Hierarchical clustering of prolonged post-concussive symptoms after 12 months: symptom-centric analysis and association with functional impairments.

BACKGROUND: Following a concussion, approximately 15% of individuals experience persistent symptoms that can lead to functional deficits. However, underlying symptom-clusters that persist beyond 12 months have not been adequately characterized, and their relevance to functional deficits are unclear. The aim of this study was to characterize the underlying clusters of prolonged post-concussive symptoms lasting more than 12 months, and to investigate their association with functional impairments. METHODS: Although hierarchical clustering is ideally suited in evaluating subjective symptom severities, it has not been applied to the Rivermead Post-Concussion Questionnaire (RPQ). The RPQ and functional impairments questions were administered via a smartphone application to 445 individuals who self-reported prolonged post-concussive symptoms. Symptom-clusters were obtained using agglomerative hierarchical clustering, and their association with functional deficits were investigated with sensitivity analyses, and corrected for multiple comparisons. RESULTS: Five symptom-clusters were identified: headache-related, sensitivity to light and sound, cognitive, mood-related, and sleep-fatigue. Individuals with more severe RPQ symptoms were more likely to report functional deficits (p < 0.0001). Whereas the headache and sensitivity clusters were associated with at most one impairment, at-least-mild sleeping difficulties and fatigue were associated with four, and moderate-to-severe cognitive difficulties with five (all p < 0.01). CONCLUSIONS: Symptom-clusters may be clinically useful for functional outcome stratification for targeted rehabilitation therapies. Further studies are required to replicate these findings in other cohorts and questionnaires, and to ascertain the effects of symptomatic intervention on functional outcomes.

Subjective brain fog: a four-dimensional characterization in 25,796 participants.

Importance: Brain fog is associated with significant morbidity and reduced productivity and gained increasing attention after COVID-19. However, this subjective state has not been systematically characterised. Objective: To characterise self-reported brain fog. Design: We systematically studied the cross-sectional associations between 29 a priori variables with the presence of "brain fog." The variables were grouped into four categories: demographics, symptoms and functional impairments, comorbidities and potential risk factors (including lifestyle factors), and cognitive score. Univariate methods determined the correlates of brain fog, with long-COVID and non-long-COVID subgroups. XGBoost machine learning model retrospectively characterised subjective brain fog. Bonferroni-corrected statistical significance was set at 5%. Setting: Digital application for remote data collection. Participants: 25,796 individuals over the age of 18 who downloaded and completed the application. Results: 7,280 of 25,796 individuals (28.2%) reported experiencing brain fog, who were generally older (mean brain fog 35.7 ± 11.9 years vs. 32.8 ± 11.6 years, p < 0.0001) and more likely to be female (OR = 1.2, p < 0.001). Associated symptoms and functional impairments included difficulty focusing or concentrating (OR = 3.3), feeling irritable (OR = 1.6), difficulty relaxing (OR = 1.2, all p < 0.0001), difficulty following conversations (OR = 2.2), remembering appointments (OR = 1.9), completing paperwork and performing mental arithmetic (ORs = 1.8, all p < 0.0001). Comorbidities included long-COVID-19 (OR = 3.8, p < 0.0001), concussions (OR = 2.4, p < 0.0001), and higher migraine disability assessment scores (MIDAS) (+34.1%, all p < 0.0001). Cognitive scores were marginally lower with brain fog (-0.1 std., p < 0.001). XGBoost achieved a training accuracy of 85% with cross-validated accuracy of 74%, and the features most predictive of brain fog in the model were difficulty focusing and following conversations, long-COVID, and severity of migraines. Conclusions and relevance: This is the largest study characterising subjective brain fog as an impairment of concentration associated with functional impairments in activities of daily living. Brain fog was particularly associated with a history of long-COVID-19, migraines, concussion, and with 0.1 standard deviations lower cognitive scores, especially on modified Stroop testing, suggesting impairments in the ability to inhibit cognitive interference. Further prospective studies in unselected brain fog sufferers should explore the full spectrum of brain fog symptoms to differentiate it from its associated conditions.

Validation of a rapid remote digital test for impaired cognition using clinical dementia rating and mini-mental state examination: An observational research study.

Background: The Clinical Dementia Rating (CDR) and Mini-Mental State Examination (MMSE) are useful screening tools for mild cognitive impairment (MCI). However, these tests require qualified in-person supervision and the CDR can take up to 60 min to complete. We developed a digital cognitive screening test (M-CogScore) that can be completed remotely in under 5 min without supervision. We set out to validate M-CogScore in head-to-head comparisons with CDR and MMSE. Methods: To ascertain the validity of the M-CogScore, we enrolled participants as healthy controls or impaired cognition, matched for age, sex, and education. Participants completed the 30-item paper MMSE Second Edition Standard Version (MMSE-2), paper CDR, and smartphone-based M-CogScore. The digital M-CogScore test is based on time-normalised scores from smartphone-adapted Stroop (M-Stroop), digit-symbols (M-Symbols), and delayed recall tests (M-Memory). We used Spearman's correlation coefficient to determine the convergent validity between M-CogScore and the 30-item MMSE-2, and non-parametric tests to determine its discriminative validity with a CDR label of normal (CDR 0) or impaired cognition (CDR 0.5 or 1). M-CogScore was further compared to MMSE-2 using area under the receiver operating characteristic curves (AUC) with corresponding optimal cut-offs. Results: 72 participants completed all three tests. The M-CogScore correlated with both MMSE-2 (rho = 0.54, p < 0.0001) and impaired cognition on CDR (Mann Whitney U = 187, p < 0.001). M-CogScore achieved an AUC of 0.85 (95% bootstrapped CI [0.80, 0.91]), when differentiating between normal and impaired cognition, compared to an AUC of 0.78 [0.72, 0.84] for MMSE-2 (p = 0.21). Conclusion: Digital screening tests such as M-CogScore are desirable to aid in rapid and remote clinical cognitive evaluations. M-CogScore was significantly correlated with established cognitive tests, including CDR and MMSE-2. M-CogScore can be taken remotely without supervision, is automatically scored, has less of a ceiling effect than the MMSE-2, and takes significantly less time to complete.

Optimizing Existing Mental Health Screening Methods in a Dementia Screening and Risk Factor App: Observational Machine Learning Study.

BACKGROUND: Mindstep is an app that aims to improve dementia screening by assessing cognition and risk factors. It considers important clinical risk factors, including prodromal symptoms, mental health disorders, and differential diagnoses of dementia. The 9-item Patient Health Questionnaire for depression (PHQ-9) and the 7-item Generalized Anxiety Disorder Scale (GAD-7) are widely validated and commonly used scales used in screening for depression and anxiety disorders, respectively. Shortened versions of both (PHQ-2/GAD-2) have been produced. OBJECTIVE: We sought to develop a method that maintained the brevity of these shorter questionnaires while maintaining the better precision of the original questionnaires. METHODS: Single questions were designed to encompass symptoms covered in the original questionnaires. Answers to these questions were combined with PHQ-2/GAD-2, and anonymized risk factors were collected by Mindset4Dementia from 2235 users. Machine learning models were trained to use these single questions in combination with data already collected by the app: age, response to a joke, and reporting of functional impairment to predict binary and continuous outcomes as measured using PHQ-9/GAD-7. Our model was developed with a training data set by using 10-fold cross-validation and a holdout testing data set and compared to results from using the shorter questionnaires (PHQ-2/GAD-2) alone to benchmark performance. RESULTS: We were able to achieve superior performance in predicting PHQ-9/GAD-7 screening cutoffs compared to PHQ-2 (difference in area under the curve 0.04, 95% CI 0.00-0.08, P=.02) but not GAD-2 (difference in area under the curve 0.00, 95% CI -0.02 to 0.03, P=.42). Regression models were able to accurately predict total questionnaire scores in PHQ-9 (R2=0.655, mean absolute error=2.267) and GAD-7 (R2=0.837, mean absolute error=1.780). CONCLUSIONS: We app-adapted PHQ-4 by adding brief summary questions about factors normally covered in the longer questionnaires. We additionally trained machine learning models that used the wide range of additional information already collected in Mindstep to make a short app-based screening tool for affective disorders, which appears to have superior or equivalent performance to well-established methods.