Abstract 080: Continuous Automated Stroke Screening Software for Early Detection of Neurological Impairment
Bibliographic record
Abstract
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.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.001 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one teacher head, not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".