Finding biomarkers of cognitive decline in active professional fighters with multimodal MRI and exploring the longitudinal relationship of these biomarkers with cognitive decline
Virendra R Mishra1, Xiaowei Zhuang1, Karthik Sreenivasan1, Zhengshi Yang1, Sarah Banks1, Charles Bernick1, and Dietmar Cordes1

1Cleveland Clinic Lou Ruvo Center for Brain Health, Las Vegas, NV, United States

Synopsis

Several cross-sectional MRI studies have shown structural differences in professional fighters but there has been no results reported in longitudinal studies of such active fighters. The professional fighters brain health study (PFBHS) is a longitudinal study of active professional fighters with age-matched healthy controls using multimodal MRI methods. In this study, we show that the features/biomarkers predicting cognitive decline at baseline are sensitive and specific over time in our cohort of longitudinal active fighters. Our study opens a new window to predict and monitor cognitive decline in patients with traumatic brain injuries.

Introduction

Studies have shown that both active and retired athletes with repeated head trauma are more likely to suffer from cognitive decline and loss of executive and attention functions when compared to age-matched healthy controls1, 2. Several cross-sectional MRI studies have shown structural differences in such athletes but there has been no results reported in longitudinal studies of such active fighters3, 4. The professional fighters brain health study (PFBHS) is a longitudinal study of active professional fighters with age-matched healthy controls using multimodal MRI methods5. In this study, we show that the features predicting cognitive decline at baseline are sensitive and specific over time in our cohort of longitudinal active fighters.

Methods

Baseline Subjects: 331 subjects (21-controls (20male (M); 30.1±8.28years), 119-boxers (108M; 29.71±7.06years), 152-mixed-martial-arts-fighters (143M; 29.05±5.04years), 22-martial-arts-fighters (19M; 28.36±5.04years) and 17-mixed-fighters (15M; 30±5.66years)) were recruited at the center. Years of education, number of professional and amateur fights, race, gender and year of first fighting were recorded at every visit. Each subject went through various neuropsychological assessment tests to measure psychomotor speed (PSY) and processing (P) speed. These scores were standardized6 (PSYSTANS/PSTANS) and the fighters were categorized as “impaired” (99-subjects) or “non-impaired” (211-subjects). Timepoint1 subjects: 79 subjects (6-controls, 19-impaired-fighters and 54-nonimpaired-fighters) were scanned again after at-least one year. Data Acquisition: All subjects, at both timepoints, were scanned with a 3T Siemens Verio scanner. Single-shot-EPI-sequence was used to acquire diffusion weighted images (DWIs) with 71 diffusion directions and b-value of 1000 s/mm2; TR/TE/Resolution=7000ms/91ms/2.5mm3. Sagittal-MPRAGE T1-weighted images were also acquired for every subject within the same session with TR/TE/FA/Resolution= 2300ms/2.98ms/9o/1mm3. Data Processing: Standard processing steps were used to fit diffusion tensors after eddy current distortion correction in FSL7. After registering each subject to MNI152 template using tbss_2_reg and tbss_3_postreg procedures from TBSS8, various diffusion metrics such as fractional anisotropy (FA), axial diffusivity (AxD), transverse diffusivity (RD) and mean diffusivity (MD) were estimated for all the 20 major white matter (WM) tracts from JHU WM atlas9. Using AAL template in MNII152 space, MD was also estimated for all the 116 gray matter AAL structures. Various other structural measures such as volume and thickness were extracted for every subject for every label in Collin’s atlas using Freesurfer v5.3.010. Feature selection: A total of 314 features (113 structural measurements, 196 diffusion measurements, gender, age, years of education, years of professional fighting and type of fighters) were used for supervised feature classification using an in-house feature selection algorithm combining least absolute shrinkage and selection operator (LASSO)11 and radial basis functional network (RBFN)12. Relationship between the features and the cognitive score: The mean of the extracted features at the baseline were plotted against PSTANS and PSYSTANS to explore if the features predicted cognitive decline in the fighters. The change in the extracted features over time were also plotted against change (Δ) in PSTANS and ΔPSYSTANS to explore the sensitivity and specificity of the predicted features on cognitive decline. Nonparametric t-tests was used to perform statistical comparisons, controlled for age and gender.

Results

Machine learning algorithm detected 6/314 features (FA of FMajor and inferior longitudinal fasciculus (ILF), left cerebellum white matter volume, left thalamic volume, thickness of left lateralorbitofrontal and left medialorbitofrontal) that predicted cognitive decline in our cohorts (prediction accuracy=0.7; Area under the curve=0.724). Mean values of all the extracted features normalized with respect to controls is shown in the left panel of Fig. 1. Boxplot of all the features (baseline and timepoint1) for the 3 groups (right panel of Fig. 1 and Fig 3) shows a significant decline (p<0.05) in the values for impaired fighters as compared to nonimpaired fighters and controls. PSTANS, ΔPSTANS, PSYSTANS and ΔPSYSTANS showed a significant relationship (p<0.05) with the predicted features (baseline and timepoint1) (Fig 2a, Fig 2b, Fig 4a and Fig 4b). Of note, significant difference in the slope (p<0.05) was observed for FA of FMajor between impaired and nonimpaired fighters (baseline and timepoint1) and left thalamic volume between control and impaired fighters (timepoint1).

Discussion and Conclusion

Using a novel machine learning approach combining LASSO and RBFN on a multimodal MRI dataset, our results show 6 features that predict cognitive decline in our cohort of professional fighters. Our results also report for the first time that the features predicting cognitive decline at baseline using machine learning algorithm are sensitive and specific over time in our longitudinal cohort of active professionals. The predictive features showed a significant relationship between the neuropsychological assessment tests and hence can be used as a surrogate to predict/monitor cognitive decline in patients with traumatic brain injuries.

Acknowledgements

This study was supported by NIH 7R01EB014284 and funding from the Lincy foundation.

References

[1] Casson et al., 1984. JAMA., 251:2663-2667. [2] McKee et al., 2013. Brain., 136:43-64. [3] Bernick and Banks., 2013. Alzheimers Res Ther., 5:23. [4] Shin et al., 2014. AJNR Am J Neuroradiol., 35:285-290. [5] Bernick et al., 2013. Am. J. Epidemol., 178 :280-286. [6] Williams et al., 2011. Arthritis Care Res., 63:1178-1187.[7] Andersson et al., 2003. Neuroimage., 20:870-888. [8] Smith et al., 2006. Neuroimage., 31:1487-1505. [9] Wakana et al., 2004. Radiology., 230:77-87. [10] Dale et al., 1999. Neuroimage., 9:179-194. [11] Tibshirani R., 1994. Journal of the Royal Statistical Society, Series B., 58:267-288. [12] Orr M., 1996. http://www.anc.ed.ac.uk/~mjo/intro.ps

Figures

(a) Mean across the three groups for every feature relative to the controls are shown in the left panel. (b) Boxplot of the features are shown for the three groups. The circle and asterisk represents the standard deviation and the mean value for all the features. **p<0.05

Mean values for each feature for all the groups are plotted against the standardized processing speed (a) and standardized psychomotor speed (b). Impaired fighters, nonimpaired fighters and controls are represented by the orange circle, green diamonds and dashed blue rectangle respectively. The linear relationship is shown by the same colors.

Boxplot of the distinguishing features at baseline and timepoint1 are shown for the three groups. The circle and asterisk represents the standard deviation and the mean value for all the features. Relationship for each feature over time is shown by the straight line for every feature and each group. **p<0.05

Change (Δ) in the values of each feature in every group is plotted against Δstandardized processing speed (a) , Δstandardized psychomotor speed (b). Impaired fighters, nonimpaired fighters and controls are represented by the orange circle, green diamonds and dashed blue rectangle respectively. The linear relationship is shown by the same colors.



Proc. Intl. Soc. Mag. Reson. Med. 24 (2016)
3359