1
|
Hartmann S, Cearns M, Pantelis C, Dwyer D, Cavve B, Byrne E, Scott I, Yuen HP, Gao C, Allott K, Lin A, Wood SJ, Wigman JTW, Amminger GP, McGorry PD, Yung AR, Nelson B, Clark SR. Combining Clinical With Cognitive or Magnetic Resonance Imaging Data for Predicting Transition to Psychosis in Ultra High-Risk Patients: Data From the PACE 400 Cohort. Biological Psychiatry: Cognitive Neuroscience and Neuroimaging 2024; 9:417-428. [PMID: 38052267 DOI: 10.1016/j.bpsc.2023.11.009] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 07/27/2023] [Revised: 10/19/2023] [Accepted: 11/26/2023] [Indexed: 12/07/2023]
Abstract
BACKGROUND Multimodal modeling that combines biological and clinical data shows promise in predicting transition to psychosis in individuals who are at ultra-high risk. Individuals who transition to psychosis are known to have deficits at baseline in cognitive function and reductions in gray matter volume in multiple brain regions identified by magnetic resonance imaging. METHODS In this study, we used Cox proportional hazards regression models to assess the additive predictive value of each modality-cognition, cortical structure information, and the neuroanatomical measure of brain age gap-to a previously developed clinical model using functioning and duration of symptoms prior to service entry as predictors in the Personal Assessment and Crisis Evaluation (PACE) 400 cohort. The PACE 400 study is a well-characterized cohort of Australian youths who were identified as ultra-high risk of transitioning to psychosis using the Comprehensive Assessment of At Risk Mental States (CAARMS) and followed for up to 18 years; it contains clinical data (from N = 416 participants), cognitive data (n = 213), and magnetic resonance imaging cortical parameters extracted using FreeSurfer (n = 231). RESULTS The results showed that neuroimaging, brain age gap, and cognition added marginal predictive information to the previously developed clinical model (fraction of new information: neuroimaging 0%-12%, brain age gap 7%, cognition 0%-16%). CONCLUSIONS In summary, adding a second modality to a clinical risk model predicting the onset of a psychotic disorder in the PACE 400 cohort showed little improvement in the fit of the model for long-term prediction of transition to psychosis.
Collapse
Affiliation(s)
- Simon Hartmann
- Discipline of Psychiatry, Adelaide Medical School, The University of Adelaide, Adelaide, South Australia, Australia; Orygen, Parkville, Victoria, Australia; Centre for Youth Mental Health, The University of Melbourne, Melbourne, Victoria, Australia.
| | - Micah Cearns
- Discipline of Psychiatry, Adelaide Medical School, The University of Adelaide, Adelaide, South Australia, Australia
| | - Christos Pantelis
- Melbourne Neuropsychiatry Centre, Department of Psychiatry, The University of Melbourne, Carlton South, Melbourne, Victoria, Australia; Western Centre for Health Research & Education, Western Hospital Sunshine, The University of Melbourne, St. Albans, Victoria, Australia
| | - Dominic Dwyer
- Orygen, Parkville, Victoria, Australia; Centre for Youth Mental Health, The University of Melbourne, Melbourne, Victoria, Australia
| | - Blake Cavve
- Telethon Kids Institute, The University of Western Australia, Perth, Western Australia, Australia
| | - Enda Byrne
- Child Health Research Center, The University of Queensland, Brisbane, Queensland, Australia
| | - Isabelle Scott
- Orygen, Parkville, Victoria, Australia; Centre for Youth Mental Health, The University of Melbourne, Melbourne, Victoria, Australia
| | - Hok Pan Yuen
- Orygen, Parkville, Victoria, Australia; Centre for Youth Mental Health, The University of Melbourne, Melbourne, Victoria, Australia
| | - Caroline Gao
- Orygen, Parkville, Victoria, Australia; Centre for Youth Mental Health, The University of Melbourne, Melbourne, Victoria, Australia
| | - Kelly Allott
- Orygen, Parkville, Victoria, Australia; Centre for Youth Mental Health, The University of Melbourne, Melbourne, Victoria, Australia
| | - Ashleigh Lin
- Telethon Kids Institute, The University of Western Australia, Perth, Western Australia, Australia
| | - Stephen J Wood
- Orygen, Parkville, Victoria, Australia; Centre for Youth Mental Health, The University of Melbourne, Melbourne, Victoria, Australia; School of Psychology, The University of Birmingham, Birmingham, England, United Kingdom
| | - Johanna T W Wigman
- Department of Psychiatry, Interdisciplinary Center Psychopathology and Emotion Regulation, University of Groningen, University Medical Center Groningen, Groningen, the Netherlands
| | - G Paul Amminger
- Orygen, Parkville, Victoria, Australia; Centre for Youth Mental Health, The University of Melbourne, Melbourne, Victoria, Australia
| | - Patrick D McGorry
- Orygen, Parkville, Victoria, Australia; Centre for Youth Mental Health, The University of Melbourne, Melbourne, Victoria, Australia
| | - Alison R Yung
- Institute for Mental and Physical Health and Clinical Translation, Deakin University, Melbourne, Victoria, Australia
| | - Barnaby Nelson
- Orygen, Parkville, Victoria, Australia; Centre for Youth Mental Health, The University of Melbourne, Melbourne, Victoria, Australia
| | - Scott R Clark
- Discipline of Psychiatry, Adelaide Medical School, The University of Adelaide, Adelaide, South Australia, Australia
| |
Collapse
|
2
|
Liu J, Capurro D, Nguyen A, Verspoor K. Attention-based multimodal fusion with contrast for robust clinical prediction in the face of missing modalities. J Biomed Inform 2023; 145:104466. [PMID: 37549722 DOI: 10.1016/j.jbi.2023.104466] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/25/2023] [Revised: 06/09/2023] [Accepted: 08/01/2023] [Indexed: 08/09/2023]
Abstract
OBJECTIVE With the increasing amount and growing variety of healthcare data, multimodal machine learning supporting integrated modeling of structured and unstructured data is an increasingly important tool for clinical machine learning tasks. However, it is non-trivial to manage the differences in dimensionality, volume, and temporal characteristics of data modalities in the context of a shared target task. Furthermore, patients can have substantial variations in the availability of data, while existing multimodal modeling methods typically assume data completeness and lack a mechanism to handle missing modalities. METHODS We propose a Transformer-based fusion model with modality-specific tokens that summarize the corresponding modalities to achieve effective cross-modal interaction accommodating missing modalities in the clinical context. The model is further refined by inter-modal, inter-sample contrastive learning to improve the representations for better predictive performance. We denote the model as Attention-based cRoss-MOdal fUsion with contRast (ARMOUR). We evaluate ARMOUR using two input modalities (structured measurements and unstructured text), six clinical prediction tasks, and two evaluation regimes, either including or excluding samples with missing modalities. RESULTS Our model shows improved performances over unimodal or multimodal baselines in both evaluation regimes, including or excluding patients with missing modalities in the input. The contrastive learning improves the representation power and is shown to be essential for better results. The simple setup of modality-specific tokens enables ARMOUR to handle patients with missing modalities and allows comparison with existing unimodal benchmark results. CONCLUSION We propose a multimodal model for robust clinical prediction to achieve improved performance while accommodating patients with missing modalities. This work could inspire future research to study the effective incorporation of multiple, more complex modalities of clinical data into a single model.
Collapse
Affiliation(s)
- Jinghui Liu
- Australian e-Health Research Centre, CSIRO, Queensland, Australia; School of Computing and Information Systems, The University of Melbourne, Victoria, Australia
| | - Daniel Capurro
- School of Computing and Information Systems, The University of Melbourne, Victoria, Australia; Centre for Digital Transformation of Health, The University of Melbourne, Victoria, Australia
| | - Anthony Nguyen
- Australian e-Health Research Centre, CSIRO, Queensland, Australia
| | - Karin Verspoor
- School of Computing and Information Systems, The University of Melbourne, Victoria, Australia; School of Computing Technologies, RMIT University, Victoria, Australia.
| |
Collapse
|
3
|
Liégeois R, Santos A, Matta V, Van De Ville D, Sayed AH. Revisiting correlation-based functional connectivity and its relationship with structural connectivity. Netw Neurosci 2020; 4:1235-1251. [PMID: 33409438 PMCID: PMC7781609 DOI: 10.1162/netn_a_00166] [Citation(s) in RCA: 27] [Impact Index Per Article: 6.8] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/10/2020] [Accepted: 08/16/2020] [Indexed: 12/25/2022] Open
Abstract
Patterns of brain structural connectivity (SC) and functional connectivity (FC) are known to be related. In SC-FC comparisons, FC has classically been evaluated from correlations between functional time series, and more recently from partial correlations or their unnormalized version encoded in the precision matrix. The latter FC metrics yield more meaningful comparisons to SC because they capture ‘direct’ statistical dependencies, that is, discarding the effects of mediators, but their use has been limited because of estimation issues. With the rise of high-quality and large neuroimaging datasets, we revisit the relevance of different FC metrics in the context of SC-FC comparisons. Using data from 100 unrelated Human Connectome Project subjects, we first explore the amount of functional data required to reliably estimate various FC metrics. We find that precision-based FC yields a better match to SC than correlation-based FC when using 5 minutes of functional data or more. Finally, using a linear model linking SC and FC, we show that the SC-FC match can be used to further interrogate various aspects of brain structure and function such as the timescales of functional dynamics in different resting-state networks or the intensity of anatomical self-connections.
Collapse
Affiliation(s)
- Raphael Liégeois
- Institute of Bioengineering, Center for Neuroprosthetics, École Polytechnique Fédérale de Lausanne, Switzerland; Centre for Informatics and Systems, University of Coimbra, Portugal
| | - Augusto Santos
- Institute of Bioengineering, Center for Neuroprosthetics, École Polytechnique Fédérale de Lausanne, Switzerland; Centre for Informatics and Systems, University of Coimbra, Portugal
| | - Vincenzo Matta
- Department of Information and Electrical Engineering and Applied Mathematics, University of Salerno, Italy
| | - Dimitri Van De Ville
- Institute of Bioengineering, Center for Neuroprosthetics, École Polytechnique Fédérale de Lausanne, Switzerland; Centre for Informatics and Systems, University of Coimbra, Portugal
| | - Ali H Sayed
- Institute of Bioengineering, Center for Neuroprosthetics, École Polytechnique Fédérale de Lausanne, Switzerland; Centre for Informatics and Systems, University of Coimbra, Portugal
| |
Collapse
|