Development and validation of a continuous measure of patient condition using the Electronic Medical Record.

Patient condition is a key element in communication between clinicians. However, there is no generally accepted definition of patient condition that is independent of diagnosis and that spans acuity levels. We report the development and validation of a continuous measure of general patient condition that is independent of diagnosis, and that can be used for medical-surgical as well as critical care patients. A survey of Electronic Medical Record data identified common, frequently collected non-static candidate variables as the basis for a general, continuously updated patient condition score. We used a new methodology to estimate in-hospital risk associated with each of these variables. A risk function for each candidate input was computed by comparing the final pre-discharge measurements with 1-year post-discharge mortality. Step-wise logistic regression of the variables against 1-year mortality was used to determine the importance of each variable. The final set of selected variables consisted of 26 clinical measurements from four categories: nursing assessments, vital signs, laboratory results and cardiac rhythms. We then constructed a heuristic model quantifying patient condition (overall risk) by summing the single-variable risks. The model's validity was assessed against outcomes from 170,000 medical-surgical and critical care patients, using data from three US hospitals. Outcome validation across hospitals yields an area under the receiver operating characteristic curve(AUC) of ≥0.92 when separating hospice/deceased from all other discharge categories, an AUC of ≥0.93 when predicting 24-h mortality and an AUC of 0.62 when predicting 30-day readmissions. Correspondence with outcomes reflective of patient condition across the acuity spectrum indicates utility in both medical-surgical units and critical care units. The model output, which we call the Rothman Index, may provide clinicians with a longitudinal view of patient condition to help address known challenges in caregiver communication, continuity of care, and earlier detection of acuity trends.

Risks of mortality associated with common laboratory tests: a novel, simple and meaningful way to set decision limits from data available in the Electronic Medical Record.

BACKGROUND: Laboratory tests provide objective measurements of physiologic functions, but are usually evaluated by demographic reference-intervals (RI), instead of risk-based decision-limits (DL). We show that hospital electronic medical record (EMR) data can be utilized to associate all-cause mortality risks with analyte test values, thereby providing more information than RIs and defining new DLs. METHODS: Our cohort was 39,964 patients admitted for any reason and discharged alive, during two 1-year periods, at Sarasota Memorial Hospital, Florida, USA. We studied five routinely-performed in-hospital laboratory tests: serum creatinine, blood urea nitrogen, serum sodium, serum potassium, and serum chloride. By associating a mortality odds ratio with small intervals of values for each analyte, we calculated relative risk of all-cause mortality as a function of test values. RESULTS: We found mortality risks below the population average within these proposed DLs: potassium 3.4-4.3 mmol/L; sodium 136-142 mmol/L; chloride 100-108 mmol/L; creatinine 0.6-1.1 mg/dL; blood urea nitrogen (BUN) 5-20 mg/dL. The DLs correspond roughly to the usually-quoted RIs, with a notable narrowing for electrolytes. Potassium and sodium have reduced upper limits, avoiding a "high-normal" area where the odds ratio rises 2 to 3 times the population average. CONCLUSIONS: Any clinical laboratory test can be transformed into a mortality odds ratio function, associating mortality risk with each value of the analyte. This provides a DL determined by mortality risk, instead of RI assumptions about distribution in a "healthy" population. The odds ratio function also provides important risk information for analyte values outside the interval.

Placing clinical variables on a common linear scale of empirically based risk as a step towards construction of a general patient acuity score from the electronic health record: a modelling study.

OBJECTIVE: To explore the hypothesis that placing clinical variables of differing metrics on a common linear scale of all-cause postdischarge mortality provides risk functions that are directly correlated with in-hospital mortality risk. DESIGN: Modelling study. SETTING: An 805-bed community hospital in the southeastern USA. PARTICIPANTS: 42302 inpatients admitted for any reason, excluding obstetrics, paediatric and psychiatric patients. OUTCOME MEASURES: All-cause in-hospital and postdischarge mortalities, and associated correlations. RESULTS: Pearson correlation coefficients comparing in-hospital risks with postdischarge risks for creatinine, heart rate and a set of 12 nursing assessments are 0.920, 0.922 and 0.892, respectively. Correlation between postdischarge risk heart rate and the Modified Early Warning System (MEWS) component for heart rate is 0.855. The minimal excess risk values for creatinine and heart rate roughly correspond to the normal reference ranges. We also provide the risks for values outside that range, independent of expert opinion or a regression model. By summing risk functions, a first-approximation patient risk score is created, which correctly ranks 6 discharge categories by average mortality with p<0.001 for differences in category means, and Tukey's Honestly Significant Difference Test confirmed that the means were all different at the 95% confidence level. CONCLUSIONS: Quantitative or categorical clinical variables can be transformed into risk functions that correlate well with in-hospital risk. This methodology provides an empirical way to assess inpatient risk from data available in the Electronic Health Record. With just the variables in this paper, we achieve a risk score that correlates with discharge disposition. This is the first step towards creation of a universal measure of patient condition that reflects a generally applicable set of health-related risks. More importantly, we believe that our approach opens the door to a way of exploring and resolving many issues in patient assessment.

Clinical implications and validity of nursing assessments: a longitudinal measure of patient condition from analysis of the Electronic Medical Record.

OBJECTIVES: This study investigates risk of mortality associated with nurses' assessments of patients by physiological system. We hypothesise that nursing assessments of in-patients performed at entry correlate with in-hospital mortality, and those performed just before discharge correlate with postdischarge mortality. DESIGN: Cohort study of in-hospital and postdischarge mortality of patients over two 1-year periods. SETTING: An 805-bed community hospital in Sarasota, Florida, USA. SUBJECTS: 42 302 inpatients admitted for any reason, excluding obstetrics, paediatric and psychiatric patients. OUTCOME MEASURES: All-cause mortalities and mortality OR. RESULTS: Patients whose entry nursing assessments, other than pain, did not meet minimum standards had significantly higher in-hospital mortality than patients meeting minimums; and final nursing assessments before discharge had large OR for postdischarge mortality. In-hospital mortality OR were found to be: food, 7.0; neurological, 9.4; musculoskeletal, 6.9; safety, 5.6; psychosocial, 6.7; respiratory, 8.1; skin, 5.2; genitourinary, 3.0; gastrointestinal, 2.3; peripheral-vascular, 3.9; cardiac, 2.8; and pain, 1.1. CI at 95% are within ±20% of these values, with p<0.001 (except for pain). Similar results applied to postdischarge mortality. All results were comparable across the two 1-year periods, with 0.85 intraclass correlation coefficient. CONCLUSIONS: Nursing assessments are strongly correlated with in-hospital and postdischarge mortality. No multivariate analysis has yet been performed, and will be the subject of a future study, thus there may be confounding factors. Nonetheless, we conclude that these assessments are clinically meaningful and valid. Nursing assessment data, which are currently unused, may allow physicians to improve patient care. The mortality OR and the dynamic nature of nursing assessments suggest that nursing assessments are sensitive indicators of a patient's condition. While these conclusions must remain qualified, pending future multivariate analyses, nursing assessment data ought to be incorporated in risk-related health research, and changes in record-keeping software are needed to make this information more accessible.