Comparación de métodos predictivos de Machine Learning para diagnosticar los niveles de Trastorno por Déficit de Atención/Hiperactividad utilizando imágenes SPECT
DOI:
https://doi.org/10.33448/rsd-v11i8.31258Palabras clave:
Diagnóstico asistido por TDAH; Diagnóstico asistido por computadora; Aprendizaje automático; Medicina nuclear; SPECT.Resumen
El TDAH (trastorno por déficit de atención con hiperactividad) es un trastorno del neurodesarrollo caracterizado por niveles nocivos de falta de atención, desorganización y/o hiperactividad-impulsividad. En la infancia, estos síntomas a menudo se superponen con los de otros trastornos y tienden a persistir en la edad adulta, interfiriendo con las relaciones y la vida académica y laboral. El diagnóstico, tradicionalmente realizado valorando al paciente, es decir, testeando y escuchando a familiares y profesores, ya ha sido ayudado por la neuroimagen. Sin embargo, el análisis visual de tales imágenes para hacer un diagnóstico psiquiátrico es una tarea compleja y, a veces, lenta. Por esta razón, las herramientas de diagnóstico asistidas por computadora han evolucionado cada vez más y, cuando se combinan con técnicas de aprendizaje automático (ML), pueden acelerar, facilitar y maximizar la precisión de los diagnósticos. Sin embargo, la investigación que evalúa los modelos ML para clasificar el TDAH considerando la gravedad utilizando imágenes del cerebro SPECT (tomografía computarizada por emisión de fotón único) es todavía muy escasa. Por ello, este artículo tiene como objetivo evaluar el desempeño de los métodos ML: k-NN (k-Nearest Neighbors), Naive Bayes, Decision Tree, MLP (Multilayer Perceptron) y SVM (Support Vector Machine) en la clasificación del TDAH. El principal objetivo de este análisis es comprobar si los sujetos tienen el trastorno o no, y clasificar la gravedad de los que lo tienen mediante imágenes SPECT. Se creó una base de datos a partir de imágenes SPECT e informes de diagnóstico. Después de preprocesar estos datos, se buscaron, entrenaron/probaron y finalmente se compararon estadísticamente los mejores hiperparámetros para los métodos de ML. Los mejores resultados se obtuvieron con SVM y k-NN, con un 98% de precisión. Aunque el diagnóstico de TDAH por neuroimagen aún no es un procedimiento clínico estándar, argumentamos que este estudio puede contribuir a la investigación del diagnóstico de TDAH y apoyar métodos para el desarrollo de sistemas CAD (diagnóstico asistido por computadora).
Citas
Abdi, H., Williams, L. J., Beaton, D., Posamentier, M. T., Harris, T. S., Krishnand, A., Devous, M. D. (2012, January 01). Analysis of regional cerebral blood flow data to discriminate among Alzheimer's disease, frontotemporal dementia, and elderly controls: a multi-block barycentric discriminant analysis (MUBADA) methodology. Journal of Alzheimer's Disease: JAD, 31(3), 189-201.
Amen, D. (2012). Daniel Amen, MD: the impact of brain imaging on psychiatry and treatment for improving brain health and function. Interview by Karen Burnett. Alternative Therapies in Health and Medicine, 18(2), 52–58.
Amen, D., Sarabi, M., Willeumier, K., Taylor, D., Raji, C., Meysami, S., Raghavendra, C. (2017). Functional SPECT neuroimaging using machine learning algorithms distinguishes autism spectrum disorder from healthy subjects. Syst Integr Neurosci, 3(3), 1-9.
American Psychiatric Association. (2013). Diagnostic and Statistical Manual of Mental Disorders (DSM-5) (5th ed.). Arlington, VA: American Psychiatric Association.
Biederman, J., Petty, C. R., Woodworth, K. Y., Lomedico, A., Hyder, L. L., Faraone, S. V. (2012). Adult outcome of attention-deficit/hyperactivity disorder: a controlled 16-year follow-up study. The Journal of Clinical Psychiatry, 73(7), 941-950.
Bishop, C. M. (2006). Pattern Recognition and Machine Learning. New York, NY: Springer.
Cascianelli, S., Scialpi, M., Amici, S., Forini, N., Minestrini, M., Fravolini, M. L., Palumbo, B. (2017). Role of Artificial Intelligence Techniques (Automatic Classifiers) in Molecular Imaging Modalities in Neurodegenerative Diseases. Current Alzheimer research, 14(2), 198-207.
Castillo-Barnes, D., Martinez-Murcia, F. J., Ortiz, A., Salas-Gonzalez, D., RamÍrez, J., Górriz, J. M. (2020). Morphological Characterization of Functional Brain Imaging by Isosurface Analysis in Parkinson’s Disease. International Journal of Neural Systems, 30(9), p. 2050044.
Castillo-Barnes, D., Ramírez, J., Segovia, F., Martínez-Murcia, F. J., Salas-Gonzalez, D., Górriz, J. M. (2018, August 14). Robust Ensemble Classification Methodology for I123-Ioflupane SPECT Images and Multiple Heterogeneous Biomarkers in the Diagnosis of Parkinson's Disease. Frontiers in Neuroinformatics, 12, 53.
Cawley, G. C., Talbot, N. L. (2010). On over-fitting in model selection and subsequent selection bias in performance evaluation. The Journal of Machine Learning Research, 11, 2079-2107.
CDC. (2021a, July 15). Data and Statistics About ADHD. Retrieved from Centers for Disease Control and Prevention: https://www.cdc.gov/ncbddd/adhd/data.html
CDC. (2021b, July 15). What is ADHD? Retrieved from Center for Disease Control and Prevention: https://www.cdc.gov/ncbddd/adhd/facts.html
Chaves, R., Ramírez, J., Górriz, J., López, M., Salas-Gonzalez, D., Álvarez, I., Segovia, F. (2009, September 15). SVM-based computer-aided diagnosis of the Alzheimer's disease using t-test NMSE feature selection with feature correlation weighting. Neuroscience Letters, 461(3), 293-297.
Chawla, N. V., Bowyer, K. W., Hall, L. O., Kegelmeyer, W. P. (2002). Smote: synthetic minority over-sampling technique. Journal of Artificial Intelligence Research, 16(1), 321–357.
Danckaerts, M., Sonuga-Barke, E. J., Banaschewski, T., Buitelaar, J., Döpfner, M., Hollis, C., Coghill, D. (2010, February). The quality of life of children with attention deficit/hyperactivity disorder: a systematic review. Eur Child Adolesc Psychiatry, 19(2), 83-105.
De Silva, S., Dayarathna, S., Ariyarathne, G., Meedeniya, D., Jayarathna, S. (2019). A Survey of Attention Deficit Hyperactivity Disorder Identification Using Psychophysiological Data. International Journal of Online and Biomedical Engineering (iJOE), 61-76.
Demšar, J. (2006). Statistical comparisons of classifiers over multiple data sets. J Mach Learn Res, 7, 1-30.
Deshpande, G., Wang, P., Rangaprakash, D., Wilamowski, B. (2015). Fully Connected Cascade Artificial Neural Network Architecture for Attention Deficit Hyperactivity Disorder Classification from Functional Magnetic Resonance Imaging Data. IEEE Transactions on Cybernetics, 45(12), 2668-2679.
Du, J., Wang, L., Jie, B., Zhang, D. (2016, April 23). Network-based classification of ADHD patients using discriminative subnetwork selection and graph kernel PCA. Computerized Medical Imaging and Graphics : the Official Journal of the Computerized Medical Imaging Society, 52, pp. 82-88.
Dubreuil-Vall, L., Ruffini, G., Camprodon, J. A. (2020, April 9). Deep Learning Convolutional Neural Networks Discriminate Adult ADHD From Healthy Individuals on the Basis of Event-Related Spectral EEG. Frontiers in neuroscience, 14, p. 251.
Faceli, K., Lorena, A. C., Gama, J., De Carvalho, A. C. (2021). Inteligência Artificial: Uma Abordagem de Aprendizado de Máquina. Rio de Janeiro: LTC.
Fayyad, U., Piatetsky-Shapiro, G., Smyth, P. (1996). From Data Mining to Knowledge Discovery in Databases. AIMag, 17(3), 37.
Ferreira, L. K., Rondina, J. M., Kubo, R., Ono, C. R., Leite, C. C., Smid, J., Buchpiguel, C. A. (2017). Support vector machine-based classification of neuroimages in Alzheimer's disease: direct comparison of FDG-PET, rCBF-SPECT and MRI data acquired from the same individuals. Braz J Psychiatry, 40(2), 181-191.
Friedman, M. (1937). The use of ranks to avoid the assumption of normality implicit in the analysis of variance. J Am Stat Assoc, 32, 675-701.
García, S., Herrera, F. (2008). An extension on “Statistical comparisons of classifiers over multiple data sets” for all pairwise comparisons. J Mach Learn Res, 9, 2677-2694.
Ghiassian, S., Greiner, R., Jin, P., Brown, M. R. (2016). Using Functional or Structural Magnetic Resonance Images and Personal Characteristic Data to Identify ADHD and Autism. Plos One, 11(12), e0166934.
Goldberg, M., Mena, I., Miller, B. (1999, July 1). Frontal and temporal lobe dysfunction in autism and other related disorders: ADHD and OCD. Retrieved July 15, 2021, from http://www.alasbimnjournal.net/contenidos/frontal-and-temporal-lobe-dysfunction-in-autism-and-other-related-disorders-adhd-and-ocd-80
Goodfellow, I., bengio, Y., courville, A. (2016). Deep Learning. Cambridge, Massachusetts: The MIT Press.
Haller, S., Badoud, S., Nguyen, D., Garibotto, V., Lovblad, K., Burkhard, P. (2012, December). Individual detection of patients with Parkinson disease using support vector machine analysis of diffusion tensor imaging data: initial results. AJNR. American Journal of Neuroradiology, 33(11), 2123-2128.
Hao, A. J., He, B. L., Yin, C. H. (2015). Discrimination of ADHD children based on Deep Bayesian Network. IET International Conference on Biomedical Image and Signal Processing (ICBISP 2015), 1-6.
Höller, Y., Bathke, A. C., Uhl, A., Strobl, N., Lang, A., Bergmann, J., Staffen, W. (2017, September). Combining SPECT and Quantitative EEG Analysis for the Automated Differential Diagnosis of Disorders with Amnestic Symptoms. Front Aging Neurosci, 7(9), 290.
Horn, J., Habert, M., Kas, A., Malek, Z., Maksud, P., Lacomblez, L., Fertil, B. (2009, October). Differential automatic diagnosis between Alzheimer's disease and frontotemporal dementia based on perfusion SPECT images. Artificial Intelligence in Medicine, 47(2), 147-158.
Hsu, S. Y., Lin, H. C., Chen, T. B., Du, W. C., Hsu, Y. H., Wu, Y. C., Chen, H. Y. (2019). Feasible Classified Models for Parkinson Disease from 99mTc-TRODAT-1 SPECT Imaging. Sensors (Basel, Switzerland), 19(7), 1740.
Huang, G., Zhu, Q., Siew, C. (2006). Extreme learning machine: Theory and applications. Neurocomputing, 70, 489-501.
Huang, S. F., Wen, Y. H., Chu, C. H., Hsu, C. C. (2020). A Shape Approximation for Medical Imaging Data. Basel, Switzerland, 20(20), 5879.
Iannaccone, R., Hauser, T. U., Ball, J., Brandeis, D., Walitza, S., Brem, S. (2015). Classifying adolescent attentiondeficit/hyperactivity disorder (ADHD) based on functional and structural imaging. Eur Child Adolesc Psychiatry, 24(10), 1279-1289.
Illán, I. A., Gorrz, J. M., Ramirez, J., Segovia, F., Jimenez-Hoyuela, J. M., Ortega Lozano, S. J. (2012). Automatic assistance to Parkinson's disease diagnosis in DaTSCAN SPECT imaging. Medical physics, 39(10), 5971-5980.
Jales, R. L., Santos-Filho, S. D. (2020). Discussion of Review on Protocols Treatments of Arachnoid Cysts Explored by Nuclear Medicine. EC Clinical and Medical Case Reports 3.6, 147-152.
Jin, L., Zeng, Q., He, J., Feng, Y., Wu, Y. (2019, January 1). A ReliefF-SVM-based method for marking dopamine-based disease characteristics: A study on SWEDD and Parkinson’s disease. Behavioural Brain Research, 356(1), pp. 400-407.
Johnston, B. A., Mwangi, B., Matthews, K., Coghill, D., Konrad, K., Steele, J. D. (2014). Brainstem abnormalities in attention deficit hyperactivity disorder support high accuracy individual diagnostic classification. Hum Brain Mapp, 35, 5179-5189.
Kautzky, A., Vanicek, T., Philippe, C., Kranz, G. S., Wadsak, W., Mitterhauser, M., Lanzenberger, R. (2020, April 07). Machine learning classification of ADHD and HC by multimodal serotonergic data. Transl Psychiatry 10, p. 104.
Kaya, G. C., Pekcanlar, A., Bekis, R., Ada, E., Miral, S., Emiroğlu, N., Durak, H. (2002). Technetium-99m HMPAO brain SPECT in children with attention deficit hyperactivity disorder. Annals of Nuclear Medicine, 16(8), 527-531.
Kuang, D., Guo, X., An, X., Zhao, Y., He, L. (2014). Discrimination of ADHD Based on fMRI Data with Deep Belief Network. In C. Springer (Ed.), ICIC 2014: Intelligent Computing in Bioinformatics, (pp. 225-232).
Lazzaro, D., Montefusco, L. B. (2002). Radial basis functions for the multivariate interpolation of large scattered data sets. Journal of Computational and Applied Mathematics, 521-536.
Marras, C., Beck, J. C., Bower, J. H., Roberts, E., Ritz, B., Ross, G. W., Group, P. F. (2018, July 10). Prevalence of Parkinson’s disease across North America. NPJ Parkinson's Disease, p. 21.
Martinez-Murcia, F. J., Górriz, J. M., J., R., Illán, I. A., Segovia, F., Castillo-Barnes, D., Salas-Gonzalez, D. (2017, 14 November). Functional Brain Imaging Synthesis Based on Image Decomposition and Kernel Modeling: Application to Neurodegenerative Diseases. Frontiers in Neuroinformatics, 11, p. 65.
Mena G, I. (2009, July). Neurospect: Imagenología funcional em Psiquiatría. Alasbimn Journal, 11(45).
Mete, M., Sakoglu, U., Spence, J. S., Devous, M. D., Sr, H. T., Adinoff, B. (2017). Successful classification of cocaine dependence using brain imaging: a generalizable machine learning approach. BMC Bioinformatics, 17(13), 357.
Murphy, K. P. (2012). Machine Learning: a Probabilistic Perspective. Cambridge, Massachusetts: MIT Press.
Murphy, K. P. (2022). Probabilistic Machine Learning: An introduction. Cambridge, Massachusetts: MIT Press.
Nemenyi, P. B. (1963). Distribution-free Multiple Comparisons. PhD thesis, Princeton University.
Nicastro, N., Wegrzyk, J., Preti, M. G., Fleury, V., Van de Ville, D., Garibotto, V., Burkhard, P. R. (2019). Classification of degenerative parkinsonism subtypes by support-vector-machine analysis and striatal 123I-FP-CIT indices. Journal of Neurology, 266, 1771-1781.
Oliveira, F. P., Castelo-Branco, M. (2015). Computer-aided diagnosis of Parkinson's disease based on [(123)I]FP-CIT SPECT binding potential images, using the voxels-as-features approach and support vector machines. J Neural Eng, 12(2).
Oliveira, F. P., Faria, D. B., Costa, D. C., Castelo-Branco, M., Tavares, J. M. (2018, June). Extraction, selection and comparison of features for an effective automated computer-aided diagnosis of Parkinson's disease based on [123I]FP-CIT SPECT images. Eur J Nucl Med Mol Imaging, 45(6), 1052-1062.
Olson, D., Delen, D. (2008). Advanced Data Mining Techniques. Springer.
O'Malley, J. P., Ziessman, H. A., Thrall, J. H. (2020). Nuclear Medicine and Molecular Imaging: The Requisites (5th ed.). Elsevier Health Sciences.
Padilla, P., López, M., Górriz, J. M., Ramírez, J., Salas-González, D., Álvarez, I. (2012). NMF-SVM Based CAD Tool Applied to Functional Brain Images for the Diagnosis of Alzheimer's Disease. IEEE Transactions on Medical Imaging, 31(2), 207-216.
Palumbo, B., Fravolini, M. L., Buresta, T., Pompili, F., Forini, N., Nigro, P., Tambasco, N. (2014, December). Diagnostic accuracy of Parkinson disease by support vector machine (SVM) analysis of 123I-FP-CIT brain SPECT data: implications of putaminal findings and age. Medicine, 93(27), e228.
Peng, X., Lin, P., Zhang, T., Wang, J. (2013). Extreme learning machine-based classification ofADHD using brain structural MRI data. Plos One, 8(11), 1-12.
Prashanth, R., Dutta Roy, S., Mandal, P. K., Ghosh, S. (2016, June). High-Accuracy Detection of Early Parkinson's Disease through Multimodal Features and Machine Learning. Int J Med Inform, 90, 13-21.
Pulini, A. A., Kerr, W. T., Loo, S. K., Lenartowicz, A. (2019). Classification accuracy of neuroimaging biomarkers in attention-deficit/hyperactivity disorder: effects ofsample size and circular analysis. Biological psychiatry. Cognitive Neuroscience and Neuroimaging, 4(2), 108–120.
Qureshi, M., Oh, J., Min, B., Jo, H. J., Lee, B. (2017). Multi-modal, Multi-measure, and Multi-class Discrimination of ADHD with Hierarchical Feature Extraction and Extreme Learning Machine Using Structural and Functional Brain MRI. Frontiers in Human Neuroscience, 11, 157.
Rondina, J. M., Ferreira, L., de Souza Duran, F. L., Kubo, R., Ono, C., Leite, C. C., Busatto, G. F. (2017, November). Selecting the most relevant brain regions to discriminate Alzheimer's disease patients from healthy controls using multiple kernel learning: A comparison across functional and structural imaging modalities and atlases. Neuroimage Clin, 9(17), 628-641.
Salas-Gonzalez, D., Segovia, F., Martínez-Murcia, F. J., Lang, E., Gorriz, J., Ramırez, J. (2016, January 01). An Optimal Approach for Selecting Discriminant Regions for the Diagnosis of Alzheimer's Disease. Current Alzheimer Research, pp. 838-844.
Santra, A., Kumar, R. (2014, Oct-Dec). Brain perfusion single photon emission computed tomography in major psychiatric disorders: From basics to clinical practice. Indian J Nucl Med, 29(4), 210–221.
Segovia, F., Górriz, J. M., Ramírez, J., Martínez-Murcia, F. J., Castillo-Barnes, D. (2019). Assisted Diagnosis of Parkinsonism Based on the Striatal Morphology. International Journal of neural systems, 29(9).
Segovia, F., Górriz, J. M., Ramírez, J., Salas-González, D., Álvarez, I., López, M., Padilla, P. (2010, April 19). Classification of functional brain images using a GMM-based multi-variate approach. Neuroscience Letters, 474(1), 58–62.
Sen, B., Borle, N. C., Greiner, R., Brown, M. R. (2018). A general prediction model for the detection of ADHD and Autism using structural and functional MRI. Plos One, 13(4).
Shiiba, T., Arimura, Y., Nagano, M., Takahashi, T., Takaki, A. (2020). Improvement of classification performance of Parkinson's disease using shape features for machine learning on dopamine transporter single photon emission computed tomography. Plos One, 15(1).
Tagare, H., DeLorenzo, C., Chelikani, S., Saperstein, L., Fulbright, R. K. (2017, May). Voxel-based logistic analysis of PPMI control and Parkinson's disease DaTscans. Neuroimage, 15(152), 299-311.
Vázquez-Abad, F. J., Bernabel, S., Dufresne, D., Sood, R., Ward, T., Amen, D. (2020). Deep Learning for Mental Illness Detection Using Brain SPECT Imaging. Medical Imaging and Computer-Aided Diagnosis (pp. 17-26). Singapore: Springer.
Wilcox, R. (2017). Introduction to Robust Estimation and Hypothesis Testing (4th ed.). London: Academic Press.
Witten, I. H., Frank, E., Hall, M. A. (2011). Data Mining: Practical machine Learning Tools and Techniques (3rd ed.). Amsterdam: Morgan Kaufmann Series in Data Management Systems Morgan Kaufmann.
Xu, J., Kochanek, K. D., Sherry, L., Murphy, B. S., Tejada-Vera, B. (2010, May). Deaths: final data for 2007. National vital statistics reports : from the Centers for Disease Control and Prevention, National Center for Health Statistics, National Vital Statistics System, 58(19), 1-19.
Zhang-James, Y., Helminen, E. C., Liu, J., Franke, B., Hoogman, M., Faraone, S. V. (2020). Machine Learning Classification of Attention-Deficit/Hyperactivity Disorder Using Structural MRI Data. bioRxiv.
Zimmermann, R. (2017). Nuclear Medicine: Radioactivity for Diagnosis and Therapy (2nd ed.). EDP Sciences.
Zou, L., Zheng, J., Miao, C., McKeown, M. J., Wang, Z. J. (2017). 3D CNN Based Automatic Diagnosis of Attention Deficit Hyperactivity Disorder Using Functional and Structural MRI. IEEE Access, 5, 23626–23636.
Descargas
Publicado
Cómo citar
Número
Sección
Licencia
Derechos de autor 2022 Marcilio de Oliveira Meira; Anne Magaly de Paula Canuto; Bruno Motta de Carvalho; Roberto Levi Cavalcanti Jales
Esta obra está bajo una licencia internacional Creative Commons Atribución 4.0.
Los autores que publican en esta revista concuerdan con los siguientes términos:
1) Los autores mantienen los derechos de autor y conceden a la revista el derecho de primera publicación, con el trabajo simultáneamente licenciado bajo la Licencia Creative Commons Attribution que permite el compartir el trabajo con reconocimiento de la autoría y publicación inicial en esta revista.
2) Los autores tienen autorización para asumir contratos adicionales por separado, para distribución no exclusiva de la versión del trabajo publicada en esta revista (por ejemplo, publicar en repositorio institucional o como capítulo de libro), con reconocimiento de autoría y publicación inicial en esta revista.
3) Los autores tienen permiso y son estimulados a publicar y distribuir su trabajo en línea (por ejemplo, en repositorios institucionales o en su página personal) a cualquier punto antes o durante el proceso editorial, ya que esto puede generar cambios productivos, así como aumentar el impacto y la cita del trabajo publicado.
