# Pre-AF 13: An Interpretable Atrial Fibrillation Risk Score Mined from Discharge Reports Source: [Pre-AF 13: An Interpretable Atrial Fibrillation Risk Score Mined from Discharge Reports]() Collection index: [llms.txt]() Data updated: 2026-06-12T05:00:05.419Z Authors: Olga Shakhmatova, Dmitrii Kriukov, Daniil Larionov, Nikita Khromov, Iaroslav Bespalov, Alexander Zolotarev, Kirill Grishchenkov, Ekaterina Ivanova, Miron Kuznetsov, Ilya Sochenkov, Elizaveta Panchenko, Artem Shelmanov, Dmitry V. Dylov Published: 2026-06-09T11:33:46.000Z ## Abstract Background. Atrial fibrillation (AF) is the most prevalent cardiac arrhythmia and a major determinant of prognosis. Established AF risk scores rely on factors (older age, hypertension) nearly ubiquitous among patients with cardiovascular disease (CVD), offering limited stratification in this high-risk group. Most target long-term (5-10 year) rather than medium-term prediction. We developed interpretable ML models predicting AF risk over a 24-month and entire follow-up horizon in CVD patients using routinely collected hospital data. Methods. Single-center retrospective study of electronic health records from the National Research Cardiology Center (Russia) for patients aged \>=18 with CVD but without pre-existing AF, hospitalized more than once between January 2012 and May 2019. A custom NLP pipeline transformed unstructured discharge reports into 73 structured features, combining a rule-based parser with transformer-based NER. Using LightAutoML we built a full model (73 features), a simple model (reduced subset), and a linear model for a bedside risk score. Performance was assessed by ROC AUC, compared with CHARGE-AF, C2HEST, MHS, and HAVOC, and interpreted via SHAP. Results. Of 80,576 records from 45,000 patients, 17,562 met inclusion criteria; 1,438 (8.19%) developed AF. The full model reached ROC AUC 0.735 (24-month) and 0.696 (entire follow-up); the simple model was nearly identical (0.725, 0.696). All non-linear models outperformed the four clinical risk scores (ROC AUC 0.53-0.64). The simple model uses 13 features and is named Pre-AF 13. SHAP identified age and left atrial volume as dominant predictors. A linear risk score (Pre-AF 9) stratified observed 24-month AF incidence from ~7% to 36%. Conclusion. Interpretable ML models built from routinely collected EHR data identify high-AF-risk CVD patients, outperforming established clinical risk scores. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Atrial Fibrillation risk classification on AF prediction dataset 24-month target (test)](): Atrial Fibrillation risk classification; AF prediction dataset 24-month target (test); Balanced Accuracy: 67.4. - [Atrial Fibrillation risk classification on AF prediction dataset 24-month target (train)](): Atrial Fibrillation risk classification; AF prediction dataset 24-month target (train); Balanced Accuracy: 0.904. - [Risk classification on AF Prediction Entire follow-up (test)](): Risk Classification; AF Prediction Entire follow-up (test); Balanced Accuracy: 63. - [Risk Classification on AF Prediction Entire follow-up (train)](): Risk Classification; AF Prediction Entire follow-up (train); Balanced Accuracy: 88. ## Original sources and implementation [Original paper]() [PDF]()