RT Journal Article
T1 Prediction of Alzheimer's disease dementia with MRI beyond the short-term: Implications for the design of predictive models
A1 Moscoso Rial, Alexis
A1 Silva Rodríguez, Jesús
A1 Aldrey Vázquez, José Manuel
A1 Cortés Hernández, Julia
A1 Fernández Ferreiro, Anxo
A1 Gómez Lado, Noemí
A1 Ruibal Morell, Álvaro
A1 Aguiar Fernández, Pablo
K1 Late MCI
K1 MCI
K1 Alzheimer
K1 Machine learning
K1 MRI
AB Magnetic resonance imaging (MRI) volumetric measures have become a standard tool for the detection of in-cipientAlzheimer'sDisease(AD)dementiainmildcognitiveimpairment(MCI).Focusedonprovidinganearlierand more accurate diagnosis, sophisticated MRI machine learning algorithms have been developed over therecentyears,mostofthemlearningtheirnon-diseasepatternsfromMCIthatremainedstableover2–3years.Inthis work, we analyzed whether these stable MCI over short-term periods are actually appropriate trainingexamples of non-disease patterns. To this aim, we compared the diagnosis of MCI patients at 2 and 5years offollow-up and investigated its impact on the predictive performance of baseline volumetric MRI measures pri-marily involved in AD, i.e., hippocampal and entorhinal cortex volumes. Predictive power was evaluated interms ofthe areaunder the ROCcurve(AUC), sensitivity,andspecificity inatrialsample of248 MCIpatientsfollowed-up over 5years. We further compared the sensitivity in those MCI that converted before 2years andthose that converted after 2years. Our results indicate that 23% of the stable MCI at 2years progressed in thenextthreeyearsandthatMRIvolumetricmeasuresaregoodpredictorsofconversiontoADdementiaevenatthemid-term, showing a better specificity and AUC as follow-up time increases. The combination of hippocampusand entorhinal cortex yielded an AUC that was significantly higher for the 5-year follow-up (AUC=73% at2yearsvs.AUC=84%at5years),aswellasforspecificity(56%vs.71%).Sensitivityshowedanon-significantslightdecrease(81%vs.78%).Remarkably,theperformanceofthismodelwascomparabletomachinelearningmodels at the same follow-up times. MRI correctly identified most of the patients that converted after 2years(with sensitivity>60%), and these patients showed a similar degree of abnormalities to those that convertedbefore 2years. This implies that most of the MCI patients that remained stable over short periods and subse-quentlyprogressedtoADdementiahadevidentatrophiesatbaseline.Therefore,machinelearningmodelsthatuse these patients to learn non-disease patterns are including an important fraction of patients with evidentpathological changes related to the disease, something that might result in reduced performance and lack ofbiological interpretability.
PB Elsevier
YR 2019
FD 2019
LK http://hdl.handle.net/10347/21445
UL http://hdl.handle.net/10347/21445
LA eng
NO Moscoso, A., Silva-Rodríguez, J., Aldrey, J.M., Cortés, J. et al. (2019). Prediction of Alzheimer's disease dementia with MRI beyond the short-term: Implications for the design of predictive models, "NeuroImage: Clinical", vol. 23, 101837
NO This work was partially supported by the project PI16/01416(ISCIIIco-fundedFEDER) and RYC-2015/17430 (RamónyCajal,Pablo Aguiar). Data collection and sharing for this project was funded by the Alzheimer's Disease Neuroimaging Initiative (ADNI)(National Institutes of Health Grant U01AG024904) and DODADNI (Department of Defense award number W81XWH-12-2-0012)
DS Minerva
RD 9 jun 2026