Using normative models pre-trained on cross-sectional data to evaluate intra-individual longitudinal changes in neuroimaging data

Abstract

Longitudinal neuroimaging studies offer valuable insight into intricate dynamics of brain development, ageing, and disease progression over time. However, prevailing analytical approaches rooted in our understanding of population variation are primarily tailored for cross-sectional studies. To fully harness the potential of longitudinal neuroimaging data, we have to develop and refine methodologies that are adapted to longitudinal designs, considering the complex interplay between population variation and individual dynamics of change. We propose a framework based on normative modelling, which extends the use of pre-trained normative models to longitudinal studies. We introduce a quantitative metric termed the "z-diff" score, which serves as an indicator of the extent of change within an individual. Notably, our framework offers advantages such as flexibility in dataset size and ease of implementation, thanks to the reference model being trained on over 58,000 individuals. To demonstrate our approach, we applied it to a longitudinal dataset of 98 patients diagnosed with early-stage schizophrenia who underwent MRI examinations shortly after diagnosis and one year later. Compared to cross-sectional analyses, which showed global thinning of grey matter at the first visit, our method revealed a significant normalization of grey matter thickness in the frontal lobe over time. Furthermore, this result was not observed when using more traditional methods of longitudinal analysis, making our approach more sensitive to temporal changes. Overall, our framework presents a flexible and effective methodology for analysing longitudinal neuroimaging data, providing insights into the progression of the disease that would otherwise be missed when using more traditional approaches.

Unraveling the Link between CNVs, General Cognition, and Individual Neuroimaging Deviation Scores from a Reference Cohort

“…Different pathogenic CNVs, when combined with environmental influences, could affect individuals differently across various life stages. Ongoing efforts to gather extensive longitudinal samples for developmental periods promise to enrich our normative models significantly 26 . This expansion will demonstrate critical time windows, shedding light on the complex interplay between genetics, environment, and brain function.…”

“…By employing this approach, z-scores can be calculated for each individual across various neuroimaging modalities, quantifying individual variations against the mean and centiles of population reference norms. Normative models thereby shift focus from group-level to individual-level inferences [22][23][24][25] and allow us to quantify atypical developmental trajectories 26,27 . Normative modeling has proven its efficacy in correlating individual behavioral phenotypes with deviations from reference cohorts, spanning disorders like schizophrenia, autism, and ADHD [28][29][30] and mapping disease progression in Alzheimer's disease 31 .…”

Heterogeneity of morphometric similarity networks in health and schizophrenia

“…Cross-sectional studies applying normative model analysis in schizophrenia are sparse but have shown that abnormal deviations of regional cortical thickness and volume are frequent at the individual level but rarely occur consistently in the same locations and with the same severity across individuals (Wolfers et al, 2018; Lv et al, 2021; Di Biase et al, 2022; Segal et al, 2023). To the best of our knowledge, there are no longitudinal normative modeling studies in individuals with chronic schizophrenia which enable assessment of intra-individual change in deviation between two timepoints and its relation to the established normative range (Di Biase et al, 2023; Barbora Rehák Bučková et al, 2024).…”