Generalizability of the Disease State Index Prediction Model for Identifying Patients Progressing from Mild Cognitive Impairment to Alzheimer's Disease

Hall, Anette; Muñoz‐Ruiz, Miguel; Mattila, Jussi; Koikkalainen, Juha; Tsolaki, Magda; Mecocci, Patrizia; Kłoszewska, Iwona; Vellas, Bruno; Lovestone, Simon; Visser, Pieter Jelle; Lötjönen, Jyrki

doi:10.3233/jad-140942

Cited by 33 publications

(32 citation statements)

References 45 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The AUCs ranged from 0.68 to 0.78 in the four cohorts. The Disease State Index is the only model which has been validated externally for predicting conversion from MCI to AD 7. The model performed well in all the four cohorts (AUC range 0.74–0.82) as well as the combined cohort (AUC 0.76).…”

Section: Discussionmentioning

confidence: 99%

Models for predicting risk of dementia: a systematic review

Hou

Feng

Zhang

et al. 2018

J Neurol Neurosurg Psychiatry

120

146

View full text Add to dashboard Cite

show abstract

Section: Discussionmentioning

confidence: 99%

Models for predicting risk of dementia: a systematic review

Hou

Feng

Zhang

et al. 2018

J Neurol Neurosurg Psychiatry

120

146

View full text Add to dashboard Cite

show abstract

“…16,[41][42][43][44][45] Paradoxalmente, estudos longitudinais de DCL/ DA-prodrómica demonstram que o MMSE contribui para prever o declínio progressivo e a evolução para demência quando associado a marcadores biológicos como a ressonância magnética 46 ou os biomarcadores do LCR. 47 Além disso, este instrumento continua a ser utilizado como crité-rio praticamente universal de gravidade ou estadiamento, para inclusão de doentes em ensaios clínicos. 48 Em Portugal, a actualidade deste estudo justifica-se pela proposta de pontuações de corte mais exigentes, de acordo com os estudos de Morgado et al 13 e de Freitas et al 14 De salientar que neste último estudo os autores já não incluíram iliteratos, uma opção que também se baseou na sua reduzida representatividade na sociedade actual.…”

Section: Discussionunclassified

Mini-Mental State Examination: Avaliação dos Novos Dados Normativos no Rastreio e Diagnóstico do Défice Cognitivo

et al. 2016

View full text Add to dashboard Cite

RESUMOIntrodução: O Mini-Mental State Examination é o teste de rastreio de défice cognitivo/demência mais difundido. No nosso país têm-se utilizado pontuações de corte definidas por grupos de literacia, mas existem novas propostas sustentadas por estudos mais representativos. Propomo-nos confirmar a influência da idade e da escolaridade no desempenho, avaliar a capacidade discriminativa dos novos dados normativos e testar a acuidade diagnóstica das pontuações de corte validadas para o défice cognitivo ligeiro e para as formas mais prevalentes de demência. The Mini-Mental State Examination is the most commonly used cognitive screening test. In Portugal, the cut-off scores are defined according to literacy groups, but different proposals have been recommended by more representative studies. We therefore propose to confirm the influence of demographical variables, such as age and education, in the subject's performance; evaluating the discriminant ability of the new normative data; and to further examine the diagnostic acuity of the validated cut-off scoring for mild cognitive impairment and for the most prevalent types of dementia. Material and Methods: Our study includes 1 441 educated subjects, divided into seven subgroups: Mild cognitive impairment, Alzheimer's disease, frontotemporal dementia, vascular dementia, dementia with Lewy bodies, community-controls and memory cliniccontrols. Results: Altogether age and education explain 10.4% of the Mini-Mental State Examination results variance, with both variables contributing significantly to the results' prediction. The diagnostic acuity based on the most recent normative data was always higher than the one obtained through the validation cut-off scoring, revealing an overall excellent specificity (superior to 90%) and different sensitivity values: excellent for mild Alzheimer's disease (91%), good for dementia with Lewy Bodies (78%) and low for mild cognitive impairment (65%), frontotemporal dementia and vascular dementia (55%). Discussion and Conclusions:The performance on the Mini-Mental State Examination is influenced by age and education, supporting the use of normative data that consider those variables. With this approach, the Mini-Mental State Examination could be a sensitive and specific instrument for the Alzheimer's disease screening among all healthcare levels. Nevertheless, its diagnostic acuity is limited in other conditions frequently seen in memory clinics, such as Mild Cognitive Impairment and other types of dementia.

show abstract

“…To combine the large set of metabolomics data, we use a supervised machine learning model, the Disease State Index (DSI), as the classifier. This model was originally introduced for early diagnosis of AD and has proven to be effective in predicting MCI progression [18,19] and the differential diagnostics of neurodegenerative diseases [20,21].…”

Section: Introductionmentioning

confidence: 99%

Metabolic Profiles Help Discriminate Mild Cognitive Impairment from Dementia Stage in Alzheimer’s Disease

Jääskeläinen

Hall

Tiainen

et al. 2020

JAD

Self Cite

View full text Add to dashboard Cite

Accurate differentiation between neurodegenerative diseases is developing quickly and has reached an effective level in disease recognition. However, there has been less focus on effectively distinguishing the prodromal state from later dementia stages due to a lack of suitable biomarkers. We utilized the Disease State Index (DSI) machine learning classifier to see how well quantified metabolomics data compares to clinically used cerebrospinal fluid (CSF) biomarkers of Alzheimer's disease (AD). The metabolic profiles were quantified for 498 serum and CSF samples using proton nuclear magnetic resonance spectroscopy. The patient cohorts in this study were dementia (with a clinical AD diagnosis) (N = 359), mild cognitive impairment (MCI) (N = 96), and control patients with subjective memory complaints (N = 43). DSI classification was conducted for MCI (N = 51) and dementia (N = 214) patients with low CSF amyloid-␤ levels indicating AD pathology and controls without such amyloid pathology (N = 36). We saw that the conventional CSF markers of AD were better at classifying controls from both dementia and MCI patients. However, quantified metabolic subclasses were more effective in classifying MCI from dementia. Our results show the consistent effectiveness of traditional CSF biomarkers in AD diagnostics. However, these markers are relatively ineffective in differentiating between MCI and the dementia stage, where the quantified metabolomics data provided significant benefit.

show abstract

Generalizability of the Disease State Index Prediction Model for Identifying Patients Progressing from Mild Cognitive Impairment to Alzheimer's Disease

Abstract: The results reveal that the prediction performance of the combined cohort is close to the average of the individual cohorts. It is feasible to use different cohorts as training sets for the DSI, if they are sufficiently similar.

Cited by 33 publications

References 45 publications

Models for predicting risk of dementia: a systematic review

Models for predicting risk of dementia: a systematic review

Mini-Mental State Examination: Avaliação dos Novos Dados Normativos no Rastreio e Diagnóstico do Défice Cognitivo

Metabolic Profiles Help Discriminate Mild Cognitive Impairment from Dementia Stage in Alzheimer’s Disease

Contact Info

Product

Resources

About