An Imaging and Blood Biomarkers Open Dataset on Alzheimer's Disease vs. Late Onset Bipolar Disorder
Ariadna Besga
Darya Chyzhyk
Manuel Graña
Ana Gonzalez-Pinto- 1Centre for Biomedical Research Network on MentalHealth, Madrid, Spain
- 2Department of Internal Medicine, Hospital Universitario de Alava, Vitoria-Gasteiz, Spain
- 3Computational Intelligence Group, University of the Basque Country (UPV/EHU), San Sebastian, Spain
- 4ACPySS, San Sebastian, Spain
- 5Department of Psychiatry, University Hospital of Alava-Santiago, Vitoria-Gasteiz, Spain
- 6School of Medicine, University of the Basque Country, Vitoria-Gasteiz, Spain
1. Introduction
Bipolar disorder (BD) is a chronic mood disorder alternating maniac/depressive with euthymic episodes. Its onset is conditioned by the environment and genetic inheritance (Bauer M. et al., 2014; Martinez-Cengotitabengoa et al., 2014; Bauer et al., 2015a,b), often during youth producing cognitive, affective, and functional impairment (Forcada et al., 2014). Late onset BD (LOBD) corresponds to ages above 50 years (Depp and Jeste, 2004; Zanetti et al., 2007; Prabhakar and Balon, 2010; Besga et al., 2011; Carlino et al., 2013; Chou et al., 2015). At this period of life it can be difficult to differentiate LOBD from Alzheimer's disease (AD) (Zahodne et al., 2015). Recent studies have found shared biomarkers between LOBD and AD patients (Berridge, 2013). Similar roles of inflammation and oxidative stress biomarkers have been found in AD (Akiyama et al., 2000; Kamer et al., 2008; Sardi et al., 2011), LOBD (Goldstein et al., 2009; Konradi et al., 2012; Leboyer et al., 2012; Lee et al., 2013; Bauer I et al., 2014; Hope et al., 2015), depression, and mania (Brydon et al., 2009; Dickerson et al., 2013; Castanon et al., 2014; Singhal et al., 2014). Further details of shared LOBD and AD traits are given in Besga et al. (2015b). Specific common psychiatric symptoms are: agitation, euphoria, disinhibition, over-activity without agitation, aggression, affective liability, dysphoria, apathy, impaired self-regulation, and psychosis (Albert and Blacker, 2006; Zahodne et al., 2015). The demographic, neuropsychological, clinical, imaging, and blood plasma analytics data used in our study, as well as the rules for eligibility and discarding of patients, appear in Graña et al. (2011) and Besga et al. (2012, 2015a, 2016, 2017), hence reproducing them here would be self-plagiarism according to journal rules. The content of this paper is as follows: first we refer the contents of the dataset and its location for downloading, then we summarize previously published results. We include the ethics statement and the trial registration reference.
2. Contents of the Dataset
The dataset has been published in the Zenodo public repository (Besga et al., 2020). Its contents are as follows:
• The clinical data includes the following information
- Demographics data, such as age, sex, civil state, environment conditions, and others
- Results of neuropsychological examination: we have carried out tests for executive function, learning and memory, and attention. Details are given in Besga et al. (2015a).
- Clinical observation: we carried out the Neuropsychiatric Inventory and the functional assessment staging (FAST). Details are given in Besga et al. (2015a).
- Blood plasma biomarkers: Neurotrophins, inflammation biomarkers, and oxidative stress biomarkers. Details are given in Besga et al. (2017).
• Magnetic Resonance Imaging (MRI) data obtained on a 1.5 Tesla scanner, that includes the following (details of data capture and preprocessing are given in Graña et al., 2011; Besga et al., 2012, 2016):
- Diffusion weighted imaging (DWI) with high b and 30 gradient directions. The original data is provided in the dataset.
- Fractional Anisotropy (FA) volumes computed from the DWI data after noise correction, registration, and diffusion tensor (DTI) computation. The original FA data and the FA volumes co-registered to MNI template using the T1-weighted data non-linear registration parameters are provided.
- T1-weighted anatomical volumes at 1 mm resolution. Both original and non-linearly registered to MNI template data are provided in the published dataset.
• Results: we provide the following results that can be used as reference for checking the integrity of the data
- Voxel based morphometry (VBM) computed using Statistical Parametric Mapping (SPM) software.1
- Tract based spatial statistics (TBSS) intermediate and final results, as well as the correlations with blood sample biomarkers computed using the FSL software (Smith et al., 2004)2 as published in Besga et al. (2017).
3. Published Results
Previously reported results of this study are as follows:
1. Machine learning based computer aided diagnosis (CAD) (Sigut et al., 2007; Salas-Gonzalez et al., 2009; Ramirez et al., 2010; Savio et al., 2011; Westman et al., 2011; Termenon et al., 2013) achieved high accuracy discrimination between AD and LOBD populations using whole brain FA (Graña et al., 2011; Besga et al., 2012). We discuss there that the good classification performance was not enough due to poor brain localization results causes by the feature extraction process.
2. Again, machine learning techniques applied on the clinical, neuropsychological test, and blood plasma biomarkers give good LOBD vs. AD classification performance (Besga et al., 2015a). Clinical variables reported the highest discriminant power, while blood plasma biomarkers reported low discriminant power. Combinations of both, improved the classification results, showing some indirect effects of blood plasma biomarkers.
3. Using eigenanatomy tools (Avants et al., 2012, 2014) we found an optimal decomposition of the FA volumes that show maximal correlation with plasma biomarkers (Besga et al., 2016). This decomposition provides the features for classifier model building to discriminate AD vs. LOBD classification, providing anatomical localization of the effects corresponding to the classification features, which are consistent with differential diagnostics.
4. The Tract-Based Spatial Statistics (TBSS) (Smith et al., 2006; Bach et al., 2014) allows us to identify strongly significant clusters in behavioral impairment relevant tracts. These clusters show specific correlation with neurotrophins biomarkers in an AD population but none with a LOBD population. We also found a strong positive correlation of inflammation biomarkers with the LOBD population (Besga et al., 2017).
4. Limitations
The major limitation for the data is the small sample size. Recruiting was a long process that took several years due to the advanced age of the participants. Another limitation to keep in mind is that the plasma biomarkers were not extracted specifically from the central nervous system (CNS) tissues, so they are biomarkers of the general state of the body not of specific locations in the CNS.
5. Conclusions
We introduce a public dataset that can be exploited for the identification of biomarkers that allow enhanced differential diagnosis of AD vs. LOBD. We summarize our findings, already published in the literature, in order to encourage innovative computational approaches to be tested on this dataset.
Data Availability Statement
The datasets presented in this study can be found in online repositories. The names of the repository/repositories and accession number(s) can be found at: Zenodo, doi: 10.5281/zenodo.3935636.
Ethics Statement
The ethics committee of the Alava University Hospital, Spain, approved this study. All patients provided written consent to participate in the study, which was conducted according to the provisions of the Helsinki declaration. The study has been registered as an observation trial3 in the ISRCTN registry.
Author Contributions
AB and AG-P have made a substantial contributions to the conception and design of the work. DC and MG contributed to the acquisition, analysis, and interpretation of data for the work. All authors contributed to drafting the work and revising it critically for important intellectual content, provided the final approval of the version to be published, and agree to be accountable for all aspects of the work in ensuring that questions related to the accuracy or integrity of any part of the work are appropriately investigated and resolved.
Funding
This research has been partially funded by the Basque Government grant IT1284-19 for the Computational Intelligence research group, and supported by FEDER funds through MINECO project TIN2017-85827-P. DC has been supported by Basque Government post-doctoral grant No Ref.: POS-2014-1-2, MOD:POSDOC. This work was supported by health research grant 2013111162 from the Department of Education, Linguistic Policy and Culture of the Basque Country Government. This project has received funding from the European Union's Horizon 2020 research and innovation programme under the Marie Sklodowska-Curie grant agreement No 777720.
Conflict of Interest
The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest.
The reviewer FS declared a past co-authorship with one of the authors MG to the handling Editor.
Footnotes
1. ^https://www.fil.ion.ucl.ac.uk/spm/
2. ^http://fsl.fmrib.ox.ac.uk/fsl/fslwiki/TBSS
3. ^http://www.controlled-trials.com/search?q=HS%2FPI2010001
References
Akiyama, H., Barger, S., Barnum, S., Bradt, B., Bauer, J., Cole, G., et al. (2000). Inflammation and Alzheimer's disease. Neurobiol. Aging 21, 383–421. doi: 10.1016/S0197-4580(00)00124-X
Albert, M., and Blacker, D. (2006). Mild cognitive impairment and dementia. Annu. Rev. Clin. Psychol. 2, 379–388. doi: 10.1146/annurev.clinpsy.1.102803.144039
Avants, B., Dhillon, P., Kandel, B., Cook, P., McMillan, C., Grossman, M., et al. (2012). Eigenanatomy improves detection power for longitudinal cortical change. Med. Image Comput. Comput. Assist. Interv. 15, 206–213. doi: 10.1007/978-3-642-33454-2_26
Avants, B. B., Libon, D. J., Rascovsky, K., Boller, A., McMillan, C. T., Massimo, L., et al. (2014). Sparse canonical correlation analysis relates network-level atrophy to multivariate cognitive measures in a neurodegenerative population. Neuroimage 84, 698–711. doi: 10.1016/j.neuroimage.2013.09.048
Bach, M., Laun, F. B., Leemans, A., Tax, C. M., Biessels, G. J., Stieltjes, B., et al. (2014). Methodological considerations on tract-based spatial statistics (tBSS). Neuroimage 100, 358–369. doi: 10.1016/j.neuroimage.2014.06.021
Bauer, I., Pascoe, M., Wollenhaupt-Aguiar, B., Kapczinski, F., and Soares, J. C. (2014). Inflammatory mediators of cognitive impairment in bipolar disorder. J. Psychiatr. Res. 56, 18–27. doi: 10.1016/j.jpsychires.2014.04.017
Bauer, M., Glenn, T., Alda, M., Andreassen, O., Angelopoulos, E., Ardau, R., et al. (2015a). Influence of birth cohort on age of onset cluster analysis in bipolar I disorder. Eur. Psychiatry 30, 99–105. doi: 10.1016/j.eurpsy.2014.10.005
Bauer, M., Glenn, T., Alda, M., Andreassen, O. A., Angelopoulos, E., Ardau, R., et al. (2014). Relationship between sunlight and the age of onset of bipolar disorder: an international multisite study. J. Affect. Disord. 167, 104–111. doi: 10.1016/j.jad.2014.05.032
Bauer, M., Glenn, T., Alda, M., Andreassen, O. A., Angelopoulos, E., Ardau, R., et al. (2015b). Influence of light exposure during early life on the age of onset of bipolar disorder. J. Psychiatr. Res. 64, 1–8. doi: 10.1016/j.jpsychires.2015.03.013
Berridge, M. J. (2013). Dysregulation of neural calcium signaling in alzheimer disease, bipolar disorder and schizophrenia. Prion 7, 2–13. doi: 10.4161/pri.21767
Besga, A., Chyzhyk, D., Gonzalez-Ortega, I., Echeveste, J., Graña-Lecuona, M., Graña, M., et al. (2017). White matter tract integrity in Alzheimer's disease vs. late onset bipolar disorder and its correlation with systemic inflammation and oxidative stress biomarkers. Front. Aging Neurosci. 9:179. doi: 10.3389/fnagi.2017.00179
Besga, A., Chyzhyk, D., Gonzalez-Ortega, I., Savio, A., Ayerdi, B., Echeveste, J., et al. (2016). Eigenanatomy on fractional anisotropy imaging provides white matter anatomical features discriminating between Alzheimer's disease and late onset bipolar disorder. Curr. Alzheimer Res. 13, 557–565. doi: 10.2174/1567205013666151116125349
Besga, A., Gonzalez, I., Echeburua, E., Savio, A., Ayerdi, B., Chyzhyk, D., et al. (2015a). Discrimination between Alzheimer's disease and late onset bipolar disorder using multivariate analysis. Front. Aging Neurosci. 7:231. doi: 10.3389/fnagi.2015.00231
Besga, A., Gonzalez-Ortega, I., Echeburua, E., Savio, A., Ayerdi, B., Chyzhyk, D., et al. (2015b). Discrimination between Alzheimer's disease and late onset bipolar disorder using multivariate analysis. Front. Aging Neurosci. 7:231.
Besga, A., Graña, M., and Chyzhyk, D. (2020). Alzheimer's Disease Versus Bipolar Disorder Versus Health Control MRI Data and Processed Results. Zenodo. doi: 10.5281/zenodo.3935636
Besga, A., Martinez-Cengotitabengoa, M., Gonzalez-Ortega, I., Gutierrez, M., Barbeito, S., and Gonzalez-Pinto, A. (2011). The role of white matter damage in late onset bipolar disorder. Maturitas 70, 160–163. doi: 10.1016/j.maturitas.2011.07.005
Besga, A., Termenon, M., Graña, M., Echeveste, J., Perez, J., and Gonzalez-Pinto, A. (2012). Discovering Alzheimer's disease and bipolar disorder white matter effects building computer aided diagnostic systems on brain diffusion tensor imaging features. Neurosci. Lett. 520, 71–76. doi: 10.1016/j.neulet.2012.05.033
Brydon, L., Walker, C., Wawrzyniak, A., Whitehead, D., Okamura, H., Yajima, J., et al. (2009). Synergistic effects of psychological and immune stressors on inflammatory cytokine and sickness responses in humans. Brain Behav. Immun. 23, 217–224. doi: 10.1016/j.bbi.2008.09.007
Carlino, A., Stinnett, J., and Kim, D. (2013). New onset of bipolar disorder in late life. Psychosomatics 54, 94–97. doi: 10.1016/j.psym.2012.01.006
Castanon, N., Lasselin, J., and Capuron, L. (2014). Neuropsychiatric comorbidity in obesity: role of inflammatory processes. Neuroendocr. Sci. 5:74. doi: 10.3389/fendo.2014.00074
Chou, P.-H., Tseng, W.-J., Chen, L.-M., Lin, C.-C., Lan, T.-H., and Chan, C.-H. (2015). Late onset bipolar disorder: a case report and review of the literature. J. Clin. Gerontol. Geriatr. 6, 27–29. doi: 10.1016/j.jcgg.2014.05.002
Depp, C., and Jeste, D. (2004). Bipolar disorder in older adults: a critical review. Bipolar Disord. 6, 343–367. doi: 10.1111/j.1399-5618.2004.00139.x
Dickerson, F., Stallings, C., Origoni, A., Vaughan, C., Katsafanas, E., Khushalani, S., et al. (2013). A combined marker of inflammation in individuals with mania. PLoS ONE 8:e73520. doi: 10.1371/journal.pone.0073520
Forcada, I., Mur, M., Mora, E., Vieta, E., Bartras-Faz, D., and Portella, M. (2014). The influence of cognitive reserve on psychosocial and neuropsychological functioning in bipolar disorder. Eur. Neuropsychopharmacol. 25, 214–222. doi: 10.1016/j.euroneuro.2014.07.018
Goldstein, B., Kemp, D., Soczynska, J., and McIntyre, R. (2009). Inflammation and the phenomenology, pathophysiology, comorbidity, and treatment of bipolar disorder: a systematic review of the literature. J. Clin. Psychiatry 70, 1078–1090. doi: 10.4088/JCP.08r04505
Graña, M., Termenon, M., Savio, A., Gonzalez-Pinto, A., Echeveste, J., Perez, J., et al. (2011). Computer aided diagnosis system for Alzheimer disease using brain diffusion tensor imaging features selected by pearson's correlation. Neurosci. Lett. 502, 225–229. doi: 10.1016/j.neulet.2011.07.049
Hope, S., Hoseth, E., Dieset, I., Mørch, R. H., Aas, M., Aukrust, P., et al. (2015). Inflammatory markers are associated with general cognitive abilities in schizophrenia and bipolar disorder patients and healthy controls. Schizophr. Res. 165, 188–194. doi: 10.1016/j.schres.2015.04.004
Kamer, A., Craig, R., Dasanayake, A., Brys, M., Glodzik-Sobanska, L., and de Leon, M. (2008). Inflammation and Alzheimer's disease: possible role of periodontal diseases. Alzheimers Dement. 4, 242–250. doi: 10.1016/j.jalz.2007.08.004
Konradi, C., Sillivan, S., and Clay, H. (2012). Mitochondria, oligodendrocytes and inflammation in bipolar disorder: evidence from transcriptome studies points to intriguing parallels with multiple sclerosis. Neurobiol. Dis. 45, 37–47. doi: 10.1016/j.nbd.2011.01.025
Leboyer, M., Soreca, I., Scott, J., Frye, M., Henry, C., Tamouza, R., et al. (2012). Can bipolar disorder be viewed as a multi-system inflammatory disease? J. Affect. Disord. 141, 1–10. doi: 10.1016/j.jad.2011.12.049
Lee, S.-Y., Chen, S.-L., Chang, Y.-H., Chen, P., and Huang, S.-Y. (2013). Inflammation's association with metabolic profiles before and after a twelve-week clinical trial in drug-naive patients with bipolar II disorder. PLoS ONE 8:e66847. doi: 10.1371/journal.pone.0066847
Martinez-Cengotitabengoa, M., Mico, J., Arango, C., Castro-Fornieles, J., Graell, M., Paya, B., et al. (2014). Basal low antioxidant capacity correlates with cognitive deficits in early onset psychosis. A 2-year follow-up study. Schizophr. Res. 156, 23–29. doi: 10.1016/j.schres.2014.03.025
Prabhakar, D., and Balon, R. (2010). Late-onset bipolar disorder a case for careful appraisal. Psychiatry 7, 34–37.
Ramirez, J., Gorriz, J., Segovia, F., Chaves, R., Salas-Gonzalez, D., Lopez, M., et al. (2010). “Early Alzheimer's disease diagnosis using partial least squares and random forests,” in 2010 IEEE International Symposium on Biomedical Imaging: From Nano to Macro (Rotterdam), 81–84. doi: 10.1109/ISBI.2010.5490408
Salas-Gonzalez, D., Górriz, J. M., Ramírez, J., López, M., Illan, I. A., Segovia, F., et al. (2009). Analysis of SPECT brain images for the diagnosis of Alzheimer's disease using moments and support vector machines. Neurosci. Lett. 461, 60–64. doi: 10.1016/j.neulet.2009.05.056
Sardi, F., Fassina, L., Venturini, L., Inguscio, M., Guerriero, F., Rolfo, E., et al. (2011). Alzheimer's disease, autoimmunity and inflammation. The good, the bad and the ugly. Autoimmun. Rev. 11, 149–153. doi: 10.1016/j.autrev.2011.09.005
Savio, A., Garcia-Sebastian, M., Chyzyk, D., Hernandez, C., Graña, M., Sistiaga, A., et al. (2011). Neurocognitive disorder detection based on feature vectors extracted from vbm analysis of structural MRI. Comput. Biol. Med. 41, 600–610. doi: 10.1016/j.compbiomed.2011.05.010
Sigut, J., Piñeiro, J., Gonzalez, E., and Torres, J. (2007). An expert system for supervised classifier design: application to alzheimer diagnosis. Expert Syst. Appl. 32, 927–938. doi: 10.1016/j.eswa.2006.01.026
Singhal, G., Jaehne, E., Corrigan, F., Toben, C., and Baune, B. (2014). Inflammasomes in neuroinflammation and changes in brain function: a focused review. Neuroendocr. Sci. 8:315. doi: 10.3389/fnins.2014.00315
Smith, S. M., Jenkinson, M., Johansen-Berg, H., Rueckert, D., Nichols, T. E., Mackay, C. E., et al. (2006). Tract-based spatial statistics: voxelwise analysis of multi-subject diffusion data. Neuroimage 31, 1487–1505. doi: 10.1016/j.neuroimage.2006.02.024
Smith, S. M., Jenkinson, M., Woolrich, M. W., Beckmann, C. F., Behrens, T. E., Johansen-Berg, H., et al. (2004). Advances in functional and structural MR image analysis and implementation as FSL. Neuroimage 23, S208–S219. doi: 10.1016/j.neuroimage.2004.07.051
Termenon, M., Graña, M., Besga, A., Echeveste, J., and Gonzalez-Pinto, A. (2013). Lattice independent component analysis feature selection on diffusion weighted imaging for Alzheimer's disease classification. Neurocomputing 114, 132–141. doi: 10.1016/j.neucom.2012.08.044
Westman, E., Simmons, A., Zhang, Y., Muehlboeck, J., Tunnard, C., Liu, Y., et al. (2011). Multivariate analysis of MRI data for Alzheimer's disease, mild cognitive impairment and healthy controls. Neuroimage 54, 1178–1187. doi: 10.1016/j.neuroimage.2010.08.044
Zahodne, L. B., Ornstein, K., Cosentino, S., Devanand, D., and Stern, Y. (2015). Longitudinal relationships between Alzheimer disease progression and psychosis, depressed mood, and agitation/aggression. Am. J. Geriatr. Psychiatry 23, 130–140. doi: 10.1016/j.jagp.2013.03.014
Keywords: late onset bipolar disorder, Alzheimer's disease, MRI data, blood biomarkers, machine learning
Citation: Besga A, Chyzhyk D, Graña M and Gonzalez-Pinto A (2020) An Imaging and Blood Biomarkers Open Dataset on Alzheimer's Disease vs. Late Onset Bipolar Disorder. Front. Aging Neurosci. 12:583212. doi: 10.3389/fnagi.2020.583212
Received: 14 July 2020; Accepted: 24 August 2020;
Published: 29 October 2020.
Edited by:
Ramesh Kandimalla, Texas Tech University Health Sciences Center, United StatesReviewed by:
Nilo Riva, San Raffaele Hospital (IRCCS), ItalyFermín Segovia, University of Granada, Spain
Copyright © 2020 Besga, Chyzhyk, Graña and Gonzalez-Pinto. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
*Correspondence: Ariadna Besga, ariadna.besgabasterra@osakidetza.net