Search

Stroke has become a leading cause of disability worldwide. Early medication and rehabilitation is the key to help post-stroke survivors recover faster. Presently, doctors rely on imaging modalities like CT/MRI for diagnosing stroke patients. The diagnosis done using these modalities can be highly subjective. Apart from this, these imaging modalities are very costly, time taking and inconvenient for the patients. So there is a need of faster, portable and an automated diagnostic system for assessing post-stroke conditions so that right measures can be taken in the right time. To cater to this need EEG comes in handy because of its portable nature. So, in this work, utility of EEG has been studied to diagnose three aspects of stroke: 1) type of stoke, 2) affected artery and 3) severity of stroke. To achieve this, one-minute resting state EEG data was used to extract 57 features. The features were ranked and selected using ranking algorithm and deep learning (DL) models were trained with supervision from information extracted using MRI data. To find out type of stroke and affected artery DWI, SWI and MRA images were used, and severity of stroke was recorded in terms of NIHSS score. Three different DL models were trained for each task i.e. type of stroke, affected artery and severity of stroke. For classifying type of stroke an accuracy of 97.74% was obtained using 37 features. For stroke severity, the model gave RMSE of 2.1955 with a high correlation value (r = 0.91). The DL model for classifying affected artery used 33 features and gave accuracy of 95.7%. It was also found that less complex time domain features and QEEG features were frequently selected out of 57 features for all the DL models. Features in delta and theta sub-bands were frequently selected along with QEEG features. The work presented here established that EEG can act as a reliable modality for faster diagnosis of stroke specifics and hence can help medical professionals in speeding the decision making process.

Summary: Background: There is a high burden of stroke, including recurrent stroke, in India. We aimed to assess the effect of a structured semi-interactive stroke prevention package in patients with subacute stroke to reduce recurrent strokes, myocardial infarction, and death. Methods: This was a multicentre, randomised, clinical trial conducted in 31 centres of the Indian Stroke Clinical Trial Network (INSTRuCT). Adult patients with first stroke and access to a mobile cellular device were randomly allocated (1:1) to intervention and control groups by the research coordinators at each centre using a central, in-house, web-based randomisation system. The participants and research coordinators at each centre were not masked to group assignment. The intervention group received regular short SMS messages and videos that promoted risk factor control and medication adherence and an educational workbook, in one of 12 languages, and the control group received standard care. The primary outcome was a composite of recurrent stroke, high-risk transient ischaemic attack, acute coronary syndrome, and death at 1 year. The outcome and safety analyses were done in the intention-to-treat population. The trial is registered with ClinicalTrials.gov, NCT03228979 and Clinical Trials Registry-India (CTRI/2017/09/009600) and was stopped for futility after interim analysis. Findings: Between April 28, 2018, and Nov 30, 2021, 5640 patients were assessed for eligibility. 4298 patients were randomised to the intervention group (n=2148) or control group (n=2150). 620 patients were not followed up at 6 months and a further 595 patients were not followed up at 1 year because the trial was stopped for futility after interim analysis. 45 patients were lost to follow-up before 1 year. Acknowledgment of receipt of the SMS messages and videos by the intervention group patients was low (17%). The primary outcome occurred in 119 (5·5%) of 2148 patients in the intervention group and 106 (4·9%) of 2150 patients in the control group (adjusted odds ratio 1·12; 95% CI 0·85–1·47; p=0·370). Among the secondary outcome measures, alcohol cessation and smoking cessation were higher in the intervention group than in the control group (alcohol cessation 231 [85%] of 272 in the intervention group vs 255 [78%] of 326 in the control group; p=0·036; smoking cessation 202 [83%] vs 206 [75%]; p=0·035). Medication compliance was better in the intervention group than in the control group (1406 [93·6%] of 1502 vs 1379 [89·8%] of 1536; p