Ruben Amarasingham

An automated model to identify heart failure patients at risk for 30-day readmission or death using electronic medical record data.

Background:A real-time electronic predictive model that identifies hospitalized heart failure (HF) patients at high risk for readmission or death may be valuable to clinicians and hospitals who care for these patients. Methods:An automated predictive model for 30-day readmission and death was derived and validated from clinical and nonclinical risk factors present on admission in 1372 HF hospitalizations to a major urban hospital between January 2007 and August 2008. Data were extracted from an electronic medical record. The performance of the electronic model was compared with mortality and readmission models developed by the Center for Medicaid and Medicare Services (CMS models) and a HF mortality model derived from the Acute Decompensated Heart Failure Registry (ADHERE model). Results:The 30-day mortality and readmission rates were 3.1% and 24.1% respectively. The electronic model demonstrated good discrimination for 30 day mortality (C statistic 0.86) and readmission (C statistic 0.72) and performed as well, or better than, the ADHERE model and CMS models for both outcomes (C statistic ranges: 0.72–0.73 and 0.56–0.66 for mortality and readmissions respectively; P < 0.05 in all comparisons). Markers of social instability and lower socioeconomic status improved readmission prediction in the electronic model (C statistic 0.72 vs. 0.61, P < 0.05). Conclusions:Clinical and social factors available within hours of hospital presentation and extractable from an EMR predicted mortality and readmission at 30 days. Incorporating complex social factors increased the models accuracy, suggesting that such factors could enhance risk adjustment models designed to compare hospital readmission rates.

Clinical Information Technologies and Inpatient Outcomes: A Multiple Hospital Study

BACKGROUND Despite speculation that clinical information technologies will improve clinical and financial outcomes, few studies have examined this relationship in a large number of hospitals. METHODS We conducted a cross-sectional study of urban hospitals in Texas using the Clinical Information Technology Assessment Tool, which measures a hospitals level of automation based on physician interactions with the information system. After adjustment for potential confounders, we examined whether greater automation of hospital information was associated with reduced rates of inpatient mortality, complications, costs, and length of stay for 167 233 patients older than 50 years admitted to responding hospitals between December 1, 2005, and May 30, 2006. RESULTS We received a sufficient number of responses from 41 of 72 hospitals (58%). For all medical conditions studied, a 10-point increase in the automation of notes and records was associated with a 15% decrease in the adjusted odds of fatal hospitalizations (0.85; 95% confidence interval, 0.74-0.97). Higher scores in order entry were associated with 9% and 55% decreases in the adjusted odds of death for myocardial infarction and coronary artery bypass graft procedures, respectively. For all causes of hospitalization, higher scores in decision support were associated with a 16% decrease in the adjusted odds of complications (0.84; 95% confidence interval, 0.79-0.90). Higher scores on test results, order entry, and decision support were associated with lower costs for all hospital admissions (-

Allocating scarce resources in real-time to reduce heart failure readmissions: a prospective, controlled study

110, -

Use of administrative claims data for identifying patients with cirrhosis.

132, and -

An Automated Model Using Electronic Medical Record Data Identifies Patients With Cirrhosis at High Risk for Readmission

538, respectively; P < .05). CONCLUSION Hospitals with automated notes and records, order entry, and clinical decision support had fewer complications, lower mortality rates, and lower costs.

The Legal And Ethical Concerns That Arise From Using Complex Predictive Analytics In Health Care

Objective To test a multidisciplinary approach to reduce heart failure (HF) readmissions that tailors the intensity of care transition intervention to the risk of the patient using a suite of electronic medical record (EMR)-enabled programmes. Methods A prospective controlled before and after study of adult inpatients admitted with HF and two concurrent control conditions (acute myocardial infarction (AMI) and pneumonia (PNA)) was performed between 1 December 2008 and 1 December 2010 at a large urban public teaching hospital. An EMR-based software platform stratified all patients admitted with HF on a daily basis by their 30-day readmission risk using a published electronic predictive model. Patients at highest risk received an intensive set of evidence-based interventions designed to reduce readmission using existing resources. The main outcome measure was readmission for any cause and to any hospital within 30 days of discharge. Results There were 834 HF admissions in the pre-intervention period and 913 in the post-intervention period. The unadjusted readmission rate declined from 26.2% in the pre-intervention period to 21.2% in the post-intervention period (p=0.01), a decline that persisted in adjusted analyses (adjusted OR (AOR)=0.73; 95% CI 0.58 to 0.93, p=0.01). In contrast, there was no significant change in the unadjusted and adjusted readmission rates for PNA and AMI over the same period. There were 45 fewer readmissions with 913 patients enrolled and 228 patients receiving intervention, resulting in a number needed to treat (NNT) ratio of 20. Conclusions An EMR-enabled strategy that targeted scarce care transition resources to high-risk HF patients significantly reduced the risk-adjusted odds of readmission.

Measuring Clinical Information Technology in the ICU Setting: Application in a Quality Improvement Collaborative

Background: Administrative data are used in clinical research, but the validity of ICD-9 codes to identify cirrhotic patients has not been well established. Goals: To determine the diagnostic accuracy of ICD-9 codes for cirrhosis in clinical practice. Study: We conducted a retrospective cohort study of patients from a safety-net hospital between 2008 and 2011. Patients were initially identified using ICD-9 codes for cirrhosis or a resultant complication. The gold-standard for diagnosis of cirrhosis was histology and/or imaging based on medical record review. Sensitivity, specificity, positive predictive values, and negative predictive values for each ICD-9 code were calculated. Diagnostic accuracy was assessed by the c-statistic using receiver operator characteristic curve analysis. Results: We identified 2893 patients with an ICD-9 code for cirrhosis, of whom 50.2% had 1 ICD-9 code, 20.3% had 2 different codes, and 29.5% had 3 or more codes. Cirrhosis was confirmed in 44.0% of patients with 1 ICD-9 code, 82.6% with 2 codes, and 95.7% of those with at least 3 codes. Ascites had a significantly lower positive predictive values for cirrhosis than other ICD-9 codes (P<0.001). The optimal combination of ICD-9 codes to identify cirrhotic patients included all codes except that of ascites, with a c-statistic of 0.71 in our derivation cohort. The sensitivity of this combination was confirmed to be 98% in a validation cohort of 285 patients with known cirrhosis. Conclusions: Administrative data can identify patients with cirrhosis with high accuracy, although ascites has a significantly lower positive predictive value than other ICD-9 codes.

An electronic medical record-based model to predict 30-day risk of readmission and death among HIV-infected inpatients.

BACKGROUND & AIMS Patients with cirrhosis have 1-month rates of readmission as high as 35%. Early identification of high-risk patients could permit interventions to reduce readmission. The aim of our study was to construct an automated 30-day readmission risk model for cirrhotic patients using electronic medical record (EMR) data available early during hospitalization. METHODS We identified patients with cirrhosis admitted to a large safety-net hospital from January 2008 through December 2009. A multiple logistic regression model for 30-day rehospitalization was developed using medical and socioeconomic factors available within 48 hours of admission and tested on a validation cohort. Discrimination was assessed using receiver operator characteristic curve analysis. RESULTS We identified 836 cirrhotic patients with 1291 unique admission encounters. Rehospitalization occurred within 30 days for 27% of patients. Significant predictors of 30-day readmission included the number of address changes in the prior year (odds ratio [OR], 1.13; 95% confidence interval [CI], 1.05-1.21), number of admissions in the prior year (OR, 1.14; 95% CI, 1.05-1.24), Medicaid insurance (OR, 1.53; 95% CI, 1.10-2.13), thrombocytopenia (OR, 0.50; 95% CI, 0.35-0.72), low level of alanine aminotransferase (OR, 2.56; 95% CI, 1.09-6.00), anemia (OR, 1.63; 95% CI, 1.17-2.27), hyponatremia (OR, 1.78; 95% CI, 1.14-2.80), and Model for End-stage Liver Disease score (OR, 1.04; 95% CI, 1.01-1.06). The risk model predicted 30-day readmission, with c-statistics of 0.68 (95% CI, 0.64-0.72) and 0.66 (95% CI, 0.59-0.73) in the derivation and validation cohorts, respectively. CONCLUSIONS Clinical and social factors available early during admission and extractable from an EMR predicted 30-day readmission in cirrhotic patients with moderate accuracy. Decision support tools that use EMR-automated data are useful for risk stratification of patients with cirrhosis early during hospitalization.

Identifying patients with diabetes and the earliest date of diagnosis in real time: an electronic health record case-finding algorithm

Predictive analytics, or the use of electronic algorithms to forecast future events in real time, makes it possible to harness the power of big data to improve the health of patients and lower the cost of health care. However, this opportunity raises policy, ethical, and legal challenges. In this article we analyze the major challenges to implementing predictive analytics in health care settings and make broad recommendations for overcoming challenges raised in the four phases of the life cycle of a predictive analytics model: acquiring data to build the model, building and validating it, testing it in real-world settings, and disseminating and using it more broadly. For instance, we recommend that model developers implement governance structures that include patients and other stakeholders starting in the earliest phases of development. In addition, developers should be allowed to use already collected patient data without explicit consent, provided that they comply with federal regulations regarding research on human subjects and the privacy of health information.

Envisioning a Social-Health Information Exchange as a Platform to Support a Patient-Centered Medical Neighborhood: A Feasibility Study

OBJECTIVE Few instruments are available to measure the performance of intensive care unit (ICU) clinical information systems. Our objectives were: 1) to develop a survey-based metric that assesses the automation and usability of an ICUs clinical information system; 2) to determine whether higher scores on this instrument correlate with improved outcomes in a multi-institution quality improvement collaborative. DESIGN This is a cross-sectional study of the medical directors of 19 Michigan ICUs participating in a state-wide quality improvement collaborative designed to reduce the rate of catheter-related blood stream infections (CRBSI). Respondents completed a survey assessing their ICUs information systems. MEASUREMENTS The mean of 54 summed items on this instrument yields the clinical information technology (CIT) index, a global measure of the ICUs information system performance on a 100 point scale. The dependent variable in this study was the rate of CRBSI after the implementation of several evidence-based recommendations. A multivariable linear regression analysis was used to examine the relationship between the CIT score and the post-intervention CRBSI rates after adjustment for the pre-intervention rate. RESULTS In this cross-sectional analysis, we found that a 10 point increase in the CIT score is associated with 4.6 fewer catheter related infections per 1,000 central line days for ICUs who participate in the quality improvement intervention for 1 year (95% CI: 1.0 to 8.0). CONCLUSIONS This study presents a new instrument to examine ICU information system effectiveness. The results suggest that the presence of more sophisticated information systems was associated with greater reductions in the bloodstream infection rate.