Saliva RNA biomarkers predict concussion duration and detect symptom recovery: a comparison with balance and cognitive testing

Abstract

Objective: The goals of this study were to assess the ability of salivary non-coding RNA (ncRNA) levels to predict post-concussion symptoms lasting ≥ 21 days, and to examine the ability of ncRNAs to identify recovery compared to cognition and balance.

Methods: RNA sequencing was performed on 505 saliva samples obtained longitudinally from 112 individuals (8-24-years-old) with mild traumatic brain injury (mTBI). Initial samples were obtained ≤ 14 days post-injury, and follow-up samples were obtained ≥ 21 days post-injury. Computerized balance and cognitive test performance were assessed at initial and follow-up time-points. Machine learning was used to define: (1) a model employing initial ncRNA levels to predict persistent post-concussion symptoms (PPCS) ≥ 21 days post-injury; and (2) a model employing follow-up ncRNA levels to identify symptom recovery. Performance of the models was compared against a validated clinical prediction rule, and balance/cognitive test performance, respectively.

Results: An algorithm using age and 16 ncRNAs predicted PPCS with greater accuracy than the validated clinical tool and demonstrated additive combined utility (area under the curve (AUC) 0.86; 95% CI 0.84-0.88). Initial balance and cognitive test performance did not differ between PPCS and non-PPCS groups (p > 0.05). Follow-up balance and cognitive test performance identified symptom recovery with similar accuracy to a model using 11 ncRNAs and age. A combined model (ncRNAs, balance, cognition) most accurately identified recovery (AUC 0.86; 95% CI 0.83-0.89).

Conclusions: ncRNA biomarkers show promise for tracking recovery from mTBI, and for predicting who will have prolonged symptoms. They could provide accurate expectations for recovery, stratify need for intervention, and guide safe return-to-activities.

Keywords: mTBI; microRNA; prognosis; return to play; spit; traumatic brain injury.

Fig. 1

Longitudinal patterns in self-reported symptoms among individuals with or without persistent post-concussion symptoms (PPCS). a A scatter plot of symptom severity score versus time post-injury for all study participants. Participants having symptom scores > 5 persisting ≥ 21 days post-injury (black dotted lines) were considered to have PPCS. b The 22 PCSS symptoms were grouped and normalized to account for unequal numbers of symptoms per group. Longitudinal symptom scores, normalized by symptom category for PPCS and non-PPCS cohorts, were fit with a local regression and visualized with the 95% confidence intervals (gray). c Longitudinal trends for the nine symptoms most commonly reported by the PPCS cohort, grouped by PPCS status. d Table comparing the most frequently reported symptoms at initial and follow-up time points for PPCS and non-PPCS participants

Fig. 2

Differences in balance, cognition, and salivary RNA levels between PPCS and non-PPCS participants emerge ≥ 21 days post-injury. a Box and whisker plots comparing grouped symptom scores between PPCS and non-PPCS participants at both initial (< 14 days) and follow-up (≥ 21 days post-injury) time points. b Plot comparing balance test performance between PPCS and non-PPCS groups across eight different tests at initial and follow-up time points. c Plot comparing cognitive test performance between PPCS and non-PPCS groups across four different tests. d, e Volcano plots comparing RNA abundance between PPCS and non-PPCS subjects at initial and follow-up timepoints. Statistical significance, − log10(p value), was plotted against the log2(fold change). A false discovery rate of 0.05 (red) and absolute fold change > 1.5 (yellow) were used as significance cut-offs. ncRNAs passing both criteria are shown in green. *p ≤ 0.05, **p ≤ 0.01, and ***p ≤ 0.001

Fig. 3

Predicting PPCS risk. A model employing 16 small non-coding RNAs and age accurately predicted PPCS a. A GBM algorithm was used to rank model features in order of variable importance. Normalized counts were scaled across RNAs, averaged across PPCS class, and plotted as a heat map to illustrate relative abundance. b A receiving-operating characteristic (ROC) curve demonstrates the ability of a rSVM classifier to identify PPCS in a training (green) and testing (blue) set. The testing confusion matrix and AUCs are reported in the plot. c ROC curves comparing the performance (AUC) of the RNA PPCS model (“RNA”) with a clinical standard (“Zemek”), as well as an additive model (“RNA + Zemek”). Performance was evaluated using tenfold cross-validation repeated 10 times. The 95% confidence intervals were calculated using the method of DeLong. d Table showing the sample breakdown and performance characteristics for the training, evaluation, and testing sets. Sensitivity, specificity, positive (PPV) and negative (NPV) predictive values, and balanced accuracy were calculated using a probability threshold of 0.26, which was optimized using the evaluation set

Fig. 4

Identifying mTBI recovery using balance, cognitive, and ncRNA measures. a 11 RNAs, eight balance test scores, four cognitive test scores, and age were used to determine mTBI recovery with high accuracy (AUC = 0.86). The Clear Edge platform was used for objective measurement of balance and cognition. b ROC curve showing the ability of three random forest classifiers to classify recovered participants at ≥ 21 days, using either (1) 12 balance and cognitive test scores and age (“BalCog”), (2) 11 RNA features and age (“RNA”), or (3) an additive model combining 1 and 2 (“RNA + BalCog”). Performance was evaluated using tenfold cross-validation repeated 10 times. The 95% confidence intervals were calculated using the method of DeLong