Objective: The use of machine-learning algorithms to classify alerts as real or artifacts in online noninvasive vital sign data streams to reduce alarm fatigue and missed true instability. Design: Observational cohort study. Setting: Twenty-four–bed trauma step-down unit. Patients: Two thousand one hundred fifty-three patients. Intervention: Noninvasive vital sign monitoring data (heart rate, respiratory rate, peripheral oximetry) recorded on all admissions at 1/20 Hz, and noninvasive blood pressure less frequently, and partitioned data into training/validation (294 admissions; 22,980 monitoring hours) and test sets (2,057 admissions; 156,177 monitoring hours). Alerts were vital sign deviations beyond stability thresholds. A four-member expert committee annotated a subset of alerts (576 in training/validation set, 397 in test set) as real or artifact selected by active learning, upon which we trained machine-learning algorithms. The best model was evaluated on test set alerts to enact online alert classification over time. Measurements and Main Results: The Random Forest model discriminated between real and artifact as the alerts evolved online in the test set with area under the curve performance of 0.79 (95% CI, 0.67–0.93) for peripheral oximetry at the instant the vital sign first crossed threshold and increased to 0.87 (95% CI, 0.71–0.95) at 3 minutes into the alerting period. Blood pressure area under the curve started at 0.77 (95% CI, 0.64–0.95) and increased to 0.87 (95% CI, 0.71–0.98), whereas respiratory rate area under the curve started at 0.85 (95% CI, 0.77–0.95) and increased to 0.97 (95% CI, 0.94–1.00). Heart rate alerts were too few for model development. Conclusions: Machine-learning models can discern clinically relevant peripheral oximetry, blood pressure, and respiratory rate alerts from artifacts in an online monitoring dataset (area under the curve > 0.87).
1 March 2017 in Annals of the American Thoracic Society
Rationale: Cardiorespiratory insufficiency (CRI) is a term applied to the manifestations of loss of normal cardiorespiratory reserve and portends a bad outcome. CRI occurs commonly in hospitalized patients, but its risk escalation patterns are unexplored. Objectives: To describe the dynamic and personal character of CRI risk evolution observed through continuous vital sign monitoring of individual step-down unit patients. Methods: Using a machine learning model, we estimated risk trends for CRI (defined as exceedance of vital sign stability thresholds) for each of 1,971 admissions (1,880 unique patients) to a 24-bed adult surgical trauma step-down unit at an urban teaching hospital in Pittsburgh, Pennsylvania using continuously recorded vital signs from standard bedside monitors. We compared and contrasted risk trends during initial 4-hour periods after step-down unit admission, and again during the 4 hours immediately before the CRI event, between cases (ever had a CRI) and control subjects (never had a CRI). We further explored heterogeneity of risk escalation patterns during the 4 hours before CRI among cases, comparing personalized to nonpersonalized risk. Measurements and Main Results: Estimated risk was significantly higher for cases (918) than control subjects (1,053; P ≤ 0.001) during the initial 4-hour stable periods. Among cases, the aggregated nonpersonalized risk trend increased 2 hours before the CRI, whereas the personalized risk trend became significantly different from control subjects 90 minutes ahead. We further discovered several unique phenotypes of risk escalation patterns among cases for nonpersonalized (14.6% persistently high risk, 18.6% early onset, 66.8% late onset) and personalized risk (7.7% persistently high risk, 8.9% early onset, 83.4% late onset). Conclusions: Insights from this proof-of-concept analysis may guide design of dynamic and personalized monitoring systems that predict CRI, taking into account the triage and real-time monitoring utility of vital signs. These monitoring systems may prove useful in the dynamic allocation of technological and clinical personnel resources in acute care hospitals.
14 February 2019 in Journal of Clinical Monitoring and Computing
Tachycardia is a strong though non-specific marker of cardiovascular stress that proceeds hemodynamic instability. We designed a predictive model of tachycardia using multi-granular intensive care unit (ICU) data by creating a risk score and dynamic trajectory. A subset of clinical and numerical signals were extracted from the Multiparameter Intelligent Monitoring in Intensive Care II database. A tachycardia episode was defined as heart rate ≥ 130/min lasting for ≥ 5 min, with ≥ 10% density. Regularized logistic regression (LR) and random forest (RF) classifiers were trained to create a risk score for upcoming tachycardia. Three different risk score models were compared for tachycardia and control (non-tachycardia) groups. Risk trajectory was generated from time windows moving away at 1 min increments from the tachycardia episode. Trajectories were computed over 3 hours leading up to the episode for three different models. From 2809 subjects, 787 tachycardia episodes and 707 control periods were identified. Patients with tachycardia had increased vasopressor support, longer ICU stay, and increased ICU mortality than controls. In model evaluation, RF was slightly superior to LR, which accuracy ranged from 0.847 to 0.782, with area under the curve from 0.921 to 0.842. Risk trajectory analysis showed average risks for tachycardia group evolved to 0.78 prior to the tachycardia episodes, while control group risks remained < 0.3. Among the three models, the internal control model demonstrated evolving trajectory approximately 75 min before tachycardia episode. Clinically relevant tachycardia episodes can be predicted from vital sign time series using machine learning algorithms.