John D. Greene

Risk-Adjusting Hospital Inpatient Mortality Using Automated Inpatient, Outpatient, and Laboratory Databases

Objectives:To develop a risk-adjustment methodology that maximizes the use of automated physiology and diagnosis data from the time period preceding hospitalization. Design:Retrospective cohort study using split-validation and logistic regression. Setting:Seventeen hospitals in a large integrated health care delivery system. Subjects:Patients (n = 259,699) hospitalized between January 2002 and June 2005. Main Outcome Measures:Inpatient and 30-day mortality. Results:Inpatient mortality was 3.50%; 30-day mortality was 4.06%. We tested logistic regression models in a randomly chosen derivation dataset consisting of 50% of the records and applied their coefficients to the validation dataset. The final model included sex, age, admission type, admission diagnosis, a Laboratory-based Acute Physiology Score (LAPS), and a COmorbidity Point Score (COPS). The LAPS integrates information from 14 laboratory tests obtained in the 24 hours preceding hospitalization into a single continuous variable. Using Diagnostic Cost Groups software, we categorized patients as having up to 40 different comorbidities based on outpatient and inpatient data from the 12 months preceding hospitalization. The COPS integrates information regarding these 41 comorbidities into a single continuous variable. Our best model for inpatient mortality had a c statistic of 0.88 in the validation dataset, whereas the c statistic for 30-day mortality was 0.86; both models had excellent calibration. Physiologic data accounted for a substantial proportion of the models predictive ability. Conclusion:Efforts to support improvement of hospital outcomes can take advantage of risk-adjustment methods based on automated physiology and diagnosis data that are not confounded by information obtained after hospital admission.

Unstudied infants: outcomes of moderately premature infants in the neonatal intensive care unit

Background: Newborns of 30–34 weeks gestation comprise 3.9% of all live births in the United States and 32% of all premature infants. They have been studied much less than very low birthweight infants. Objective: To measure in-hospital outcomes and readmission within three months of discharge of moderately premature infants. Design: Prospective cohort study including retrospective chart review and telephone interviews after discharge. Setting: Ten birth hospitals in California and Massachusetts. Patients: Surviving moderately premature infants born between October 2001 and February 2003. Main outcome measures: (a) Occurrence of assisted ventilation during the hospital stay after birth; (b) adverse in-hospital outcomes—for example, necrotising enterocolitis; (c) readmission within three months of discharge. Results: With the use of prospective cluster sampling, 850 eligible infants and their families were identified, randomly selected, and enrolled. A total of 677 families completed a telephone interview three months after hospital discharge. During the birth stay, these babies experienced substantial morbidity: 45.7% experienced assisted ventilation, and 3.2% still required supplemental oxygen at 36 weeks. Readmission within three months occurred in 11.2% of the cohort and was higher among male infants and those with chronic lung disease. Conclusions: Moderately premature infants experience significant morbidity, as evidenced by high rates of assisted ventilation, use of oxygen at 36 weeks, and readmission. Such morbidity deserves more research.

The Kaiser Permanente inpatient risk adjustment methodology was valid in an external patient population

OBJECTIVES Accurately predicting hospital mortality is necessary to measure and compare patient care. External validation of predictive models is required to truly prove their utility. This study assessed the Kaiser Permanente inpatient risk adjustment methodology for hospital mortality in a patient population distinct from that used for its derivation. STUDY DESIGN AND SETTING Retrospective cohort study at two hospitals in Ottawa, Canada, involving all inpatients admitted between January 1998 and April 2002 (n=188,724). Statistical models for inpatient mortality were derived on a random half of the cohort and validated on the other half. RESULTS Inpatient mortality was 3.3%. The model using original parameter estimates had excellent discrimination (c-statistic 89.4, 95% confidence interval [CI] 0.891-0.898) but poor calibration. Using data-based parameter estimates, discrimination was excellent (c-statistic 0.915, 95% CI 0.912-0.918) and remained so when patient comorbidity was expressed in the model using the Elixhauser Index (0.901, 0.898-0.904) or the Charlson Index (0.894, 0.891-0.897). These models accurately predicted the risk of hospital death. CONCLUSION The Kaiser Permanente inpatient risk adjustment methodology is a valid model for predicting hospital mortality risk. It performed equally well regardless of methods used to summarize patient comorbidity.

Risk-adjusting hospital mortality using a comprehensive electronic record in an integrated health care delivery system.

Objective:Using a comprehensive inpatient electronic medical record, we sought to develop a risk-adjustment methodology applicable to all hospitalized patients. Further, we assessed the impact of specific data elements on model discrimination, explanatory power, calibration, integrated discrimination improvement, net reclassification improvement, performance across different hospital units, and hospital rankings. Design:Retrospective cohort study using logistic regression with split validation. Participants:A total of 248,383 patients who experienced 391,584 hospitalizations between January 1, 2008 and August 31, 2011. Setting:Twenty-one hospitals in an integrated health care delivery system in Northern California. Results:Inpatient and 30-day mortality rates were 3.02% and 5.09%, respectively. In the validation dataset, the greatest improvement in discrimination (increase in c statistic) occurred with the introduction of laboratory data; however, subsequent addition of vital signs and end-of-life care directive data had significant effects on integrated discrimination improvement, net reclassification improvement, and hospital rankings. Use of longitudinally captured comorbidities did not improve model performance when compared with present-on-admission coding. Our final model for inpatient mortality, which included laboratory test results, vital signs, and care directives, had a c statistic of 0.883 and a pseudo-R2 of 0.295. Results for inpatient and 30-day mortality were virtually identical. Conclusions:Risk-adjustment of hospital mortality using comprehensive electronic medical records is feasible and permits one to develop statistical models that better reflect actual clinician experience. In addition, such models can be used to assess hospital performance across specific subpopulations, including patients admitted to intensive care.

Intra-hospital transfers to a higher level of care: Contribution to total hospital and intensive care unit (ICU) mortality and length of stay (LOS)†‡

BACKGROUND Patients who experience intra-hospital transfers to a higher level of care (eg, ward to intensive care unit [ICU]) are known to have high mortality. However, these findings have been based on single-center studies or studies that employ ICU admissions as the denominator. OBJECTIVE To employ automated bed history data to examine outcomes of intra-hospital transfers using all hospital admissions as the denominator. DESIGN Retrospective cohort study. SETTING A total of 19 acute care hospitals. PATIENTS A total of 150,495 patients, who experienced 210,470 hospitalizations, admitted to these hospitals between November 1st, 2006 and January 31st, 2008. MEASUREMENTS Predictors were age, sex, admission type, admission diagnosis, physiologic derangement on admission, and pre-existing illness burden; outcomes were: 1) occurrence of intra-hospital transfer, 2) death following admission to the hospital, 3) death following transfer, and 4) total hospital length of stay (LOS). RESULTS A total of 7,868 hospitalizations that began with admission to either a general medical surgical ward or to a transitional care unit (TCU) had at least one transfer to a higher level of care. These hospitalizations constituted only 3.7% of all admissions, but accounted for 24.2% of all ICU admissions, 21.7% of all hospital deaths, and 13.2% of all hospital days. Models based on age, sex, preadmission laboratory test results, and comorbidities did not predict the occurrence of these transfers. CONCLUSIONS Patients transferred to higher level of care following admission to the hospital have excess mortality and LOS.

The Timing of Early Antibiotics and Hospital Mortality in Sepsis.

Rationale: Prior sepsis studies evaluating antibiotic timing have shown mixed results. Objectives: To evaluate the association between antibiotic timing and mortality among patients with sepsis receiving antibiotics within 6 hours of emergency department registration. Methods: Retrospective study of 35,000 randomly selected inpatients with sepsis treated at 21 emergency departments between 2010 and 2013 in Northern California. The primary exposure was antibiotics given within 6 hours of emergency department registration. The primary outcome was adjusted in‐hospital mortality. We used detailed physiologic data to quantify severity of illness within 1 hour of registration and logistic regression to estimate the odds of hospital mortality based on antibiotic timing and patient factors. Measurements and Main Results: The median time to antibiotic administration was 2.1 hours (interquartile range, 1.4‐3.1 h). The adjusted odds ratio for hospital mortality based on each hour of delay in antibiotics after registration was 1.09 (95% confidence interval [CI], 1.05‐1.13) for each elapsed hour between registration and antibiotic administration. The increase in absolute mortality associated with an hours delay in antibiotic administration was 0.3% (95% CI, 0.01‐0.6%; P = 0.04) for sepsis, 0.4% (95% CI, 0.1‐0.8%; P = 0.02) for severe sepsis, and 1.8% (95% CI, 0.8‐3.0%; P = 0.001) for shock. Conclusions: In a large, contemporary, and multicenter sample of patients with sepsis in the emergency department, hourly delays in antibiotic administration were associated with increased odds of hospital mortality even among patients who received antibiotics within 6 hours. The odds increased within each sepsis severity strata, and the increased odds of mortality were greatest in septic shock.

The Natural History of Changes in Preferences for Life‐Sustaining Treatments and Implications for Inpatient Mortality in Younger and Older Hospitalized Adults

To compare changes in preferences for life‐sustaining treatments (LSTs) and subsequent mortality of younger and older inpatients.

Flexible, cluster-based analysis of the electronic medical record of sepsis with composite mixture models

The widespread adoption of electronic medical records (EMRs) in healthcare has provided vast new amounts of data for statistical machine learning researchers in their efforts to model and predict patient health status, potentially enabling novel advances in treatment. In the case of sepsis, a debilitating, dysregulated host response to infection, extracting subtle, uncataloged clinical phenotypes from the EMR with statistical machine learning methods has the potential to impact patient diagnosis and treatment early in the course of their hospitalization. However, there are significant barriers that must be overcome to extract these insights from EMR data. First, EMR datasets consist of both static and dynamic observations of discrete and continuous-valued variables, many of which may be missing, precluding the application of standard multivariate analysis techniques. Second, clinical populations observed via EMRs and relevant to the study and management of conditions like sepsis are often heterogeneous; properly accounting for this heterogeneity is critical. Here, we describe an unsupervised, probabilistic framework called a composite mixture model that can simultaneously accommodate the wide variety of observations frequently observed in EMR datasets, characterize heterogeneous clinical populations, and handle missing observations. We demonstrate the efficacy of our approach on a large-scale sepsis cohort, developing novel techniques built on our model-based clusters to track patient mortality risk over time and identify physiological trends and distinct subgroups of the dataset associated with elevated risk of mortality during hospitalization.

Prediction of Recurrent Clostridium Difficile Infection Using Comprehensive Electronic Medical Records in an Integrated Healthcare Delivery System.

BACKGROUND Predicting recurrent Clostridium difficile infection (rCDI) remains difficult. METHODS We employed a retrospective cohort design. Granular electronic medical record (EMR) data had been collected from patients hospitalized at 21 Kaiser Permanente Northern California hospitals. The derivation dataset (2007-2013) included data from 9,386 patients who experienced incident CDI (iCDI) and 1,311 who experienced their first CDI recurrences (rCDI). The validation dataset (2014) included data from 1,865 patients who experienced incident CDI and 144 who experienced rCDI. Using multiple techniques, including machine learning, we evaluated more than 150 potential predictors. Our final analyses evaluated 3 models with varying degrees of complexity and 1 previously published model. RESULTS Despite having a large multicenter cohort and access to granular EMR data (eg, vital signs, and laboratory test results), none of the models discriminated well (c statistics, 0.591-0.605), had good calibration, or had good explanatory power. CONCLUSIONS Our ability to predict rCDI remains limited. Given currently available EMR technology, improvements in prediction will require incorporating new variables because currently available data elements lack adequate explanatory power. Infect Control Hosp Epidemiol 2017;38:1196-1203.

Data that drive: Closing the loop in the learning hospital system

The learning healthcare system describes a vision of US healthcare that capitalizes on science, information technology, incentives, and care culture to drive improvements in the quality of health care. The inpatient setting, one of the most costly and impactful domains of healthcare, is an ideal setting in which to use data and information technology to foster continuous learning and quality improvement. The rapid digitization of inpatient medicine offers incredible new opportunities to use data from routine care to generate new discovery and thus close the virtuous cycle of learning. We use an object lesson-sepsis care within the 21 hospitals of the Kaiser Permanente Northern California integrated healthcare delivery system-to offer insight into the critical elements necessary for developing a learning hospital system. We then describe how a hospital-wide data-driven approach to inpatient care can facilitate improvements in the quality of hospital care. Journal of Hospital Medicine 2016;11:S11-S17.