Hargobind S Khurana1, Robert H Groves2, Michael P Simons3, Mary Martin4, Brenda Stoffer5, Sherri Kou6, Richard Gerkin7, Eric Reiman8, Sairam Parthasarathy9. 1. Banner TeleHealth, Mesa, Ariz; Care Management, Banner Health, Phoenix, Ariz; Health Management, Banner Health, Phoenix, Ariz. Electronic address: Hargobind.Khurana@bannerhealth.com. 2. Banner TeleHealth, Mesa, Ariz; Care Management, Banner Health, Phoenix, Ariz; Health Management, Banner Health, Phoenix, Ariz. 3. Banner Medical Group, Phoenix, Ariz; Banner Estrella Medical Center, Phoenix, Ariz. 4. Banner Corporate Center, Phoenix, Ariz. 5. Information Technology Clinical Systems, Banner Health, Phoenix, Ariz. 6. Clinical Performance Analytics, Banner Health, Phoenix, Ariz. 7. University of Arizona College of Medicine-Phoenix. 8. Banner Research, Banner Health, Phoenix, Ariz; Banner Alzheimer's Institute, Phoenix, Ariz. 9. University of Arizona and Banner University Medical Center, Tucson.
Abstract
BACKGROUND: Real-time automated continuous sampling of electronic medical record data may expeditiously identify patients at risk for death and enable prompt life-saving interventions. We hypothesized that a real-time electronic medical record-based alert could identify hospitalized patients at risk for mortality. METHODS: An automated alert was developed and implemented to continuously sample electronic medical record data and trigger when at least 2 of 4 systemic inflammatory response syndrome criteria plus at least one of 14 acute organ dysfunction parameters was detected. The systemic inflammatory response syndrome and organ dysfunction alert was applied in real time to 312,214 patients in 24 hospitals and analyzed in 2 phases: training and validation datasets. RESULTS: In the training phase, 29,317 (18.8%) triggered the alert and 5.2% of such patients died, whereas only 0.2% without the alert died (unadjusted odds ratio 30.1; 95% confidence interval, 26.1-34.5; P < .0001). In the validation phase, the sensitivity, specificity, area under the curve, and positive and negative likelihood ratios for predicting mortality were 0.86, 0.82, 0.84, 4.9, and 0.16, respectively. Multivariate Cox-proportional hazard regression model revealed greater hospital mortality when the alert was triggered (adjusted hazards ratio 4.0; 95% confidence interval, 3.3-4.9; P < .0001). Triggering the alert was associated with additional hospitalization days (+3.0 days) and ventilator days (+1.6 days; P < .0001). CONCLUSION: An automated alert system that continuously samples electronic medical record data can be implemented, has excellent test characteristics, and can assist in the real-time identification of hospitalized patients at risk for death.
BACKGROUND: Real-time automated continuous sampling of electronic medical record data may expeditiously identify patients at risk for death and enable prompt life-saving interventions. We hypothesized that a real-time electronic medical record-based alert could identify hospitalized patients at risk for mortality. METHODS: An automated alert was developed and implemented to continuously sample electronic medical record data and trigger when at least 2 of 4 systemic inflammatory response syndrome criteria plus at least one of 14 acute organ dysfunction parameters was detected. The systemic inflammatory response syndrome and organ dysfunction alert was applied in real time to 312,214 patients in 24 hospitals and analyzed in 2 phases: training and validation datasets. RESULTS: In the training phase, 29,317 (18.8%) triggered the alert and 5.2% of such patients died, whereas only 0.2% without the alert died (unadjusted odds ratio 30.1; 95% confidence interval, 26.1-34.5; P < .0001). In the validation phase, the sensitivity, specificity, area under the curve, and positive and negative likelihood ratios for predicting mortality were 0.86, 0.82, 0.84, 4.9, and 0.16, respectively. Multivariate Cox-proportional hazard regression model revealed greater hospital mortality when the alert was triggered (adjusted hazards ratio 4.0; 95% confidence interval, 3.3-4.9; P < .0001). Triggering the alert was associated with additional hospitalization days (+3.0 days) and ventilator days (+1.6 days; P < .0001). CONCLUSION: An automated alert system that continuously samples electronic medical record data can be implemented, has excellent test characteristics, and can assist in the real-time identification of hospitalized patients at risk for death.
Authors: Craig A Umscheid; Joel Betesh; Christine VanZandbergen; Asaf Hanish; Gordon Tait; Mark E Mikkelsen; Benjamin French; Barry D Fuchs Journal: J Hosp Med Date: 2014-09-26 Impact factor: 2.960
Authors: Curtis H Weiss; Farzad Moazed; Colleen A McEvoy; Benjamin D Singer; Igal Szleifer; Luís A N Amaral; Mary Kwasny; Charles M Watts; Stephen D Persell; David W Baker; Jacob I Sznajder; Richard G Wunderink Journal: Am J Respir Crit Care Med Date: 2011-05-26 Impact factor: 21.405
Authors: Kirsi-Maija Kaukonen; Michael Bailey; David Pilcher; D Jamie Cooper; Rinaldo Bellomo Journal: N Engl J Med Date: 2015-03-17 Impact factor: 91.245
Authors: Suneetha Ramani Moonesinghe; Michael G Mythen; Priya Das; Kathryn M Rowan; Michael P W Grocott Journal: Anesthesiology Date: 2013-10 Impact factor: 7.892
Authors: Christine Eichelberger; Aarti Patel; Zhijie Ding; Christopher D Pericone; Jennifer H Lin; Christopher W Baugh Journal: Cardiol Ther Date: 2020-03-02
Authors: Eveline Mestrom; Ashley De Bie; Melissa van de Steeg; Merel Driessen; Louis Atallah; Rick Bezemer; R Arthur Bouwman; Erik Korsten Journal: PLoS One Date: 2019-05-08 Impact factor: 3.240
Authors: Robert A Raschke; Robert H Groves; Hargobind S Khurana; Nidhi Nikhanj; Ethel Utter; Didi Hartling; Brenda Stoffer; Kristina Nunn; Shona Tryon; Michelle Bruner; Maria Calleja; Steven C Curry Journal: BMJ Open Qual Date: 2017-10-21