The ability to perform accurate prognosis of patients is crucial for proactive clinical decision making, informed resource management and personalised care. Existing outcome prediction models suffer from a low recall of infrequent positive outcomes. We present a highly-scalable and robust machine learning framework to automatically predict adversity represented by mortality and ICU admission from time-series vital signs and laboratory results obtained within the first 24 hours of hospital admission. The stacked platform comprises two components: a) an unsupervised LSTM Autoencoder that learns an optimal representation of the time-series, using it to differentiate the less frequent patterns which conclude with an adverse event from the majority patterns that do not, and b) a gradient boosting model, which relies on the constructed representation to refine prediction, incorporating static features of demographics, admission details and clinical summaries. The model is used to assess a patient's risk of adversity over time and provides visual justifications of its prediction based on the patient's static features and dynamic signals. Results of three case studies for predicting mortality and ICU admission show that the model outperforms all existing outcome prediction models, achieving PR-AUC of 0.93 (95$%$ CI: 0.878 - 0.969) in predicting mortality in ICU and general ward settings and 0.987 (95$%$ CI: 0.985-0.995) in predicting ICU admission.

中文翻译：

---

用于从电子健康记录数据预测短期和长期住院结果的知识提炼集成框架

对患者进行准确预后的能力对于主动临床决策、知情资源管理和个性化护理至关重要。现有的结果预测模型对罕见的积极结果的回忆率很低。我们提出了一个高度可扩展且强大的机器学习框架，可根据入院前 24 小时内获得的时间序列生命体征和实验室结果自动预测以死亡率和入住 ICU 为代表的逆境。堆叠平台包含两个组件：a) 一个无监督的 LSTM 自动编码器，它学习时间序列的最佳表示，使用它来区分以不良事件结束的不太频繁的模式和大多数没有出现不良事件的模式，以及 b) a梯度提升模型，它依赖于构建的表示来改进预测，结合人口统计、入院细节和临床总结的静态特征。该模型用于评估患者随时间推移的逆境风险，并根据患者的静态特征和动态信号为其预测提供视觉依据。三个预测死亡率和 ICU 入住率的案例研究结果表明，该模型优于所有现有的结果预测模型，在预测 ICU 和普通病房环境中的死亡率方面实现 PR-AUC 为 0.93（95$%$ CI：0.878 - 0.969）和 0.987 (95$%$ CI: 0.985-0.995) 预测入住 ICU。随着时间的推移，逆境的风险，并根据患者的静态特征和动态信号提供其预测的视觉理由。三个预测死亡率和 ICU 入住率的案例研究结果表明，该模型优于所有现有的结果预测模型，在预测 ICU 和普通病房环境中的死亡率方面实现 PR-AUC 为 0.93（95$%$ CI：0.878 - 0.969）和 0.987 (95$%$ CI: 0.985-0.995) 预测入住 ICU。随着时间的推移，逆境的风险，并根据患者的静态特征和动态信号提供其预测的视觉理由。三个预测死亡率和 ICU 入住率的案例研究结果表明，该模型优于所有现有的结果预测模型，在预测 ICU 和普通病房死亡率方面的 PR-AUC 为 0.93（95$%$ CI：0.878 - 0.969）和 0.987 (95$%$ CI: 0.985-0.995) 预测入住 ICU。