Makine Öğrenme ve Psikiyatri Alanında Güncel Uygulamalar
Özet
Yapay zeka ve onun bir alt kolu olan makine öğrenimi (MÖ), büyük veri kümelerini analiz etme ve tahmine dayalı modeller geliştirme yetenekleriyle tıp dünyasında köklü değişimler yaratmaktadır. Geleneksel tanı kriterlerinin (ICD-10, DSM-5) nesnel belirteçlerden ziyade insani deneyimlere dayanması ve hastalıkları sınırlı şekilde tanımlaması, psikiyatri alanında MÖ uygulamalarına duyulan ihtiyacı artırmıştır. Makine öğrenimi; veri toplama, hazırlık, model seçimi, eğitim, değerlendirme, hiper-parametre ayarlama ve tahminleme olmak üzere yedi aşamalı bir süreçle yürütülür. Klinik psikiyatri alanında bu teknoloji; teşhis, prognoz, tedavi tahmini ve potansiyel biyomarkerların tespiti amacıyla aktif olarak kullanılmaktadır. Nörogörüntüleme çalışmalarında, MR ve fMR verileri MÖ algoritmalarıyla analiz edilerek Alzheimer ve bipolar bozukluk gibi hastalıkların erken teşhisi birey seviyesinde yüksek doğrulukla sağlanabilmektedir. Gen analizinde ise şizofreni gibi kalıtsal hastalıkların genetik varyantları ile risk faktörleri tespit edilmekte, hibrit modeller sayesinde tanısal kesinlik artırılmaktadır. Ayrıca mobil algılama ve akıllı telefon uygulamaları yoluyla gerçek zamanlı veri toplanarak intihar riski, self-mutilasyon, bağımlılık seviyeleri ve duygu durum değişiklikleri dinamik olarak öngörülebilmektedir. Tüm bu baş döndürücü gelişmelere rağmen, veri hazırlığındaki zorluklar, veri güvenliği sorunları ve biyoetik ilkeler (iyilik, zarar vermeme, özerklik, adalet) psikiyatride MÖ kullanımında dikkatle yapılandırılması gereken kritik engeller olarak varlığını korumaktadır.
Artificial intelligence and its subfield, machine learning (ML), are driving profound transformations in medicine through their ability to analyze large datasets and develop predictive models. Since traditional diagnostic criteria (ICD-10, DSM-5) rely on human experience rather than objective markers and remain limited in defining diseases, the need for ML applications in psychiatry has significantly increased. Machine learning operates through a seven-step process consisting of data collection, preparation, model selection, training, evaluation, hyperparameter tuning, and prediction. In clinical psychiatry, this technology is actively utilized for diagnosis, prognosis, treatment prediction, and the identification of potential biomarkers. In neuroimaging, MRI and fMRI data are analyzed with ML algorithms to achieve high-accuracy, individual-level early diagnosis for disorders like Alzheimer's and bipolar disorder. In genetic analysis, genetic variants and risk factors of hereditary diseases such as schizophrenia are identified, and diagnostic certainty is enhanced using hybrid models. Additionally, passive data collection via mobile sensing and smartphone applications allows for the dynamic prediction of suicide risk, self-mutilation, addiction levels, and mood changes. Despite these staggering advancements, challenges in data preparation, data security issues, and bioethical principles (beneficence, non-maleficence, autonomy, justice) remain critical hurdles that must be carefully structured in psychiatric ML implementation.
Referanslar
Muthukrishnan, N., Maleki, F., Ovens, K., Reinhold, C., Forghani, B., & Forghani, R. (2020). Brief History of Artificial Intelligence. Neuroimaging clinics of North America, 30(4), 393–399. https://doi.org/10.1016/j.nic.2020.07.004
Kaul, V., Enslin, S., & Gross, S. A. (2020). History of artificial intelligence in medicine. Gastrointestinal endoscopy, 92(4), 807–812. https://doi.org/10.1016/j.gie.2020.06.040
Fan J, Han F, Liu H. (2014) “Challenges of Big Data Analysis.” National Science Review 1: 293–314. https://doi.org/10.1093/nsr/nwt032.
https://www.mathworks.com/discovery/machine-learning.html, ET:10.06.2022
https://www.techtarget.com/searchenterpriseai/definition/machine-learning-ML ET.10.06.2022
Bzdok D, Meyer-Lindenberg A. (2017). “Machine Learning for Precision Psychiatry: Opportunities and Challenges.” Biological Psychiatry: Cognitive Neuroscience and Neuroimaging 3: 223–30. https://doi.org/10.1016/j.bpsc.2017.11.007
Fusar-Poli P, Hijazi Z, Stahl D et al. (2018), “The Science of Prognosis in Psychiatry: A Review.” JAMA Psychiatry, 75(12), 1289–1297. https://doi.org/10.1001/jamapsychiatry.2018.2530
World Health Organisation, International statistical classification of diseases and related health problems. - 10th revision, Fifth edition, 2016. ISBN 978 92 4 154916 5
American Psychiatric Association: Diagnostic and Statistical Manual of Mental Disorders, Fifth Edition, Text Revision. Washington, DC, American Psychiatric Association, 2022.
Hyman SE. (2007) “Can Neuroscience Be Integrated into the DSM‑V?” Nature Review Neuroscience 8:725–32. https://doi.org/10.1038/nrn2218
Hedderich DM, Eickhoff SB. (2021). Machine learning for psychiatry: getting doctors at the black box?. Molecular psychiatry, 26(1), 23–25. https://doi.org/10.1038/s41380-020-00931-z
Cearns M, Hahn T, Baune BT. (2019). Recommendations and future directions for supervised machine learning in psychiatry. Translational psychiatry, 9(1), 271. https://doi.org/10.1038/s41398-019-0607-2
Gal MS, Rubinfeld DL 2019. “Data Standardization.” New York University Law Review 94: 34.
Li XT, Huang RY. (2021). Standardization of imaging methods for machine learning in neuro-oncology. Neuro-oncology advances, 2(Suppl 4), iv49–iv55. https://doi.org/10.1093/noajnl/vdaa054
Willemink MJ, Koszek WA, Hardell C. et al. (2020). Preparing Medical Imaging Data for Machine Learning. Radiology, 295(1), 4–15. https://doi.org/10.1148/radiol.2020192224
Sharma D, Kumar N. 2017. “A Review on Machine Learning Algorithms, Tasks and Applications”, International Journal of Advanced Research in Computer Engineering & Technology (IJARCET) Volume 6, Issue 10, October 2017, ISSN: 2278 – 1323
Dey, Ayon. 2016. “Machine Learning Algorithms: A Review.” (IJCSIT ) International Journal of Computer Science and Information Technologies, 7 (3): 2016, 1174–79.
Zhang Y, Dong Z, Phillips P. et al. (2015). Detection of subjects and brain regions related to Alzheimer's disease using 3D MRI scans based on eigenbrain and machine learning. Frontiers in computational neuroscience, 9, 66. https://doi.org/10.3389/fncom.2015.00066
Yang H, Liu J, Sui J.,et al. (2010). A Hybrid Machine Learning Method for Fusing fMRI and Genetic Data: Combining both Improves Classification of Schizophrenia. Frontiers in human neuroscience, 4, 192. https://doi.org/10.3389/fnhum.2010.00192
Trakadis YJ, Sardaar S, Chen A. et al. (2019). Machine learning in schizophrenia genomics, a case-control study using 5,090 exomes. American journal of medical genetics. Part B, Neuropsychiatric genetics : the official publication of the International Society of Psychiatric Genetics, 180(2), 103–112. https://doi.org/10.1002/ajmg.b.32638
Pelin H, Ising M, Stein F. et al. (2021). Identification of transdiagnostic psychiatric disorder subtypes using unsupervised learning. Neuropsychopharmacology : official publication of the American College of Neuropsychopharmacology, 46(11), 1895–1905. https://doi.org/10.1038/s41386-021-01051-0
Zeng LL, Shen H, Liu L et al. (2014). Unsupervised classification of major depression using functional connectivity MRI. Human brain mapping, 35(4), 1630–1641. https://doi.org/10.1002/hbm.2227
Matsubara T, Tashiro T, Uehara K. (2019). Deep Neural Generative Model of Functional MRI Images for Psychiatric Disorder Diagnosis. IEEE transactions on bio-medical engineering, 66(10), 2768–2779. https://doi.org/10.1109/TBME.2019.2895663
Khajehnejad M, Saatlou FH, Mohammadzade H. (2017). Alzheimer's Disease Early Diagnosis Using Manifold-Based Semi-Supervised Learning. Brain sciences, 7(8), 109. https://doi.org/10.3390/brainsci7080109
Squarcina L, Dagnew TM, Rivolta MW. et al. (2019). Automated cortical thickness and skewness feature selection in bipolar disorder using a semi-supervised learning method. Journal of affective disorders, 256, 416–423. https://doi.org/10.1016/j.jad.2019.06.019
Baker TE, Zeighami Y, Dagher A. et al. (2020). Smoking Decisions: Altered Reinforcement Learning Signals Induced by Nicotine State. Nicotine & tobacco research : official journal of the Society for Research on Nicotine and Tobacco, 22(2), 164–171. https://doi.org/10.1093/ntr/nty136
Ding J, Tarokh V, Yang Y. (2018) “Model Selection Techniques: An Overview.” IEEE Signal Processing Magazine, 35 (6) , art. no. 8498082 , pp. 16-34.
Raschka, S. (2018) “Model Evaluation, Model Selection, and Algorithm Selection in Machine Learning,” https://ar5iv.labs.arxiv.org/html/1811.12808 , E.T. 16/04/2022
Brnabic A, Hess, LM (2021). Systematic literature review of machine learning methods used in the analysis of real-world data for patient-provider decision making. BMC medical informatics and decision making, 21(1), 54. https://doi.org/10.1186/s12911-021-01403-2
Amidi A, Amidi S. 2018. “Machine Learning Tips and Tricks Cheatsheet.” Https://stanford.edu/~shervine/teaching/cs-229/cheatsheet-machine-learning-tips-and-tricks. 2018. (ET.19/07/2022)
Juba, B., & Le, H. S. (2019). Precision-Recall versus Accuracy and the Role of Large Data Sets. Proceedings of the AAAI Conference on Artificial Intelligence, 33(01), 4039-4048. https://doi.org/10.1609/aaai.v33i01.33014039
Yang L, Shami A. 2020. “On Hyperparameter Optimization of Machine Learning Algorithms: Theory and Practice.” Neurocomputing 415: 295–316.
Han H, Jiang X. 2014. “Overcoming Support Vector Machine Overfitting in Diagnosis.” Cancer Informatics 13: 145–58.
Jabbar HK. 2014. “Methods To Avoid Over-Fitting And Under-Fitting In Supervised Machine Learning (Comparative Study).” Computer Science, 11.
Srivastava, Nitish, Geoffrey Hinton, Alex Krizhevsky, et al. 2014. “Dropout: A Simple Way to Prevent Neural Networks from Overfitting.” Journal of Machine Learning Research 15: 1929–58.
Hinton GE, Srivastava N, Krizhevsky A. et al. (2012) “Improving Neural Networks by Preventing Co-Adaptation of Feature Detectors,” Neural and Evolutionary Computing 18. https://doi.org/10.48550/arXiv.1207.0580
Obermeyer, Z., & Emanuel, E. J. (2016). Predicting the Future - Big Data, Machine Learning, and Clinical Medicine. The New England journal of medicine, 375(13), 1216–1219. https://doi.org/10.1056/NEJMp1606181
Kim YK, Na KS. 2017. “Application of Machine Learning Classification for Structural Brain MRI in Mood Disorders: Critical Review from a Clinical Perspective.” Progress in Neuropsychopharmacology & Biological Psychiatry. https://doi.org/10.1016/j.pnpbp.2017.06.024.
Dwyer DB, Falkai P, Koutsouleris N. (2018). Machine Learning Approaches for Clinical Psychology and Psychiatry. Annual review of clinical psychology, 14, 91–118. https://doi.org/10.1146/annurev-clinpsy-032816-045037
Munson, MA. 2011. “A Study on the Importance of and Time Spent on Different Modeling Steps” ACM SIGKDD Explorations Newsletter,Volume 13, Issue 2, December 2011 pp 65 -71 https://doi.org/10.1145/2207243.2207253
Mann DL. (2021). Will Artificial Intelligence Transform Translational Medicine: (Not So) Elementary, My Dear Watson. JACC. Basic to translational science, 6(4), 400–401. https://doi.org/10.1016/j.jacbts.2021.03.005
Lotter W, Diab AR, Haslam B. et al. (2021). Robust breast cancer detection in mammography and digital breast tomosynthesis using an annotation-efficient deep learning approach. Nature medicine, 27(2), 244–249. https://doi.org/10.1038/s41591-020-01174-9
Ardila D, Kiraly AP, Bharadwaj S. et al. (2019). End-to-end lung cancer screening with three-dimensional deep learning on low-dose chest computed tomography. Nature medicine, 25(6), 954–961. https://doi.org/10.1038/s41591-019-0447-x
“Digital Mental Health.” 2021. https://mdhs.unimelb.edu.au/our-organisation/institutes-centres-departments/cymh/research/research-groups/digital-mental-health. (ET.19/07/2022)
Walter M, Alizadeh S, Jamalabadi H. et al. (2019). Translational machine learning for psychiatric neuroimaging. Progress in neuro-psychopharmacology & biological psychiatry, 91, 113–121. https://doi.org/10.1016/j.pnpbp.2018.09.014
Yu K, Cheung C, Leung M. et al. (2010). Are Bipolar Disorder and Schizophrenia Neuroanatomically Distinct? An Anatomical Likelihood Meta-analysis. Frontiers in human neuroscience, 4, 189. https://doi.org/10.3389/fnhum.2010.00189
Yüksel C, McCarthy J, Shinn A. et al. (2012). Gray matter volume in schizophrenia and bipolar disorder with psychotic features. Schizophrenia research, 138(2-3), 177–182. https://doi.org/10.1016/j.schres.2012.03.003
Brambilla P, Nicoletti MA, Sassi RB. et al.(2003). Magnetic resonance imaging study of corpus callosum abnormalities in patients with bipolar disorder. Biological psychiatry, 54(11), 1294–1297. https://doi.org/10.1016/s0006-3223(03)00070-2
Hilker R, Helenius D, Fagerlund B. et al. (2018). Heritability of Schizophrenia and Schizophrenia Spectrum Based on the Nationwide Danish Twin Register. Biological psychiatry, 83(6), 492–498. https://doi.org/10.1016/j.biopsych.2017.08.017
Cardno AG, Gottesman II. (2000). Twin studies of schizophrenia: from bow-and-arrow concordances to star wars Mx and functional genomics. American journal of medical genetics, 97(1), 12–17.
Ganapathiraju MK, Thahir M, Handen A. et al. (2016). Schizophrenia interactome with 504 novel protein-protein interactions. NPJ schizophrenia, 2, 16012. https://doi.org/10.1038/npjschz.2016.12
Pisanu C, Squassina A 2019. “Treatment-Resistant Schizophrenia: Insights From Genetic Studies and Machine Learning Approaches.” Frontiers in Pharmacology 10: 7.
Vivian-Griffiths T, Baker E, Schmidt KM. et al. (2019). Predictive modeling of schizophrenia from genomic data: Comparison of polygenic risk score with kernel support vector machines approach. American journal of medical genetics. Part B, Neuropsychiatric genetics : the official publication of the International Society of Psychiatric Genetics, 180(1), 80–85. https://doi.org/10.1002/ajmg.b.32705
Schwarze, K, Buchanan J, Taylor JC et al. 2018. “Are Whole-Exome and Whole-Genome Sequencing Approaches Cost-Effective? A Systematic Review of the Literature.” GENETICS in MEDICINE 20 (10): 9.
Monk B, Rajkovic A, Petrus S, et al. 2021. “A Machine Learning Method to Identify Genetic Variants Potentially Associated With Alzheimer’s Disease”, Frontiers in Genetics. doi: 10.3389/fgene.2021.647436
Zeng X. 2017. “Mobile Sensing Through Deep Learning.” Niagara Falls, 2. http://dx.doi.org/10.1145/3086467.3086476.
Kappes JR, Kirchhebner J, Huber DA, et al. 2021. “Self-Harm Among Forensic Psychiatric Inpatients With Schizophrenia Spectrum Disorders: An Explorative Analysis.” Int J Offender Ther Comp Criminology, December.
Ari B, Ari A, Sengur A. (2020). Suicide Prediction from Hemogram with Machine Learning. Avrupa Bilim ve Teknoloji Dergisi, (Special Issue), 364-369.
Torous J, Larsen ME, Depp C, et al.(2018). Smartphones, Sensors, and Machine Learning to Advance Real-Time Prediction and Interventions for Suicide Prevention: a Review of Current Progress and Next Steps. Current psychiatry reports, 20(7), 51. https://doi.org/10.1007/s11920-018-0914-y
Arenas-Castañeda PE, Aroca Bisquert F, Martinez-Nicolas I, et al. (2020). Universal mental health screening with a focus on suicidal behaviour using smartphones in a Mexican rural community: protocol for the SMART-SCREEN population-based survey. BMJ open, 10(7), e035041. https://doi.org/10.1136/bmjopen-2019-035041
Perez Arribas I, Goodwin GM, Geddes JR. et al. 2018). A signature-based machine learning model for distinguishing bipolar disorder and borderline personality disorder. Translational psychiatry, 8(1), 274. https://doi.org/10.1038/s41398-018-0334-0
Bayes, A., Spoelma, M. J., Hadzi-Pavlovic, D., & Parker, G. (2021). Differentiation of bipolar disorder versus borderline personality disorder: A machine learning approach. Journal of affective disorders, 288, 68–73. https://doi.org/10.1016/j.jad.2021.03.082
Fukazawa Y, Ito T, Okimura T, et al. (2019). Predicting anxiety state using smartphone-based passive sensing. Journal of biomedical informatics, 93, 103151. https://doi.org/10.1016/j.jbi.2019.103151
Kim IB, Park SC. (2021). Machine Learning-Based Definition of Symptom Clusters and Selection of Antidepressants for Depressive Syndrome. Diagnostics (Basel, Switzerland), 11(9), 1631. https://doi.org/10.3390/diagnostics11091631
Costa P.T., McCrae R.R. (1992) Revised NEO Per-sonality Inventory (NEO-PI-R) and NEO Five-Factor Inventory (NEO-FFI) ProfessionalManual, Odessa, FL, Psychological Assessment Resources.
Askland, K. D., Garnaat, S., Sibrava, N. J., Boisseau, C. L., Strong, D., Mancebo, M., Greenberg, B., Rasmussen, S., & Eisen, J. (2015). Prediction of remission in obsessive compulsive disorder using a novel machine learning strategy. International journal of methods in psychiatric research, 24(2), 156–169. https://doi.org/10.1002/mpr.1463
Abbas A, Hansen BJ, Koesmahargyo V, et al. (2022). Facial and Vocal Markers of Schizophrenia Measured Using Remote Smartphone Assessments: Observational Study. JMIR formative research, 6(1), e26276. https://doi.org/10.2196/26276
Koutsouleris N, Dwyer DB, Degenhardt F. et al. PRONIA Consortium (2021). Multimodal Machine Learning Workflows for Prediction of Psychosis in Patients With Clinical High-Risk Syndromes and Recent-Onset Depression. JAMA psychiatry, 78(2), 195–209. https://doi.org/10.1001/jamapsychiatry.2020.3604
Soyster PD, Ashlock L, Fisher AJ. Pooled and person-specific machine learning models for predicting future alcohol consumption, craving, and wanting to drink: A demonstration of parallel utility. Psychol Addict Behav. 2022 May;36(3):296-306. doi: 10.1037/adb0000666. Epub 2021 Apr 22. PMID: 35041441.
Lee J, Kim W. Prediction of Problematic Smartphone Use: A Machine Learning Approach. Int J Environ Res Public Health. 2021 Jun 15;18(12):6458. doi: 10.3390/ijerph18126458. PMID: 34203674; PMCID: PMC8296286.
Lauvsnes A, Langaas M, Toussaint P, et al. (2020). Mobile Sensing in Substance Use Research: A Scoping Review. Telemedicine journal and e-health : the official journal of the American Telemedicine Association, 26(10), 1191–1196. https://doi.org/10.1089/tmj.2019.0241
Berrouiguet S, Barrigón ML, Castroman JL. et al. (2019). Combining mobile-health (mHealth) and artificial intelligence (AI) methods to avoid suicide attempts: the Smartcrises study protocol. BMC psychiatry, 19(1), 277. https://doi.org/10.1186/s12888-019-2260-y
Chen M, Decary M. (2020). Artificial intelligence in healthcare: An essential guide for health leaders. Healthcare management forum, 33(1), 10–18. https://doi.org/10.1177/0840470419873123
Starke G, De Clercq E, Borgwardt S. et al. 2021. “Computing Schizophrenia: Ethical Challenges for Machine Learning in Psychiatry.” Psychological Medicine 51.
Mouchabac S, Leray P, Adrien V. et al. 2021. “Prevention of Suicidal Relapses in Adolescents With a Smartphone Application: Bayesian Network Analysis of a Preclinical Trial Using In Silico Patient Simulations.” J Med Internet Res. 23
Walsh T, Levy N, Bell G, et al. 2019. “The Effective and Ethical Development of Artificial Intelligence.” Australian Council of Learned Academies.
