Search

Resting-state functional connectivity (RSFC) is widely used to predict phenotypic traits in individuals. Large sample sizes can significantly improve prediction accuracies. However, for studies of certain clinical populations or focused neuroscience inquiries, small-scale datasets often remain a necessity. We have previously proposed a “meta-matching” approach to translate prediction models from large datasets to predict new phenotypes in small datasets. We demonstrated a large improvement over classical kernel ridge regression (KRR) when translating models from a single source dataset (UK Biobank) to the Human Connectome Project Young Adults (HCP-YA) dataset. In the current study, we propose two meta-matching variants (“meta-matching with dataset stacking” and “multilayer meta-matching”) to translate models from multiple source datasets across disparate sample sizes to predict new phenotypes in small target datasets. We evaluate both approaches by translating models trained from five source datasets (with sample sizes ranging from 862 participants to 36,834 participants) to predict phenotypes in the HCP-YA and HCP-Aging datasets. We find that multilayer meta-matching modestly outperforms meta-matching with dataset stacking. Both meta-matching variants perform better than the original “meta-matching with stacking” approach trained only on the UK Biobank. All meta-matching variants outperform classical KRR and transfer learning by a large margin. In fact, KRR is better than classical transfer learning when less than 50 participants are available for finetuning, suggesting the difficulty of classical transfer learning in the very small sample regime. The multilayer meta-matching model is publicly available at https://github.com/ThomasYeoLab/Meta_matching_models/tree/main/rs-fMRI/v2.0.

As the global health crisis unfolded, many academic conferences moved online in 2020. This move has been hailed as a positive step towards inclusivity in its attenuation of economic, physical, and legal barriers and effectively enabled many individuals from groups that have traditionally been underrepresented to join and participate. A number of studies have outlined how moving online made it possible to gather a more global community and has increased opportunities for individuals with various constraints, e.g., caregiving responsibilities. Yet, the mere existence of online conferences is no guarantee that everyone can attend and participate meaningfully. In fact, many elements of an online conference are still significant barriers to truly diverse participation: the tools used can be inaccessible for some individuals; the scheduling choices can favour some geographical locations; the set-up of the conference can provide more visibility to well-established researchers and reduce opportunities for early-career researchers. While acknowledging the benefits of an online setting, especially for individuals who have traditionally been underrepresented or excluded, we recognize that fostering social justice requires inclusivity to actively be centered in every aspect of online conference design. Here, we draw from the literature and from our own experiences to identify practices that purposefully encourage a diverse community to attend, participate in, and lead online conferences. Reflecting on how to design more inclusive online events is especially important as multiple scientific organizations have announced that they will continue offering an online version of their event when in-person conferences can resume.

We currently observe a disconcerting phenomenon in machine learning studies in psychiatry: While we would expect larger samples to yield better results due to the availability of more data, larger machine learning studies consistently show much weaker performance than the numerous small-scale studies. Here, we systematically investigated this effect focusing on one of the most heavily studied questions in the field, namely the classification of patients suffering from Major Depressive Disorder (MDD) and healthy controls based on neuroimaging data. Drawing upon structural MRI data from a balanced sample of N = 1868 MDD patients and healthy controls from our recent international Predictive Analytics Competition (PAC), we first trained and tested a classification model on the full dataset which yielded an accuracy of 61%. Next, we mimicked the process by which researchers would draw samples of various sizes (N = 4 to N = 150) from the population and showed a strong risk of misestimation. Specifically, for small sample sizes (N = 20), we observe accuracies of up to 95%. For medium sample sizes (N = 100) accuracies up to 75% were found. Importantly, further investigation showed that sufficiently large test sets effectively protect against performance misestimation whereas larger datasets per se do not. While these results question the validity of a substantial part of the current literature, we outline the relatively low-cost remedy of larger test sets, which is readily available in most cases.

Neuroimaging and genetics studies have advanced our understanding of the neurobiology of sleep and its disorders. However, individual studies usually have limitations to identifying consistent and reproducible effects, including modest sample sizes, heterogeneous clinical characteristics and varied methodologies. These issues call for a large-scale multi-centre effort in sleep research, in order to increase the number of samples, and harmonize the methods of data collection, preprocessing and analysis using pre-registered well-established protocols. The Enhancing NeuroImaging Genetics through Meta-Analysis (ENIGMA) consortium provides a powerful collaborative framework for combining datasets across individual sites. Recently, we have launched the ENIGMA-Sleep working group with the collaboration of several institutes from 15 countries to perform large-scale worldwide neuroimaging and genetics studies for better understanding the neurobiology of impaired sleep quality in population-based healthy individuals, the neural consequences of sleep deprivation, pathophysiology of sleep disorders, as well as neural correlates of sleep disturbances across various neuropsychiatric disorders. In this introductory review, we describe the details of our currently available datasets and our ongoing projects in the ENIGMA-Sleep group, and discuss both the potential challenges and opportunities of a collaborative initiative in sleep medicine.

Human interactions with the world are influenced by memories of recent events. This effect, often triggered by perceptual cues, occurs naturally and without conscious effort. However, the neuroscience of involuntary memory in a dynamic milieu has received much less attention than the mechanisms of voluntary retrieval with deliberate purpose. Here, we investigate the neural processes driven by naturalistic cues that relate to, and presumably trigger the retrieval of recent experiences. Viewing the continuation of recently viewed clips evokes greater bilateral activation in anterior hippocampus, precuneus and angular gyrus than naïve clips. While these regions manifest reciprocal connectivity, continued viewing specifically modulates the effective connectivity from the anterior hippocampus to the precuneus. The strength of this modulation predicts participants' confidence in later voluntary recall of news details. Our study reveals network mechanisms of dynamic, involuntary memory retrieval and its relevance to metacognition in a rich context resembling everyday life.

Motor speech disorders, including apraxia of speech (AOS), account for over 50% of the communication disorders following stroke. Given its prevalence and impact, and the need to understand its neural mechanisms, we used resting state functional MRI to examine functional connectivity within a network of regions previously hypothesized as being associated with AOS (bilateral anterior insula (aINS), inferior frontal gyrus (IFG), and ventral premotor cortex (PM)) in a group of 32 left hemisphere stroke patients and 18 healthy, age-matched controls. Two expert clinicians rated severity of AOS, dysarthria and nonverbal oral apraxia of the patients. Fifteen individuals were categorized as AOS and 17 were AOS-absent. Comparison of connectivity in patients with and without AOS demonstrated that AOS patients had reduced connectivity between bilateral PM, and this reduction correlated with the severity of AOS impairment. In addition, AOS patients had negative connectivity between the left PM and right aINS and this effect decreased with increasing severity of non-verbal oral apraxia. These results highlight left PM involvement in AOS, begin to differentiate its neural mechanisms from those of other motor impairments following stroke, and help inform us of the neural mechanisms driving differences in speech motor planning and programming impairment following stroke.