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).
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).
Authors: U Rajendra Acharya; S Vinitha Sree; M Muthu Rama Krishnan; N Krishnananda; Shetty Ranjan; Pai Umesh; Jasjit S Suri Journal: Comput Methods Programs Biomed Date: 2013-08-16 Impact factor: 5.428
Authors: U Rajendra Acharya; S Vinitha Sree; Ricardo Ribeiro; Ganapathy Krishnamurthi; Rui Tato Marinho; Joao Sanches; Jasjit S Suri Journal: Med Phys Date: 2012-07 Impact factor: 4.071
Authors: Jonathan J Halford; Robert J Schalkoff; Jing Zhou; Selim R Benbadis; William O Tatum; Robert P Turner; Saurabh R Sinha; Nathan B Fountain; Amir Arain; Paul B Pritchard; Ekrem Kutluay; Gabriel Martz; Jonathan C Edwards; Chad Waters; Brian C Dean Journal: J Neurosci Methods Date: 2012-11-19 Impact factor: 2.390
Authors: Guohua Lu; John-Stuart Brittain; Peter Holland; John Yianni; Alexander L Green; John F Stein; Tipu Z Aziz; Shouyan Wang Journal: Neurosci Lett Date: 2009-06-25 Impact factor: 3.046
Authors: Barbara J Drew; Patricia Harris; Jessica K Zègre-Hemsey; Tina Mammone; Daniel Schindler; Rebeca Salas-Boni; Yong Bai; Adelita Tinoco; Quan Ding; Xiao Hu Journal: PLoS One Date: 2014-10-22 Impact factor: 3.240
Authors: Rohan Joshi; Zheng Peng; Xi Long; Loe Feijs; Peter Andriessen; Carola Van Pul Journal: IEEE J Transl Eng Health Med Date: 2019-11-22 Impact factor: 3.316
Authors: Lujie Chen; Olufunmilayo Ogundele; Gilles Clermont; Marilyn Hravnak; Michael R Pinsky; Artur W Dubrawski Journal: Ann Am Thorac Soc Date: 2017-03
Authors: Marilyn Hravnak; Tiffany Pellathy; Lujie Chen; Artur Dubrawski; Anthony Wertz; Gilles Clermont; Michael R Pinsky Journal: J Electrocardiol Date: 2018-07-29 Impact factor: 1.438