Stroke is an acute neurological dysfunction attributed to a focal injury of the central nervous system due to reduced blood flow to the brain. Nowadays, stroke is a global threat associated with premature death and huge economic consequences. Hence, there is an urgency to model the effect of several risk factors on stroke occurrence, and artificial intelligence (AI) seems to be the appropriate tool. In the present study, we aimed to (i) develop reliable machine learning (ML) prediction models for stroke disease; (ii) cope with a typical severe class imbalance problem, which is posed due to the stroke patients’ class being significantly smaller than the healthy class; and (iii) interpret the model output for understanding the decision-making mechanism. The effectiveness of the proposed ML approach was investigated in a comparative analysis with six well-known classifiers with respect to metrics that are related to both generalization capability and prediction accuracy. The best overall false-negative rate was achieved by the Multi-Layer Perceptron (MLP) classifier (18.60%). Shapley Additive Explanations (SHAP) were employed to investigate the impact of the risk factors on the prediction output. The proposed AI method could lead to the creation of advanced and effective risk stratification strategies for each stroke patient, which would allow for timely diagnosis and the right treatments.

Ischemic stroke (IS) exhibits significant heterogeneity in terms of etiology and pathophysiology. Several recent studies highlight the significance of inflammation in the onset and progression of IS. White blood cell subtypes, such as neutrophils and monocytes, participate in the inflammatory response in various ways. On the other hand, high-density lipoproteins (HDL) exhibit substantial anti-inflammatory and antioxidant actions. Consequently, novel inflammatory blood biomarkers have emerged, such as neutrophil to HDL ratio (NHR) and monocyte to HDL ratio (MHR). Literature research of two databases (MEDLINE and Scopus) was conducted to identify all relevant studies published between 1 January 2012 and 30 November 2022 dealing with NHR and MHR as biomarkers for IS prognosis. Only full-text articles published in the English language were included. Thirteen articles have been traced and are included in the present review. Our findings highlight the utility of NHR and MHR as novel stroke prognostic biomarkers, the widespread application, and the calculation of which, along with their inexpensive cost, make their clinical application extremely promising.

Stroke constitutes the primary source of adult functional disability, exhibiting a paramount socioeconomic burden. Thus, it is of great importance that the prediction of stroke outcome be both prompt and accurate. Although modern neuroimaging and neurophysiological techniques are accessible, easily available blood biomarkers reflecting underlying stroke-related pathophysiological processes, including glial and/or neuronal death, neuroendocrine responses, inflammation, increased oxidative stress, blood–brain barrier disruption, endothelial dysfunction, and hemostasis, are required in order to facilitate stroke prognosis. A literature search of two databases (MEDLINE and Science Direct) was conducted in order to trace all relevant studies published between 1 January 2010 and 31 December 2021 that focused on the clinical utility of brain natriuretic peptide, glial fibrillary acidic protein, the red cell distribution width, the neutrophil-to-lymphocyte ratio, matrix metalloproteinase-9, and aquaporin-4 as prognostic tools in stroke survivors. Only full-text articles published in English were included. Twenty-eight articles were identified and are included in this review. All studied blood-derived biomarkers proved to be valuable prognostic tools poststroke, the clinical implementation of which may accurately predict the survivors’ functional outcomes, thus significantly enhancing the rehabilitation efficiency of stroke patients. Along with already utilized clinical, neurophysiological, and neuroimaging biomarkers, a blood-derived multi-biomarker panel is proposed as a reasonable approach to enhance the predictive power of stroke prognostic models.

The purpose of the present study was to review all available work published within the last decade focusing on coping strategies in stroke caregivers and their impact on quality of Life (QoL) and psycho-emotional status. A literature search of two databases (MEDLINE, Scopus) was conducted to identify all relevant full-text English studies published between 2013–2023. Sixteen articles were traced and were finally included. Cognitive and behavioral coping strategies were beneficial for stroke caregivers’ and survivors’ QoL. The level of mutuality in the caregiver-survivor relationship was associated with the impact of depressive symptoms on caregivers’ QoL and the protective effect of mutuality on survivors’ QoL over time. The level and quality of social support were positively associated with QoL for stroke caregivers and survivors. Caregivers’ preparedness was a moderator for the impact of depression on both caregivers’ and survivors’ QoL. High levels of spirituality had a significant role in ameliorating the negative impact of depressive symptoms on the psychological and physical QoL of stroke caregivers and survivors. In conclusion, the study of coping strategies can be used as a psychological reserve in the process of stroke rehabilitation and actively contribute to improving the QoL of both caregivers and stroke survivors.

Stroke is one of the main causes of long-term disabilities, increasing the cost of national healthcare systems due to the elevated costs of rigorous treatment that is required, as well as personal cost because of the decreased ability of the patient to work. Traditional rehabilitation strategies rely heavily on individual clinical data and the caregiver’s experience to evaluate the patient and not in data extracted from population data. The use of machine learning (ML) algorithms can offer evaluation tools that will lead to new personalized interventions. The aim of this scoping review is to introduce the reader to key directions of ML techniques for the prediction of functional outcomes in stroke rehabilitation and identify future scientific research directions. The search of the relevant literature was performed using PubMed and Semantic Scholar online databases. Full-text articles were included if they focused on ML in predicting the functional outcome of stroke rehabilitation. A total of 26 out of the 265 articles met our inclusion criteria. The selected studies included ML approaches and were directly related to the inclusion criteria. ML can play a key role in supporting decision making during pre- and post-treatment interventions for post-stroke survivors, by utilizing multidisciplinary data sources.

This study compared the five most commonly used equations for calculating gait symmetry in discrete variables among Parkinson’s disease patients. Twelve patients (five women and seven men) performed ten consecutive gait trials on a 10 m walkway. Gait data were collected using eight optoelectronic cameras (100 fr/s). The analysis focused on various spatiotemporal parameters, including cadence, step time, stride time, single support, double support, walking speed, step length, stride length, step width, and foot angle. Five symmetry indices were calculated for each trial rather than averaging the ten recorded trials. The variability in and reliability of each symmetry equation were assessed using the coefficient of variation (CV) and intraclass correlation coefficient (ICC), respectively. Additionally, Bland–Altman plots were produced to visualize the agreement between each pair of methods for each spatiotemporal parameter. The results revealed that the symmetry ratio method exhibited lower variability and higher reliability compared with the other four indices across all spatiotemporal gait parameters. However, it was found that the reliability of a single trial was generally poor, regardless of the symmetry calculation formula used. Therefore, we recommend basing measurements of gait asymmetry in Parkinson’s disease on multiple trials.