Assessment of the Sensitivity of a Smartphone App to Assist Patients in the Identification of Stroke and Myocardial Infarction: Cross-Sectional Study
Bibliographic record
Abstract
Background: Most people do not recognize symptoms of neurological and cardiac emergencies in a timely manner. This leads to delays in hospital arrival and reduced access to therapies that can open arteries. We created a smartphone app to help patients and families evaluate if symptoms may be high risk for stroke or heart attack (myocardial infarction, MI). The ECHAS (Emergency Call for Heart Attack and Stroke) app guides users to assess their risk through evidence-based questions and a test of weakness in one arm by evaluating finger-tapping on the smartphone. Objective: This study is an initial step in the accuracy evaluation of the app focused on sensitivity. We evaluated whether the app provides appropriate triage advice for patients with known stroke or MI symptoms in the Emergency Department. We designed this study to evaluate the sensitivity of the app, since the most dangerous output of the app would be failure to recognize the need for emergency evaluation. Specificity is also important, but the consequences of low specificity are less dangerous than those of low sensitivity. Methods: In this single-center cross-sectional study, we enrolled patients presenting with symptoms of possible stroke or MI. The ECHAS app assessment consisted of a series of evidence-based questions regarding symptoms and a test of finger-tapping speed and accuracy on the phone's screen to detect unilateral arm weakness. The primary outcome was the sensitivity of the ECHAS app in detecting the need for ED evaluation. The secondary outcome was the sensitivity of the ECHAS app in detecting the need for hospital admission. Two independent and blinded board-certified physicians reviewed the medical record and adjudicated the appropriateness of the ED visit based on a 5-point score (ground truth). Finally, we asked patients semistructured questions about the app's ease of use, drawbacks, and benefits. Results: We enrolled 202 patients (57 with stroke and 145 with MI). The ECHAS score was strongly correlated with the ground truth appropriateness score (Spearman correlation 0.41, P<.001). The ECHAS app had a sensitivity of 0.98 for identifying patients in whom ED evaluation was appropriate. The app had a sensitivity of 1.0 for identifying patients who were admitted to the hospital because of their ED evaluation. Patients completed an app session in an average of 111 (SD 60) seconds for the stroke pathway and 60 (SD 33) seconds for the MI pathway. Patients reported that the app was easy to use and valuable for personal emergency situations at home. Conclusions: The ECHAS app demonstrated a high sensitivity for the detection of patients who required emergency evaluation for symptoms of stroke or MI. This study supports the need for a study of specificity of the app, and then a prospective trial of the app in patients at increased risk of MI and stroke.
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 machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.008 | 0.021 |
| Meta-epidemiology (narrow) | 0.000 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.002 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 0.001 |
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 source (direct Gemma or distilled Codex), 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".