METHODS: EMR data from 184,361 admissions containing 4,538,418 BG measurements from five hospitals in the Johns Hopkins Health System were collected from patients who were discharged between January 1, 2015 and May 31, 2019. Index BGs used for prediction included the 5th to penultimate BG measurements (N = 2,740,539). The outcome was category of next BG measurement: hypoglycemic (BG ≤ 70 mg/dl), controlled (BG 71-180 mg/dl), or hyperglycemic (BG > 180 mg/dl). A random forest algorithm that included a broad range of clinical covariates predicted the outcome and was validated internally and externally.
RESULTS: In our internal validation test set, 72·8%, 25·7%, and 1·5% of BG measurements occurring after the index BG were controlled, hyperglycemic, and hypoglycemic respectively. The sensitivity/specificity for prediction of controlled, hyperglycemic, and hypoglycemic were 0·77/0·81, 0·77/0·89, and 0·73/0·91, respectively. On external validation in four hospitals, the ranges of sensitivity/specificity for prediction of controlled, hyperglycemic, and hypoglycemic were 0·64-0·70/0·80-0·87, 0·75-0·80/0·82-0·84, and 0·76-0·78/0·87-0·90, respectively.
CONCLUSIONS: A machine learning algorithm using EMR data can accurately predict the category of a hospitalized patient\'s next BG measurement. Further studies should determine the effectiveness of integration of this model into the EMR in reducing rates of hypoglycemia and hyperglycemia.
方法:从2015年1月1日至2019年5月31日出院的患者中收集了来自约翰·霍普金斯大学卫生系统五家医院的184,361例住院患者的EMR数据,其中包含4,538,418例BG测量值。用于预测的指数BG包括第5至倒数第二个BG测量值(N=2,740,539)。结果是下一次BG测量的类别:低血糖(BG≤70mg/dl),受控(BG71-180mg/dl),或高血糖(BG>180mg/dl)。包含广泛临床协变量的随机森林算法预测了结果,并在内部和外部进行了验证。
结果:在我们的内部验证测试集中,72·8%,25·7%,和1·5%的BG测量发生在指数BG控制后,高血糖,和低血糖。预测受控的敏感性/特异性,高血糖,和低血糖分别为0·77/0·81、0·77/0·89和0·73/0·91。在四家医院的外部验证中,预测受控,高血糖,和低血糖分别为0·64-0·70/0·80-0·87,0·75-0·80/0·82-0·84和0·76-0·78/0·87-0·90。
结论:使用EMR数据的机器学习算法可以准确预测住院患者下一次BG测量的类别。进一步的研究应确定将该模型整合到EMR中降低低血糖和高血糖率的有效性。