Search

Electronic health records enable automated data capture for risk models but may introduce bias. We present the Philips Critical Care Outcome Prediction Model (CCOPM) focused on addressing model features sensitive to data drift to improve benchmarking ICUs on mortality performance.Retrospective, multicenter study of ICU patients randomized in 3:2 fashion into development and validation cohorts. Generalized additive models (GAM) with features designed to mitigate biases introduced from documentation of admission diagnosis, Glasgow Coma Scale (GCS), and extreme vital signs were developed using clinical features representing the first 24 hours of ICU admission.eICU Research Institute database derived from ICUs participating in the Philips eICU telecritical care program.A total of 572,985 adult ICU stays discharged from the hospital between January 1, 2017, and December 31, 2018, were included, yielding 509,586 stays in the final cohort; 305,590 and 203,996 in development and validation cohorts, respectively.None.Model discrimination was compared against Acute Physiology and Chronic Health Evaluation (APACHE) IVa/IVb models on the validation cohort using the area under the receiver operating characteristic (AUROC) curve. Calibration assessed by actual/predicted ratios, calibration-in-the-large statistics, and visual analysis. Performance metrics were further stratified by subgroups of admission diagnosis and ICU characteristics. Historic data from two health systems with abrupt changes in Glasgow Coma Scale (GCS) documentation were assessed in the year prior to and after data shift. CCOPM outperformed APACHE IVa/IVb for ICU mortality (AUROC, 0.925 vs 0.88) and hospital mortality (AUROC, 0.90 vs 0.86). Better calibration performance was also attained among subgroups of different admission diagnoses, ICU types, and over unique ICU-years. The CCOPM provided more stable predictions compared with APACHE IVa within an external cohort of greater than 120,000 patients from two health systems with known changes in GCS documentation.These mortality risk models demonstrated excellent performance compared with APACHE while appearing to mitigate bias introduced through major shifts in GCS documentation at two large health systems. This provides evidence to support using automated capture rather than trained personnel for capture of GCS data used in benchmarking ICUs on mortality performance.

Rationale: Whether critical care improvements over the last 10 years extend to all hospitals has not been described. Objectives: To examine the temporal trends of critical care outcomes in minority and non–minority-serving hospitals using an inception cohort of critically ill patients. Measurements and Main Results: Using the Philips Health Care electronic ICU Research Institute Database, we identified minority-serving hospitals as those with an African American or Hispanic ICU census more than twice its regional mean. We examined almost 1.1 million critical illness admissions among 208 ICUs from across the United States admitted between 2006 and 2016. Adjusted hospital mortality (primary) and length of hospitalization (secondary) were the main outcomes. Large pluralities of African American (25%, n = 27,242) and Hispanic individuals (48%, n = 26,743) were cared for in minority-serving hospitals, compared with only 5.2% (n = 42,941) of white individuals. Over the last 10 years, although the risk of critical illness mortality steadily decreased by 2% per year (95% confidence interval [CI], 0.97–0.98) in non–minority-serving hospitals, outcomes within minority-serving hospitals did not improve comparably. This disparity in temporal trends was particularly noticeable among African American individuals, where each additional calendar year was associated with a 3% (95% CI, 0.96–0.97) lower adjusted critical illness mortality within a non–minority-serving hospital, but no change within minority-serving hospitals (hazard ratio, 0.99; 95% CI, 0.97–1.01). Similarly, although ICU and hospital lengths of stay decreased by 0.08 (95% CI, −0.08 to −0.07) and 0.16 (95% CI, −0.16 to −0.15) days per additional calendar year, respectively, in non–minority-serving hospitals, there was little temporal change for African American individuals in minority-serving hospitals. Conclusions: Critically ill African American individuals are disproportionately cared for in minority-serving hospitals, which have shown significantly less improvement than non–minority-serving hospitals over the last 10 years.

Illness severity scores are regularly employed for quality improvement and benchmarking in the intensive care unit, but poor generalization performance, particularly with respect to probability calibration, has limited their use for decision support. These models tend to perform worse in patients at a high risk for mortality. We hypothesized that a sequential modeling approach wherein an initial regression model assigns risk and all patients deemed high risk then have their risk quantified by a second, high-risk-specific, regression model would result in a model with superior calibration across the risk spectrum. We compared this approach to a logistic regression model and a sophisticated machine learning approach, the gradient boosting machine. The sequential approach did not have an effect on the receiver operating characteristic curve or the precision-recall curve but resulted in improved reliability curves. The gradient boosting machine achieved a small improvement in discrimination performance and was similarly calibrated to the sequential models.

ObjectiveDescribe the changes in patient population, bed occupancy, severity of illness and ventilator requirements across a large health system in the greater New York City area during the pandemic response in comparison with the 2019 baseline.DesignObservational, descriptive study of ICUs monitored by a tele-ICU system across Northwell Health. Inclusion criteria: All patients admitted to Northwell Health tele-ICUs during 2019 and between March 23, 2020 and April 6, 2020.ExposureA data extract was developed to collect data every hour for each ICU bed in the Northwell tele-critical care program as a quality reporting initiative to understand ICU capacity and resource utilization. A similar extract was developed for each hour of 2019.Main Outcomes and MeasuresAverage of any given hour during the pre-COVID-19 and pandemic periods for the following metrics: proportion of beds occupied, proportion of ventilated patients, severity of illness (measured by the ICU Discharge Readiness Score (DRS)), and length of stay (LOS).ResultsHourly analysis of data from 186 ICU beds from 14 ICUs and 9 hospitals were included, representing 10,714 patients in 2019 and 465 patients between March 23 and April 6, 2020. Average hourly occupancy increased from 64% to 78%, while the proportion of patients invasively ventilated increased from 33.9% to 84.2%. Median DRS (severity of illness score) increased from 1.08 (IQR: 0.24-6.98) to 39.38 (IQR: 12.00-71.28). Proportion of patients with Hispanic ethnicity doubled (7.8% to 16.6%; pConclusions and RelevanceIn addition to the expected increase in ICU occupancy and ventilator requirements, this large group of ICUs in midst of the COVID-19 epidemic are faced with managing a cohort of ICU patients with a dramatically higher severity of illness than their typical census.

Background Admission to high-acuity ICUs has been associated with improved outcomes compared with outcomes in low-acuity ICUs, although the mechanism for these findings is unclear. Research Question The goal of this study was to determine if high-acuity ICUs more effectively implement evidence-based processes of care that have been associated with improved clinical outcomes. Study Design and Methods This retrospective cohort study was performed in adult ICU patients admitted to 322 ICUs in 199 hospitals in the Philips ICU telemedicine database between 2010 and 2015. The primary exposure was ICU acuity, defined as the mean Acute Physiology and Chronic Health Evaluation IVa score of all admitted patients in a calendar year, stratified into quartiles. Multivariable logistic regression was used to examine relations of ICU acuity with adherence to evidence-based VTE and stress ulcer prophylaxis, and with the avoidance of potentially harmful events. These events included hypoglycemia, sustained hyperglycemia, and liberal transfusion practices (defined as RBC transfusions prescribed for nonbleeding patients with preceding hemoglobin levels ≥ 7 g/dL). Results Among 1,058,510 ICU admissions, adherence to VTE and stress ulcer prophylaxis was high across acuity levels. In adjusted analyses, those admitted to low-acuity ICUs compared with the highest acuity ICUs were more likely to experience hypoglycemic events (adjusted OR [aOR], 1.12; 95% CI, 1.04-1.19), sustained hyperglycemia (aOR, 1.07; 95% CI, 1.04-1.10), and liberal transfusion practices (aOR, 1.55; 95% CI, 1.33-1.82). Interpretation High-acuity ICUs were associated with better adherence to several evidence-based practices, which may be a marker of high-quality care. Future research should investigate how high-acuity ICUs approach ICU organization to identify targets for improving the quality of critical care across all ICU acuity levels.

Objective Identify opportunities to improve the interaction between clinicians and Tele-Critical Care (Tele-CC) programs through an analysis of alert occurrence and reactivation in a specific Tele-CC application. Materials and Methods Data were collected automatically through the Philips eCaremanager® software system used at multiple hospitals in the Avera health system. We evaluated the distribution of alerts per patient, frequency of alert types, time between consecutive alerts, and Tele-CC clinician choice of alert reactivation times. Results Each patient generated an average of 79.8 alerts during their ICU stay (median 31.0; 25th – 75th percentile 10.0–89.0) with 46.4 for blood pressure and 38.4 for oxygenation. The most frequent alerts for continuous physiological parameters were: MAP limit (28.9 %), O2/RR (26.4 %), MAP trend (16.5 %), HR trend (12.1 %), and HR limit (11.3 %). The median time between consecutive alerts for one parameter was less than 10 min for 86 % of patients. Tele-CC providers responded to all alert types with immediate reactivation 47–88 % of the time. Limit alerts had longer reactivation times than their trend alert counterparts (p-value Conclusions The alert type specific differences in frequency, time occurrence and provider choice of reactivation time provide insight into how clinicians interact with the Tele-CC system. Systems engineering enhancements to Tele-CC software algorithms may reduce alert burden and thereby decrease clinicians’ cognitive workload for alert assessment. Further study of Tele-CC alert generation, alert presentation to clinicians, and the clinicians’ options to respond to these alerts may reduce provider workload, minimize alert desensitization, and optimize the ability of Tele-CC clinicians to provide efficient and timely critical care management.

Background Proton pump inhibitors (PPIs) and histamine type 2 receptor blockers (H2Bs) are used for stress ulcer prophylaxis. Although the PPIs have greater potency for acid suppression, their relative effectiveness for preventing clinically important GI bleeding (CIGIB) has not been established. The goal of this study was to determine whether prophylactic PPIs were associated with lower risk of CIGIB than H2Bs among critically ill adults. Methods This retrospective cohort study included adults with critical illness from January 1, 2008, to June 30, 2012, who had at least one stress ulcer risk factor and received a PPI or H2B for ≥ 3 days. Cox proportional hazards regression propensity score matching and instrumental variable analyses were used to control for selection bias and confounding by unmeasured factors. The Acute Physiology and Chronic Health Evaluation Score version IV score was used to adjust for differences of acuity. The main outcome and exposure was CIGIB. Results Among 70,093 patients at risk, 49,576 (70.7%) received prophylaxis for at least 3 days, and 424 patients (0.6%) met the definition for experiencing CIGIB. The hazard for CIGIB was two times greater for PPI users compared with H2B users (adjusted hazard ratio, 1.82 [95% CI, 1.19-2.78]; hazard ratio, 2.37 [95% CI, 1.61-3.5]). Sensitivity analyses failed to detect any plausible scenario in which PPIs were superior to H2Bs for the prevention of CIGIB. Conclusions H2Bs were robustly and consistently associated with significantly lower CIGIB risk compared with PPIs in this population.

Evaluate the accuracy of different ICU risk models repurposed as continuous markers of severity of illness.Nonintervention cohort study.eICU Research Institute ICUs using tele-ICU software calculating continuous ICU Discharge Readiness Scores between January 2013 and March 2016.Five hundred sixty-one thousand four hundred seventy-eight adult ICU patients with an ICU length of stay between 4 hours and 30 days.Not available.Hourly Acute Physiology and Chronic Health Evaluation IV, Sequential Organ Failure Assessment, and Discharge Readiness Scores were calculated beginning hour 4 of the ICU stay. Primary outcome was the area under the receiver operating characteristic curve for the mean score with ICU mortality. Secondary outcomes included area under the receiver operating characteristic curves for ICU mortality with admission, median, maximum and last scores, and for death within 24 hours. The trajectories of each score were visualized by plotting the hourly averages against time in the ICU, stratified by mortality and length of stay. The area under the receiver operating characteristic curves for mean Acute Physiology and Chronic Health Evaluation, Sequential Organ Failure Assessment, and Discharge Readiness Scores were 0.90 (0.89-0.90), 0.86 (0.86-0.86), and 0.94 (0.94-0.94), respectively. The area under the receiver operating characteristic curves for hourly Acute Physiology and Chronic Health Evaluation, Sequential Organ Failure Assessment, and Discharge Readiness Scores predicting 24-hour mortality were 0.81 (0.81-0.81), 0.76 (0.76-0.76), and 0.86 (0.86-0.86). Discharge Readiness Scores had a higher area under the receiver operating characteristic curve than both Acute Physiology and Chronic Health Evaluation and Sequential Organ Failure Assessment for each metric. Acute Physiology and Chronic Health Evaluation and Sequential Organ Failure Assessment scores increased throughout the first 24 hours in both survivors and nonsurvivors; Discharge Readiness Scores continuously decreased in survivors and temporarily decreased before increasing by hour 36 in nonsurvivors with longer length of stays.Acute Physiology and Chronic Health Evaluation, Sequential Organ Failure Assessment, and Discharge Readiness Scores all have relatively high discrimination for ICU mortality when used continuously; Discharge Readiness Scores tended to have slightly higher area under the receiver operating characteristic curves for each endpoint. These findings validate the use of these models on a population level for continuous risk adjustment in the ICU, although Acute Physiology and Chronic Health Evaluation and Sequential Organ Failure Assessment appear slower to respond to improvements in patient status than Discharge Readiness Scores, and Discharge Readiness Scores may reflect physiologic improvement from interventions, potentially underestimating risk.

Many ICU patients do not require critical care interventions. Whether aggressive care environments increase risks to low-acuity patients is unknown. We evaluated whether ICU acuity was associated with outcomes of low mortality-risk patients. We hypothesized that admission to high-acuity ICUs would be associated with worse outcomes. This hypothesis was based on two possibilities: 1) high-acuity ICUs may have a culture of aggressive therapy that could lead to potentially avoidable complications and 2) high-acuity ICUs may focus attention toward the many sicker patients and away from the fewer low-risk patients.Retrospective cohort study.Three hundred twenty-two ICUs in 199 hospitals in the Philips eICU database between 2010 and 2015.Adult ICU patients at low risk of dying, defined as an Acute Physiology and Chronic Health Evaluation-IVa-predicted mortality of 3% or less.ICU acuity, defined as the mean Acute Physiology and Chronic Health Evaluation IVa score of all admitted patients in a calendar year, stratified into quartiles.We used generalized estimating equations to test whether ICU acuity is independently associated with a primary outcome of ICU length of stay and secondary outcomes of hospital length of stay, hospital mortality, and discharge destination. The study included 381,997 low-risk patients. Mean ICU and hospital length of stay were 1.8 ± 2.1 and 5.2 ± 5.0 days, respectively. Mean Acute Physiology and Chronic Health Evaluation IVa-predicted hospital mortality was 1.6% ± 0.8%; actual hospital mortality was 0.7%. In adjusted analyses, admission to low-acuity ICUs was associated with worse outcomes compared with higher-acuity ICUs. Specifically, compared with the highest-acuity quartile, ICU length of stay in low-acuity ICUs was increased by 0.24 days; in medium-acuity ICUs by 0.16 days; and in high-acuity ICUs by 0.09 days (all p0.001). Similar patterns existed for hospital length of stay. Patients in lower-acuity ICUs had significantly higher hospital mortality (odds ratio, 1.28 [95% CI, 1.10-1.49] for low-; 1.24 [95% CI, 1.07-1.42] for medium-, and 1.14 [95% CI, 0.99-1.31] for high-acuity ICUs) and lower likelihood of discharge home (odds ratio, 0.86 [95% CI, 0.82-0.90] for low-, 0.88 [95% CI, 0.85-0.92] for medium-, and 0.95 [95% CI, 0.92-0.99] for high-acuity ICUs).Admission to high-acuity ICUs is associated with better outcomes among low mortality-risk patients. Future research should aim to understand factors that confer benefit to patients with different risk profiles.

Background Longitudinal analyses of large, detailed adult critical care datasets provide insights into practice trends and generate useful outcome and process benchmarks. Methods Data representing 991,571 consecutive critical care visits to 160 US adult ICUs from 2009 to 2013 from the eICU Research Institute clinical practice database were used to quantitate patient characteristics, APACHE IV–based acuity predictions, treatments, and outcomes. Analyses for changes over time were performed for patient characteristics, entry and discharge locations, primary admission diagnosis, treatments, adherence to consensus ICU best practices, length of stay (LOS), and inpatient mortality. Results We detected significant trends for increasing age, BMI, and risk of mortality, higher frequency of admission from an ED and stepdown unit, and more frequent hospital discharge to substance abuse centers and skilled nursing facilities. Significantly more patients were admitted for sepsis, emphysema, coma, congestive heart failure, diabetic ketoacidosis, and fewer were admitted for asthma, unspecified chest pain, coronary artery bypass graft, and stroke care. The frequency of noninvasive mechanical ventilation and adherence to critical care best practices significantly increased, whereas the duration of renal replacement therapies, frequency of transfusions, antimicrobial use, critical care complications, LOS, and inpatient mortality decreased. Conclusions Analyses of patients, practices, and outcomes from a large geographically dispersed sample of adult ICUs revealed trends of increasing age and acuity, higher rates of adherence to best practice, use of noninvasive mechanical ventilation, and decreased use of antimicrobials, transfusions, and duration of renal replacement therapies. Acuity-adjusted LOS and in hospital mortality decreased.

OBJECTIVES To investigate the association between body mass index and mortality in a large, ICU population and determine if the relationship is observed among a subgroup of patients ordered early enteral nutrition. DESIGN Retrospective cohort study within a national clinical mixed ICU database of patients admitted between January 1, 2008, and June 30, 2015. SETTING Initial ICU admissions among patients monitored by tele-ICU programs and recorded in the Philips eICU Research Institute database. PATIENTS A total of 1,042,710 adult patient stays with ICU length of stay more than 24 hours, of which 74,771 were ordered enteral nutrition within the first 48 hours. INTERVENTION None. MEASUREMENTS AND MAIN RESULTS Patient stays from 409 ICUs were included. The average age, Acute Physiology and Chronic Health Evaluation IV score, and hospital mortality were 63.6 years, 56.7, and 9.0%, respectively. Hospital mortality among body mass index categories was estimated by multivariable modified Poisson regression models. Compared with the body mass index category 25.0-29.9 kg/m, hospital mortality was higher among underweight (body mass index, < 18.5; relative risk, 1.35; 95% CI, 1.32-1.39), normal weight (body mass index, 18.5-24.9; relative risk, 1.10; 95% CI, 1.09-1.12), and the extremely obese (body mass index, ≥ 50.0; relative risk, 1.10; 95% CI, 1.05-1.15). However, the risk was not statistically different from patients with body mass index 30.0-49.9 kg/m. Among patients ordered early enteral nutrition, the risk of mortality in the body mass index category 25.0-29.9 kg/m was not statistically different from those in the normal weight or extremely obese groups. CONCLUSIONS A survival advantage for overweight and obese patients was observed in this large cohort of critically ill patients. However, among those ordered early enteral nutrition, the survival disadvantage for body mass index categories less than 25.0 kg/m was minimal or unobservable when compared with higher body mass index categories.

This article examines the history of the telemedicine intensive care unit (tele-ICU), the current state of clinical decision support systems (CDSS) in the tele-ICU, applications of machine learning (ML) algorithms to critical care, and opportunities to integrate ML with tele-ICU CDSS. The enormous quantities of data generated by tele-ICU systems is a major driver in the development of the large, comprehensive, heterogeneous, and granular data sets necessary to develop generalizable ML CDSS algorithms, and deidentification of these data sets expands opportunities for ML CDSS research.

Objective: To compare the characteristics, use of invasive ventilation and outcomes of patients admitted with critical asthma syndrome (CAS) to ICUs in Australia and New Zealand (ANZ), and a large ...

Critical care patients are monitored closely through the course of their illness. As a result of this monitoring, large amounts of data are routinely collected for these patients. Philips Healthcare has developed a telehealth system, the eICU Program, which leverages these data to support management of critically ill patients. Here we describe the eICU Collaborative Research Database, a multi-center intensive care unit (ICU)database with high granularity data for over 200,000 admissions to ICUs monitored by eICU Programs across the United States. The database is deidentified, and includes vital sign measurements, care plan documentation, severity of illness measures, diagnosis information, treatment information, and more. Data are publicly available after registration, including completion of a training course in research with human subjects and signing of a data use agreement mandating responsible handling of the data and adhering to the principle of collaborative research. The freely available nature of the data will support a number of applications including the development of machine learning algorithms, decision support tools, and clinical research.

Purpose The goal of this study was to examine the real-world patterns of care and interventions among intensive care unit (ICU) patients with hypervolemic and euvolemic hyponatremia using a large clinical database. Materials and Methods The Phillips eICU Research Institute database was used to investigate hyponatremia treatment patterns and trends, mortality, and ICU and hospital length of stay. Demographics, clinical characteristics, and outcome variables were compared in patients corrected for hyponatremia using both a more strict and a less strict definition. Results At admission, 35%, 55%, and 10% of patients had mild, moderate, and severe hyponatremia, respectively. At the end of an ICU stay, the percentage of patients who did not have corrected serum sodium concentration was 48% (using a more strict definition) and 24% (using a less strict definition). Using either definition of correction, patients with serum sodium correction had lower mortality and longer survival than did patients without corrected serum sodium concentration. Conclusions A significant proportion of hyponatremia is not corrected during an ICU stay. Critically ill patients with hyponatremia who have their serum sodium corrected have lower mortality and longer survival, highlighting the need for more attention to hyponatremia and its correction in critically ill patients.

Our objective was to quantify the association between intensive care unit-acquired dysglycemia (hyperglycemia, hypoglycemia, and high variability) and in-hospital mortality.Retrospective, observational study.eICU Research Institute participating hospitals with an active tele-ICU program between January 1, 2008, and September 30, 2010, representing 784,392 adult intensive care unit patients.A total of 194,772 patients met inclusion criteria with an intensive care unit length of stay48 hrs.None.Acute Physiology and Chronic Health Evaluation IV standardized mortality ratios were calculated for dysglycemia present at admission and acquired in the intensive care unit. Intensive care unit-acquired dysglycemia was modeled using multivariable modified Poisson regression to account for confounding not incorporated in Acute Physiology and Chronic Health Evaluation. Dysglycemia severity was assessed by the relative risk of in-hospital mortality associated with the maximum, time-weighted average daily glucose; lowest glucose value throughout the intensive care unit stay; and quintiles of variability (coefficient of variation). The association of duration beyond thresholds of dysglycemia on mortality was also modeled. The adjusted relative risk (95% confidence interval) of mortality for the maximum intensive care unit average daily glucose was 1.13 (1.04-1.58), 1.43 (1.30-1.58), 1.63 (1.47-1.81), 1.76 (1.55-1.99), and 1.89 (1.62-2.19) for 110-150 mg/dL, 151-180 mg/dL, 180-240 mg/dL, 240-300 mg/dL, and300 mg/dL, respectively, compared to patients whose highest average daily glucose was 80-110 mg/dL. The relative risk of mortality for the lowest glucose value was 1.67 (1.37-2.03), 1.53 (1.37-1.70), 1.12 (1.04-1.21), and 1.06 (1.01-1.11) for20 mg/dL, 20-40 mg/dL, 40-60 mg/dL, and 60-80 mg/dL, respectively, compared to patients whose lowest value was 80-110 mg/dL. The relative risk of mortality increased with greater duration of hyperglycemia and with increased variability. The relative risk for the highest compared to lowest quintile of variability was 1.61 (1.47-1.78). The association of duration of hyperglycemia on mortality was more pronounced with more severe hyperglycemia.The risk of mortality progressively increased with severity and duration of deviation from euglycemia and with increased variability. These data suggest that severe intensive care unit-acquired hyperglycemia, hypoglycemia, and variability are associated with similar risks of mortality.

Part 2 of this review of ICU scoring systems examines how scoring system data should be used to assess ICU performance. There often are two different consumers of these data: lCU clinicians and quality leaders who seek to identify opportunities to improve quality of care and operational efficiency, and regulators, payors, and consumers who want to compare performance across facilities. The former need to know how to garner maximal insight into their care practices; this includes understanding how length of stay (LOS) relates to quality, analyzing the behavior of different subpopulations, and following trends over time. Segregating patients into low-, medium-, and high-risk populations is especially helpful, because care issues and outcomes may differ across this severity continuum. Also, LOS behaves paradoxically in high-risk patients (survivors often have longer LOS than nonsurvivors); failure to examine this subgroup separately can penalize ICUs with superior outcomes. Consumers of benchmarking data often focus on a single score, the standardized mortality ratio (SMR). However, simple SMRs are disproportionately affected by outcomes in high-risk patients, and differences in population composition, even when performance is otherwise identical, can result in different SMRs. Future benchmarking must incorporate strategies to adjust for differences in population composition and report performance separately for low-, medium- and high-acuity patients. Moreover, because many ICUs lack the resources to care for high-acuity patients (predicted mortality >50%), decisions about where patients should receive care must consider both ICU performance scores and their capacity to care for different types of patients.

This review examines the use of scoring systems to assess ICU performance. APACHE (Acute Physiology and Chronic Health Evaluation), MPM (mortality probability model), and SAPS (simplified acute physiology score) are the three major ICU scoring systems in use today. Central to all three is the use of physiologic data for severity adjustment. Differences in the size, nature, and time horizon of the data set translate into minor differences in accuracy and difficulty of data abstraction. APACHE IV provides ICU and hospital predictions for mortality and length of stay, whereas MPM and SAPS only provide hospital mortality predictions (although new algorithms generated from MPM data elements may predict ICU length of stay adequately). The primary use of scoring systems is for assessing ICU performance, with the ratio of actual-to-predicted outcomes in the study cohort providing performance comparisons to the reference ICUs. The reliability of scoring system predictions depends on the completeness and accuracy of the abstracted data; accordingly, ICUs must implement robust data quality control processes. CIs of the ratios are inversely related to sample size, and care must be taken to avoid overinterpreting changes in outcomes. ICU structural and process issues also can affect scoring system performance measures. Despite good discrimination and calibration, scoring systems are used in only 10% to 15% of US ICUs. Without ICU performance data, there is little hope of improving quality and reducing costs. Current demands for transparency and computerization of documentation are likely to drive future use of ICU scoring systems.

Background The volume‐outcome relationship associated with intensive care unit ( ICU ) experience with managing acute myocardial infarction ( AMI ) remains inadequately understood. Methods and Results Within a multicenter clinical ICU database, we identified patients with a primary ICU admission diagnosis of AMI between 2008 and 2010 to evaluate whether annual AMI volume of an individual ICU is associated with mortality, length‐of‐stay, or quality indicators. Patients were categorized into those treated in ICU s with low‐annual‐ AMI volume (≤50th percentile, AMI patients/month, n=569 patients) versus high‐annual‐ AMI volume (≥90th percentile, ≥8 AMI patients/month, n=17 553 patients). Poisson regression and generalized estimating equation with negative binomial regression were used to calculate the relative risk (95% CI ) for mortality and length‐of‐stay, respectively, associated with admission to a low‐ AMI ‐volume ICU . When compared with high‐ AMI ‐volume, patients admitted to low‐ AMI ‐volume ICU s had substantially more medical comorbidities, higher in‐hospital mortality (11% versus 4%, P P AMI (reperfusion therapy, antiplatelets, β‐blockers, and statins). However, after adjustment for baseline patient characteristics, low‐ AMI ‐volume ICU was no longer an independent predictor of in‐hospital mortality (relative risk 1.17 [0.87 to 1.56]) or hospital length‐of‐stay (relative risk 1.01 [0.94 to 1.08]). Similar findings were noted in secondary analyses of ICU mortality and ICU length‐of‐stay. Conclusions Admission to an ICU with lower annual AMI volume is associated with higher in‐hospital mortality, longer hospitalization, and lower use of evidence‐based therapies for AMI . However, the relationship between low‐ AMI ‐volume and outcomes is no longer present after accounting for the higher‐risk medical comorbidities and clinical characteristics of patients admitted to these ICU s.

Severe sepsis remains a significant medical problem affecting up to 18 million individuals worldwide. Mortality remains high ranging between 28% and 50%. Owing to this and the time-sensitive nature of this disease state, early identification and prompt interventions are necessary to improve outcomes. Technology associated with telemedicine may help in screening, identifying, and monitoring the attainment of the severe sepsis bundle elements in a timely manner. However, the heterogeneity of systemic inflammatory response syndrome and clinical assessment necessary to diagnose and assess patients with severe sepsis makes technology alone insufficient to improve the outcomes in these patients.

With growing concerns that big data will only augment the problem of unreliable research, the Laboratory of Computational Physiology at the Massachusetts Institute of Technology organized the Critical Data Conference in January 2014. Thought leaders from academia, government, and industry across disciplines—including clinical medicine, computer science, public health, informatics, biomedical research, health technology, statistics, and epidemiology—gathered and discussed the pitfalls and challenges of big data in health care. The key message from the conference is that the value of large amounts of data hinges on the ability of researchers to share data, methodologies, and findings in an open setting. If empirical value is to be from the analysis of retrospective data, groups must continuously work together on similar problems to create more effective peer review. This will lead to improvement in methodology and quality, with each iteration of analysis resulting in more reliability.

Many factors are known to influence the unfractionated heparin (UFH) dosage required to achieve therapeutic anticoagulation, including weight, sex, age, tobacco smoking, and diabetes mellitus. However, no interaction between thyroid function and UFH has been documented. An 83-year-old Caucasian woman had active hyperthyroidism that appeared to significantly increase her dosage requirements for UFH. The patient had atrial fibrillation secondary to the hyperthyroidism. She had no known factors that would increase UFH requirements. A UHF dosage of 1400 U/hour was needed to achieve a therapeutic level of anticoagulation (activated partial thromboplastin time 62 sec). After she was treated for hyperthyroidism, her atrial fibrillation resolved and UFH was discontinued. On day 9 of her hospital admission, atrial fibrillation resumed, and the patient's thyroid function began to normalize. Unfractionated heparin was restarted, and this time therapeutic anticoagulation was achieved with only 800 U/hour. This patient's experience suggests a previously undocumented and clinically significant relationship between active hyperthyroidism and altered dosage requirements for UFH. Recognition of this potential interaction may shorten the time required for patients with hyperthyroidism to achieve therapeutic anticoagulation, thereby preventing complications associated with subtherapeutic anticoagulation.