ORIGINAL RESEARCH

Findings from the Implementation of a Validated Readmission

Predictive Tool in the Discharge Workflow of a Medical Intensive
Care Unit
Uchenna R. Ofoma1, Subhash Chandra2, Rahul Kashyap3, Vitaly Herasevich3, Adil Ahmed4, Ognjen Gajic4,
Brian W. Pickering3, and Christopher J. Farmer4
1
Division of Critical Care Medicine, Geisinger Medical Center, Danville, Pennsylvania; 2Department of Internal Medicine, Greater
Baltimore Medical Center, Baltimore, Maryland; and 3Department of Anesthesiology and 4Division of Pulmonary and Critical Care
Medicine, Department of Internal Medicine, Mayo Clinic, Rochester, Minnesota

Abstract APACHE III scores (P = 0.03). In the implementation cohort,

Rationale: Provider decisions about patients to be discharged
from the intensive care unit (ICU) are often based on subjective
intuition, sometimes leading to premature discharge and early
readmission. The Stability and Work Load Index for Transfer
(SWIFT) score, as a risk stratification tool, has moderate ability
to predict patients at risk of ICU readmission.
Objectives: To describe findings following the incorporation
of the SWIFT score into the discharge workflow of a medical
ICU.
Methods: The study involved 5,293 consecutive patients
discharged alive from the medical ICU of an academic medical
center. The SWIFT score and associated percentage risk for
readmission were incorporated into daily rounds for purpose
of discharge decision-making. We measured readmission rates
before and after implementation and observed changes in
provider discharge decisions for individual patients after
SWIFT discussions.
26.2% of subjects had SWIFT scores greater than 15 and thus
were predicted to have a higher risk of unplanned readmissions.
In this high-risk group, 25% had SWIFT discussed in their
discharge planning. There was modification of provider discharge
decisions in 108 (30%) of cases in which the SWIFT was discussed.
SWIFT score values above a prespecified cutoff of 15 were
associated with physician tendency to prolong ICU stay or to
discharge to a monitored setting (P , 0.001). There was no
difference in 24-hour or 7-day readmission rates between the
baseline and implementation cohorts (1.9 vs. 2.4%, P = 0.24;
6.5 vs. 7.4%, P = 0.26, respectively) even after adjustment for
severity of illness.
Conclusions: Using the SWIFT score as an adjunct to clinical
judgment, physicians modified their discharge decisions in one-
third of subjects. Introducing such tools into the discharge
workflow may present change management challenges that limit
the evaluation of their impact on readmission rates and other
relevant ICU outcomes.

Measurements and Main Results: Baseline (n = 1,906) and Keywords: care transitions; readmissions; risk stratification;
implementation (n = 1,938) cohorts differed with respect to quality

(Received in original form December 9, 2013; accepted in final form March 12, 2014 )
Author Contributions: V.H., A.A., O.G., B.W.P., and C.J.F. contributed to the study’s conception, design, implementation and data gathering. R.K. and S.C.
were responsible for data analysis and interpretation. U.R.O. and S.C. were responsible for drafting the manuscript. V.H., O.G., B.W.P., and C.J.F. critically
revised the article. All eight authors assisted in the subsequent revisions and have read and approved of the final manuscript.
Correspondence and requests for reprints should be addressed to Uchenna R. Ofoma, M.D., Division of Critical Care Medicine, Geisinger Medical Center, 100
North Academy Avenue, Danville, PA 17822. E-mail: uofoma@geisinger.edu
This article has an online supplement, which is accessible from this issue’s table of contents online at www.atsjournals.org
Ann Am Thorac Soc Vol 11, No 5, pp 737–743, Jun 2014
Copyright © 2014 by the American Thoracic Society
DOI: 10.1513/AnnalsATS.201312-436OC
Internet address: www.atsjournals.org

Unplanned readmissions to the intensive costs (1, 2). There is growing concern admission. Broad guidelines have been
care unit (ICU) are associated with that early readmissions to the ICU may published regarding appropriate ICU
increased length of stay, mortality, and indicate premature discharge from index discharge (3). However, decisions about

Ofoma, Chandra, Kashyap, et al.: Readmission Prediction Tool in ICU Discharge Workflow 737

which patients are ready to be discharged
from the ICU are often based on the
subjective intuition of the clinician (4, 5).
Physicians’ approach toward decision-
making at the time of ICU discharge can
be further influenced by a variety of factors
not related to patient physiology and acuity
of illness. These include the availability
of beds, staffing, and workload pressure
(6–8).
It has also been suggested that severity
of illness and prognostic scoring systems,
as adjuncts to clinical judgment, may
better identify patients ready for discharge
from the ICU (3, 9). To this effect,
multiple scoring systems have been
proposed (10–12). However, there are no
prospective studies of their implementation
in clinical practice, and it remains
unknown whether such implementation
can improve processes and unexpected
outcomes of care for patients after ICU
discharge.
In the present study, we incorporated
the Stability and Workload Index for
Transfer (SWIFT) score into the usual
discharge rounds workflow of the same
ICU where it was initially derived and
validated and observed how the SWIFT
score influenced physician discharge
decision-making. We also measured
readmission rates after SWIFT introduction
and compared them with baseline pre-
implementation rates. Some of the results of
this study have been previously reported in
the form of an abstract (13).
Methods
Study Design and Settings
The study was conducted in an adult
medical ICU at the Mayo Clinic in
Rochester, Minnesota, from December 2007
to December 2009. The characteristics of
the ICU have been previously published
(14). The institutional review board
approved the study protocol and waived
the need for informed consent.
A baseline (December 2007–November
2008) period of usual discharge activity
was followed by an interventional
(December 2008–November 2009) period.
As part of a quality initiative to reduce ICU
readmission rates, an automatically
calculated SWIFT score was provided as
part of the nursing and attending rounding
flow sheets, as well as to the charge nurse
for the duration of the study. Physicians
738
and nurses received education from Mayo
quality coaches regarding the prognostic
performance of the score and about its
incorporation into the rounding workflow.
The SWIFT score for each patient was
calculated with an automatic web-based
tool at 6:45 A.M. every day, based on the
most recently available values of SWIFT
components (15). If a laboratory value
was not obtained for a given patient,
then it was assumed to be normal or
noncontributory. The charge nurse was
instructed to provide the bedside nurse and
the consulting physician with a copy of
the SWIFT score for all patients in the
ICU every morning on rounds. However,
for purposes of implementation, SWIFT
discussion was limited to patients
concerning whom a discharge decision
had been made on a specific rounding day.
Criteria to conclude that a physician had
decided to discharge a patient included
the discussion of possible discharge,
followed by an agreement and explicit
instruction by the consultant to the house
staff to discharge. After a decision to
discharge the patient from the unit
(without having seen the score) was made,
the patient’s nurse revealed the SWIFT
score to the physician team. The patient’s
nurse was instructed to encourage the
bedside providers to comment on the
discharge plan after revelation of the
SWIFT score. The nurse then recorded
the outcome of the discussion, using the
study reporting tool. When the SWIFT
score was not calculated because of
limitations of the automatic tool, (e.g.,
for patients who were not physically located
in the ICU at 6:45 A.M.), no “SWIFT
discussion” took place and these patients
were analyzed as such. Plan-Do-Study-Act
(PDSA) cycles were performed on
a quarterly basis during the implementation
period to continually assess the impact
of our change.
Electronic Resources
The current Mayo Clinic Electronic
Medical Record (EMR) fits the definition
of a comprehensive EMR (16). A
comprehensive EMR is defined as having
24 key functions in all clinical units. The
Critical Care Independent Multidisciplinary
Program of the hospital has an established
near-real-time relational database, called
METRIC Data Mart. Details of METRIC
Data Mart and the Mayo Clinic EMR
have been previously published elsewhere
AnnalsATS Volume 11 Number 5 | June 2014
ORIGINAL RESEARCH
(17). METRIC Data Mart contains a near-
real-time copy of pertinent ICU patient
physiologic monitoring data, medication
orders, laboratory and radiologic
investigations, physician and nursing
notes, and respiratory therapy data,
which were used for automatic SWIFT
score calculation. Access to the database
is accomplished through open database
connectivity.
Subjects
A consecutive cohort of adult (aged 18 yr
or older) patients discharged from the
medical ICU during the study period
was enrolled. Patients who were
discharged to a comfort/palliative care
facility or to another hospital or those
transferred to another ICU were excluded
from the study analysis. Only index
discharges and readmissions were
studied.
Sample Size
With a baseline composite 7-day
readmission rate of the study ICU of
8.5% (11), and with 1,000 patients before
and 1,000 patients after the intervention,
the study was calculated to have a power
of 0.84 to detect a 3.5% decrease in
composite readmission rate, using a one-
sided chi-square comparison and assuming
50% compliance with the intervention.
In choosing a one-sided test, we
hypothesized that introduction of the
SWIFT score would lead to more
conservative discharge strategies and
thereby lower readmission rates.
The SWIFT Score
The SWIFT score (11) is a previously
validated tool that predicts the likelihood
of ICU readmission within 24 hours of
discharge for individual patients, based
on a number of easily collected parameters
available at the point of ICU discharge.
SWIFT score parameters include source
of ICU admission, ICU length of stay, last
measured PaO2/FIO2 (fraction of inspired
oxygen) ratio, Glasgow Coma Scale score
at time of ICU discharge, and last arterial
blood gas PaCO2 (Table 1). The minimum
and maximum possible scores are 0 and
64, respectively. A SWIFT score value
greater than 15 has a sensitivity and
specificity of 50% and 85%, respectively,
for predicting readmission within 24 hours
of ICU discharge.
 ORIGINAL RESEARCH
Table 1. SWIFT score calculation worksheet
Variable
Original source of this ICU admission
Emergency department
Transfer from a ward or outside hospital (any type of nursing care unit)
Total ICU length of stay (duration in days)
,2
2–10
.10
Last measured PaO2/FIO2 ratio (during this ICU admission)
.400
,400 and .150
,150 and .100
,100
Glasgow Coma Scale score at time of ICU discharge
.14
11–14
8–10
,8
Last arterial blood gas PaCO2
,45 mm Hg
.45 mm Hg
Definition of abbreviations: ICU = intensive care unit; FIO2 = fraction of inspired oxygen; SWIFT =
Stability and Work Load Index for Transfer.
Reproduced by permission from Reference 1.
Measurements
We observed changes in physician discharge
decisions concerning subjects the physician
was contemplating discharging to
a general care setting, after revelation
and discussion of the SWIFT score. We
measured 24-hour and 7-day unplanned
readmission rates as well as elements of
resource utilization before and after
SWIFT implementation.
Changes to physician discharge decision
were categorized as follows: (1) discharge
to a monitored setting, (2) postponement
of ICU discharge, or (3) discharge with
enhanced verbal communication with the
receiving services in the general care unit.
Enhanced verbal communication was
defined as the itemization of specific
relevant issues identified during the
rounding discussion and ensuring that
these were communicated verbally by
consulting and resident physicians,
nurses, and respiratory therapists to their
counterparts on the receiving services.
(During the baseline period, elements of
this enhanced communication strategy
were not mandated, occurred variably,
and were not always verbal). The three
provider behavioral categorizations were
mutually exclusive. The combined end
points of discharge to a monitored bed
and postponement of ICU discharge were
designated a priori as change in discharge
Ofoma, Chandra, Kashyap, et al.: Readmission Prediction Tool in ICU Discharge Workflow
as appropriate for the distribution of
the data. Categorical data are presented
Score as percent frequency of occurrence.
The Pearson chi-square test was used to
compare categorical patient characteristics,
0 readmission rates, categorical components
8 of resource utilization measures (invasive
and noninvasive mechanical ventilation
0
1 rates), and the association between
14 discrete SWIFT score categories and
provider discharge actions. An independent
0 sample t test was used to compare means
5
10
of continuous patient characteristics and
13 duration of mechanical ventilation, and
the Mann–Whitney test was used to
0 compare ICU and hospital length of stay
6 between the periods before and after the
14
24 intervention. Descriptive statistics were
used to describe changes in provider
0 behavior during SWIFT implementation.
5 For readmission rates, prospective
comparisons were made between the
baseline and implementation cohorts.
All the statistical analyses were done with
the JMP (SAS, Cary, NC) statistical
package.
plan. Using a prespecified SWIFT score
cutoff of 15, we tested for association
between higher SWIFT scores (.15) Results
and dichotomized provider discharge
behavioral categorizations of enhanced Over the study period, a total of 5,293
communication and change in discharge patients were discharged alive. We excluded
plan. from analysis 321 subjects whose medical
Provider discharge decisions were records had no authorization for research
recorded with a standardized reporting at the Mayo Clinic, 15 subjects who were
checklist tool. A checklist filled out by less than 18 years of age, and 1,113 subjects
a patient’s nurse and signed off by the who were either transferred to another
charge nurse at the time of discharge ICU or discharged directly from the ICU
planning was collected by the study to home or other institutions. Of 3,844
coordinator. Prespecified measures of remaining index discharges, 1,906 occurred
resource utilization included ICU and before and 1,938 occurred after the
hospital length of stay, as well as rates SWIFT score implementation (Figure 1).
of use and duration of invasive and A calculated SWIFT score was available
noninvasive mechanical ventilation. at the time of discharge for 1,738
All the patients were monitored until subjects during the implementation period.
ICU readmission, hospital discharge, Specific characteristics of the baseline
or death. and implementation cohorts are presented
Post-hoc analysis adjusting for in Table 2. Subjects discharged from
severity of illness between the baseline the ICU during the baseline and
and implementation cohorts was implementation periods differed
performed by matching subjects on significantly with respect to sex and
the basis of exact APACHE (Acute admission severity of illness.
Physiology and Chronic Health
Evaluation) III scores. Provider Discharge Behavior
The SWIFT score discussion was
Data Management and Analysis implemented in 356 discharges,
All continuous data are reported as either representing 18.4% of total ICU discharges.
mean with standard deviation (SD) or Among a high-risk group with SWIFT
median with interquartile range (IQR) scores greater than 15 (n = 508), the
739
 ORIGINAL RESEARCH

implementation period (P = 0.24). The

corresponding values for 7-day readmission
rates were 124 (6.5%) and 143 (7.4%)
(P = 0.26) (Table 2). In the implementation
cohort, there was no difference in readmission
rates between subjects concerning whom
SWIFT was discussed and those concerning
whom the discussion did not take place:
24-hour and 7-day readmission rates were
1.4 versus 2.7% (P = 0.18) and 7.2 versus
7.4% (P = 0.9), respectively. These findings
were not altered after adjusting for severity
of illness (Table 4).

Resource Utilization
The observed measures of resource
Figure 1. Flow diagram. *Transferred to one of nine specialized care units at the Mayo Clinic utilization before and after implementation
Rochester, based on need for specialized care. ICU = intensive care unit. of the SWIFT score are outlined in Table 2.
Compared with the baseline period, the
cohort from the SWIFT implementation
period had decreased ICU length of stay
implementation rate was 25%. Rates of with 15 or less) was significantly associated (2.05 vs. 2.19 d; P = 0.04), decreased rate of
discussion of SWIFT score varied over the with physician behavior to change noninvasive ventilation use (14.6 vs. 17.6%;
study duration (P , 0.001), with a peak discharge plan (discharge to a monitored P = 0.01), fewer days of noninvasive
in the second quarter (Table 3). Discussion setting or postpone discharge; P , 0.001). ventilation (0.15 vs. 0.20; P = 0.007), and
of the SWIFT score at the time of discharge marginally decreased number of days of
led to changes in discharge plan (change Readmission Rates invasive ventilation (0.53 vs. 0.63; P = 0.06).
from intended general care unit discharge In the implementation cohort, 26.2% of There was no difference in the proportion
destination to a monitored unit or decision subjects had SWIFT scores greater than of patients using invasive ventilation (19.8
to keep in ICU for longer) for 12.6% of 15 and thus were predicted to have a higher vs. 21.1%; P = 0.29). These differences were
patients and to discharge with enhanced risk of unplanned readmissions. The largely attenuated in subgroup APACHE
verbal communication with the receiving number and rate of observed 24-hour III–matched secondary analysis using the
services for 17.7% discharges (Figure 2). readmissions were 36 (1.9%) during the 356 implementation cohort subjects
A SWIFT score of more than 15 (compared baseline period and 47 (2.4%) during the concerning whom the SWIFT score was
discussed and comparing them with
subjects from the baseline cohort. There
Table 2. Characteristics, resource utilization measures, and readmission rates in were also no differences in 24-hour and
baseline and SWIFT implementation cohorts 7-day readmission rates in this matched
comparison (Table 4).
Characteristic Baseline SWIFT P Value
(n = 1,906) (n = 1,938)

Age, yr* 64 (19) 63 (18) 0.14

Discussion
Sex: male, n (%) 967 (50.7) 1,109 (57.5) ,0.0001
Admission APACHE III* 69.2 (24.7) 67.5 (24.0) 0.03 In this study, we examined changes
BMI, kg/m2* 31.3 (16.8) 30.9 (9.2) 0.60 in provider discharge decisions and
Race: white, n (%) 1,632 (89.0) 1,623 (87.5) 0.54 readmission rates after introducing a clinical
Resource Utilization†
Invasive ventilation use, n (%) 403 (21.1) 381 (19.8) 0.29 prediction tool into the ICU discharge
Invasive ventilation, d 0.63 0.53 0.06 workflow. Our intervention was adopted
Noninvasive ventilation use, n (%) 336 (17.6) 282 (14.6) 0.01 in one-fifth of all discharge instances. In
Noninvasive ventilation, d 0.20 0.15 0.007 these instances, higher SWIFT values were
Hospital length of stay, d 11.6 9.0 ,0.001 associated with physician’s consideration
ICU length of stay, d 2.20 2.05 0.04
Readmission rate† for more conservative discharge practices
24-h 36 (1.9) 47 (2.4) 0.24 in subjects who would otherwise have
7-d 124 (6.5) 143 (7.4) 0.26 been dismissed to a general care setting.
Despite these behavioral changes, we found
Definition of abbreviations: APACHE = Acute Physiology and Chronic Health Evaluation; BMI = body
mass index; ICU = intensive care unit; SWIFT = Stability and Work Load Index for Transfer.
no difference in the prospective and
*Mean (SD). cross-sectional rates of unplanned ICU
†
Unadjusted statistics. readmissions.

740 AnnalsATS Volume 11 Number 5 | June 2014

 ORIGINAL RESEARCH

Table 3. Compliance with SWIFT implementation and observed changes in provider Given the observed compliance rates,
discharge decisions the effective study sample likely was
underpowered to detect any true difference
Variable First Second Third Fourth in readmission rates.
Quarter Quarter Quarter Quarter Apart from low adoption rates, other
factors could also potentially explain why
Total discharges 504 451 468 515 our intervention did not impact on
SWIFT score . 15* 140 (30.0) 126 (31.6) 122 (29.8) 120 (25.8) readmission rates. It is possible that the
SWIFT score discussed† 86 (17.1) 119 (26.4) 77 (16.5) 74 (14.4) SWIFT score may not adequately capture
Change in discharge plan‡ 13 (15.1) 17 (14.3) 8 (10.4) 7 (9.4)
Monitored setting 5 (5.8) 13 (10.9) 7 (9.1) 4 (5.4)
all factors that are critical to preventing
Discharge postponed 8 (9.3) 5 (4.2) 1 (1.3) 2 (2.7) readmissions. The derivative components of
Enhanced communication‡ 20 (23.3) 22 (18.5) 10 (13.0) 11 (14.9) the SWIFT score are composed mostly of
Readmissions within 24 h† 17 (3.4) 6 (1.3) 16 (3.4) 8 (1.6) patient-centered factors, and data from
Table E1 in the online supplement, showing
Definition of abbreviation: SWIFT = Stability and Work Load Index for Transfer.
*SWIFT score was calculated for 1,738 discharges. Quarterly breakdown not shown. association between scores greater than 15
†
Numbers expressed as percentage of total discharges. and increased resource utilization, suggest
‡
Numbers expressed as percentage of total cases in which SWIFT was discussed. that the SWIFT score can be considered
a marker for severity of illness. Apart from
We observed a SWIFT implementation SWIFT data. As illustrated in Table 3 severity of illness and other patient-related
rate of 18% of all discharges and 25% of (footnotes), the electronic SWIFT score, factors (11, 19–21), studies also suggest that
discharges with SWIFT score above 15. Such which was computed at 6:45 A.M. daily, there may be a relationship between ICU
low compliance rates are reflective of was available for only 1,738 of 1,938 readmissions and physician- or hospital-
a failure in change management, given that discharges. Second, the SWIFT score lacked related factors such as patient inflow
this implementation was performed in the precision for individual patients and volumes (22), ICU occupancy (23), and
same ICU where the SWIFT score was despite efforts at provider education, it decision-making practices (24). These
initially derived and validated. Coiera (18) often did not make sense to rotating ICU factors are not part of the SWIFT score
outlined four major causes for the failure providers and its implementation did not calculation.
of decision support systems to be used fit naturally into the established routine Another potential limitation of this
clinically. Several of these factors process of care. These factors were study is that the design makes it difficult to
may partly explain why the SWIFT identified in our PDSA assessments as directly link SWIFT introduction with
implementation rate at our study ICU barriers to full-fledged adoption and outcomes. For example, we cannot attribute
was low. First, we depended totally on an probably led to a waning of enthusiasm the significantly lower rates of resource
electronic system to calculate and supply with the implementation over time. utilization during the implementation

Figure 2. SWIFT implementation and provider discharge decision flow chart. *Subgroup utilized for post hoc APACHE-matched comparisons. †Includes
200 subjects for whom the SWIFT score was not available at discharge. APACHE = Acute Physiology and Chronic Health Evaluation; ICU = intensive care
unit; SWIFT = Stability and Work Load Index for Transfer.

Ofoma, Chandra, Kashyap, et al.: Readmission Prediction Tool in ICU Discharge Workflow 741
 ORIGINAL RESEARCH

Table 4. Readmission rates and resource utilization in APACHE-matched subgroups power to provide clinicians with confidence
to use the results to guide decision-making,
Variable Before* After† Difference and the need to be able to modify user
(n = 93) (n = 93) (P Value) behavior while improving patient outcomes
(27). Further studies addressing our
Readmission within 24 h 3 (3.2) 0 (0) 0.25 observed and perceived barriers to
Readmission within 7 d 8 (8.6) 6 (6.5) 0.8 adoption and other study limitations are
Invasive ventilation use, n (%) 25 (26.9) 25 (26.9) 1 needed to further elucidate any potential
Invasive ventilation, d‡ 0.85 (2.4) 0.67 (1.6) 0.9 impact of readmission predictive tools
Noninvasive ventilation use, n (%) 21 (22.6) 16 (17.2) 0.5
Noninvasive ventilation, d‡ 0.16 (0.4) 0.11 (0.4) 0.3 on readmission rates and other ICU
Hospital length of stay, d 6.3 6.1 0.68 outcomes.
ICU length of stay, d 1 2 0.12

Definition of abbreviations: APACHE = Acute Physiology and Chronic Health Evaluation; ICU =
intensive care unit. Conclusions
*APACHE-matched subgroup of baseline cohort (exact APACHE III scores).
†
Subgroup with SWIFT score discussed during implementation (n = 356).
‡
Median values of 0, thus mean and SD reported. Readmission prediction tools can help
physicians optimize the timing of ICU
discharge. This study suggests that physician
period to the SWIFT introduction. Also, our The Society of Critical Care Medicine decision-making at the time of patient
study collected data on a limited number has recommended using the unplanned discharge is potentially modifiable by one of
of baseline characteristics and adjusted ICU readmission rate within 48 hours such tools. However, introducing such tools
only for severity of illness. The study could as a clinical performance measure (25). into the discharge workflow may present
have been strengthened by the addition However, in order for readmission rates change management challenges that limit
of more characteristics of the study cohorts, to be a viable quality measure, physicians the evaluation of the impact of such tools on
which could have allowed for better must be able to alter the rate (26). readmission rates and other relevant ICU
adjustment for potential differences in Theoretically, one of the proposed ways outcomes. n
patient demographics using logistic that they can do this is by the use of risk
regression analysis. This becomes more stratification and clinical prediction tools Author disclosures are available with the text of
important, given that matching based on such as the SWIFT score as an adjunct this article at www.atsjournals.org.
exact APACHE III scores markedly reduced to clinical judgment, thereby potentially
the sample available for adjustment analysis. making safer ICU discharge decisions. Acknowledgment: The authors thank Andrew
Also, the overall quality improvement Standards for the evaluation of C. Hanson (Mayo Clinic Department of
atmosphere during the implementation a clinical prediction tool such as the SWIFT Biomedical Statistics and Informatics) for his work
with SWIFT tool programming, as well as the staff
may have contaminated the discharge score include the need to be validated to and nurse quality coaches of the 6 Mary Brigh
decision-making process, even when the provide evidence of reproducible accuracy, Medical Intensive Care Unit at the Mayo Clinic
SWIFT score was not discussed. the need to have sufficient predictive Rochester.

References
1 Rosenberg AL, Hofer TP, Hayward RA, Strachan C, Watts CM. Who
bounces back? Physiologic and other predictors of intensive care
unit readmission. Crit Care Med 2001;29:511–518.
2 Rosenberg AL, Watts C. Patients readmitted to ICUs: a systematic
review of risk factors and outcomes. Chest 2000;118:492–
502.
3 Task Force of the American College of Critical Care Medicine, Society
of Critical Care Medicine. Guidelines for intensive care unit
admission, discharge, and triage. Crit Care Med 1999;27:633–638.
4 Shear LM, Steingrub JS, Teres D, Shear L. ICU patient triage ranking:
a flawed practice. Crit Care Med 1988;16:409.
5 Heidegger CP, Treggiari MM, Romand JA. A nationwide survey of
intensive care unit discharge practices. Intensive Care Med 2005;31:
1676–1682.
6 Strosberg MA. Intensive care units in the triage mode: an organizational
perspective. Hosp Health Serv Adm 1991;36:95–109.
7 Sax FL, Charlson ME. Utilization of critical care units: a prospective
study of physician triage and patient outcome. Arch Intern Med
1987;147:929–934.
8 Goldfrad C, Rowan K. Consequences of discharges from intensive care
at night. Lancet 2000;355:1138–1142.
9 Zimmerman JE, Wagner DP, Draper EA, Knaus WA. Improving
intensive care unit discharge decisions: supplementing physician
judgment with predictions of next day risk for life support. Crit Care
Med 1994;22:1373–1384.
10 Frost SA, Tam V, Alexandrou E, Hunt L, Salamonson Y, Davidson PM,
Parr MJ, Hillman KM. Readmission to intensive care: development
of a nomogram for individualising risk. Crit Care Resusc 2010;12:
83–89.
11 Gajic O, Malinchoc M, Comfere TB, Harris MR, Achouiti A, Yilmaz M,
Schultz MJ, Hubmayr RD, Afessa B, Farmer JC. The Stability and
Workload Index for Transfer score predicts unplanned intensive care
unit patient readmission: initial development and validation. Crit Care
Med 2008;36:676–682.
12 Ouanes I, Schwebel C, Français A, Bruel C, Philippart F, Roucaud N,
Soufir L, Adrie C, Garrouste-Orgeas M, Timsit J-F, et al. Prediction of
early readmission after a stay in the ICU: validation of the SWIFT
score and construction of the FAIR score in a multicenter cohort.
Intensive Care Med 2009;35:296.
13 Ofoma U, Kashyap R, Daniels C, Gajic O, Pickering B, Farmer C. Does
implementation of a previously validated prediction tool reduce
readmission rates into a medical intensive care unit? [abstract].
Chest 2012;142:278A.
14 Afessa B, Keegan MT, Hubmayr RD, Naessens JM, Gajic O, Long
KH, Peters SG. Evaluating the performance of an institution

742 AnnalsATS Volume 11 Number 5 | June 2014

 ORIGINAL RESEARCH
using an intensive care unit benchmark. Mayo Clin Proc 2005;80:
174–180.
15 Chandra S, Agarwal D, Hanson A, Farmer JC, Pickering BW, Gajic O,
Herasevich V. The use of an electronic medical record based
automatic calculation tool to quantify risk of unplanned readmission
to the intensive care unit: a validation study. J Crit Care 2011;26:634.
e9–634.e15.
16 Jha AK, DesRoches CM, Campbell EG, Donelan K, Rao SR, Ferris TG,
Shield A, Rosenbaum S, Blumenthal D. Use of electronic health
records in U.S. hospitals. N Engl J Med 2009;360:1628–1638.
17 Herasevich V, Pickering BW, Dong Y, Peters SG, Gajic O. Informatics
infrastructure for syndrome surveillance, decision support, reporting,
and modeling of critical illness. Mayo Clin Proc 2010;85:247–254.
18 Coiera E. Guide to health informatics, 2nd ed. London: Hodder Arnold;
2003. pp. xxvii, 440.
19 Frost SA, Alexandrou E, Bogdanovski T, Salamonson Y, Davidson PM,
Parr MJ, Hillman KM. Severity of illness and risk of readmission to
intensive care: a meta-analysis. Resuscitation 2009;80:505–510.
20 Rosenberg AL, Hofer TP, Hayward RA, Strachan C, Watts CM. Who
bounces back? Physiologic and other predictors of intensive care
unit readmission. Crit Care Med 2001;29:511–518.
Ofoma, Chandra, Kashyap, et al.: Readmission Prediction Tool in ICU Discharge Workflow
21 Ho KM, Dobb GJ, Lee KY, Finn J, Knuiman M, Webb SA. The effect of
comorbidities on risk of intensive care readmission during the same
hospitalization: a linked data cohort study. J Crit Care 2009;24:101–107.
22 Baker DR, Pronovost PJ, Morlock LL, Geocadin RG, Holzmueller CG.
Patient flow variability and unplanned readmissions to an intensive
care unit. Crit Care Med 2009;37:2882–2887.
23 Chrusch CA, Olafson KP, McMillan PM, Roberts DE, Gray PR. High
occupancy increases the risk of early death or readmission after
transfer from intensive care. Crit Care Med 2009;37:2753–2758.
24 Yoon KB, Koh SO, Han DW, Kang OC. Discharge decision-making by
intensivists on readmission to the intensive care unit. Yonsei Med J
2004;45:193–198.
25 Society of Critical Care Medicine Quality Indicators Committee.
Candidate critical care quality indicators. Anaheim, CA: Society of
Critical Care Medicine; 1995.
26 Kramer AA, Higgins TL, Zimmerman JE. Intensive care unit
readmissions in US hospitals: patient characteristics, risk factors,
and outcomes. Crit Care Med 2012;40:3–10.
27 Laupacis A, Sekar N, Stiell IG. Clinical prediction rules: a review and
suggested modifications of methodological standards. JAMA 1997;
277:488–494.
743
Reproduced with permission of the copyright owner. Further reproduction prohibited without
permission.