Post-stroke Anxiety Analysis via Machine Learning Methods

Abstract

Post-stroke anxiety (PSA) has caused wide public concern in recent years, and the study on risk factors analysis and prediction is still an open issue. With the deepening of the research, machine learning has been widely applied to various scenarios and make great achievements increasingly, which brings new approaches to this field. In this paper, 395 patients with acute ischemic stroke are collected and evaluated by anxiety scales (i.e., HADS-A, HAMA, and SAS), hence the patients are divided into anxiety group and non-anxiety group. Afterward, the results of demographic data and general laboratory examination between the two groups are compared to identify the risk factors with statistical differences accordingly. Then the factors with statistical differences are incorporated into a multivariate logistic regression to obtain risk factors and protective factors of PSA. Statistical analysis shows great differences in gender, age, serious stroke, hypertension, diabetes mellitus, drinking, and HDL-C level between PSA group and non-anxiety group with HADS-A and HAMA evaluation. Meanwhile, as evaluated by SAS scale, gender, serious stroke, hypertension, diabetes mellitus, drinking, and HDL-C level differ in the PSA group and the non-anxiety group. Multivariate logistic regression analysis of HADS-A, HAMA, and SAS scales suggest that hypertension, diabetes mellitus, drinking, high NIHSS score, and low serum HDL-C level are related to PSA. In other words, gender, age, disability, hypertension, diabetes mellitus, HDL-C, and drinking are closely related to anxiety during the acute stage of ischemic stroke. Hypertension, diabetes mellitus, drinking, and disability increased the risk of PSA, and higher serum HDL-C level decreased the risk of PSA. Several machine learning methods are employed to predict PSA according to HADS-A, HAMA, and SAS scores, respectively. The experimental results indicate that random forest outperforms the competitive methods in PSA prediction, which contributes to early intervention for clinical treatment.

Serum Neurofilament Light Predicts 6-Month Mental Health Outcomes in a Cohort of Patients With Acute Ischemic Stroke

“…Post-stroke mental health disorders, including PSD (17), PSA (18), and PSI (19), are harmful to the quality of life in patients with AIS. Furthermore, these neuropsychological consequences of AIS have adverse effects on functional improvement of AIS.…”

“…Accordingly, the 9item Patient Health Questionnaire (PHQ-9; range, 0-27) (13), the 7-item Generalized Anxiety Disorder (GAD-7) scale (range, 0-21) ( 14), the 7-item Insomnia Severity Index (ISI; range, 0-28) (15), were used to assess the severity of symptoms of depression, anxiety, and insomnia, respectively. The total scores of these measurement tools were interpreted as follows: PHQ-9, normal (0-4), mild (5-9), moderate (10)(11)(12)(13)(14), and severe (15)(16)(17)(18)(19)(20)(21)(22)(23)(24)(25)(26)(27) depression; GAD-7, normal (0-4), mild (5-9), moderate (10)(11)(12)(13)(14), and severe (15)(16)(17)(18)(19)(20)(21) anxiety; ISI, normal (0-7), subthreshold (8)(9)(10)(11)(12)(13)(14), moderate (15)(16)(17)(18)(19)(20)(21), and severe (22)…”

Post-Stroke Neuropsychiatric Complications: Types, Pathogenesis, and Therapeutic Intervention

“…Post-stroke anxiety (PSAn), a consequence of poor motor functioning and substantial decline in quality of life, is a common mental disorder that compromises patient rehabilitation, and, in turn, results in a lasting and steady deterioration of life quality. Previous accumulative studies have reported that PSAn occurs in 18% to 34% of survivors during the first year after stroke, and the rates did not lower meaningfully up to 5 years after stroke [ 59 - 62 ]. Nevertheless, as a serious psychological and physiological problem, PSAn is relatively neglected, presently, compared to other post-stroke psychological disorders.…”

A machine learning approach for predicting suicidal ideation in post stroke patients

“…Most of the developed stroke prediction models are reported in studies on diagnosis, sequela, mortality, and physical function, and cannot be conveniently used practically owing to the associated invasive measurements and analyses 13 – 16 . Additionally, while studies on predictive model development for stroke-related emotional disorders, such as post-stroke anxiety and PSD have been conducted 17 , 18 , the predictors used in these models were assessed at one-month post-stroke, at which point full depressive symptoms may not be present. Additionally, procedures need to be devised for the comparison of different machine learning models to select the best among them.…”