How Do We Alleviate Long-Term Psychological Distress for Surrogate Decision Makers?

Our perspective as clinicians is focused on the patient; however, when patients present with severe stroke, we rely on family or surrogate decision-makers to assist with decisions regarding life-sustaining treatment. In this issue of Neurology®, Morgenstern et al.1 report on long-term psychological distress among surrogate decision-makers for patients with severe stroke. The authors used validated measures of post-traumatic stress, anxiety, and depression among family surrogate decision-makers and found between 17% and 28% of surrogates to have high scores on measures of psychological distress. One or more high levels of the psychological outcomes were found in 17%-43% of surrogates, 2 or more were found in 12%-27%, and all 3 were found in 5%-16% of surrogates. The study population included a biethnic community of predominantly nonimmigrant Mexican American (MA) and non-Hispanic White (NHW) persons, and outcomes were evaluated by ethnicity. Symptoms of post-traumatic stress remained worse among MA surrogates in the fully adjusted model; however, they were no longer significant for anxiety or depression after adjustment. The authors conclude that psychological distress is common among family surrogate decision-makers in the year after stroke and may be worse among MA surrogates. The authors propose that efforts are needed to support family members of all ethnic groups after severe stroke.

Large Vessel Occlusion Prediction in the Emergency Department with National Institutes of Health Stroke Scale Components: A Machine Learning Approach.

OBJECTIVE: To determine the feasibility of using a machine learning algorithm to screen for large vessel occlusions (LVO) in the Emergency Department (ED). MATERIALS AND METHODS: A retrospective cohort of consecutive ED stroke alerts at a large comprehensive stroke center was analyzed. The primary outcome was diagnosis of LVO at discharge. Components of the National Institutes of Health Stroke Scale (NIHSS) were used in various clinical methods and machine learning algorithms to predict LVO, and the results were compared with the baseline method (aggregate NIHSS score with threshold of 6). The Area-Under-Curve (AUC) was used to measure the overall performance of the models. Bootstrapping (n = 1000) was applied for the statistical analysis. RESULTS: Of 1133 total patients, 67 were diagnosed with LVO. A Gaussian Process (GP) algorithm significantly outperformed other methods including the baseline methods. AUC score for the GP algorithm was 0.874 ± 0.025, compared with the simple aggregate NIHSS score, which had an AUC score of 0.819 ± 0.024. A dual-stage GP algorithm is proposed, which offers flexible threshold settings for different patient populations, and achieved an overall sensitivity of 0.903 and specificity of 0.626, in which sensitivity of 0.99 was achieved for high-risk patients (defined as initial NIHSS score > 6). CONCLUSION: Machine learning using a Gaussian Process algorithm outperformed a clinical cutoff using the aggregate NIHSS score for LVO diagnosis. Future studies would be beneficial in exploring prospective interventions developed using machine learning in screening for LVOs in the emergent setting.