It is increasingly recognized that Alzheimer’s disease (AD) exists before dementia is present and that shifts in amyloid beta occur long before clinical symptoms can be detected. Early detection of... Show moreIt is increasingly recognized that Alzheimer’s disease (AD) exists before dementia is present and that shifts in amyloid beta occur long before clinical symptoms can be detected. Early detection of these molecular changes is a key aspect for the success of interventions aimed at slowing down rates of cognitive decline. Recent evidence indicates that of the two established methods for measuring amyloid, a decrease in cerebrospinal fluid (CSF) amyloid β1−42 (Aβ1−42) may be an earlier indicator of Alzheimer’s disease risk than measures of amyloid obtained from Positron Emission Tomography (PET). However, CSF collection is highly invasive and expensive. In contrast, blood collection is routinely performed, minimally invasive and cheap. In this work, we develop a blood-based signature that can provide a cheap and minimally invasive estimation of an individual’s CSF amyloid status using a machine learning approach. We show that a Random Forest model derived from plasma analytes can accurately predict subjects as having abnormal (low) CSF Aβ1−42 levels indicative of AD risk (0.84 AUC, 0.78 sensitivity, and 0.73 specificity). Refinement of the modeling indicates that only APOEε4 carrier status and four plasma analytes (CGA, Aβ1−42, Eotaxin 3, APOE) are required to achieve a high level of accuracy. Furthermore, we show across an independent validation cohort that individuals with predicted abnormal CSF Aβ1−42 levels transitioned to an AD diagnosis over 120 months significantly faster than those with predicted normal CSF Aβ1−42 levels and that the resulting model also validates reasonably across PET Aβ1−42 status (0.78 AUC). This is the first study to show that a machine learning approach, using plasma protein levels, age and APOEε4 carrier status, is able to predict CSF Aβ1−42 status, the earliest risk indicator for AD, with high accuracy. Show less
Introduction Development and behaviour in Cornelia de Lange Syndrome (CdLS), including autism characteristics, have been described infrequently stratified to genetic cause and only a few studies... Show moreIntroduction Development and behaviour in Cornelia de Lange Syndrome (CdLS), including autism characteristics, have been described infrequently stratified to genetic cause and only a few studies have considered behavioural characteristics in relation to developmental level. Here, we describe the behavioural phenotype in individuals with CdLS with SMC1A variants. Methods We performed an international, interdisciplinary study on 51 individuals with SMC1A variants. Results of questionnaire studies are compared to those in individuals with Down Syndrome and with Autism Spectrum Disorder. Results on cognition and self-injurious behaviour (SIB) are compared to those in individuals with CdLS caused by NIPBL variants. For Dutch participants with SMC1A variants we performed direct in-person assessments of cognition, autism, and added an interview and questionnaire on adaptive behaviour and sensory processing. Results Individuals with SMC1A variants show a higher cognitive level and less SIB than individuals with NIPBL variants. Individuals with SMC1A variants without classic CdLS phenotype but with a Rett-like phenotype show more severe intellectual disability and more SIB compared to those with a CdLS phenotype. Autism is less present if outcomes in direct in-person assessments are evaluated taking developmental level into account compared to results based on a questionnaire. Conclusions Behaviour in individuals with CdLS should be evaluated taking genetic cause into account. Detailed interdisciplinary approaches are of clinical importance to inform tailored care and may eventually improve quality of life of patients and families. Show less
