Predicting conversion of brain β-amyloid positivity in amyloid-negative individuals

Abstract

Background Cortical deposition of β-amyloid (Aβ) plaque is one of the main hallmarks of Alzheimer’s disease (AD). While Aβ positivity has been the main concern so far, predicting whether Aβ (−) individuals will convert to Aβ (+) has become crucial in clinical and research aspects. In this study, we aimed to develop a classifier that predicts the conversion from Aβ (−) to Aβ (+) using artificial intelligence. Methods Data were obtained from the Alzheimer’s Disease Neuroimaging Initiative (ADNI) cohort regarding patients who were initially Aβ (−). We developed an artificial neural network-based classifier with baseline age, gender, APOE ε4 genotype, and global and regional standardized uptake value ratios (SUVRs) from positron emission tomography. Ten times repeated 10-fold cross-validation was performed for model measurement, and the feature importance was assessed. To validate the prediction model, we recruited subjects at the Samsung Medical Center (SMC). Results A total of 229 participants (53 converters) from the ADNI dataset and a total of 40 subjects (10 converters) from the SMC dataset were included. The average area under the receiver operating characteristic values of three developed models are as follows: Model 1 (age, gender, APOE ε4) of 0.674, Model 2 (age, gender, APOE ε4, global SUVR) of 0.814, and Model 3 (age, gender, APOE ε4, global and regional SUVR) of 0.841. External validation result showed an AUROC of 0.900. Conclusion We developed prediction models regarding Aβ positivity conversion. With the growing recognition of the need for earlier intervention in AD, the results of this study are expected to contribute to the screening of early treatment candidates.

Machine learning prediction of future amyloid beta positivity in amyloid-negative individuals

“…Similarly, another study by the same group 39 , detected baseline Aβ-positivity using demographic, APOE, and cognitive information and achieved an AUC of 0.65 in cognitively healthy individuals. However, we are aware of only two studies that have focused on predicting future Aβ-positivity 12,44 . The first study by Elman et al 44 examined the association of baseline cognitive measures with progression to Aβ-positivity in Aβ-negative individuals.…”

“…The first study by Elman et al 44 examined the association of baseline cognitive measures with progression to Aβ-positivity in Aβ-negative individuals. The second study conducted by Park et al 12 employed machine learning algorithms to predict future Aβ-positivity in Aβ-negative individuals. In Park et al 12 study, they used a PET biomarker for subject classification in Aβ+/Aβ-groups and developed a classifier with baseline age, gender, APOE4 genotype, and PET SUVR measures in ADNI data.…”

“…The second study conducted by Park et al 12 employed machine learning algorithms to predict future Aβ-positivity in Aβ-negative individuals. In Park et al 12 study, they used a PET biomarker for subject classification in Aβ+/Aβ-groups and developed a classifier with baseline age, gender, APOE4 genotype, and PET SUVR measures in ADNI data. They achieved a cross-validated AUC of 0.67 using basic demographic and genetic factors, which improved to 0.84 when including PET SUVR measures.…”

“…They achieved a cross-validated AUC of 0.67 using basic demographic and genetic factors, which improved to 0.84 when including PET SUVR measures. Our work has a similar objective to the study by Park et al 12 , but we focused on widely available non-invasive measures to predict future Aβ conversion. Moreover, a key characteristic of our study was to assess the future predictability of Aβ-positivity determined based on either CSF and PET biomarkers whereas Park et al 12 only considered a PET-based definition.…”

Advanced brain imaging for the diagnosis of Alzheimer disease

“…For example, lecanemab, a humanized IgG1 monoclonal antibody that targets soluble aggregated Aβ species (protofibrils), demonstrated robust amyloid-PET reduction in early AD [50]. One recent study developed a DL model to predict amyloid-PET positivity conversion, which might contribute to the screening of early treatment candidates [54] as it has been reported that positivity in both amyloid and tau PET scans put cognitively unimpaired individual at high risk for future cognitive decline [55 ▪▪ ]. In clinical settings, large multicentre studies have shown that amyloid-PET results change both diagnosis and patient management and that quantification can accurately predict rates of cognitive decline.…”