Predicting AD Conversion: Comparison between Prodromal AD Guidelines and Computer Assisted PredictAD Tool

Y. Liu, Jussi Mattila, M.Á.M. Ruiz, T. Paajanen, Juha Koikkalainen, Mark van Gils, S.-K. Herukka, G. Waldemar, Jyrki Lötjönen, H. Soininen (Corresponding Author)

Research output: Contribution to journalArticleScientificpeer-review

31 Citations (Scopus)

Abstract

Purpose

To compare the accuracies of predicting AD conversion by using a decision support system (PredictAD tool) and current research criteria of prodromal AD as identified by combinations of episodic memory impairment of hippocampal type and visual assessment of medial temporal lobe atrophy (MTA) on MRI and CSF biomarkers.

Methods

Altogether 391 MCI cases (158 AD converters) were selected from the ADNI cohort. All the cases had baseline cognitive tests, MRI and/or CSF levels of Aβ1–42 and Tau. Using baseline data, the status of MCI patients (AD or MCI) three years later was predicted using current diagnostic research guidelines and the PredictAD software tool designed for supporting clinical diagnostics. The data used were 1) clinical criteria for episodic memory loss of the hippocampal type, 2) visual MTA, 3) positive CSF markers, 4) their combinations, and 5) when the PredictAD tool was applied, automatically computed MRI measures were used instead of the visual MTA results. The accuracies of diagnosis were evaluated with the diagnosis made 3 years later.

Results

The PredictAD tool achieved the overall accuracy of 72% (sensitivity 73%, specificity 71%) in predicting the AD diagnosis. The corresponding number for a clinician’s prediction with the assistance of the PredictAD tool was 71% (sensitivity 75%, specificity 68%). Diagnosis with the PredictAD tool was significantly better than diagnosis by biomarkers alone or the combinations of clinical diagnosis of hippocampal pattern for the memory loss and biomarkers (p≤0.037).

Conclusion

With the assistance of PredictAD tool, the clinician can predict AD conversion more accurately than the current diagnostic criteria.
Original languageEnglish
Article numbere55246
Number of pages8
JournalPLoS ONE
Volume8
Issue number2
DOIs
Publication statusPublished - 2013
MoE publication typeA1 Journal article-refereed

Fingerprint

atrophy
biomarkers
Guidelines
Biomarkers
Temporal Lobe
Magnetic resonance imaging
Atrophy
Episodic Memory
Memory Disorders
decision support systems
Data storage equipment
Sensitivity and Specificity
prediction
Vision Disorders
Decision support systems
Research
Software
testing

Cite this

Liu, Y., Mattila, J., Ruiz, M. Á. M., Paajanen, T., Koikkalainen, J., van Gils, M., ... Soininen, H. (2013). Predicting AD Conversion: Comparison between Prodromal AD Guidelines and Computer Assisted PredictAD Tool. PLoS ONE, 8(2), [e55246]. https://doi.org/10.1371/journal.pone.0055246
Liu, Y. ; Mattila, Jussi ; Ruiz, M.Á.M. ; Paajanen, T. ; Koikkalainen, Juha ; van Gils, Mark ; Herukka, S.-K. ; Waldemar, G. ; Lötjönen, Jyrki ; Soininen, H. / Predicting AD Conversion: Comparison between Prodromal AD Guidelines and Computer Assisted PredictAD Tool. In: PLoS ONE. 2013 ; Vol. 8, No. 2.
@article{7860f5ffbaa342eeaeb146d3e40909a1,
title = "Predicting AD Conversion: Comparison between Prodromal AD Guidelines and Computer Assisted PredictAD Tool",
abstract = "PurposeTo compare the accuracies of predicting AD conversion by using a decision support system (PredictAD tool) and current research criteria of prodromal AD as identified by combinations of episodic memory impairment of hippocampal type and visual assessment of medial temporal lobe atrophy (MTA) on MRI and CSF biomarkers.MethodsAltogether 391 MCI cases (158 AD converters) were selected from the ADNI cohort. All the cases had baseline cognitive tests, MRI and/or CSF levels of Aβ1–42 and Tau. Using baseline data, the status of MCI patients (AD or MCI) three years later was predicted using current diagnostic research guidelines and the PredictAD software tool designed for supporting clinical diagnostics. The data used were 1) clinical criteria for episodic memory loss of the hippocampal type, 2) visual MTA, 3) positive CSF markers, 4) their combinations, and 5) when the PredictAD tool was applied, automatically computed MRI measures were used instead of the visual MTA results. The accuracies of diagnosis were evaluated with the diagnosis made 3 years later.ResultsThe PredictAD tool achieved the overall accuracy of 72{\%} (sensitivity 73{\%}, specificity 71{\%}) in predicting the AD diagnosis. The corresponding number for a clinician’s prediction with the assistance of the PredictAD tool was 71{\%} (sensitivity 75{\%}, specificity 68{\%}). Diagnosis with the PredictAD tool was significantly better than diagnosis by biomarkers alone or the combinations of clinical diagnosis of hippocampal pattern for the memory loss and biomarkers (p≤0.037).ConclusionWith the assistance of PredictAD tool, the clinician can predict AD conversion more accurately than the current diagnostic criteria.",
author = "Y. Liu and Jussi Mattila and M.{\'A}.M. Ruiz and T. Paajanen and Juha Koikkalainen and {van Gils}, Mark and S.-K. Herukka and G. Waldemar and Jyrki L{\"o}tj{\"o}nen and H. Soininen",
year = "2013",
doi = "10.1371/journal.pone.0055246",
language = "English",
volume = "8",
journal = "PLoS ONE",
issn = "1932-6203",
publisher = "Public Library of Science",
number = "2",

}

Liu, Y, Mattila, J, Ruiz, MÁM, Paajanen, T, Koikkalainen, J, van Gils, M, Herukka, S-K, Waldemar, G, Lötjönen, J & Soininen, H 2013, 'Predicting AD Conversion: Comparison between Prodromal AD Guidelines and Computer Assisted PredictAD Tool', PLoS ONE, vol. 8, no. 2, e55246. https://doi.org/10.1371/journal.pone.0055246

Predicting AD Conversion: Comparison between Prodromal AD Guidelines and Computer Assisted PredictAD Tool. / Liu, Y.; Mattila, Jussi; Ruiz, M.Á.M.; Paajanen, T.; Koikkalainen, Juha; van Gils, Mark; Herukka, S.-K.; Waldemar, G.; Lötjönen, Jyrki; Soininen, H. (Corresponding Author).

In: PLoS ONE, Vol. 8, No. 2, e55246, 2013.

Research output: Contribution to journalArticleScientificpeer-review

TY - JOUR

T1 - Predicting AD Conversion: Comparison between Prodromal AD Guidelines and Computer Assisted PredictAD Tool

AU - Liu, Y.

AU - Mattila, Jussi

AU - Ruiz, M.Á.M.

AU - Paajanen, T.

AU - Koikkalainen, Juha

AU - van Gils, Mark

AU - Herukka, S.-K.

AU - Waldemar, G.

AU - Lötjönen, Jyrki

AU - Soininen, H.

PY - 2013

Y1 - 2013

N2 - PurposeTo compare the accuracies of predicting AD conversion by using a decision support system (PredictAD tool) and current research criteria of prodromal AD as identified by combinations of episodic memory impairment of hippocampal type and visual assessment of medial temporal lobe atrophy (MTA) on MRI and CSF biomarkers.MethodsAltogether 391 MCI cases (158 AD converters) were selected from the ADNI cohort. All the cases had baseline cognitive tests, MRI and/or CSF levels of Aβ1–42 and Tau. Using baseline data, the status of MCI patients (AD or MCI) three years later was predicted using current diagnostic research guidelines and the PredictAD software tool designed for supporting clinical diagnostics. The data used were 1) clinical criteria for episodic memory loss of the hippocampal type, 2) visual MTA, 3) positive CSF markers, 4) their combinations, and 5) when the PredictAD tool was applied, automatically computed MRI measures were used instead of the visual MTA results. The accuracies of diagnosis were evaluated with the diagnosis made 3 years later.ResultsThe PredictAD tool achieved the overall accuracy of 72% (sensitivity 73%, specificity 71%) in predicting the AD diagnosis. The corresponding number for a clinician’s prediction with the assistance of the PredictAD tool was 71% (sensitivity 75%, specificity 68%). Diagnosis with the PredictAD tool was significantly better than diagnosis by biomarkers alone or the combinations of clinical diagnosis of hippocampal pattern for the memory loss and biomarkers (p≤0.037).ConclusionWith the assistance of PredictAD tool, the clinician can predict AD conversion more accurately than the current diagnostic criteria.

AB - PurposeTo compare the accuracies of predicting AD conversion by using a decision support system (PredictAD tool) and current research criteria of prodromal AD as identified by combinations of episodic memory impairment of hippocampal type and visual assessment of medial temporal lobe atrophy (MTA) on MRI and CSF biomarkers.MethodsAltogether 391 MCI cases (158 AD converters) were selected from the ADNI cohort. All the cases had baseline cognitive tests, MRI and/or CSF levels of Aβ1–42 and Tau. Using baseline data, the status of MCI patients (AD or MCI) three years later was predicted using current diagnostic research guidelines and the PredictAD software tool designed for supporting clinical diagnostics. The data used were 1) clinical criteria for episodic memory loss of the hippocampal type, 2) visual MTA, 3) positive CSF markers, 4) their combinations, and 5) when the PredictAD tool was applied, automatically computed MRI measures were used instead of the visual MTA results. The accuracies of diagnosis were evaluated with the diagnosis made 3 years later.ResultsThe PredictAD tool achieved the overall accuracy of 72% (sensitivity 73%, specificity 71%) in predicting the AD diagnosis. The corresponding number for a clinician’s prediction with the assistance of the PredictAD tool was 71% (sensitivity 75%, specificity 68%). Diagnosis with the PredictAD tool was significantly better than diagnosis by biomarkers alone or the combinations of clinical diagnosis of hippocampal pattern for the memory loss and biomarkers (p≤0.037).ConclusionWith the assistance of PredictAD tool, the clinician can predict AD conversion more accurately than the current diagnostic criteria.

U2 - 10.1371/journal.pone.0055246

DO - 10.1371/journal.pone.0055246

M3 - Article

VL - 8

JO - PLoS ONE

JF - PLoS ONE

SN - 1932-6203

IS - 2

M1 - e55246

ER -