ENHANCING STROKE PROGNOSIS PREDICTION USING DEEP CONVOLUTION NEURAL NETWORKS
Bibliographic record
Abstract
Stroke is a disease of the central nervous system that occurs very quickly. The onset of the disease can lead to severe neurological deficits and, in the acute phase, death. The National Institute of Health Stroke Scale (NIHSS), Barthel Index (BI), and Modified Rankin Scale (mRS) are the best tools for evaluating whether or not a stroke patient will improve at the time of onset and in the future. This study investigated the collection of patient demographics, CT imaging findings, MRI imaging findings, and NIHSS, Barthel, and mRS to determine whether a stroke patient is likely to get better at the time of onset and at the time of prognosis, and since previous studies have used artificial intelligence models to predict only one indicator, this will result in more time spent on prediction. This study investigates the collection of patient demographics, CT imaging findings, MRI imaging findings, and NIHSS, BI, and mRS indices on admission, and compares whether the four models can have good predictive effect in predicting the predicted values of the three indices at one time. Finally, the explainable models were used to explore which of the parameters were more important for us to predict the predicted values of the indicators. The results of the study showed that deep convolutional neural networks yielded better predictive results in both the training sample set and the validation dataset: post-discharge NIHSS: 86.18, 9.28, 7.38; post-discharge BI: 664.69, 25.78, 17.84; and post-discharge BmRS: 3.83, 1.96, 1.63, respectively. The present study showed that the top five important characteristics were Contralateral (Contra) Common Carotid Artery (CCA) Pulsatility Index (PI), Ipsilateral (Ipsi) External Carotid A (ECA) Resistance Index (RI), Hypoperfusion Intensity Ratio (HIR), inpatient CT Alberta Stroke Program Early CT Score (ASPECTS), and Ipsi ECA PI. Therefore, this study found a new model that can validate the values of these three indicators after discharge and inform healthcare professionals about the importance of each value for the implementation of follow-up programs.
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 | 0.001 | 0.003 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 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 | 0.000 |
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 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".