BACKGROUND: Analysis and modeling of data monitoring vital signs and waveforms in patients in a surgical/trauma intensive care unit (STICU) may allow for early identification and treatment of patients with evolving respiratory failure. METHODS: Between February 2011 and March 2012, data of vital signs and waveforms for STICU patients were collected. Every-15-minute calculations (n = 172,326) of means and standard deviations of heart rate (HR), respiratory rate (RR), pulse-oxygen saturation (SpO2), cross-correlation coefficients, and cross-sample entropy for HR-RR, RR-SpO2, and HR-SpO2, and cardiorespiratory coupling were calculated. Urgent intubations were recorded. Univariate analyses were performed for the periods <24 and ≥24 hours before intubation. Multivariate predictive models for the risk of unplanned intubation were developed and validated internally by subsequent sample and bootstrapping techniques. RESULTS: Fifty unplanned intubations (41 patients) were identified from 798 STICU patients. The optimal multivariate predictive model (HR, RR, and SpO2 means, and RR-SpO2 correlation coefficient) had a receiving operating characteristic (ROC) area of 0.770 (95% confidence interval [CI], 0.712-0.841). For this model, relative risks of intubation in the next 24 hours for the lowest and highest quintiles were 0.20 and 2.95, respectively (15-fold increase, baseline risk 1.46%). Adding age and days since previous extubation to this model increased ROC area to 0.865 (95 % CI, 0.821-0.910). CONCLUSION: Among STICU patients, a multivariate model predicted increases in risk of intubation in the following 24 hours based on vital sign data available currently on bedside monitors. Further refinement could allow for earlier detection of respiratory decompensation and intervention to decrease preventable morbidity and mortality in surgical/trauma patients.
BACKGROUND: Analysis and modeling of data monitoring vital signs and waveforms in patients in a surgical/trauma intensive care unit (STICU) may allow for early identification and treatment of patients with evolving respiratory failure. METHODS: Between February 2011 and March 2012, data of vital signs and waveforms for STICU patients were collected. Every-15-minute calculations (n = 172,326) of means and standard deviations of heart rate (HR), respiratory rate (RR), pulse-oxygen saturation (SpO2), cross-correlation coefficients, and cross-sample entropy for HR-RR, RR-SpO2, and HR-SpO2, and cardiorespiratory coupling were calculated. Urgent intubations were recorded. Univariate analyses were performed for the periods <24 and ≥24 hours before intubation. Multivariate predictive models for the risk of unplanned intubation were developed and validated internally by subsequent sample and bootstrapping techniques. RESULTS: Fifty unplanned intubations (41 patients) were identified from 798 STICU patients. The optimal multivariate predictive model (HR, RR, and SpO2 means, and RR-SpO2 correlation coefficient) had a receiving operating characteristic (ROC) area of 0.770 (95% confidence interval [CI], 0.712-0.841). For this model, relative risks of intubation in the next 24 hours for the lowest and highest quintiles were 0.20 and 2.95, respectively (15-fold increase, baseline risk 1.46%). Adding age and days since previous extubation to this model increased ROC area to 0.865 (95 % CI, 0.821-0.910). CONCLUSION: Among STICU patients, a multivariate model predicted increases in risk of intubation in the following 24 hours based on vital sign data available currently on bedside monitors. Further refinement could allow for earlier detection of respiratory decompensation and intervention to decrease preventable morbidity and mortality in surgical/traumapatients.
Authors: Patrick R Norris; Asli Ozdas; Hanqing Cao; Anna E Williams; Frank E Harrell; Judith M Jenkins; John A Morris Journal: Ann Surg Date: 2006-06 Impact factor: 12.969
Authors: John A Morris; Patrick R Norris; Asli Ozdas; Lemuel R Waitman; Frank E Harrell; Anna E Williams; Hanqing Cao; Judith M Jenkins Journal: J Trauma Date: 2006-06
Authors: J Randall Moorman; John B Delos; Abigail A Flower; Hanqing Cao; Boris P Kovatchev; Joshua S Richman; Douglas E Lake Journal: Physiol Meas Date: 2011-10-25 Impact factor: 2.833
Authors: David K Warren; Sunita J Shukla; Margaret A Olsen; Marin H Kollef; Christopher S Hollenbeak; Michael J Cox; Max M Cohen; Victoria J Fraser Journal: Crit Care Med Date: 2003-05 Impact factor: 7.598
Authors: Travis J Moss; Douglas E Lake; J Forrest Calland; Kyle B Enfield; John B Delos; Karen D Fairchild; J Randall Moorman Journal: Crit Care Med Date: 2016-09 Impact factor: 7.598
Authors: Tellen D Bennett; Tiffany J Callahan; James A Feinstein; Debashis Ghosh; Saquib A Lakhani; Michael C Spaeder; Stanley J Szefler; Michael G Kahn Journal: J Pediatr Date: 2019-01-25 Impact factor: 4.406
Authors: Caroline M Ruminski; Matthew T Clark; Douglas E Lake; Rebecca R Kitzmiller; Jessica Keim-Malpass; Matthew P Robertson; Theresa R Simons; J Randall Moorman; J Forrest Calland Journal: J Clin Monit Comput Date: 2018-08-18 Impact factor: 1.977
Authors: Anne S M Costa; Paulo H M Costa; Carlos E B de Lima; Luiz E M Pádua; Luciana A Campos; Ovidiu C Baltatu Journal: Front Neurosci Date: 2016-01-11 Impact factor: 4.677
Authors: Jessica Keim-Malpass; Sarah J Ratcliffe; Liza P Moorman; Matthew T Clark; Katy N Krahn; Oliver J Monfredi; Susan Hamil; Gholamreza Yousefvand; J Randall Moorman; Jamieson M Bourque Journal: JMIR Res Protoc Date: 2021-07-02