Effective Prediction of Mortality by Heart Disease Among Women in Jordan Using the Chi-Squared Automatic Interaction Detection Model: Retrospective Validation Study
Bibliographic record
Abstract
BACKGROUND: Many current studies have claimed that the actual risk of heart disease among women is equal to that in men. Using a large machine learning algorithm (MLA) data set to predict mortality in women, data mining techniques have been used to identify significant aspects of variables that help in identifying the primary causes of mortality within this target category of the population. OBJECTIVE: This study aims to predict mortality caused by heart disease among women, using an artificial intelligence technique-based MLA. METHODS: A retrospective design was used to retrieve big data from the electronic health records of 2028 women with heart disease. Data were collected for Jordanian women who were admitted to public health hospitals from 2015 to the end of 2021. We checked the extracted data for noise, consistency issues, and missing values. After categorizing, organizing, and cleaning the extracted data, the redundant data were eliminated. RESULTS: Out of 9 artificial intelligence models, the Chi-squared Automatic Interaction Detection model had the highest accuracy (93.25%) and area under the curve (0.825) among the build models. The participants were 62.6 (SD 15.4) years old on average. Angina pectoris was the most frequent diagnosis in the women's extracted files (n=1,264,000, 62.3%), followed by congestive heart failure (n=764,000, 37.7%). Age, systolic blood pressure readings with a cutoff value of >187 mm Hg, medical diagnosis (women diagnosed with congestive heart failure were at a higher risk of death [n=31, 16.58%]), pulse pressure with a cutoff value of 98 mm Hg, and oxygen saturation (measured using pulse oximetry) with a cutoff value of 93% were the main predictors for death among women. CONCLUSIONS: To predict the outcomes in this study, we used big data that were extracted from the clinical variables from the electronic health records. The Chi-squared Automatic Interaction Detection model-an MLA-confirmed the precise identification of the key predictors of cardiovascular mortality among women and can be used as a practical tool for clinical prediction.
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 | 0.009 | 0.014 |
| 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 | 0.000 | 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".