Gary S Phillips1, Tiffany M Osborn2, Kathleen M Terry3, Foster Gesten4, Mitchell M Levy5, Stanley Lemeshow6. 1. Center for Biostatistics, Department of Biomedical Informatics, Ohio State University, Columbus, OH. 2. Division of Emergency Medicine, Department of Surgery, Washington University, St. Louis, MO. 3. IPRO, Lake Success, NY. 4. Quality and Health Care Delivery, Greater New York Hospital Association, New York, NY. 5. Division of Pulmonary, Critical Care and Sleep Medicine, Department of Medicine, Alpert Medical School at Brown University, Providence, RI. 6. The Ohio State University College of Public Health, Columbus, OH.
Abstract
OBJECTIVES: In accordance with Rory's Regulations, hospitals across New York State developed and implemented protocols for sepsis recognition and treatment to reduce variations in evidence informed care and preventable mortality. The New York Department of Health sought to develop a risk assessment model for accurate and standardized hospital mortality comparisons of adult septic patients across institutions using case-mix adjustment. DESIGN: Retrospective evaluation of prospectively collected data. PATIENTS: Data from 43,204 severe sepsis and septic shock patients from 179 hospitals across New York State were evaluated. SETTINGS: Prospective data were submitted to a database from January 1, 2015, to December 31, 2015. INTERVENTIONS: None. MEASUREMENT AND MAIN RESULTS: Maximum likelihood logistic regression was used to estimate model coefficients used in the New York State risk model. The mortality probability was estimated using a logistic regression model. Variables to be included in the model were determined as part of the model-building process. Interactions between variables were included if they made clinical sense and if their p values were less than 0.05. Model development used a random sample of 90% of available patients and was validated using the remaining 10%. Hosmer-Lemeshow goodness of fit p values were considerably greater than 0.05, suggesting good calibration. Areas under the receiver operator curve in the developmental and validation subsets were 0.770 (95% CI, 0.765-0.775) and 0.773 (95% CI, 0.758-0.787), respectively, indicating good discrimination. Development and validation datasets had similar distributions of estimated mortality probabilities. Mortality increased with rising age, comorbidities, and lactate. CONCLUSIONS: The New York Sepsis Severity Score accurately estimated the probability of hospital mortality in severe sepsis and septic shock patients. It performed well with respect to calibration and discrimination. This sepsis-specific model provides an accurate, comprehensive method for standardized mortality comparison of adult patients with severe sepsis and septic shock.
OBJECTIVES: In accordance with Rory's Regulations, hospitals across New York State developed and implemented protocols for sepsis recognition and treatment to reduce variations in evidence informed care and preventable mortality. The New York Department of Health sought to develop a risk assessment model for accurate and standardized hospital mortality comparisons of adult septic patients across institutions using case-mix adjustment. DESIGN: Retrospective evaluation of prospectively collected data. PATIENTS: Data from 43,204 severe sepsis and septic shockpatients from 179 hospitals across New York State were evaluated. SETTINGS: Prospective data were submitted to a database from January 1, 2015, to December 31, 2015. INTERVENTIONS: None. MEASUREMENT AND MAIN RESULTS: Maximum likelihood logistic regression was used to estimate model coefficients used in the New York State risk model. The mortality probability was estimated using a logistic regression model. Variables to be included in the model were determined as part of the model-building process. Interactions between variables were included if they made clinical sense and if their p values were less than 0.05. Model development used a random sample of 90% of available patients and was validated using the remaining 10%. Hosmer-Lemeshow goodness of fit p values were considerably greater than 0.05, suggesting good calibration. Areas under the receiver operator curve in the developmental and validation subsets were 0.770 (95% CI, 0.765-0.775) and 0.773 (95% CI, 0.758-0.787), respectively, indicating good discrimination. Development and validation datasets had similar distributions of estimated mortality probabilities. Mortality increased with rising age, comorbidities, and lactate. CONCLUSIONS: The New York Sepsis Severity Score accurately estimated the probability of hospital mortality in severe sepsis and septic shockpatients. It performed well with respect to calibration and discrimination. This sepsis-specific model provides an accurate, comprehensive method for standardized mortality comparison of adult patients with severe sepsis and septic shock.
Authors: Chanu Rhee; Maximilian S Jentzsch; Sameer S Kadri; Christopher W Seymour; Derek C Angus; David J Murphy; Greg S Martin; Raymund B Dantes; Lauren Epstein; Anthony E Fiore; John A Jernigan; Robert L Danner; David K Warren; Edward J Septimus; Jason Hickok; Russell E Poland; Robert Jin; David Fram; Richard Schaaf; Rui Wang; Michael Klompas Journal: Crit Care Med Date: 2019-04 Impact factor: 7.598
Authors: Heather E Hsu; Francisca Abanyie; Michael S D Agus; Fran Balamuth; Patrick W Brady; Richard J Brilli; Joseph A Carcillo; Raymund Dantes; Lauren Epstein; Anthony E Fiore; Jeffrey S Gerber; Runa H Gokhale; Benny L Joyner; Niranjan Kissoon; Michael Klompas; Grace M Lee; Charles G Macias; Karen M Puopolo; Carmen D Sulton; Scott L Weiss; Chanu Rhee Journal: Pediatrics Date: 2019-12 Impact factor: 7.124
Authors: Keith Corl; Mitchell Levy; Gary Phillips; Kathleen Terry; Marcus Friedrich; Amal N Trivedi Journal: Health Aff (Millwood) Date: 2019-07 Impact factor: 6.301
Authors: Mitchell M Levy; Foster C Gesten; Gary S Phillips; Kathleen M Terry; Christopher W Seymour; Hallie C Prescott; Marcus Friedrich; Theodore J Iwashyna; Tiffany Osborn; Stanley Lemeshow Journal: Am J Respir Crit Care Med Date: 2018-12-01 Impact factor: 21.405
Authors: Chanu Rhee; Rui Wang; Yue Song; Zilu Zhang; Sameer S Kadri; Edward J Septimus; David Fram; Robert Jin; Russell E Poland; Jason Hickok; Kenneth Sands; Michael Klompas Journal: Crit Care Explor Date: 2019-10-14