenotyping in mobile mental health. In this review, we provide a comprehensive review of ML methodologies and applications by combining neuroimaging, neuromodulation, and advanced mobile technologies in psychiatry practice. We further review the role of ML in molecular phenotyping and cross-species biomarker identification in precision psychiatry. We also discuss explainable AI (XAI) and neuromodulation in a closed human-in-the-loop manner and highlight the ML potential in multi-media information extraction and multi-modal data fusion. Finally, we discuss conceptual and practical challenges in precision psychiatry and highlight ML opportunities in future research.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Integrated analysis of multimodal single-cell data
Hao, Y., Hao, S., Andersen-Nissen, E., Mauck, W. M., Zheng, S., Butler, A., Lee, M. J., Wilk, A. J., Darby, C., Zagar, M., et al. (2020) · doi:10.1101/2020.10.12.335331 · Cited by 15,508
Kessler, R. C., Chiu, W. T., Demler, O., & Walters, E. E. (2005) · Archives of General Psychiatry · doi:10.1001/archpsyc.62.6.617 · Cited by 12,052
Insel, T., Cuthbert, B., Garvey, M., Heinssen, R., Pine, D. S., Quinn, K., Sanislow, C., & Wang, P. (2010) · American Journal of Psychiatry · doi:10.1176/appi.ajp.2010.09091379 · Cited by 7,067 · cited 1×
“2 Patterns 3, November 11, 2022 of dysfunction in psychological or neurobiological systems; it attempts to bridge the power of multi-disciplinary (such as the genetics, neuroscience, and behavioral science) research approaches.(6,7) The current gold standard for diagnosis and treatment outcome in mental disorders—the…”
BackgroundConvolutional neural networks: an overview and application in radiology
Yamashita, R., Nishio, M., Do, R. K. G., & Togashi, K. (2018) · Insights into Imaging · doi:10.1007/s13244-018-0639-9 · Cited by 4,682 · cited 1×
“Due to its strength in utilizing neighborhood information to learn hierarchies of features [142], CNN has been one of the most successful deep learning models applied in various medical applications.”
BackgroundFriston, K. J., Harrison, L., & Penny, W. (2003) · NeuroImage · doi:10.1016/s1053-8119(03)00202-7 · Cited by 4,583
Rajpurkar, P., Chen, E., Banerjee, O., & Topol, E. J. (2022) · Nature Medicine · doi:10.1038/s41591-021-01614-0 · Cited by 3,212 · cited 1×
“From a user experience point of view, it is important to consider both the mental health professionals using the application [370] as well as their patients [371].”
BackgroundFunctional connectome fingerprinting: Identifying individuals using patterns of brain connectivity
Finn, E. S., Shen, X., Scheinost, D., Rosenberg, M. D., Huang, J., Chun, M. M., Papademetris, X., & Constable, R. T. (2015) · Nature Neuroscience · doi:10.1038/nn.4135 · Cited by 2,747
Czeisler, M. É., Lane, R. I., Petrosky, E., Wiley, J. F., Christensen, A., Njai, R., Weaver, M. D., Robbins, R., Facer-Childs, E. R., Barger, L. K., et al. (2020) · MMWR. Morbidity and Mortality Weekly Report · doi:10.15585/mmwr.mm6932a1 · Cited by 2,686
Slide-seq: A scalable technology for measuring genome-wide expression at high spatial resolution
Rodriques, S. G., Stickels, R. R., Goeva, A., Martin, C. A., Murray, E., Vanderburg, C. R., Welch, J., Chen, L. M., Chen, F., & Macosko, E. Z. (2019) · Science · doi:10.1126/science.aaw1219 · Cited by 2,424
Ferrari, M., & Quaresima, V. (2012) · NeuroImage · doi:10.1016/j.neuroimage.2012.03.049 · Cited by 2,274 · cited 1×
“hemodynamic activities for functional neuroimaging [37].”
Resting-state connectivity biomarkers define neurophysiological subtypes of depression
Drysdale, A. T., Grosenick, L., Downar, J., Dunlop, K., Mansouri, F., Meng, Y., Fetcho, R. N., Zebley, B., Oathes, D. J., Etkin, A., et al. (2017) · Nature Medicine · doi:10.1038/nm.4246 · Cited by 2,170 · cited 4×
“For instance, low-dimensional representations of depression-related connectivity features have been successfully identified by applying canonical correlation analysis (CCA) to resting-state fMRI (rsfMRI) connectivity and clinical symptoms.(15) The discovered representations defined two disease dimensions corresponding…”
BackgroundMethodInfluentialThe Geneva Minimalistic Acoustic Parameter Set (GeMAPS) for Voice Research and Affective Computing
Eyben, F., Scherer, K. R., Schuller, B. W., Sundberg, J., Andre, E., Busso, C., Devillers, L. Y., Epps, J., Laukka, P., Narayanan, S. S., et al. (2016) · IEEE Transactions on Affective Computing · doi:10.1109/taffc.2015.2457417 · Cited by 1,818 · cited 1×
“Table 4 lists some commonly used acoustic features in the analysis of mental illnesses.(187) These categories have enabled standardization and interpretation of ML-analyzed speech data in clinical applications.”
BackgroundResting-state fMRI in the human connectome project
Smith, S. M., Beckmann, C. F., Andersson, J., Auerbach, E. J., Bijsterbosch, J., Douaud, G., Duff, E., Feinberg, D. A., Griffanti, L., Harms, M. P., et al. (2013) · NeuroImage · doi:10.1016/j.neuroimage.2013.05.039 · Cited by 1,502
The NIMH Research Domain Criteria (RDoC) Project: Precision Medicine for Psychiatry
Insel, T. R. (2014) · American Journal of Psychiatry · doi:10.1176/appi.ajp.2014.14020138 · Cited by 1,472 · cited 1×
“Distinctfrom the traditional case-control design, the NIMH’s RDoC aims to address the heterogeneity and comorbidity in psychiatry by linking symptom dimensions with biological systems, cutting across the diagnostic spectrum [46].”
MethodIntegrative single-cell analysis
Stuart, T., & Satija, R. (2019) · Nature Reviews Genetics · doi:10.1038/s41576-019-0093-7 · Cited by 1,460
Medical image analysis using convolutional neural networks: a review
Anwar, S. M., Majid, M., Qayyum, A., Awais, M., Alnowami, M., & Khan, M. K. (2018) · Journal of Medical Systems · doi:10.1007/s10916-018-1088-1 · Cited by 1,431 · cited 1×
“Convolutional neural networks (CNNs) Different from conventional multi-layer perceptron or autoencoder assigning a different weight to each input feature, CNNs were designed to better capture the spatial and local structure information from pixels or voxels.(110,147) Due to its strength in utilizing neighborhood infor…”
Mechanisms of stress in the brain
McEwen, B. S., Bowles, N. P., Gray, J. D., Hill, M. N., Hunter, R. G., Karatsoreos, I. N., & Nasca, C. (2015) · Nature Neuroscience · doi:10.1038/nn.4086 · Cited by 1,386
Self-citationCuthbert, B. N. (2014) · World Psychiatry · doi:10.1002/wps.20087 · Cited by 1,377 · cited 1×
“The ultimate goal of RDoC is to find “new ways of classifying psychiatric diseases based on multiple dimensions of biology and behavior” [49].”
BackgroundMultimodal Data Fusion: An Overview of Methods, Challenges, and Prospects
Lahat, D., Adali, T., & Jutten, C. (2015) · Proceedings of the IEEE · doi:10.1109/jproc.2015.2460697 · Cited by 1,296 · cited 1×
“Multimodal data fusion techniques present a framework to infer information how di ff erent data modalities interact and can be integrated for improved disease prediction [254, 255, 43].”
BackgroundDo no harm: a roadmap for responsible machine learning for health care
Wiens, J., Saria, S., Sendak, M., Ghassemi, M., Liu, V. X., Doshi-Velez, F., Jung, K., Heller, K., Kale, D., Saeed, M., et al. (2019) · Nature Medicine · doi:10.1038/s41591-019-0548-6 · Cited by 1,266
Dynamic models of large-scale brain activity
Breakspear, M. (2017) · Nature Neuroscience · doi:10.1038/nn.4497 · Cited by 1,239
Torous, J., Bucci, S., Bell, I. H., Kessing, L. V., Faurholt‐Jepsen, M., Whelan, P., Carvalho, A. F., Keshavan, M., Linardon, J., & Firth, J. (2021) · World Psychiatry · doi:10.1002/wps.20883 · Cited by 1,199 · cited 1×
“Digital measurements We are entering a new era of digital psychiatry.(11,245) In 2016, the Harvard professor Jukka-Pekka Onnela coined the term ‘‘digital phenotype,’’(246) which refers to the use of mobile devices and other digital data sources to measure behavior and physiology for understanding brain activity that i…”
BackgroundHigh-definition spatial transcriptomics for in situ tissue profiling
Vickovic, S., Eraslan, G., Salmén, F., Klughammer, J., Stenbeck, L., Schapiro, D., Äijö, T., Bonneau, R., Bergenstråhle, L., Navarro, J. F., et al. (2019) · Nature Methods · doi:10.1038/s41592-019-0548-y · Cited by 1,150
Deep multimodal learning: a survey on recent advances and trends
Ramachandram, D., & Taylor, G. W. (2017) · IEEE Signal Processing Magazine · doi:10.1109/msp.2017.2738401 · Cited by 1,139 · cited 1×
“Empowered by cutting-edge deep learning techniques, emerging methods have been increasingly developed for deep multimodal fusion [275].”
BackgroundLarge-scale cortical correlation structure of spontaneous oscillatory activity
Hipp, J. F., Hawellek, D. J., Corbetta, M., Siegel, M., & Engel, A. K. (2012) · Nature Neuroscience · doi:10.1038/nn.3101 · Cited by 1,113
Single-cell RNA-seq denoising using a deep count autoencoder
Eraslan, G., Simon, L. M., Mircea, M., Mueller, N. S., & Theis, F. J. (2019) · Nature Communications · doi:10.1038/s41467-018-07931-2 · Cited by 1,084 · cited 1×
“Deep learning approaches, such as the autoencoder, provide another example of tools used for denoising and dimensionality reduction with computational scalability [311, 312, 313].”
MethodMachine learning in mental health: a scoping review of methods and applications
Shatte, A. B. R., Hutchinson, D. M., & Teague, S. J. (2019) · Psychological Medicine · doi:10.1017/s0033291719000151 · Cited by 1,047 · cited 2×
“The past two decades have witnessed substantial growth of ML applications for psychiatry in the literature, reflected in many applications and reviews [10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20].”
BackgroundIdentification of autism spectrum disorder using deep learning and the ABIDE dataset
Heinsfeld, A. S., Franco, A. R., Craddock, R. C., Buchweitz, A., & Meneguzzi, F. (2018) · NeuroImage: Clinical · doi:10.1016/j.nicl.2017.08.017 · Cited by 1,016
Computational psychiatry as a bridge from neuroscience to clinical applications
Huys, Q. J. M., Maia, T. V., & Frank, M. J. (2016) · Nature Neuroscience · doi:10.1038/nn.4238 · Cited by 1,002 · cited 1×
“Sharing the same goal of XAI, computational psychiatry tries to combine multiple levels and types of computation with multiple types of data in an e ff ort to improve understanding, prediction and treatment of mental illness [340].”
BackgroundFunctional connectomics from resting-state fMRI
Smith, S. M., Vidaurre, D., Beckmann, C. F., Glasser, M. F., Jenkinson, M., Miller, K. L., Nichols, T. E., Robinson, E. C., Salimi-Khorshidi, G., Woolrich, M. W., et al. (2013) · Trends in Cognitive Sciences · doi:10.1016/j.tics.2013.09.016 · Cited by 952 · cited 1×
“A promising direction for probing brain function using neuroimaging is to investigate brain connectivity (or connectome) [39].”
BackgroundJoint profiling of chromatin accessibility and gene expression in thousands of single cells
Cao, J., Cusanovich, D. A., Ramani, V., Aghamirzaie, D., Pliner, H. A., Hill, A. J., Daza, R. M., McFaline-Figueroa, J. L., Packer, J. S., Christiansen, L., et al. (2018) · Science · doi:10.1126/science.aau0730 · Cited by 938
Insel, T. R., & Cuthbert, B. N. (2015) · Science · doi:10.1126/science.aab2358 · Cited by 840
High-throughput sequencing of the transcriptome and chromatin accessibility in the same cell
Chen, S., Lake, B. B., & Zhang, K. (2019) · Nature Biotechnology · doi:10.1038/s41587-019-0290-0 · Cited by 810 · cited 1×
“The combination of multimodal data generated from the simultaneous assessment of transcriptomic profiles with regulatory landscape or spatial location in the same single cell [315, 316, 317, 318] will allow a deeper molecular characterization of discrete cellular states [310].”
BackgroundPersonal Sensing: Understanding Mental Health Using Ubiquitous Sensors and Machine Learning
Mohr, D. C., Zhang, M., & Schueller, S. M. (2017) · Annual Review of Clinical Psychology · doi:10.1146/annurev-clinpsy-032816-044949 · Cited by 802 · cited 1×
“Devices that collect data streams from patients, such as surveys, cognitive tests, social medial interactions, GPS coordinates, and behavioral patterns (e.g., keyboard typing), have great potentials for monitoring, managing and predicting the individual’s mental health [226, 227].”
BackgroundConfident Learning: Estimating Uncertainty in Dataset Labels
Northcutt, C., Jiang, L., & Chuang, I. (2021) · Journal of Artificial Intelligence Research · doi:10.1613/jair.1.12125 · Cited by 795
636,120 Ways to Have Posttraumatic Stress Disorder
Galatzer-Levy, I. R., & Bryant, R. A. (2013) · Perspectives on Psychological Science · doi:10.1177/1745691613504115 · Cited by 778 · cited 1×
“cesses and provides high measurement accuracy through direct rapid sampling, which is in contrast to traditional clinical measures that are taken sporadically over a long period.(164,247,248) These measurement approaches have relevance in multiple areas including treatment development, treatment selection, and ongoing…”
BackgroundSelf-citationLetham, B., Rudin, C., McCormick, T. H., & Madigan, D. (2015) · The Annals of Applied Statistics · doi:10.1214/15-aoas848 · Cited by 766 · cited 1×
“Hybrid rule-based ML models This type of MLmodels can be used for generating rules, such as a decision rule set: IF (condition) THEN (outcome 1) ELSE (outcome 2) statement, where the conditional clause will be learned from data.(341) This type of model has more expressive power but less portability.”
MethodTorous, J., Kiang, M. V., Lorme, J., & Onnela, J.-P. (2016) · JMIR Mental Health · doi:10.2196/mental.5165 · Cited by 758 · cited 2×
“Devices that collect data streams from patients, such as surveys, cognitive tests, social medial interactions, GPS coordinates, and behavioral patterns (e.g., keyboard typing), have great potentials for monitoring, managing and predicting the individual’s mental health [226, 227].”
BackgroundSex-specific transcriptional signatures in human depression
Labonté, B., Engmann, O., Purushothaman, I., Menard, C., Wang, J., Tan, C., Scarpa, J. R., Moy, G., Loh, Y.-H. E., Cahill, M., et al. (2017) · Nature Medicine · doi:10.1038/nm.4386 · Cited by 748
Harnessing Smartphone-Based Digital Phenotyping to Enhance Behavioral and Mental Health
Onnela, J.-P., & Rauch, S. L. (2016) · Neuropsychopharmacology · doi:10.1038/npp.2016.7 · Cited by 726 · cited 1×
“In 2016, the Harvard professor Jukka-Pekka Onnela coined the term digital phenotype [235], which refers to the use of mobile devices and other digital data sources to measure behavior and physiology for understanding brain activity that is relevant to pathological states.”
BackgroundUnderstanding heterogeneity in clinical cohorts using normative models: Beyond case-control studies
Marquand, A. F., Rezek, I., Buitelaar, J., & Beckmann, C. F. (2016) · Biological Psychiatry · doi:10.1016/j.biopsych.2015.12.023 · Cited by 683 · cited 1×
“Semi-supervised learning also provides an elegant way through normative modeling [130] to characterize neurobiological heterogeneity by quantifying individual deviations.”
BackgroundFacebook language predicts depression in medical records
Eichstaedt, J. C., Smith, R. J., Merchant, R. M., Ungar, L. H., Crutchley, P., Preoţiuc-Pietro, D., Asch, D. A., & Schwartz, H. A. (2018) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.1802331115 · Cited by 643
Promises and limitations of human intracranial electroencephalography
Parvizi, J., & Kastner, S. (2018) · Nature Neuroscience · doi:10.1038/s41593-018-0108-2 · Cited by 631
Fox, M. D., Buckner, R. L., Liu, H., Chakravarty, M. M., Lozano, A. M., & Pascual-Leone, A. (2014) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.1405003111 · Cited by 617 · cited 1×
“Can alternate or simultaneous neu-rostimulations at multiple sites more e ff ectively influence the network connectivity or bring additional benefit in treatment [357]?”
BackgroundMachine learning and natural language processing in mental health: systematic review
Le Glaz, A., Haralambous, Y., Kim-Dufor, D.-H., Lenca, P., Billot, R., Ryan, T. C., Marsh, J., DeVylder, J., Walter, M., Berrouiguet, S., et al. (2021) · Journal of Medical Internet Research · doi:10.2196/15708 · Cited by 576 · cited 1×
“Language is not only one of the primary expressions of human behavior that carries a variety of implicit and explicit markers relevant to mental health [193, 194], but also more abundantly available compared to speech data.”
BackgroundMethods in predictive techniques for mental health status on social media: a critical review
Chancellor, S., & De Choudhury, M. (2020) · npj Digital Medicine · doi:10.1038/s41746-020-0233-7 · Cited by 557 · cited 1×
“While social media solves the scale issue with millions of samples available, most social media data lack clinically-valid labels [217].”
BackgroundFriston, K. J., Kahan, J., Biswal, B., & Razi, A. (2014) · NeuroImage · doi:10.1016/j.neuroimage.2013.12.009 · Cited by 553 · cited 1×
“DCM has been widely used in characterizing the e ff ective connectivity of a functional network based on task or resting-state fMRI [346, 347], where the model parameter estimation and inference is done by unsupervised learning.”
MethodDARPA's explainable artificial intelligence (XAI) program
Gunning, D. (2019) · Proceedings of the 24th International Conference on Intelligent User Interfaces · doi:10.1145/3301275.3308446 · Cited by 546
Nagy, C., Maitra, M., Tanti, A., Suderman, M., Théroux, J.-F., Davoli, M. A., Perlman, K., Yerko, V., Wang, Y. C., Tripathy, S. J., et al. (2020) · Nature Neuroscience · doi:10.1038/s41593-020-0621-y · Cited by 532
Parcellating cortical functional networks in individuals
Wang, D., Buckner, R. L., Fox, M. D., Holt, D. J., Holmes, A. J., Stoecklein, S., Langs, G., Pan, R., Qian, T., Li, K., et al. (2015) · Nature Neuroscience · doi:10.1038/nn.4164 · Cited by 527
Nagy, C., Maitra, M., Tanti, A., Suderman, M., Théroux, J.-F., Mechawar, N., Ragoussis, J., & Turecki, G. (2018) · doi:10.1101/384479 · Cited by 523
Reward Processing in Depression: A Conceptual and Meta-Analytic Review Across fMRI and EEG Studies
Keren, H., O’Callaghan, G., Vidal-Ribas, P., Buzzell, G. A., Brotman, M. A., Leibenluft, E., Pan, P. M., Meffert, L., Kaiser, A., Wolke, S., et al. (2018) · American Journal of Psychiatry · doi:10.1176/appi.ajp.2018.17101124 · Cited by 521 · cited 1×
“Typical measures of taskrelated brain activities include event-related potential and event-related spectral perturbation, and reward or emotional processing-related functional activation [39], [40].”
BackgroundCausal inference and counterfactual prediction in machine learning for actionable healthcare
Prosperi, M., Guo, Y., Sperrin, M., Koopman, J. S., Min, J. S., He, X., Rich, S., Wang, M., Buchan, I. E., & Bian, J. (2020) · Nature Machine Intelligence · doi:10.1038/s42256-020-0197-y · Cited by 459 · cited 1×
“Causal inference methods supported by ML models [366] can help with “precision” treatment design [367], which is the next step in the patient’s journey after precision diagnosis.”
MethodThe Heterogeneity Problem: Approaches to Identify Psychiatric Subtypes
Feczko, E., Miranda-Dominguez, O., Marr, M., Graham, A. M., Nigg, J. T., & Fair, D. A. (2019) · Trends in Cognitive Sciences · doi:10.1016/j.tics.2019.03.009 · Cited by 443 · cited 2×
“The symptom-based diagnosis covered hundreds of thousands of di ff erent symptom combinations, which has caused extensive clinical heterogeneity [44, 45].”
BackgroundConceptualizing mental disorders as deviations from normative functioning
Marquand, A. F., Kia, S. M., Zabihi, M., Wolfers, T., Buitelaar, J. K., & Beckmann, C. F. (2019) · Molecular Psychiatry · doi:10.1038/s41380-019-0441-1 · Cited by 433 · cited 1×
“However, subtyping analysis is widely viewed as hypothesis generating and poses significant challenges related to reproducibility and physiological interpretability.(43,47) Linking subtype identification to a particular outcome or question using well-designed ML approaches is vital to address these challenges.”
BackgroundToward clinical digital phenotyping: a timely opportunity to consider purpose, quality, and safety
Huckvale, K., Venkatesh, S., & Christensen, H. (2019) · npj Digital Medicine · doi:10.1038/s41746-019-0166-1 · Cited by 433
Thieme, A., Belgrave, D., & Doherty, G. (2020) · ACM Transactions on Computer-Human Interaction · doi:10.1145/3398069 · Cited by 406
Machine learning in major depression: from classification to treatment outcome prediction
Gao, S., Calhoun, V. D., & Sui, J. (2018) · CNS Neuroscience & Therapeutics · doi:10.1111/cns.13048 · Cited by 370
Deep learning in mental health outcome research: a scoping review
Su, C., Xu, Z., Pathak, J., & Wang, F. (2020) · Translational Psychiatry · doi:10.1038/s41398-020-0780-3 · Cited by 368 · cited 2×
“The past two decades have witnessed substantial growth of ML applications for psychiatry in the literature, reflected in many applications and reviews [10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20].”
BackgroundMental health monitoring with multimodal sensing and machine learning: A survey
Garcia-Ceja, E., Riegler, M., Nordgreen, T., Jakobsen, P., Oedegaard, K. J., & Tørresen, J. (2018) · Pervasive and Mobile Computing · doi:10.1016/j.pmcj.2018.09.003 · Cited by 356 · cited 1×
“Smartphones, wearables and other connected devices equipped with ambient sensors (Figure 7B) are increasingly capable of recording physiological measurements that are known to a ff ect mental health [218].”
BackgroundCutillo, C. M., Sharma, K. R., Foschini, L., Kundu, S., Mackintosh, M., Mandl, K. D., MI in Healthcare Workshop Working Group, Beck, T., Collier, E., Colvis, C., et al. (2020) · npj Digital Medicine · doi:10.1038/s41746-020-0254-2 · Cited by 337 · cited 1×
“In a recently published white paper “Machine intelligence for healthcare”, four important features are emphasized for ML systems [152].”
BackgroundWagner, B., Horn, A. B., & Maercker, A. (2014) · Journal of Affective Disorders · doi:10.1016/j.jad.2013.06.032 · Cited by 311 · cited 1×
“While still in their infancy, early evidence has shown that tele-health services can perform at parity with traditional in person therapy [253].”
BackgroundSui, J., Jiang, R., Bustillo, J., & Calhoun, V. (2020) · Biological Psychiatry · doi:10.1016/j.biopsych.2020.02.016 · Cited by 309
An electroencephalographic signature predicts antidepressant response in major depression
Wu, W., Zhang, Y., Jiang, J., Lucas, M. V., Fonzo, G. A., Rolle, C. E., Cooper, C., Chin-Fatt, C., Krepel, N., Cornelssen, C. A., et al. (2020) · Nature Biotechnology · doi:10.1038/s41587-019-0397-3 · Cited by 302
Self-citationPredicting suicide attempts in adolescents with longitudinal clinical data and machine learning
Walsh, C. G., Ribeiro, J. D., & Franklin, J. C. (2018) · Journal of Child Psychology and Psychiatry · doi:10.1111/jcpp.12916 · Cited by 264 · cited 1×
“Symptoms derived from the free text in EHR data can be used to predict a diagnosis for bipolar disorder [196], situational aggression [197], and suicidal ideation [198], with reported performances comparable to clinicians.”
MethodKorngiebel, D. M., & Mooney, S. D. (2021) · npj Digital Medicine · doi:10.1038/s41746-021-00464-x · Cited by 259
Prochaska, J. J., Vogel, E. A., Chieng, A., Kendra, M., Baiocchi, M., Pajarito, S., & Robinson, A. (2021) · Journal of Medical Internet Research · doi:10.2196/24850 · Cited by 257 · cited 1×
“WoeBot [230] Language Depression, Anxiety Mindstrong [220] Keystrokes Serious mental illness Sonde Health [164] Voice Mental fitness Ellipsis Health [163] Voice Stress Amazon Halo [231] Voice Emotion detection Apple Watch [186] Mobility, Sleep Depression Alphabet Fitbit [232] Skin conductance Stress Kintsugi [233] Voi…”
BackgroundArtificial intelligence and the future of psychiatry: Insights from a global physician survey
Doraiswamy, P. M., Blease, C., & Bodner, K. (2020) · Artificial Intelligence in Medicine · doi:10.1016/j.artmed.2019.101753 · Cited by 253
Economides, M., Martman, J., Bell, M. J., & Sanderson, B. (2018) · Mindfulness · doi:10.1007/s12671-018-0905-4 · Cited by 250
Generative Adversarial Networks and Its Applications in Biomedical Informatics
Lan, L., You, L., Zhang, Z., Fan, Z., Zhao, W., Zeng, N., Chen, Y., & Zhou, X. (2020) · Frontiers in Public Health · doi:10.3389/fpubh.2020.00164 · Cited by 237 · cited 10×
“to generate synthetic brain images, speech, video, physiological data, and EHRs [376]–[378].”
BackgroundInfluentialZulueta, J., Piscitello, A., Rasic, M., Easter, R., Babu, P., Langenecker, S. A., McInnis, M., Ajilore, O., Nelson, P. C., Ryan, K., et al. (2018) · Journal of Medical Internet Research · doi:10.2196/jmir.9775 · Cited by 233 · cited 1×
“In addition, some of the less obvious measurements (such as keystroke usage patterns) have also been shown to be implicated by mental illness [220], [221].”
BackgroundMentalBERT: Publicly Available Pretrained Language Models for Mental Healthcare
Ji, S., Zhang, T., Ansari, L., Fu, J., Tiwari, P., & Cambria, E. (2022) · Proceedings of the Language Resources and Evaluation Conference · doi:10.63317/2d7umxifj8wz · Cited by 233
Time to reality check the promises of machine learning-powered precision medicine.
Wilkinson, J., Arnold, K. F., Murray, E. J., van Smeden, M., Carr, K., Sippy, R., de Kamps, M., Beam, A., Konigorski, S., Lippert, C., et al. (2020) · The Lancet Digital Health · doi:10.1016/s2589-7500(20)30200-4 · Cited by 233 · cited 2×
“However, the amount of precision that can be modeled us-ing ML is far beyond the first level [158, 159].”
BackgroundDeep learning for small and big data in psychiatry
Koppe, G., Meyer-Lindenberg, A., & Durstewitz, D. (2021) · Neuropsychopharmacology · doi:10.1038/s41386-020-0767-z · Cited by 189 · cited 3×
“This poses potential overfitting and interpretability challenges in psychiatric applications [18].”
BackgroundBickman, L. (2020) · Administration and Policy in Mental Health and Mental Health Services Research · doi:10.1007/s10488-020-01065-8 · Cited by 184 · cited 1×
“However, the amount of precision that can be modeled using ML is far beyond the first level.(181,182) During psychiatric evaluation, psychiatrists may try to build a mental model of what is going on in the patient’s life in about 30 min.”
BackgroundDetecting Bipolar Depression From Geographic Location Data
Palmius, N., Tsanas, A., Saunders, K. E. A., Bilderbeck, A. C., Geddes, J. R., Goodwin, G. M., & De Vos, M. (2017) · IEEE Transactions on Biomedical Engineering · doi:10.1109/tbme.2016.2611862 · Cited by 180
A Scoping Review of Machine Learning in Psychotherapy Research
Aafjes-van Doorn, K., Kamsteeg, C., Bate, J., & Aafjes, M. (2021) · Psychotherapy Research · doi:10.1080/10503307.2020.1808729 · Cited by 179 · cited 1×
“In a new era of evidence-based psychiatry tailored to individual patients, objectively measurable endophenotypes could allow for early disease detection, personalized treatment selection, and dosage adjustment to reduce the burden of disease.(18,107,108) These promising applications in psychiatric disorders have been…”
BackgroundKetamine elicits sustained antidepressant-like activity via a serotonin-dependent mechanism
Gigliucci, V., O’Dowd, G., Casey, S., Egan, D., Gibney, S., & Harkin, A. (2013) · Psychopharmacology · doi:10.1007/s00213-013-3024-x · Cited by 177
Subtyping cognitive profiles in Autism Spectrum Disorder using a Functional Random Forest algorithm
Feczko, E., Balba, N. M., Miranda-Dominguez, O., Cordova, M., Karalunas, S. L., Irwin, L., Demeter, D. V., Hill, A. P., Langhorst, B. H., Grieser Painter, J., et al. (2018) · NeuroImage · doi:10.1016/j.neuroimage.2017.12.044 · Cited by 173
Reggente, N., Moody, T. D., Morfini, F., Sheen, C., Rissman, J., O’Neill, J., & Feusner, J. D. (2018) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.1716686115 · Cited by 154 · cited 1×
“LASSO provides an alternative approach that performs simultaneous feature selection and prediction to learn a compact feature pattern for the accurate prediction of a specific brain disease or clinical outcome [90].”
MethodSeppälä, J., De Vita, I., Jämsä, T., Miettunen, J., Isohanni, M., Rubinstein, K., Feldman, Y., Grasa, E., Corripio, I., Berdun, J., et al. (2019) · JMIR Mental Health · doi:10.2196/mental.9819 · Cited by 148 · cited 1×
“variety of ailments including depression, anxiety, psychosis, and bipolar disorder [225], [226].”
BackgroundCharacteristics and challenges of the clinical pipeline of digital therapeutics
Patel, N. A., & Butte, A. J. (2020) · npj Digital Medicine · doi:10.1038/s41746-020-00370-8 · Cited by 143 · cited 1×
“Examples that are in development or have received FDA (Food and Drug Administration) approval include treatments for substance use disorder (SUD), ADHD, schizophrenia, ASD, MDD, PTSD, and generalized anxiety disorder (GAD) [250].”
BackgroundFrom Treatment to Healing:Envisioning a Decolonial Digital Mental Health
Pendse, S. R., Nkemelu, D., Bidwell, N. J., Jadhav, S., Pathare, S., De Choudhury, M., & Kumar, N. (2022) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3491102.3501982 · Cited by 115
Quantifying the association between psychotherapy content and clinical outcomes using deep learning
Ewbank, M. P., Cummins, R., Tablan, V., Bateup, S., Catarino, A., Martin, A. J., & Blackwell, A. D. (2020) · JAMA Psychiatry · doi:10.1001/jamapsychiatry.2019.2664 · Cited by 108 · cited 1×
“A number of companies such as Mindstrong Health [219], IesoTrigger Health [245], and Headspace Health [246, 247], have attempted to integrate digital phenotyping to identify when patients are in acute clinical need.”
BackgroundThe PTSD Systems Biology Consortium, Dean, K. R., Hammamieh, R., Mellon, S. H., Abu-Amara, D., Flory, J. D., Guffanti, G., Wang, K., Daigle, B. J., Gautam, A., et al. (2020) · Molecular Psychiatry · doi:10.1038/s41380-019-0496-z · Cited by 101
Bigio, B., Mathé, A. A., Sousa, V. C., Zelli, D., Svenningsson, P., McEwen, B. S., & Nasca, C. (2016) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.1603111113 · Cited by 85 · cited 1×
“pus in the responses to stress—a primary risk factor for multiple psychiatric diseases—with the ventral hippocampus being sensitive not only to the effects of stress(313) but also a target for the responses to next-generation anti-depressants.(314,315) The expansion ofNGS to single-cell resolution assaysprovides oppor…”
BackgroundSelf-citationGueorguieva, R., Chekroud, A. M., & Krystal, J. H. (2017) · The Lancet Psychiatry · doi:10.1016/s2215-0366(17)30038-x · Cited by 67
Chandler, C., Foltz, P. W., & Elvevåg, B. (2019) · Schizophrenia Bulletin · doi:10.1093/schbul/sbz105 · Cited by 61 · cited 1×
“These concepts are equally applicable to precision psychiatry [11].”
BackgroundAbbas, A., Sauder, C., Yadav, V., Koesmahargyo, V., Aghjayan, A., Marecki, S., Evans, M., & Galatzer-Levy, I. R. (2021) · Frontiers in Digital Health · doi:10.3389/fdgth.2021.610006 · Cited by 49 · cited 1×
“…digital phenotyping parameters that reflect gross motor activity including speech characteristics (rate of speech, tone) and facial / head movements are associated with suicidal risk [241], SSRI response in MDD [242], negative symptomatology in schizophrenia [243], and Parkinsonian tremor [244].”
BackgroundSelf-citationThe Transition of Academic Mental Health Clinics to Telehealth During the COVID-19 Pandemic
Folk, J. B., Schiel, M. A., Oblath, R., Feuer, V., Sharma, A., Khan, S., Doan, B., Kulkarni, C., Ramtekkar, U., Hawks, J., et al. (2022) · Journal of the American Academy of Child & Adolescent Psychiatry · doi:10.1016/j.jaac.2021.06.003 · Cited by 47
Ewbank, M. P., Cummins, R., Tablan, V., Catarino, A., Buchholz, S., & Blackwell, A. D. (2021) · Psychotherapy Research · doi:10.1080/10503307.2020.1788740 · Cited by 39 · cited 1×
“This has led to development of models that can identify patterns in patient’s and clinician’s language that are markers of improved outcomes [248], which can be further used to measure success of various therapy modalities, treatment design, as well as to improve care quality [249].”
BackgroundLecei, A., van Hulst, B. M., de Zeeuw, P., van der Pluijm, M., Rijks, Y., & Durston, S. (2019) · NeuroImage: Clinical · doi:10.1016/j.nicl.2018.11.011 · Cited by 27
Galatzer-Levy, I., Abbas, A., Ries, A., Homan, S., Sels, L., Koesmahargyo, V., Yadav, V., Colla, M., Scheerer, H., Vetter, S., et al. (2021) · Journal of Medical Internet Research · doi:10.2196/25199 · Cited by 23
Self-citationThukral, A., Ershad, F., Enan, N., Rao, Z., & Yu, C. (2018) · IEEE Nanotechnology Magazine · doi:10.1109/mnano.2017.2781290 · Cited by 19 · cited 1×
“(C) Human neuroimaging at various spatial and temporal resolution (copyright IEEE; figure reproduced from Thukral et al.(13) with permission).”
BackgroundRobust Speech and Natural Language Processing Models for Depression Screening
Lu, Y., Harati, A., Rutowski, T., Oliveira, R., Chlebek, P., & Shriberg, E. (2020) · 2020 IEEE Signal Processing in Medicine and Biology Symposium (SPMB) · doi:10.1109/spmb50085.2020.9353611 · Cited by 9
Cited by
(2023) · doi:10.2196/54369 · Cited by 127
Smith, A., Hachen, S., Schleifer, R., Bhugra, D., Buadze, A., & Liebrenz, M. (2023) · International Journal of Social Psychiatry · doi:10.1177/00207640231178451 · Cited by 57
“Due to its popular uptake, the system has been depicted as part of a ‘turning point’ for AI (B. Chen, 2022).”
BackgroundWang, Y., Gu, X., Hou, W., Zhao, M., Sun, L., & Guo, C. (2023) · Brain Sciences · doi:10.3390/brainsci13020306 · Cited by 17
“Research has suggested that the traditional diagnosis of cognitive disorders remains limited to subjective symptoms and observable features, and that ML offers a novel paradigm that can enable automated and more objective evaluation of various psychiatric diseases [5].”
BackgroundLet’s Move Towards Precision Suicidology
Courtet, P., & Saiz, P. A. (2025) · Current Psychiatry Reports · doi:10.1007/s11920-025-01605-9 · Cited by 7
Metadata
- Authors
- Chen, Z. S., Kulkarni, P. (., Galatzer-Levy, I. R., Bigio, B., Nasca, C., & Zhang, Y.
- Venue
- Patterns
- Publisher
- Elsevier BV
- Published
- 2022-11
- Volume
- 3
- Issue
- 11
- Pages
- 100602
- ISSN
- 2666-3899 (ISSN-L)
- OpenAlex
- W4308806761
- Cited by
- 210
- References
- 95
- FWCI
- 8.42
- Type
- journal article
- Language
- en
- Open access
- gold
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.