Diagnosis of Cognitive Impairment Compatible with Early Diagnosis of Alzheimer’s Disease

Summary

Background: Early detection of Alzheimer’s disease (AD) has become one of the principal focuses of research in medicine, particularly when the disease is incipient or even prodromic, because treatments are more effective in these stages. Lexical-semantic- conceptual deficit (LSCD) in the oral definitions of semantic categories for basic objects is an important early indicator in the evaluation of the cognitive state of patients. Objectives: The objective of this research is to define an economic procedure for cognitive impairment (CI) diagnosis, which may be associated with early stages of AD, by analysing cognitive alterations affecting declarative semantic memory. Because of its low cost, it could be used for routine clinical evaluations or screenings, leading to more expensive and selective tests that confirm or rule out the disease accurately. It should necessarily be an explanatory procedure, which would allow us to study the evolution of the disease in relation to CI, the irregularities in different semantic categories, and other neurodegenerative diseases. On the basis of these requirements, we hypothesise that Bayesian networks (BNs) are the most appropriate tool for this purpose. Methods: We have developed a BN for CI diagnosis in mild and moderate AD patients by analysing the oral production of semantic features. The BN causal model represents LSCD in certain semantic categories, both of living things (dog, pine, and apple) and non-living things (chair, car, and trousers), as symptoms of CI. The model structure, the qualitative part of the model, uses domain knowledge obtained from psychology experts and epidemiological studies. Further, the model parameters, the quantitative part of the model, are learnt automatically from epidemiological studies and Peraita and Grasso’s linguistic corpus of oral definitions. This corpus was prepared with an incidental sampling and included the analysis of the oral linguistic production of 81 participants (42 cognitively healthy elderly people and 39 mild and moderate AD patients) from Madrid region’s hospitals. Experienced neurologists diagnosed these cases following the National Institute of Neurological and Communicative Disorders and Stroke/Alzheimer’s Disease and Related Disorders Association (NINCDSADRDA)’s Alzheimer’s criteria, performing, among other explorations and tests, a minimum neuropsychological exploration that included the Mini-Mental State Examination test. Results: BN’s classification performance is remarkable compared with other machine learning methods, achieving 91% accuracy and 94% precision in mild and moderate AD patients. Apart from this, the BN model facilitates the explanation of the reasoning process and the validation of the conclusions and allows the study of uncommon declarative semantic memory impairments. Conclusions: Our method is able to analyse LSCD in a wide set of semantic categories throughout the progression of CI, being a valuable first screening method in AD diagnosis in its early stages. Because of its low cost, it can be used for routine clinical evaluations or screenings to detect AD in its early stages. Besides, due to its knowledge-based structure, it can be easily extended to provide an explanation of the diagnosis and to the study of other neurodegenerative diseases. Further, this is a key advantage of BNs over other machine learning methods with similar performance: it is a recognisable and explanatory model that allows one to study irregularities in different semantic categories.

Keywords

Bayesian networks - cognitive impairment - Alzheimer’s disease - neurodegenerative diseases - cognitive impairment of semantic content - linguistic corpus of oral definitions - lexical-semantic-conceptual deficit

• References

• 1 Nordberg A, Carter SF, Rinne J, Drzezga A, Brooks DJ, Vandenberghe R. et al. A European multicentre PET study of fibrillar amyloid in Alzheimer’s disease. Eur J Nucl Med Mol Imaging 2013; 40 (Suppl. 01) 104-114.
• 2 Johnson KA, Minoshima S, Bohnen NI, Donohoe KJ, Rowe CC, Carrillo MC. et al. Appropriate Use Criteria for Amyloid PET: A Report of the Amyloid Imaging Task Force, the Society of Nuclear Medicine and Molecular Imaging, and the Alzheimer’s Association. Alzheimers Dement 2013; 9 (Suppl. 01) 1-16.
• 3 Hu WT, Holtzman DM, Fagan AM, Shaw LM, Perrin R, Arnold SE. et al. Plasma multianalyte profiling in mild cognitive impairment and Alzheimer disease. Neurology 2012; 79 (Suppl. 09) 897-905.
• 4 Maddalena A, Papassotiropoulos A, Jung HH, Müller-Tillmanns B, Hegi T, Nitsch RM. et al. Biochemical Diagnosis of Alzheimer Disease by Measuring the Cerebrospinal Fluid Ratio of Phosphorylated tau Protein toAmyloid Peptide42. JAMA 2003; 60: 1202-1206.
• 5 Peña-Casanova J. Enfermedad de Alzheimer. Del diagnóstico a la terapia: conceptos y hechos. Fundación la Caixa. 1999 Available from: http://www.fundacio1.lacaixa.es/webflc/wip0icop.nsf/vico/LibroAlz1_esp.pdf/$file/LibroAlz1_esp.pdf
• 6 Domínguez-Orozco ME. Social-healthcare coordination and integral evaluation in dementia: The role of alzheimer family associations. Papeles del Psicólogo 2013; 34 (Suppl. 02) 123-131.
• 7 McRae K, Cree GS, Seidenberg MS, McNorgan C. Semantic feature production norms for a large set of living and nonliving things. Behav Res Methods 2005; 37 (Suppl. 04) 547-559.
• 8 Capitani E, Laiacona M, Mahon B, Caramazza A. What are the facts of semantic category-specific deficits? A critical review of the clinical evidence. Cogn Neuropsychol 2003; 20 (Suppl. 03) 213-261.
• 9 Rogers TT, Plaut DC. Connectionist perspectives on category-specific deficits. In: Forde E, Humphreys G. (eds.). Category Specificity in Brain and Mind. East Sussex, England: Psychology Press; 2002. pp 251-290.
• 10 Garrard P, Rentoumi V, Gesierich B, Miller B, Gorno-Tempini ML. Machine learning approaches to diagnosis and laterality effects in semantic. Cortex 2014; 55: 122-129.
• 11 Orimaye SO, Wong JSM, Golden KJ. Learning Predictive Linguistic Features for Alzheimer’s Disease and related Dementias using Verbal Utterances. Workshop on Computational Linguistics and Clinical Psychology: From Linguistic Signal to Clinical Reality. Baltimore, Maryland USA: 2014. pp 78-87.
• 12 Williams JA, Weakley A, Cook DJ, SchmitterEdgecombe M. Machine Learning Techniques for Diagnostic Differentiation of Mild Cognitive Impairment and Dementia. In: Expanding the Boundaries of Health Informatics using Artificial Intelligence. Papers from AAAI 2013 Workshop. Bellevue, Washington: 2013. pp 71-76.
• 13 Seixas FL. et al. A Bayesian network decision model for supporting the diagnosis of dementia, Alzheimer’s disease and mild cognitive impairment. Computers in Biology and Medicine 2014; 51 (Suppl. 00) 140-158.
• 14 Sun Y. et al. Diagnose the mild cognitive impairment by constructing Bayesian network with missing data. Expert Systems with Applications 2011; 38 (Suppl. 01) 442-449.
• 15 Evanthia E, Tripoliti DI. A supervised method to assist the diagnosis of Alzheimer’s Disease. Proceedings of the 29th Annual International Conference of the IEEE EMBS: 3426–3429. Lyon: 2007
• 16 Chen R, Herskovits EH. Machine-learning techniques for building a diagnostic model for very mild dementia. Neuroimage 2010; 52 (Suppl. 01) 234-244.
• 17 Matic A, Mehta P, Rehg JM, Osmani V, Mayora O. Monitoring Dressing Activity Failures through RFID and Video. Methods Inf Med 2012; 51 (Suppl. 01) 45-54.
• 18 Kearns WD, Nams VO, Fozard JL. Tortuosity in Movement Paths Is Related to Cognitive Impairment. Methods Inf Med 2010; 6 (Suppl. 49) 592-598.
• 19 Peraita H, Grasso L. Corpus lingüístico de definiciones de categorías semánticas de personas mayores sanas y con la enfermedad de Alzheimer Una investigación transcultural hispano-argentina. Fundación BBVA. 2010 Available from: http://www.fbbva.es/TLFU/dat/DT%203_2010_corus%20linguistico_peraita_web.pdf
• 20 Fernández-Martínez M, Castro-Flores J, Pérez-delas-Heras S, Mandaluniz-Lekumberri A, Gordejuela M, Zarranz J. Prevalencia de la demencia en mayores de 65 años en una comarca del País Vasco. Rev Neurol 2008; 46 (Suppl. 02) 89-96.
• 21 Project Elvira, UNED.. Available from: http://www.ia.uned.es/~elvira/index-en.html
• 22 Folstein M, Folstein S, McHugh P. “Mini-Mental State” a Practical Method for Grading the Cognitive State of Patients for the Clinician. J Psychiatr Res 1975; 12 (Suppl. 03) 189-198.
• 23 European Commission Report.. Alzheimer disease and other dementias. 2013 From: http://ec.europa.eu/health/major_chronic_diseases/diseases/alzheimer/index_en.htm
• 24 Alzheimer’s Association (USA) Report.. 2013 Alzheimer Disease Facts and Figures, 2013. Available from: http://www.alz.org/downloads/facts_figures_2013.pdf
• 25 Stern Y, Gurland B, Tatemichi TK, Xin-Tang M, Wilder D, Richard M. Influence of Education and Occupation on the Incidence of Alzheimer’s Disease. JAMA 1994; 271 (Suppl. 13) 1004-1010.
• 26 Bentler P. Multivariate Analysis with Latent Variables. Annu Rev Psychol 1980; 31: 419-456.
• 27 Bollen KA. Latent variables in psychology and the social sciences. Annu Rev Psychol 2002; 53: 605-634.
• 28 Guerrero JM, Martínez-Tomás R, Rincón M. Clustering of semantic variables for early diagnosis of cognitive impairment. 1st Internacional Workshop on Artificial Intelligence in Healthcare and Biomedical. Tenerife. 2011 Available from: http://perseo.inf.um.es/~aike/aihealth11/Proceedings/caepia2011_153.pdf
• 29 Guerrero JM. Aportaciones desde la Psicología Cognitiva y la Inteligencia Artificial al diagnóstico de la enfermedad de Alzheimer. Tesis doctoral, UNED, Departamento de Inteligencia Artificial Madrid: 2013 Available from: http://espacio.uned.es/fez/eserv.php?pid=tesisuned:IngInf-Jmguerrero&dsID=Documento.pdf
• 30 Witten IH, Frank E, Hall MA. Data Mining. Practical Machine Learning Tools and Techniques (3rd ed.). New York: Morgan Kaufmann; 2011
• 31 Fawcett T. ROC Graphs: Notes and Practical Considerations for Researchers. Notes and Practical Considerations for researchers, HP Laboratories, 1501 Page Mill Road Palo Alto: 2004