Department of Academic Cardiology, Hull University Teaching Hospital NHS Trust, Hull, UK.
Department of Computer Science and Technology, University of Hull, Hull, UK.
ESC Heart Fail. 2022 Oct;9(5):3009-3018. doi: 10.1002/ehf2.14028. Epub 2022 Jun 23.
Risk changes with the progression of disease and the impact of treatment. We developed a dynamic risk stratification Markov chain model using artificial intelligence in patients with chronic heart failure (CHF).
We described the pattern of behaviour among 7496 consecutive patients assessed for suspected HF. The following mutually exclusive health states were defined and assessed every 4 months: death, hospitalization, outpatient visit, no event, and leaving the service altogether (defined as no event at any point following assessment). The observed figures at the first transition (4 months) weres 427 (6%), 1559 (21%), 2254 (30%), 1414 (19%), and 1842 (25%), respectively. The probabilities derived from the first two transitions (i.e. from baseline to 4 months and from 4 to 8 months) were used to construct the model. An example of the model's prediction is that at cycle 4, the cumulative probability of death was 14%; leaving the system, 37%; being hospitalized between 12 and 16 months, 10%; having an outpatient visit, 8%; and having no event, 31%. The corresponding observed figures were 14%, 41%, 10%, 15%, and 21%, respectively. The model predicted that during the first 2 years, a patient had a probability of dying of 0.19, and the observed value was 0.18.
A model derived from the first 8 months of follow-up is strongly predictive of future events in a population of patients with chronic heart failure. The course of CHF is more linear than is commonly supposed, and thus more predictable.
风险随着疾病的进展和治疗的影响而变化。我们使用人工智能为慢性心力衰竭（CHF）患者开发了一种动态风险分层马尔可夫链模型。
我们描述了对疑似 HF 进行评估的 7496 例连续患者的行为模式。定义并评估了以下互斥的健康状态：死亡、住院、门诊就诊、无事件和完全离开服务（定义为在评估后任何时候均无事件）。首次（4 个月）转移的观察结果分别为 427（6%）、1559（21%）、2254（30%）、1414（19%）和 1842（25%）。从前两次转移（即从基线到 4 个月和从 4 到 8 个月）获得的概率用于构建模型。模型预测的一个示例是，在第 4 个周期，死亡的累积概率为 14%；离开系统，37%；在 12 至 16 个月期间住院，10%；门诊就诊，8%；无事件，31%。相应的观察值分别为 14%、41%、10%、15%和 21%。该模型预测，在最初的 2 年内，患者有 0.19 的概率死于心力衰竭，而观察值为 0.18。
源自前 8 个月随访的模型可强烈预测慢性心力衰竭患者人群的未来事件。心力衰竭的病程比通常认为的更线性，因此更可预测。
