Abstract 080: Continuous Automated Stroke Screening Software for Early Detection of Neurological Impairment
Introduction Stroke is the second leading cause of death worldwide leaving up to 50 % of Survivor chronically disabled after their event. Early diagnosis and treatment can significantly lower mortality and morbidity, significantly reducing the economic burden of long‐term disability. Due to the pain...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2023-11-01
|
| Series: | Stroke: Vascular and Interventional Neurology |
| Online Access: | https://www.ahajournals.org/doi/10.1161/SVIN.03.suppl_2.080 |
| _version_ | 1797221251344760832 |
|---|---|
| author | Mahsa Eskian Vera Sharashidze Jeremy J. Heit Foad Taghdiri Hesham Masoud Grahame Gould |
| author_facet | Mahsa Eskian Vera Sharashidze Jeremy J. Heit Foad Taghdiri Hesham Masoud Grahame Gould |
| author_sort | Mahsa Eskian |
| collection | DOAJ |
| description | Introduction Stroke is the second leading cause of death worldwide leaving up to 50 % of Survivor chronically disabled after their event. Early diagnosis and treatment can significantly lower mortality and morbidity, significantly reducing the economic burden of long‐term disability. Due to the painless nature of most stroke events, many lack the stimulus to seek emergency assistance, further compounded by a symptomatology of deficit resulting in being unaware of the symptoms or lacking the ability to call for help when needed. A continuous automated stroke screening software tool was developed to address these pitfalls in prehospital care, allowing for the early detection of neurological impairment and the release of a medical emergency alert to facilitate emergency medical care. Methods Python version 3.11.3, NumPy, OpenCV, and mediapipe were used for facial and hand land marking with mathematical models employed to detect eye gaze direction, facial symmetry, eyelid closure and left or right hand detection. Results We were able to demonstrate consistent performance of the final software to continuously detect the eye gaze deviation, or center in real time video capturing (Figure‐1). Software is also capable of detecting lower facial palsy through facial symmetry recognition of smiling to demonstrate a right or left sided palsy (Figure‐2). The ability to blink can be detected to differentiate motor neuron palsy and used as a measure of mental status demonstration of the ability to follow a simple midline command (Figure‐3). Detection of lateralizing hand presentation to the camera allows the software to be used in detecting hemi‐neglect, and antigravity muscle strength in upper extremity. (Figure 1‐3). Conclusion Our developed automated stroke screening software can be used for continuous, physician independent, monitoring of neurologic patients and the detection of acute deficits and emergency alert to facilitate early care. The software is designed for use in medical emergency alert systems, tele stroke assessments, and remote surveillance of the neurological examination in intensive care unit or patients in isolation. Here we present the initial software development and capability, we are currently studying our detection models on patients with neurological deficits in varied practice settings. |
| first_indexed | 2024-03-07T15:39:10Z |
| format | Article |
| id | doaj.art-fac37d48bc2f4795ab3e7d0be1b4e763 |
| institution | Directory Open Access Journal |
| issn | 2694-5746 |
| language | English |
| last_indexed | 2024-04-24T13:02:28Z |
| publishDate | 2023-11-01 |
| publisher | Wiley |
| record_format | Article |
| series | Stroke: Vascular and Interventional Neurology |
| spelling | doaj.art-fac37d48bc2f4795ab3e7d0be1b4e7632024-04-05T10:51:56ZengWileyStroke: Vascular and Interventional Neurology2694-57462023-11-013S210.1161/SVIN.03.suppl_2.080Abstract 080: Continuous Automated Stroke Screening Software for Early Detection of Neurological ImpairmentMahsa Eskian0Vera Sharashidze1Jeremy J. Heit2Foad Taghdiri3Hesham Masoud4Grahame Gould5SUNY Upstate Medical University New York United StatesNYU Grossman School of Medicine New York United StatesStanford University School of Medicine California United StatesUniversity of Toronto Ontario CanadaSUNY Upstate Medical University New York United StatesSUNY Upstate Medical University New York United StatesIntroduction Stroke is the second leading cause of death worldwide leaving up to 50 % of Survivor chronically disabled after their event. Early diagnosis and treatment can significantly lower mortality and morbidity, significantly reducing the economic burden of long‐term disability. Due to the painless nature of most stroke events, many lack the stimulus to seek emergency assistance, further compounded by a symptomatology of deficit resulting in being unaware of the symptoms or lacking the ability to call for help when needed. A continuous automated stroke screening software tool was developed to address these pitfalls in prehospital care, allowing for the early detection of neurological impairment and the release of a medical emergency alert to facilitate emergency medical care. Methods Python version 3.11.3, NumPy, OpenCV, and mediapipe were used for facial and hand land marking with mathematical models employed to detect eye gaze direction, facial symmetry, eyelid closure and left or right hand detection. Results We were able to demonstrate consistent performance of the final software to continuously detect the eye gaze deviation, or center in real time video capturing (Figure‐1). Software is also capable of detecting lower facial palsy through facial symmetry recognition of smiling to demonstrate a right or left sided palsy (Figure‐2). The ability to blink can be detected to differentiate motor neuron palsy and used as a measure of mental status demonstration of the ability to follow a simple midline command (Figure‐3). Detection of lateralizing hand presentation to the camera allows the software to be used in detecting hemi‐neglect, and antigravity muscle strength in upper extremity. (Figure 1‐3). Conclusion Our developed automated stroke screening software can be used for continuous, physician independent, monitoring of neurologic patients and the detection of acute deficits and emergency alert to facilitate early care. The software is designed for use in medical emergency alert systems, tele stroke assessments, and remote surveillance of the neurological examination in intensive care unit or patients in isolation. Here we present the initial software development and capability, we are currently studying our detection models on patients with neurological deficits in varied practice settings.https://www.ahajournals.org/doi/10.1161/SVIN.03.suppl_2.080 |
| spellingShingle | Mahsa Eskian Vera Sharashidze Jeremy J. Heit Foad Taghdiri Hesham Masoud Grahame Gould Abstract 080: Continuous Automated Stroke Screening Software for Early Detection of Neurological Impairment Stroke: Vascular and Interventional Neurology |
| title | Abstract 080: Continuous Automated Stroke Screening Software for Early Detection of Neurological Impairment |
| title_full | Abstract 080: Continuous Automated Stroke Screening Software for Early Detection of Neurological Impairment |
| title_fullStr | Abstract 080: Continuous Automated Stroke Screening Software for Early Detection of Neurological Impairment |
| title_full_unstemmed | Abstract 080: Continuous Automated Stroke Screening Software for Early Detection of Neurological Impairment |
| title_short | Abstract 080: Continuous Automated Stroke Screening Software for Early Detection of Neurological Impairment |
| title_sort | abstract 080 continuous automated stroke screening software for early detection of neurological impairment |
| url | https://www.ahajournals.org/doi/10.1161/SVIN.03.suppl_2.080 |
| work_keys_str_mv | AT mahsaeskian abstract080continuousautomatedstrokescreeningsoftwareforearlydetectionofneurologicalimpairment AT verasharashidze abstract080continuousautomatedstrokescreeningsoftwareforearlydetectionofneurologicalimpairment AT jeremyjheit abstract080continuousautomatedstrokescreeningsoftwareforearlydetectionofneurologicalimpairment AT foadtaghdiri abstract080continuousautomatedstrokescreeningsoftwareforearlydetectionofneurologicalimpairment AT heshammasoud abstract080continuousautomatedstrokescreeningsoftwareforearlydetectionofneurologicalimpairment AT grahamegould abstract080continuousautomatedstrokescreeningsoftwareforearlydetectionofneurologicalimpairment |