Mark Thoelke, MD

Insulin therapy in the hospital setting can cause hypoglycemia, which may lead to increased mortality and length of stay (LOS).[1, 2, 3] Hypoglycemia is associated with cardiovascular, cerebrovascular, and patient fall events.[4, 5] The Centers for Medicare and Medicaid Services have designated both severe hypoglycemia (SH) with harm and diabetic ketoacidosis as hospital acquired conditions (HAC) or never events. The Society for Hospital Medicine (SHM) defines SH in the hospital as a blood glucose (BG) <40 mg/dL. Minimizing episodes of SH is important for patient health outcomes, patient safety, and for healthcare facilities' safety metrics.

Many factors contribute to SH including excessive insulin doses, medication errors, inappropriate timing of insulin doses with food intake, changes in nutritional status, impaired renal function, and changes in medications such as steroids.[6] As part of a multiyear project in patient safety, an inpatient hypoglycemia alert algorithm was developed based on a multivariate analysis of individual patient demographic, pharmacy, laboratory, and glucometric data. The algorithm was previously shown to have a 75% sensitivity to predict episodes of SH.[7] In this study, we tested whether a predictive real‐time informatics hypoglycemia alert based on the tested algorithm, along with trained nurses, would result in a decreased frequency of SH events compared to usual care. We hypothesized that this alert would result in a reduction of SH events in those patients at high risk for hypoglycemia.

METHODS

Study Design and Population

This prospective cohort‐intervention study involved inpatients admitted to Barnes‐Jewish Hospital in St. Louis, Missouri, the academic hospital of Washington University School of Medicine (WUSM), from August 2011 through December 2011. Fourteen floors, including 10 internal medicine and 4 cardiology medicine floors, were selected based upon a high frequency of severe hypoglycemic events noted in 2010. Six of the internal medicine floors were designated as intervention floors, and 8 were designated as control floors, including the 4 cardiology units. The study population consisted of patients receiving diabetic medications on study floors who had a BG <90 mg/dL during their hospital stay (Figure 1). The study was approved by the WUSM institutional review board and included a waiver of consent for individual patients.

Figure 1

The pharmacy informatics system was programmed with the previously developed hypoglycemia alert to prospectively identify those patients at high risk of hypoglycemia based on real‐time patient information.[7] Patients were identified as high risk on study floors if insulin or an oral antihyperglycemic agent was prescribed and if their hypoglycemia informatics generated risk score was >35 within 24 hours of having a capillary or venous BG<90 mg/dL. The risk score of 35 corresponded to a 50% sensitivity for a subsequent BG <60 mg/dL and a 75% sensitivity for a BG <40 mg/dL. Patients who generated an alert once during their hospital stay were assigned to 1 of 3 categories based on their admission division and risk score: high‐risk intervention (HR‐I), high‐risk control (HR‐C), or low risk (LR). LR patients also had a BG <90 mg/dL during their stay, but a risk score of <35.

The electronic alert for HR‐I patients was sent by pager to division‐specific charge nurses. Fourteen charge nurses on intervention divisions were trained to assess the alert, interview the patient, identify an alternate dosing strategy, and collaborate with the patient's physicians. HR‐C patients were identified on control divisions based on the same criteria as intervention patients, but no alert was generated. Control patients' charts were reviewed and evaluated upon discharge by the research team‐certified diabetes nurse educator to determine whether the treating physician had identified the SH risk and had changed insulin orders.

Nurses and physicians caring for patients on study divisions provided informed consent to participate in the study. Nurses' satisfaction with the alert process and physician interaction was assessed with a collaboration scale that was completed after each alert (see Supporting Information, Appendix A, in the online version of this article).[8]

RESULTS

DISCUSSION

Hospitals are accountable for safe and effective care of patients with hyperglycemia, which includes prevention of medication‐induced hypoglycemia. We have developed a predictive informatics hypoglycemia risk alert that, when tested in a real‐world situation, significantly reduced the rate of SH in hospitalized patients without increasing severe hyperglycemia. The alert algorithm correctly identified patients who were at high risk for hypoglycemia and allowed caretakers the opportunity to lower that risk. The positive predictive value of the alert was low but acceptable at 9.7%, owing to the overall low rate of hypoglycemia in the patient population.

The alert model tested involved 3 components for success: the automated alert, trained charge nurse responders, and an interaction between the nurse responder and the care provider. HR‐I patients were interviewed and assessed for problems associated with oral intake, dietary habits, medication compliance, and hypoglycemia at home prior to communicating with physicians. The extensive training and proficiency in patient assessment and SBAR communication process required by nurses was paramount in the success of the alert. However, the alert provided a definitive risk assessment that was actionable, versus more global instruction, which has not had the same impact in risk reduction. Based on feedback collected from nurses at the study end, they felt the alert process was within their scope of practice and was not unduly burdensome. They also found that the training in diabetes management and SBAR communication techniques, in addition to the alert system, were useful in protecting patients from medication harm.

Physicians for HR‐C patients missed many opportunities to effectively intervene and thereby reduce the likelihood of an SH event. Our assumption is that the clinicians did not ascertain the risk of SH, which was reflected by the fact that orders were changed in 40.7% of HR‐I patients versus only 20.5% in the HR‐C group. Having alerts go directly to nurses rather than physicians permitted inclusion of additional information, such as caloric intake and testing schedules, so that changes in orders would have greater context, and the importance of mild hypoglycemia would not be overlooked.[16] Glycemic control is challenging for providers in the inpatient setting, as there is little time to test and titrate doses of insulin to achieve control. Tight glycemic control has become the primary focus of diabetes management in the outpatient setting to reduce long‐term risks of microvascular complications.[17, 18] However, establishing glycemic targets in the inpatient setting has been difficult because the risk for hypoglycemia increases with tighter control.[19, 20] Inpatient hypoglycemia has been associated with increased mortality, particularly in critically ill patients.[21, 22] Many factors contribute to hypoglycemia including low creatinine clearance, low body weight, untested insulin doses, errors in insulin administration, unexpected dietary changes, changes in medications affecting BG levels, poor communication during times of patient transfer to different care teams, and poor coordination of BG testing with insulin administration at meal times. A multifaceted approach aimed at improving both clinician and nurse awareness, and providing real‐time risk assessment is clearly required to insure patient safety.[6, 13, 23, 24]

There are significant economic benefits to avoiding SH in the hospital given the adverse outcomes associated with HACs and the extra cost associated with these conditions. In hospitalized patients, hypoglycemia worsens outcomes leading to higher costs due to longer LOS (by 3 days), higher inpatient charges (38.9%), and higher risk of discharge to a skilled nursing facility.[1, 3, 25, 26] Conversely, improved glycemic control can reduce surgical site infections, perioperative morbidity, and hospital LOS.[27] The high prevalence of insulin use among inpatients, many of whom have high‐risk characteristics, creates a milieu for both hyper‐ and hypoglycemia. Other groups have described a drop in hypoglycemia rates related to the use of standardized diabetes order sets and nurse and physician education, but this is the first study that used informatics in a prospective manner to identify patients who are at high risk for developing hypoglycemia and then specifically targeted those patients.[28] The alert process was modeled after a similar alert developed in our institution for identifying medicine patients at risk for sepsis.[29] Given the paucity of data related to inpatient glycemia risk reduction, this study is particularly relevant for improving patient safety.

The major limitation of this study is that it was not randomized at the patient level. Patients were assigned to intervention and control groups based on their occupancy on specific hospital floors to avoid treatment bias. Bias was assessed due to this nonrandom assignment by comparing demographic and clinical factors of HR patients between intervention and control floors, and found significant differences in HbA1c and admitting diagnosis. As the control group had lower HbA1c values than the intervention group, and it is known from the Diabetes Control and Complications Trial and Action to Control Cardiovascular Risk in Diabetes trial that lower HbA1c increases the risk of hypoglycemia, our results may be biased by the level of glucose control on admission.[30, 31] Admitting diagnoses differed significantly between intervention and control patients as did the Charlson Comorbidity Index score; however, the hypoglycemia alert system does not include patient diagnoses or comorbidities, and as such provided equipoise with regard to risk reduction regardless of presenting illness. This study included trained nurses, which may be beyond the scope of every institution and thereby limit the effectiveness of the alert in reducing risk. However, as a result of this study, the alert was expanded to other acute care floors at our hospital as well as other hospitals in the Barnes‐Jewish Hospital system.

In summary, this study showed a 68% decrease in episodes of SH in a high‐risk patient cohort on diabetic medications using a hypoglycemia alert system. The results of this study demonstrate the validity of a systems‐based approach to reduce SH in high‐risk inpatients.

Insulin therapy in the hospital setting can cause hypoglycemia, which may lead to increased mortality and length of stay (LOS).[1, 2, 3] Hypoglycemia is associated with cardiovascular, cerebrovascular, and patient fall events.[4, 5] The Centers for Medicare and Medicaid Services have designated both severe hypoglycemia (SH) with harm and diabetic ketoacidosis as hospital acquired conditions (HAC) or never events. The Society for Hospital Medicine (SHM) defines SH in the hospital as a blood glucose (BG) <40 mg/dL. Minimizing episodes of SH is important for patient health outcomes, patient safety, and for healthcare facilities' safety metrics.

Many factors contribute to SH including excessive insulin doses, medication errors, inappropriate timing of insulin doses with food intake, changes in nutritional status, impaired renal function, and changes in medications such as steroids.[6] As part of a multiyear project in patient safety, an inpatient hypoglycemia alert algorithm was developed based on a multivariate analysis of individual patient demographic, pharmacy, laboratory, and glucometric data. The algorithm was previously shown to have a 75% sensitivity to predict episodes of SH.[7] In this study, we tested whether a predictive real‐time informatics hypoglycemia alert based on the tested algorithm, along with trained nurses, would result in a decreased frequency of SH events compared to usual care. We hypothesized that this alert would result in a reduction of SH events in those patients at high risk for hypoglycemia.

METHODS

Study Design and Population

This prospective cohort‐intervention study involved inpatients admitted to Barnes‐Jewish Hospital in St. Louis, Missouri, the academic hospital of Washington University School of Medicine (WUSM), from August 2011 through December 2011. Fourteen floors, including 10 internal medicine and 4 cardiology medicine floors, were selected based upon a high frequency of severe hypoglycemic events noted in 2010. Six of the internal medicine floors were designated as intervention floors, and 8 were designated as control floors, including the 4 cardiology units. The study population consisted of patients receiving diabetic medications on study floors who had a BG <90 mg/dL during their hospital stay (Figure 1). The study was approved by the WUSM institutional review board and included a waiver of consent for individual patients.

Figure 1

The pharmacy informatics system was programmed with the previously developed hypoglycemia alert to prospectively identify those patients at high risk of hypoglycemia based on real‐time patient information.[7] Patients were identified as high risk on study floors if insulin or an oral antihyperglycemic agent was prescribed and if their hypoglycemia informatics generated risk score was >35 within 24 hours of having a capillary or venous BG<90 mg/dL. The risk score of 35 corresponded to a 50% sensitivity for a subsequent BG <60 mg/dL and a 75% sensitivity for a BG <40 mg/dL. Patients who generated an alert once during their hospital stay were assigned to 1 of 3 categories based on their admission division and risk score: high‐risk intervention (HR‐I), high‐risk control (HR‐C), or low risk (LR). LR patients also had a BG <90 mg/dL during their stay, but a risk score of <35.

The electronic alert for HR‐I patients was sent by pager to division‐specific charge nurses. Fourteen charge nurses on intervention divisions were trained to assess the alert, interview the patient, identify an alternate dosing strategy, and collaborate with the patient's physicians. HR‐C patients were identified on control divisions based on the same criteria as intervention patients, but no alert was generated. Control patients' charts were reviewed and evaluated upon discharge by the research team‐certified diabetes nurse educator to determine whether the treating physician had identified the SH risk and had changed insulin orders.

Nurses and physicians caring for patients on study divisions provided informed consent to participate in the study. Nurses' satisfaction with the alert process and physician interaction was assessed with a collaboration scale that was completed after each alert (see Supporting Information, Appendix A, in the online version of this article).[8]

RESULTS

DISCUSSION

Hospitals are accountable for safe and effective care of patients with hyperglycemia, which includes prevention of medication‐induced hypoglycemia. We have developed a predictive informatics hypoglycemia risk alert that, when tested in a real‐world situation, significantly reduced the rate of SH in hospitalized patients without increasing severe hyperglycemia. The alert algorithm correctly identified patients who were at high risk for hypoglycemia and allowed caretakers the opportunity to lower that risk. The positive predictive value of the alert was low but acceptable at 9.7%, owing to the overall low rate of hypoglycemia in the patient population.

The alert model tested involved 3 components for success: the automated alert, trained charge nurse responders, and an interaction between the nurse responder and the care provider. HR‐I patients were interviewed and assessed for problems associated with oral intake, dietary habits, medication compliance, and hypoglycemia at home prior to communicating with physicians. The extensive training and proficiency in patient assessment and SBAR communication process required by nurses was paramount in the success of the alert. However, the alert provided a definitive risk assessment that was actionable, versus more global instruction, which has not had the same impact in risk reduction. Based on feedback collected from nurses at the study end, they felt the alert process was within their scope of practice and was not unduly burdensome. They also found that the training in diabetes management and SBAR communication techniques, in addition to the alert system, were useful in protecting patients from medication harm.

Physicians for HR‐C patients missed many opportunities to effectively intervene and thereby reduce the likelihood of an SH event. Our assumption is that the clinicians did not ascertain the risk of SH, which was reflected by the fact that orders were changed in 40.7% of HR‐I patients versus only 20.5% in the HR‐C group. Having alerts go directly to nurses rather than physicians permitted inclusion of additional information, such as caloric intake and testing schedules, so that changes in orders would have greater context, and the importance of mild hypoglycemia would not be overlooked.[16] Glycemic control is challenging for providers in the inpatient setting, as there is little time to test and titrate doses of insulin to achieve control. Tight glycemic control has become the primary focus of diabetes management in the outpatient setting to reduce long‐term risks of microvascular complications.[17, 18] However, establishing glycemic targets in the inpatient setting has been difficult because the risk for hypoglycemia increases with tighter control.[19, 20] Inpatient hypoglycemia has been associated with increased mortality, particularly in critically ill patients.[21, 22] Many factors contribute to hypoglycemia including low creatinine clearance, low body weight, untested insulin doses, errors in insulin administration, unexpected dietary changes, changes in medications affecting BG levels, poor communication during times of patient transfer to different care teams, and poor coordination of BG testing with insulin administration at meal times. A multifaceted approach aimed at improving both clinician and nurse awareness, and providing real‐time risk assessment is clearly required to insure patient safety.[6, 13, 23, 24]

There are significant economic benefits to avoiding SH in the hospital given the adverse outcomes associated with HACs and the extra cost associated with these conditions. In hospitalized patients, hypoglycemia worsens outcomes leading to higher costs due to longer LOS (by 3 days), higher inpatient charges (38.9%), and higher risk of discharge to a skilled nursing facility.[1, 3, 25, 26] Conversely, improved glycemic control can reduce surgical site infections, perioperative morbidity, and hospital LOS.[27] The high prevalence of insulin use among inpatients, many of whom have high‐risk characteristics, creates a milieu for both hyper‐ and hypoglycemia. Other groups have described a drop in hypoglycemia rates related to the use of standardized diabetes order sets and nurse and physician education, but this is the first study that used informatics in a prospective manner to identify patients who are at high risk for developing hypoglycemia and then specifically targeted those patients.[28] The alert process was modeled after a similar alert developed in our institution for identifying medicine patients at risk for sepsis.[29] Given the paucity of data related to inpatient glycemia risk reduction, this study is particularly relevant for improving patient safety.

The major limitation of this study is that it was not randomized at the patient level. Patients were assigned to intervention and control groups based on their occupancy on specific hospital floors to avoid treatment bias. Bias was assessed due to this nonrandom assignment by comparing demographic and clinical factors of HR patients between intervention and control floors, and found significant differences in HbA1c and admitting diagnosis. As the control group had lower HbA1c values than the intervention group, and it is known from the Diabetes Control and Complications Trial and Action to Control Cardiovascular Risk in Diabetes trial that lower HbA1c increases the risk of hypoglycemia, our results may be biased by the level of glucose control on admission.[30, 31] Admitting diagnoses differed significantly between intervention and control patients as did the Charlson Comorbidity Index score; however, the hypoglycemia alert system does not include patient diagnoses or comorbidities, and as such provided equipoise with regard to risk reduction regardless of presenting illness. This study included trained nurses, which may be beyond the scope of every institution and thereby limit the effectiveness of the alert in reducing risk. However, as a result of this study, the alert was expanded to other acute care floors at our hospital as well as other hospitals in the Barnes‐Jewish Hospital system.

In summary, this study showed a 68% decrease in episodes of SH in a high‐risk patient cohort on diabetic medications using a hypoglycemia alert system. The results of this study demonstrate the validity of a systems‐based approach to reduce SH in high‐risk inpatients.

Insulin therapy in the hospital setting can cause hypoglycemia, which may lead to increased mortality and length of stay (LOS).[1, 2, 3] Hypoglycemia is associated with cardiovascular, cerebrovascular, and patient fall events.[4, 5] The Centers for Medicare and Medicaid Services have designated both severe hypoglycemia (SH) with harm and diabetic ketoacidosis as hospital acquired conditions (HAC) or never events. The Society for Hospital Medicine (SHM) defines SH in the hospital as a blood glucose (BG) <40 mg/dL. Minimizing episodes of SH is important for patient health outcomes, patient safety, and for healthcare facilities' safety metrics.

Many factors contribute to SH including excessive insulin doses, medication errors, inappropriate timing of insulin doses with food intake, changes in nutritional status, impaired renal function, and changes in medications such as steroids.[6] As part of a multiyear project in patient safety, an inpatient hypoglycemia alert algorithm was developed based on a multivariate analysis of individual patient demographic, pharmacy, laboratory, and glucometric data. The algorithm was previously shown to have a 75% sensitivity to predict episodes of SH.[7] In this study, we tested whether a predictive real‐time informatics hypoglycemia alert based on the tested algorithm, along with trained nurses, would result in a decreased frequency of SH events compared to usual care. We hypothesized that this alert would result in a reduction of SH events in those patients at high risk for hypoglycemia.

METHODS

Study Design and Population

This prospective cohort‐intervention study involved inpatients admitted to Barnes‐Jewish Hospital in St. Louis, Missouri, the academic hospital of Washington University School of Medicine (WUSM), from August 2011 through December 2011. Fourteen floors, including 10 internal medicine and 4 cardiology medicine floors, were selected based upon a high frequency of severe hypoglycemic events noted in 2010. Six of the internal medicine floors were designated as intervention floors, and 8 were designated as control floors, including the 4 cardiology units. The study population consisted of patients receiving diabetic medications on study floors who had a BG <90 mg/dL during their hospital stay (Figure 1). The study was approved by the WUSM institutional review board and included a waiver of consent for individual patients.

Figure 1

The pharmacy informatics system was programmed with the previously developed hypoglycemia alert to prospectively identify those patients at high risk of hypoglycemia based on real‐time patient information.[7] Patients were identified as high risk on study floors if insulin or an oral antihyperglycemic agent was prescribed and if their hypoglycemia informatics generated risk score was >35 within 24 hours of having a capillary or venous BG<90 mg/dL. The risk score of 35 corresponded to a 50% sensitivity for a subsequent BG <60 mg/dL and a 75% sensitivity for a BG <40 mg/dL. Patients who generated an alert once during their hospital stay were assigned to 1 of 3 categories based on their admission division and risk score: high‐risk intervention (HR‐I), high‐risk control (HR‐C), or low risk (LR). LR patients also had a BG <90 mg/dL during their stay, but a risk score of <35.

The electronic alert for HR‐I patients was sent by pager to division‐specific charge nurses. Fourteen charge nurses on intervention divisions were trained to assess the alert, interview the patient, identify an alternate dosing strategy, and collaborate with the patient's physicians. HR‐C patients were identified on control divisions based on the same criteria as intervention patients, but no alert was generated. Control patients' charts were reviewed and evaluated upon discharge by the research team‐certified diabetes nurse educator to determine whether the treating physician had identified the SH risk and had changed insulin orders.

Nurses and physicians caring for patients on study divisions provided informed consent to participate in the study. Nurses' satisfaction with the alert process and physician interaction was assessed with a collaboration scale that was completed after each alert (see Supporting Information, Appendix A, in the online version of this article).[8]

RESULTS

DISCUSSION

Hospitals are accountable for safe and effective care of patients with hyperglycemia, which includes prevention of medication‐induced hypoglycemia. We have developed a predictive informatics hypoglycemia risk alert that, when tested in a real‐world situation, significantly reduced the rate of SH in hospitalized patients without increasing severe hyperglycemia. The alert algorithm correctly identified patients who were at high risk for hypoglycemia and allowed caretakers the opportunity to lower that risk. The positive predictive value of the alert was low but acceptable at 9.7%, owing to the overall low rate of hypoglycemia in the patient population.

The alert model tested involved 3 components for success: the automated alert, trained charge nurse responders, and an interaction between the nurse responder and the care provider. HR‐I patients were interviewed and assessed for problems associated with oral intake, dietary habits, medication compliance, and hypoglycemia at home prior to communicating with physicians. The extensive training and proficiency in patient assessment and SBAR communication process required by nurses was paramount in the success of the alert. However, the alert provided a definitive risk assessment that was actionable, versus more global instruction, which has not had the same impact in risk reduction. Based on feedback collected from nurses at the study end, they felt the alert process was within their scope of practice and was not unduly burdensome. They also found that the training in diabetes management and SBAR communication techniques, in addition to the alert system, were useful in protecting patients from medication harm.

Physicians for HR‐C patients missed many opportunities to effectively intervene and thereby reduce the likelihood of an SH event. Our assumption is that the clinicians did not ascertain the risk of SH, which was reflected by the fact that orders were changed in 40.7% of HR‐I patients versus only 20.5% in the HR‐C group. Having alerts go directly to nurses rather than physicians permitted inclusion of additional information, such as caloric intake and testing schedules, so that changes in orders would have greater context, and the importance of mild hypoglycemia would not be overlooked.[16] Glycemic control is challenging for providers in the inpatient setting, as there is little time to test and titrate doses of insulin to achieve control. Tight glycemic control has become the primary focus of diabetes management in the outpatient setting to reduce long‐term risks of microvascular complications.[17, 18] However, establishing glycemic targets in the inpatient setting has been difficult because the risk for hypoglycemia increases with tighter control.[19, 20] Inpatient hypoglycemia has been associated with increased mortality, particularly in critically ill patients.[21, 22] Many factors contribute to hypoglycemia including low creatinine clearance, low body weight, untested insulin doses, errors in insulin administration, unexpected dietary changes, changes in medications affecting BG levels, poor communication during times of patient transfer to different care teams, and poor coordination of BG testing with insulin administration at meal times. A multifaceted approach aimed at improving both clinician and nurse awareness, and providing real‐time risk assessment is clearly required to insure patient safety.[6, 13, 23, 24]

There are significant economic benefits to avoiding SH in the hospital given the adverse outcomes associated with HACs and the extra cost associated with these conditions. In hospitalized patients, hypoglycemia worsens outcomes leading to higher costs due to longer LOS (by 3 days), higher inpatient charges (38.9%), and higher risk of discharge to a skilled nursing facility.[1, 3, 25, 26] Conversely, improved glycemic control can reduce surgical site infections, perioperative morbidity, and hospital LOS.[27] The high prevalence of insulin use among inpatients, many of whom have high‐risk characteristics, creates a milieu for both hyper‐ and hypoglycemia. Other groups have described a drop in hypoglycemia rates related to the use of standardized diabetes order sets and nurse and physician education, but this is the first study that used informatics in a prospective manner to identify patients who are at high risk for developing hypoglycemia and then specifically targeted those patients.[28] The alert process was modeled after a similar alert developed in our institution for identifying medicine patients at risk for sepsis.[29] Given the paucity of data related to inpatient glycemia risk reduction, this study is particularly relevant for improving patient safety.

The major limitation of this study is that it was not randomized at the patient level. Patients were assigned to intervention and control groups based on their occupancy on specific hospital floors to avoid treatment bias. Bias was assessed due to this nonrandom assignment by comparing demographic and clinical factors of HR patients between intervention and control floors, and found significant differences in HbA1c and admitting diagnosis. As the control group had lower HbA1c values than the intervention group, and it is known from the Diabetes Control and Complications Trial and Action to Control Cardiovascular Risk in Diabetes trial that lower HbA1c increases the risk of hypoglycemia, our results may be biased by the level of glucose control on admission.[30, 31] Admitting diagnoses differed significantly between intervention and control patients as did the Charlson Comorbidity Index score; however, the hypoglycemia alert system does not include patient diagnoses or comorbidities, and as such provided equipoise with regard to risk reduction regardless of presenting illness. This study included trained nurses, which may be beyond the scope of every institution and thereby limit the effectiveness of the alert in reducing risk. However, as a result of this study, the alert was expanded to other acute care floors at our hospital as well as other hospitals in the Barnes‐Jewish Hospital system.

In summary, this study showed a 68% decrease in episodes of SH in a high‐risk patient cohort on diabetic medications using a hypoglycemia alert system. The results of this study demonstrate the validity of a systems‐based approach to reduce SH in high‐risk inpatients.

Chronic kidney disease is increasingly recognized as a significant public health issue, especially as our population ages. In the United States, it is estimated that 19.2 million individuals have chronic kidney disease (CKD), with an increasing prevalence in the elderly.1 CKD is associated with a higher mortality rate, as well as an increased risk of having several comorbidities, including anemia, coronary artery disease, and congestive heart failure.24 Early recognition, intervention, and management of patients with CKD by physicians has been shown to slow progression of disease and decrease complications.57 In the hospital setting, patients with CKD are at increased risk of medication dosing errors and acute renal failure (ARF).810

Serum creatinine is the most commonly used laboratory marker for assessing renal function. However, creatinine level is an imprecise measure of overall renal function, especially in older patients. The most recent National Kidney Foundation/ Kidney Disease Outcomes Quality Initiative (K/DOQI) guidelines recommend laboratory reporting of a calculated estimate of GFR.11 Equations used to calculate estimated GFR in adults, including the Cockcroft‐Gault (C‐G) equation, have been shown to provide an estimate of renal function, which can be used to clinically stratify varying levels of impaired renal function.11 Several studies have demonstrated that recognition of CKD by physicians is low in various clinical settings, especially in elderly patients.1215 Compliance with renal‐dose medication guidelines has also frequently been noted to be poor.16, 17

The investigators conducted a chart review study before and after reporting of estimated GFR to physicians in a hospital setting to assess the effect on physician recognition of CKD, the primary outcome. Secondary outcomes included the effect of reporting GFR on physician prescribing behaviors at the time of hospital discharge, including dosing of renal‐dosed antibiotics and use of nonsteroidal anti‐inflammatory (NSAID) and cyclooxygenase type 2 inhibitor (COX‐2) medications.

METHODS

This study was a retrospective chart review, with a prospective chart review as a comparison. Patients selected were admitted to a general medical floor in a 900‐bed academic medical center over the 2 years from 2002 to 2004. Computerized databases of laboratory values and weights obtained during hospitalization were used to select patients who fulfilled the following criteria: age > 65 years, all creatinine values during hospitalization < 1.6 mg/dL, and calculated estimated creatinine clearance (CrCl) < 60 mL/min using the Cockcroft‐Gault (C‐G) formula. The C‐G equation was developed for estimating CrCl and has also been extensively tested as a predictor of GFR. K/DOQI guidelines identify the C‐G equation as the most frequently used equation to estimate GFR in adults.11 To ensure steady‐state renal function, patients were excluded if creatinine varied by more than 0.4 mg/dL during their hospitalization. Based on an anticipated CKD recognition rate of 24%,13 our study sample size was selected to detect a 13% difference in the primary end point between the pre‐ and postintervention groups with 80% power. The study was approved by the institutional review board of the medical school.

Patient charts were reviewed with data obtained from the medical record, including physician notes, discharge summaries, orders, medication lists, and discharge prescriptions. Physician recognition was defined by documentation of CKD, calculated CrCl, or GFR in the physician notes or discharge summary. Charts were reviewed for diagnosis of hypertension (HTN) or diabetes (DM), and discharge medications including NSAID and COX‐2 medications and use and correct dosing of antibiotics requiring dose adjustment in patients with decreased GFR. Aspirin was not included as an NSAID.

For the prospective chart review portion, patients were selected at the time of admission on the basis of the same criteria. A notification was placed in the chart prominently listing the patient's estimated GFR calculated using the C‐G equation. Also included was a list of the stages of chronic renal disease based on the most recent K/DOQI guidelines11 and recommendations on dosing of select renal‐dosed antibiotics. Patients were again excluded if creatinine varied more than 0.4 mg/dL during their hospitalization.

RESULTS

DISCUSSION

This study has confirmed the findings of other investigators that significant CKD is underdiagnosed by physicians, especially in elderly patients with creatinine values within the normal laboratory range.13, 14 Investigators have demonstrated improved documentation of CKD with reporting of creatinine clearance and other simple educational interventions in an outpatient setting.13 In this study, reporting of estimated GFR did result in a significantly higher rate of recognition, but the overall rate was still very low in both groups (3.9%‐12.6%).

Although physician recognition of CKD did increase with the reporting of estimated GFR, this study found no significant impact on prescribing behaviors. Previous studies have shown an association between documentation of specific diagnoses and appropriate physician management.15, 18 However, the current data suggest that simply reporting GFR and increasing physician recognition of CKD may not lead to a significant decrease in medication dosing errors and that more extensive educational measures may be required.

Hospitalist physicians are increasingly serving as the primary caregivers for an aging population of hospitalized patients, and it is imperative that physicians recognize decreased GFR in elderly patients. Clearly, medication dosing errors are occurring in these patients, increasing the risk of adverse drug reactions.19 Elderly patients with renal impairment are also at increased risk of ARF while hospitalized.9, 10 Recognition of CKD by inpatient physicians identifies those patients who require preventive measures including maintenance of adequate hydration and avoidance of hypotension and nephrotoxic agents. Prevention of ARF in these patients has important clinical implications, as the mortality of patients is higher for elderly patients who develop hospital‐acquired ARF than for those presenting with community‐acquired ARF.20 Development of ARF has also been shown to increase length of hospitalization.21 Hospitalist physicians can also use the period of hospitalization as an opportunity to identify patients at risk of progressive CKD and in need of close follow‐up and possible referral to a nephrologist.

This study had several limitations. It was performed at a single institution, and therefore results may not be generalizable to all medical centers. The primary outcome of CKD documentation is an imperfect measure of recognition. The fact that chart documentation of CKD increased following the intervention suggests that documentation is associated with recognition, although it may be an underestimate. The effects of reporting estimated GFR on other secondary outcomes, including dosing of other medications, prevention of ARF, and length of hospital stay were not examined and deserve further investigation. The C‐G equation was chosen to calculate estimated GFR. There may be some advantage to using the Modification of Diet in Renal Disease equation as an alternative, but it is unclear if this is true in elderly female patients, who made up most of our study population.2225 Although using a prediction equation is clearly superior to using creatinine measurement solely to assess renal function in patients, further study is needed to identify the most accurate and effective formula for calculating estimated GFR in elderly patients.

The low rate of recognition of CKD by physicians found in this and other studies demonstrates the strong need for improvement in this area. Low recognition of CKD and a high rate of medication dosing errors despite reporting of the estimated GFR suggest that simply reporting GFR in addition to creatinine level is not sufficient. Further research is indicated to identify pragmatic educational tools and feedback mechanisms that effectively improve inpatient physician recognition of CKD and decrease medication dosing errors in elderly hospitalized patients.

Chronic kidney disease is increasingly recognized as a significant public health issue, especially as our population ages. In the United States, it is estimated that 19.2 million individuals have chronic kidney disease (CKD), with an increasing prevalence in the elderly.1 CKD is associated with a higher mortality rate, as well as an increased risk of having several comorbidities, including anemia, coronary artery disease, and congestive heart failure.24 Early recognition, intervention, and management of patients with CKD by physicians has been shown to slow progression of disease and decrease complications.57 In the hospital setting, patients with CKD are at increased risk of medication dosing errors and acute renal failure (ARF).810

Serum creatinine is the most commonly used laboratory marker for assessing renal function. However, creatinine level is an imprecise measure of overall renal function, especially in older patients. The most recent National Kidney Foundation/ Kidney Disease Outcomes Quality Initiative (K/DOQI) guidelines recommend laboratory reporting of a calculated estimate of GFR.11 Equations used to calculate estimated GFR in adults, including the Cockcroft‐Gault (C‐G) equation, have been shown to provide an estimate of renal function, which can be used to clinically stratify varying levels of impaired renal function.11 Several studies have demonstrated that recognition of CKD by physicians is low in various clinical settings, especially in elderly patients.1215 Compliance with renal‐dose medication guidelines has also frequently been noted to be poor.16, 17

The investigators conducted a chart review study before and after reporting of estimated GFR to physicians in a hospital setting to assess the effect on physician recognition of CKD, the primary outcome. Secondary outcomes included the effect of reporting GFR on physician prescribing behaviors at the time of hospital discharge, including dosing of renal‐dosed antibiotics and use of nonsteroidal anti‐inflammatory (NSAID) and cyclooxygenase type 2 inhibitor (COX‐2) medications.

METHODS

This study was a retrospective chart review, with a prospective chart review as a comparison. Patients selected were admitted to a general medical floor in a 900‐bed academic medical center over the 2 years from 2002 to 2004. Computerized databases of laboratory values and weights obtained during hospitalization were used to select patients who fulfilled the following criteria: age > 65 years, all creatinine values during hospitalization < 1.6 mg/dL, and calculated estimated creatinine clearance (CrCl) < 60 mL/min using the Cockcroft‐Gault (C‐G) formula. The C‐G equation was developed for estimating CrCl and has also been extensively tested as a predictor of GFR. K/DOQI guidelines identify the C‐G equation as the most frequently used equation to estimate GFR in adults.11 To ensure steady‐state renal function, patients were excluded if creatinine varied by more than 0.4 mg/dL during their hospitalization. Based on an anticipated CKD recognition rate of 24%,13 our study sample size was selected to detect a 13% difference in the primary end point between the pre‐ and postintervention groups with 80% power. The study was approved by the institutional review board of the medical school.

Patient charts were reviewed with data obtained from the medical record, including physician notes, discharge summaries, orders, medication lists, and discharge prescriptions. Physician recognition was defined by documentation of CKD, calculated CrCl, or GFR in the physician notes or discharge summary. Charts were reviewed for diagnosis of hypertension (HTN) or diabetes (DM), and discharge medications including NSAID and COX‐2 medications and use and correct dosing of antibiotics requiring dose adjustment in patients with decreased GFR. Aspirin was not included as an NSAID.

For the prospective chart review portion, patients were selected at the time of admission on the basis of the same criteria. A notification was placed in the chart prominently listing the patient's estimated GFR calculated using the C‐G equation. Also included was a list of the stages of chronic renal disease based on the most recent K/DOQI guidelines11 and recommendations on dosing of select renal‐dosed antibiotics. Patients were again excluded if creatinine varied more than 0.4 mg/dL during their hospitalization.

RESULTS

DISCUSSION

This study has confirmed the findings of other investigators that significant CKD is underdiagnosed by physicians, especially in elderly patients with creatinine values within the normal laboratory range.13, 14 Investigators have demonstrated improved documentation of CKD with reporting of creatinine clearance and other simple educational interventions in an outpatient setting.13 In this study, reporting of estimated GFR did result in a significantly higher rate of recognition, but the overall rate was still very low in both groups (3.9%‐12.6%).

Although physician recognition of CKD did increase with the reporting of estimated GFR, this study found no significant impact on prescribing behaviors. Previous studies have shown an association between documentation of specific diagnoses and appropriate physician management.15, 18 However, the current data suggest that simply reporting GFR and increasing physician recognition of CKD may not lead to a significant decrease in medication dosing errors and that more extensive educational measures may be required.

Hospitalist physicians are increasingly serving as the primary caregivers for an aging population of hospitalized patients, and it is imperative that physicians recognize decreased GFR in elderly patients. Clearly, medication dosing errors are occurring in these patients, increasing the risk of adverse drug reactions.19 Elderly patients with renal impairment are also at increased risk of ARF while hospitalized.9, 10 Recognition of CKD by inpatient physicians identifies those patients who require preventive measures including maintenance of adequate hydration and avoidance of hypotension and nephrotoxic agents. Prevention of ARF in these patients has important clinical implications, as the mortality of patients is higher for elderly patients who develop hospital‐acquired ARF than for those presenting with community‐acquired ARF.20 Development of ARF has also been shown to increase length of hospitalization.21 Hospitalist physicians can also use the period of hospitalization as an opportunity to identify patients at risk of progressive CKD and in need of close follow‐up and possible referral to a nephrologist.

This study had several limitations. It was performed at a single institution, and therefore results may not be generalizable to all medical centers. The primary outcome of CKD documentation is an imperfect measure of recognition. The fact that chart documentation of CKD increased following the intervention suggests that documentation is associated with recognition, although it may be an underestimate. The effects of reporting estimated GFR on other secondary outcomes, including dosing of other medications, prevention of ARF, and length of hospital stay were not examined and deserve further investigation. The C‐G equation was chosen to calculate estimated GFR. There may be some advantage to using the Modification of Diet in Renal Disease equation as an alternative, but it is unclear if this is true in elderly female patients, who made up most of our study population.2225 Although using a prediction equation is clearly superior to using creatinine measurement solely to assess renal function in patients, further study is needed to identify the most accurate and effective formula for calculating estimated GFR in elderly patients.

The low rate of recognition of CKD by physicians found in this and other studies demonstrates the strong need for improvement in this area. Low recognition of CKD and a high rate of medication dosing errors despite reporting of the estimated GFR suggest that simply reporting GFR in addition to creatinine level is not sufficient. Further research is indicated to identify pragmatic educational tools and feedback mechanisms that effectively improve inpatient physician recognition of CKD and decrease medication dosing errors in elderly hospitalized patients.

Chronic kidney disease is increasingly recognized as a significant public health issue, especially as our population ages. In the United States, it is estimated that 19.2 million individuals have chronic kidney disease (CKD), with an increasing prevalence in the elderly.1 CKD is associated with a higher mortality rate, as well as an increased risk of having several comorbidities, including anemia, coronary artery disease, and congestive heart failure.24 Early recognition, intervention, and management of patients with CKD by physicians has been shown to slow progression of disease and decrease complications.57 In the hospital setting, patients with CKD are at increased risk of medication dosing errors and acute renal failure (ARF).810

Serum creatinine is the most commonly used laboratory marker for assessing renal function. However, creatinine level is an imprecise measure of overall renal function, especially in older patients. The most recent National Kidney Foundation/ Kidney Disease Outcomes Quality Initiative (K/DOQI) guidelines recommend laboratory reporting of a calculated estimate of GFR.11 Equations used to calculate estimated GFR in adults, including the Cockcroft‐Gault (C‐G) equation, have been shown to provide an estimate of renal function, which can be used to clinically stratify varying levels of impaired renal function.11 Several studies have demonstrated that recognition of CKD by physicians is low in various clinical settings, especially in elderly patients.1215 Compliance with renal‐dose medication guidelines has also frequently been noted to be poor.16, 17

The investigators conducted a chart review study before and after reporting of estimated GFR to physicians in a hospital setting to assess the effect on physician recognition of CKD, the primary outcome. Secondary outcomes included the effect of reporting GFR on physician prescribing behaviors at the time of hospital discharge, including dosing of renal‐dosed antibiotics and use of nonsteroidal anti‐inflammatory (NSAID) and cyclooxygenase type 2 inhibitor (COX‐2) medications.

METHODS

This study was a retrospective chart review, with a prospective chart review as a comparison. Patients selected were admitted to a general medical floor in a 900‐bed academic medical center over the 2 years from 2002 to 2004. Computerized databases of laboratory values and weights obtained during hospitalization were used to select patients who fulfilled the following criteria: age > 65 years, all creatinine values during hospitalization < 1.6 mg/dL, and calculated estimated creatinine clearance (CrCl) < 60 mL/min using the Cockcroft‐Gault (C‐G) formula. The C‐G equation was developed for estimating CrCl and has also been extensively tested as a predictor of GFR. K/DOQI guidelines identify the C‐G equation as the most frequently used equation to estimate GFR in adults.11 To ensure steady‐state renal function, patients were excluded if creatinine varied by more than 0.4 mg/dL during their hospitalization. Based on an anticipated CKD recognition rate of 24%,13 our study sample size was selected to detect a 13% difference in the primary end point between the pre‐ and postintervention groups with 80% power. The study was approved by the institutional review board of the medical school.

Patient charts were reviewed with data obtained from the medical record, including physician notes, discharge summaries, orders, medication lists, and discharge prescriptions. Physician recognition was defined by documentation of CKD, calculated CrCl, or GFR in the physician notes or discharge summary. Charts were reviewed for diagnosis of hypertension (HTN) or diabetes (DM), and discharge medications including NSAID and COX‐2 medications and use and correct dosing of antibiotics requiring dose adjustment in patients with decreased GFR. Aspirin was not included as an NSAID.

For the prospective chart review portion, patients were selected at the time of admission on the basis of the same criteria. A notification was placed in the chart prominently listing the patient's estimated GFR calculated using the C‐G equation. Also included was a list of the stages of chronic renal disease based on the most recent K/DOQI guidelines11 and recommendations on dosing of select renal‐dosed antibiotics. Patients were again excluded if creatinine varied more than 0.4 mg/dL during their hospitalization.

RESULTS

DISCUSSION

This study has confirmed the findings of other investigators that significant CKD is underdiagnosed by physicians, especially in elderly patients with creatinine values within the normal laboratory range.13, 14 Investigators have demonstrated improved documentation of CKD with reporting of creatinine clearance and other simple educational interventions in an outpatient setting.13 In this study, reporting of estimated GFR did result in a significantly higher rate of recognition, but the overall rate was still very low in both groups (3.9%‐12.6%).

Although physician recognition of CKD did increase with the reporting of estimated GFR, this study found no significant impact on prescribing behaviors. Previous studies have shown an association between documentation of specific diagnoses and appropriate physician management.15, 18 However, the current data suggest that simply reporting GFR and increasing physician recognition of CKD may not lead to a significant decrease in medication dosing errors and that more extensive educational measures may be required.

Hospitalist physicians are increasingly serving as the primary caregivers for an aging population of hospitalized patients, and it is imperative that physicians recognize decreased GFR in elderly patients. Clearly, medication dosing errors are occurring in these patients, increasing the risk of adverse drug reactions.19 Elderly patients with renal impairment are also at increased risk of ARF while hospitalized.9, 10 Recognition of CKD by inpatient physicians identifies those patients who require preventive measures including maintenance of adequate hydration and avoidance of hypotension and nephrotoxic agents. Prevention of ARF in these patients has important clinical implications, as the mortality of patients is higher for elderly patients who develop hospital‐acquired ARF than for those presenting with community‐acquired ARF.20 Development of ARF has also been shown to increase length of hospitalization.21 Hospitalist physicians can also use the period of hospitalization as an opportunity to identify patients at risk of progressive CKD and in need of close follow‐up and possible referral to a nephrologist.

This study had several limitations. It was performed at a single institution, and therefore results may not be generalizable to all medical centers. The primary outcome of CKD documentation is an imperfect measure of recognition. The fact that chart documentation of CKD increased following the intervention suggests that documentation is associated with recognition, although it may be an underestimate. The effects of reporting estimated GFR on other secondary outcomes, including dosing of other medications, prevention of ARF, and length of hospital stay were not examined and deserve further investigation. The C‐G equation was chosen to calculate estimated GFR. There may be some advantage to using the Modification of Diet in Renal Disease equation as an alternative, but it is unclear if this is true in elderly female patients, who made up most of our study population.2225 Although using a prediction equation is clearly superior to using creatinine measurement solely to assess renal function in patients, further study is needed to identify the most accurate and effective formula for calculating estimated GFR in elderly patients.

The low rate of recognition of CKD by physicians found in this and other studies demonstrates the strong need for improvement in this area. Low recognition of CKD and a high rate of medication dosing errors despite reporting of the estimated GFR suggest that simply reporting GFR in addition to creatinine level is not sufficient. Further research is indicated to identify pragmatic educational tools and feedback mechanisms that effectively improve inpatient physician recognition of CKD and decrease medication dosing errors in elderly hospitalized patients.