Development and validation of risk score for patients in primary care setting in Poland
Bibliographic record
Abstract
Abstract Background Suitable, optimal risk prediction in primary care is still a large challenge. Current tools enable the creation of risk scales based on data for specific populations, which can be a large support to recognized risk scales used in primary and secondary prevention. Purpose Therefore, we decided to suggest a new risk score generated with the machine-learning tools based on the data from consecutive patients in the family physicians’ practices within the LIPIDOGRAM cohort study 2015. Methods The LIPIDOGRAM 2015 study was carried out in 2015 and 2016 in the primary care setting all 16 administrative regions of Poland. 438 physicians participating in the study were proportionally distributed to the number of inhabitants in each administrative region. Each patient was asked to fill the detailed questionnaire on chronic diseases, treatment, and lifestyle. The primary outcome, based on the data from the National Health Fund, was all-cause mortality. A machine learning-based framework AutoScore was used to generate risk score basing on the variables obtained from questionnaires. Dataset was divided into training, validation, and test cohort in the proportion of 0.6, 0.1 and 0.3 respectively. Performance of the risk score was evaluated using ROC analysis in the test set Kaplan-Meier analysis of survival according to quartiles of the score was carried out. Results 13 611 patients were finally recruited. 5 years follow-up data was available for 13 419 patients (98.6%). A score based on age, sex, body mass index (BMI), alcohol consumption, smoking, presence of comorbidities - hypertension, diabetes mellitus, atrial fibrillation, chronic kidney disease, hypertension, history of myocardial infarction, self-declared physical activity, place of residence and education level that is presented in detail in Table 1, achieved an AUC of 0.825 (95% CI - 0.794-0.856) (Figure 1). Conclusions Risk scales created based on data representative of primary care patients can be easily created thanks to modern statistical tools. Such scores may include variables that better describe local communities, such as education level, place of residence, physical activity, or alcohol consumption, and in the consequence may better predict and monitor (in case of intervention) the risk of all-cause and cause-specific mortality.Developed predictive model.Test set results. 5-year prognosis.
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 | 0.004 | 0.014 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.003 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.002 |
| 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".