用住院记录训练可解释模型，精准预测心血管病患者两年内房颤风险。
Pre-AF 13: An Interpretable Atrial Fibrillation Risk Score Mined from Discharge Reports
- 从出院报告提取73个特征，用轻量ML构建可解释模型。
- 新模型24个月预测AUC达0.725，显著高于传统评分（最高0.64）。
- 仅13个变量的预判分数（Pre-AF 13）适合临床快速评估。
房颤是常见心律失常，影响预后。现有风险评分多依赖老年、高血压等普遍因素，在心血管疾病患者中分层能力有限，且多针对5-10年长期风险。本研究基于俄罗斯国家心脏病研究中心的电子病历数据，对45,000名无既往房颤的心血管病患者（80,576条记录）进行回顾性分析，采用定制NLP管道将非结构化出院报告转化为73个结构化特征，结合规则解析与Transformer命名实体识别。利用LightAutoML构建全模型（73特征）、简化模型（子集）和线性模型，生成床边可用的风险评分。性能以ROC AUC评估，对比CHARGE-AF、C2HEST、MHS、HAVOC等临床评分。结果：17,562人符合纳入标准，其中1,438人（8.19%）在随访期内发生房颤。全模型24个月与全程随访的AUC分别为0.735和0.696；简化模型表现接近（0.725, 0.696），均优于四个传统评分（AUC 0.53–0.64）。简化模型含13个特征，命名为Pre-AF 13。SHAP分析显示年龄和左心房容积为关键预测因子。线性风险评分（Pre-AF 9）将24个月房颤发病率从约7%分层至36%。结论：基于常规电子病历的可解释机器学习模型能有效识别高房颤风险心血管病患者，优于现有临床评分。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。