A Multicriteria Model Applied in the Diagnosis of Alzheimer's Disease: A Bayesian Network

Pinheiro, Plácido Rogério; Castro, Ana Karoline Araújo de; Pinheiro, Mirian Calí­ope Dantas

doi:10.1109/cse.2008.44

Cited by 34 publications

(16 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…They used a maximum a posteriori decision rule to assign the feature vectors to normal and AD groups and reported 98.33% and 93.41% accuracy rate for PET and SPECT images, respectively. The Bayesian network, a probabilistic graphical model representing the variables and their dependences using a directed acyclic graph, is used by Pinheiro et al (2008) for the diagnosis of AD. The direction of the arcs between the variables represents the consequence-cause between the variables.…”

Section: Probabilistic Methodsmentioning

confidence: 99%

Imaging and machine learning techniques for diagnosis of Alzheimer’s disease

Mirzaei

Adeli

2016

Reviews in the Neurosciences

109

View full text Add to dashboard Cite

AbstractAlzheimer’s disease (AD) is a common health problem in elderly people. There has been considerable research toward the diagnosis and early detection of this disease in the past decade. The sensitivity of biomarkers and the accuracy of the detection techniques have been defined to be the key to an accurate diagnosis. This paper presents a state-of-the-art review of the research performed on the diagnosis of AD based on imaging and machine learning techniques. Different segmentation and machine learning techniques used for the diagnosis of AD are reviewed including thresholding, supervised and unsupervised learning, probabilistic techniques, Atlas-based approaches, and fusion of different image modalities. More recent and powerful classification techniques such as the enhanced probabilistic neural network of Ahmadlou and Adeli should be investigated with the goal of improving the diagnosis accuracy. A combination of different image modalities can help improve the diagnosis accuracy rate. Research is needed on the combination of modalities to discover multi-modal biomarkers.

show abstract

Section: Probabilistic Methodsmentioning

confidence: 99%

Imaging and machine learning techniques for diagnosis of Alzheimer’s disease

Mirzaei

Adeli

2016

Reviews in the Neurosciences

109

View full text Add to dashboard Cite

show abstract

“…For example, BNs allow users to handle the criteria as uncertain and facilitate linking them with each other when the corresponding real world dependence actually exists (Fenton and Neil, 2001). Despite these positive attributes and BN MCDA frameworks suggested by Watthayu and Peng (2004) and Sedki et al (2010), we managed to find only two actual published management applications (Dorner et al, 2007;Pinheiro et al, 2008) by using the keywords BNs and MCDA.…”

Section: Bns and Influence Diagramsmentioning

confidence: 96%

Evaluating the impact of nutrient abatement measures on the ecological status of coastal waters: a Bayesian network for decision analysis

Lehikoinen

Helle

Klemola

et al. 2014

IJMCDM

View full text Add to dashboard Cite

Environmental managers must make decisions about complex problems that have a high degree of uncertainty such as, which nutrient abatement measure optimally improves the condition of an ecosystem. Although data and models that provide information on this subject exist, their knowledge may be fragmentary and difficult to interpret. We present a user-friendly modelling tool that integrates results of different models and data-analyses. It can be used by decision-makers for assessing the probabilities of different nutrient abatement scenarios for achieving specific targets set by the Water Framework Directive for Finnish coastal waters in the Gulf of Finland. The results suggest that significant reductions in nutrient loads are required to achieve good ecological status in Finnish coastal waters, and in the event of increased precipitation these targets may be less likely to be attained. Moreover, different approaches to the status classification lead to very different conclusions. Evaluating the impact of nutrient abatement measures 115

show abstract

“…A hybrid model combining Multicriteria Decision Aiding) (MCDA) and Bayesian Network (BN) has been proposed by [10] with a ranking model based on MCDA and BN for aiding the diagnosis of AD. Their model indicates which assessment patient items have the highest impact for determining the AD diagnosis.…”

Section: Related Workmentioning

confidence: 99%

New Approach for Clinical Decision Support System of Alzheimer’s Disease Diagnosis

Maâtar¹,

Abdelmoula²,

Masmoudi³

2019

IJCA

View full text Add to dashboard Cite

Alzheimer's disease is a chronic dementia. It destroys gradually the memory and get worse over time. The diagnosis of AD is generally made very late. The great challenge is reaching an early and accurate diagnosis. In this case, a Clinical Decision Support System (CDSS) to help physicians diagnose AD and related disorders: mild cognitive impairment (MCI) and Dementia (D) is proposed. The originality of the idea is that many parameters are included such as cognitive test scores, neurological, biological, clinical and demographic data and this is in order to carry on the most accurate diagnosis for every subject. The Support Vector Machine showed that the proposed CDSS decision model achieves good performance.

show abstract

A Multicriteria Model Applied in the Diagnosis of Alzheimer's Disease: A Bayesian Network

Cited by 34 publications

References 21 publications

Imaging and machine learning techniques for diagnosis of Alzheimer’s disease

Imaging and machine learning techniques for diagnosis of Alzheimer’s disease

Evaluating the impact of nutrient abatement measures on the ecological status of coastal waters: a Bayesian network for decision analysis

New Approach for Clinical Decision Support System of Alzheimer’s Disease Diagnosis

Contact Info

Product

Resources

About