Review of Machine Learning Algorithms for Diagnosing Mental Illness
2
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
ObjectiveaaEnhanced technology in computer and internet has driven scale and quality of data to be improved in various areas including healthcare sectors. Machine Learning (ML) has played a pivotal role in efficiently analyzing those big data, but a general misunderstanding of ML algorithms still exists in applying them (e.g., ML techniques can settle a problem of small sample size, or deep learning is the ML algorithm). This paper reviewed the research of diagnosing mental illness using ML algorithm and suggests how ML techniques can be employed and worked in practice. MethodsaaResearches about mental illness diagnostic using ML techniques were carefully reviewed. Five traditional ML algorithms-Support Vector Machines (SVM), Gradient Boosting Machine (GBM), Random Forest, Naïve Bayes, and K-Nearest Neighborhood (KNN)-frequently used for mental health area researches were systematically organized and summarized. ResultsaaBased on literature review, it turned out that Support Vector Machines (SVM), Gradient Boosting Machine (GBM), Random Forest, Naïve Bayes, and K-Nearest Neighborhood (KNN) were frequently employed in mental health area, but many researchers did not clarify the reason for using their ML algorithm though every ML algorithm has its own advantages. In addition, there were several studies to apply ML algorithms without fully understanding the data characteristics. ConclusionaaResearchers using ML algorithms should be aware of the properties of their ML algorithms and the limitation of the results they obtained under restricted data conditions. This paper provides useful information of the properties and limitation of each ML algorithm in the practice of mental health.
Abstract
ObjectiveaaEnhanced technology in computer and internet has driven scale and quality of data to be improved in various areas including healthcare sectors. Machine Learning (ML) has played a pivotal role in efficiently analyzing those big data, but a general misunderstanding of ML algorithms still exists in applying them (e.g., ML techniques can settle a problem of small sample size, or deep learning is the ML algorithm). This paper reviewed the research of diagnosing mental illness using ML algorithm and suggests how ML techniques can be employed and worked in practice. MethodsaaResearches about mental illness diagnostic using ML techniques were carefully reviewed. Five traditional ML algorithms-Support Vector Machines (SVM), Gradient Boosting Machine (GBM), Random Forest, Naïve Bayes, and K-Nearest Neighborhood (KNN)-frequently used for mental health area researches were systematically organized and summarized. ResultsaaBased on literature review, it turned out that Support Vector Machines (SVM), Gradient Boosting Machine (GBM), Random Forest, Naïve Bayes, and K-Nearest Neighborhood (KNN) were frequently employed in mental health area, but many researchers did not clarify the reason for using their ML algorithm though every ML algorithm has its own advantages. In addition, there were several studies to apply ML algorithms without fully understanding the data characteristics. ConclusionaaResearchers using ML algorithms should be aware of the properties of their ML algorithms and the limitation of the results they obtained under restricted data conditions. This paper provides useful information of the properties and limitation of each ML algorithm in the practice of mental health.
참고문헌 (43)
- Ozgur C, "Selection of Statistical Software for Solving Big Data Problems: A Guide for Businesses, Students, and Universities", pp.1~12 (2015), SAGE Open
- "OECD What is PISA?"[URL]
- McAfee A, "Big data : the management revolution", Harv Bus Rev, 90, pp.60~66 (2012)
- Sagiroglu S, "Big Data: A Review", IEEE Int Conf Collab Technol Syst (CTS), pp.42~47 (2013)
- Kruse CS, "Challenges and opportunities of big data in health care : a systematic review", JMIR Med Inform, 4, pp.e38~ (2016)
- "Facebook processes more than 500 TB of data daily"[URL]
- "5 Billion Pieces of Content And 500+ Terabytes Ingested Every Day; How Big Is Facebook’s Data?"[URL]
- "Big Data in Healthcare Hype and Hope"[URL]
- Goense J, "fMRI at High Spatial Resolution : Implications for BOLD-Models", Front Comput Neurosci, 10, pp.66~ (2016)
- Nuwer MR, "The development of EEG brain mapping", J Clin Neurophysiol, 7, pp.459~471 (1990)
- Turing AM, "Parsing the Turing Test. 1", pp.23~65 (2009), Springer
- Kohavi R, "Glossary of terms", Mach Learn, 30, pp.271~274 (1998)
- Zhou L, "Machine learning on big data : opportunities and challenges", Neurocomputing, 237, pp.350~361 (2017)
- Mullainathan S, "Machine learning : an applied econometric approach", J Econ Perspect, 31, pp.87~106 (2017)
- Obermeyer Z, "Predicting the future—big data, machine learning, and clinical medicine", N Engl J Med, 375, pp.1216~1219 (2016)
- Tsai CW, "Big data analytics : a survey", J Big Data, 2, pp.1~32 (2015)
- Kaura P, "Big data and machine learning based secure healthcare framework", Procedia Comput Sci, 132, pp.1049~1059 (2018)
- "AlphaGo seals 4-1 victory over Go grandmaster Lee sedol"[URL]
- Zhang GP, "Avoiding pitfalls in neural network research", IEEE Trans Syst Man Cybern C Appl Rev, 37, pp.3~16 (2007)
- Makridakis S, "Statistical and machine learning forecasting methods : concerns and ways forward", PLoS ONE, 13, pp.e0194889~ (2018)
- Hearst MA, "Support vector machines", IEEE Intell Syst Appl, 13, pp.18~28 (1998)
- Friedman JH, "Greedy function approximation : a gradient boosting machine", Ann Stat, 29, pp.1189~1232 (2001)
- Liaw A, "Classification and regression by RandomForest", R News, 2, pp.18~22 (2002)
- Rish I, "An empirical study of the naive Bayes classifier", IJCAI 2001 Work Empir Methods Artif Intell, 3, pp.41~46 (2001)
- Cover T, "Nearest neighbor pattern classification", IEEE Trans Inf Theory, 13, pp.21~27 (1967)
- Duan KB, "Which Is the Best Multiclass SVM Method? An Empirical Study", Multiple Classifier Systems. MCS 2005. Lecture Notes in Computer Science, 3541, pp.278~285 (2005), Springer
- Khoshgoftaar TM, "An empirical study of learning from imbalanced data using random forest", ICTAI 2007, 2, pp.310~317 (2007)
- Lin Y, "Random forests and adaptive nearest neighbors", J Am Stat Assoc, 101, pp.578~590 (2006)
- Mason L, "Boosting algorithms as gradient descent", Adv Neural Inf Process Syst, pp.512~518 (2000)
- Schapire RE, "Nonlinear Estimation and Classification. Lecture Notes in Statistics, vol 171", pp.149~171 (2003), Springer
- Augsburger M, "When do traumatic experiences alter risktaking behavior? A machine learning analysis of reports from refugees", PLoS ONE, 12, pp.e0177617~ (2017)
- Galatzer-Levy IR, "Utilization of machine learning for prediction of post-traumatic stress : a re-examination of cortisol in the prediction and pathways to non-remitting PTSD", Transl Psychiatry, 7, pp.e0~ (2017)
- Karstoft KI, "Bridging a translational gap : using machine learning to improve the prediction of PTSD", BMC Psychiatry, 15, pp.30~ (2015)
- Schnack HG, "Can structural MRI aid in clinical classification? A machine learning study in two independent samples of patients with schizophrenia, bipolar disorder and healthy subjects", Neuroimage, 84, pp.299~306 (2014)
- Greenstein D, "Using multivariate machine learning methods and structural MRI to classify childhood onset schizophrenia and healthy controls", Front Psychiatry, 3, pp.53~ (2012)
- Malley JD, "Probability machines : consistent probability estimation using nonparametric learning machines", Methods Inf Med, 51, pp.74~81 (2012)
- Malley JD, "Statistical Learning for Biomedical Data" (2011), Cambridge University Press
- Yang H, "A hybrid machine learning method for fusing fMRI and genetic data : combining both improves classification of schizophrenia", Front Hum Neurosci, 4, pp.192~ (2010)
- Chekroud AM, "Cross-trial prediction of treatment outcome in depression : a machine learning approach", Lancet Psychiatry, 3, pp.243~250 (2016)
- Nakai Y, "Detecting abnormal word utterances in children with autism spectrum disorders : machine-learning-based voice analysis versus speech therapists", Percept Mot Skills, 124, pp.961~973 (2017)
- Maenner MJ, "Development of a Machine Learning Algorithm for the Surveillance of Autism Spectrum Disorder", PLoS ONE, 11, pp.e0168224~ (2016)
- Bosl W, "EEG complexity as a biomarker for autism spectrum disorder risk", BMC Med, 9, pp.18~ (2011)