Predicting Discharge to a Long-Term Acute Care Hospital After Admission to an Intensive Care Unit

Szubski, Caleb R.; Tellez, Alejandra; Klika, Alison K.; Xu, Meng; Kattan, Michael W.; Guzmán, Jorge; Barsoum, Wael K.

doi:10.4037/ajcc2014985

Cited by 23 publications

(26 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…4–7 While it is important to pursue LOS prediction to understand total hospitalization costs, these methods lack sufficient clinical context to accurately predict the discharge date. Instead, the focus of this research project is to identify, based on the most recent clinical data, which NICU patients will likely be discharged home in the next 2–10 days.…”

Section: Introductionmentioning

confidence: 99%

Predicting Discharge Dates From the NICU Using Progress Note Data

Temple¹,

Lehmann

Fabbri³

2015

Pediatrics

View full text Add to dashboard Cite

Background and Objectives Discharging patients from the Neonatal Intensive Care Unit (NICU) may be delayed for non-medical reasons including the need for medical equipment, parental education, and children’s services. We describe a method to predict and identify patients that will be medically ready for discharge in the next 2–10 days – providing lead-time to address non-medical reasons for delayed discharge. Methods A retrospective study examined 26 features (17 extracted, 9 engineered) from daily progress notes of 4,693 patients (103,206 patient-days) from the NICU of a large, academic children’s hospital. These data were used to develop a supervised machine learning problem to predict days to discharge (DTD). Random forest classifiers were trained using combinations of examined features and ICD-9-based subpopulations to determine the most important features and those features which most accurately predicted days to discharge. Results Three of the four sub-populations (Premature, Cardiac, GI surgery) and all patients combined performed similarly at 2, 4, 7, and 10 DTD with AUC ranging from 0.854–0.865 at 2 DTD and 0.723–0.729 at 10 DTD. Neurosurgery patients performed worse at every DTD measure scoring 0.749 at 2 DTD and 0.614 at 10 DTD. This model was also able to identify important features and provide “rule-of-thumb” criteria for patients close to discharge. Using DTD equal to 4 and 2 features (oral percentage of feedings and weight) we constructed a model with an AUC of 0.843. Conclusion Using clinical features from daily progress notes provides an accurate method to predict when NICU patients are nearing discharge.

show abstract

Section: Introductionmentioning

confidence: 99%

Predicting Discharge Dates From the NICU Using Progress Note Data

Temple¹,

Lehmann

Fabbri³

2015

Pediatrics

View full text Add to dashboard Cite

show abstract

“…Okazało się, że rozkład ten był podobny w obu grupach wiekowych. Dane te trudno jest jednak odnieść do informacji pochodzących z Europy Zachodniej i Stanów Zjednoczonych, gdzie opieka po pobycie na oddziale intensywnej terapii jest zupełnie inaczej zorganizowana niż w Polsce [12,13]. W badaniach własnych chorzy z grupy "80+" oraz młodszej grupy wiekowej opuszczali OAiIT w podobnym stanie ogólnym.…”

Section: Omó Wi E Ni E W Y Ni K óW I D Ys K U Sj Aunclassified

The course and outcome of patients older than 79 years treated in intensive care unit

Knapik¹,

Zbieralska²,

Kłaczek³

et al. 2016

Ann. Acad. Med. Siles.

View full text Add to dashboard Cite

W S T Ę P :Pacjenci powyżej 79 roku życia stanowią rosnący odsetek chorych przyjmowanych na oddziały anestezjologii i intensywnej terapii (OAiIT). Celem pracy była ocena charakterystyki pacjentów po 79 roku życia przyjmowanych na OAiIT, przebiegu i wyników ich leczenia oraz czasu przeżycia po wypisie z oddziału, a także zbadanie korelacji tych wyników z uzyskanymi w pozostałej populacji leczonej w tym czasie w OAiIT. M A T E R I A Ł I M E T O D Y :Retrospektywną analizę przeprowadzono u 870 kolejnych chorych przyjętych na OAiIT w Śląskim Centrum Chorób Serca w kolejnych 8 latach. Analizowano wyłącznie pierwsze przyjęcia -z analizy wykluczono wszystkie powtórne i kolejne hospitalizacje. Do badanej grupy włączono 75 chorych powyżej 79 roku życia (8,6%). Na potrzeby wszystkich obliczeń przyjęto, że istotność statystyczna występuje przy wartości współczynnika p < 0,05. W Y N I K I : Przyczyny przyjęcia chorych powyżej 79 roku życia i młodszych były podobne, wyjątek stanowił istotnie wyższy odsetek chorych przyjmowanych z powodu powikłań ostrego zespołu wieńcowego (38,7% vs 26,7%; p = 0,03) i zapalenia płuc (8,0% vs 2,9%; p = 0,04). Na OAiIT zmarło 44,0% starszych chorych i 41,4% pozostałej populacji (p = 0,75). Śmiertelność do 30 dnia po wypisie była jednak znacznie wyższa w najstarszej grupie chorych (45,2% vs 27,3%; p = 0,02). Śmiertelność roczna, według analizy Kaplana-Meiera, wyniosła 82% w grupie chorych powyżej 79 roku życia i 48% chorych w pozostałej populacji (p = 0,00003). W N I O S K I : Pacjenci powyżej 79 roku życia stanowią znaczącą grupę chorych wymagających leczenia na OAiIT. Śmiertelność szpitalna wśród najstarszych chorych jest zbliżona do pozostałej populacji, jednak odległe wyniki leczenia są bardzo złe, co może wynikać z niskiej jakości opieki po wypisie z OAiIT. S Ł O W A K L U C Z O W Eoddział intensywnej terapii, śmiertelność, chorzy w podeszłym wieku

show abstract

“…In particular, socioeconomic factors, such as insurance coverage [ 14 ], the level of support at home, and baseline functional status [ 15 ], have been shown to influence discharge destination. Additional factors, including older age, use of mechanical ventilation or the need for tracheotomy (in the setting of chronic respiratory failure), the presence of severe pressure ulcers, declines in cognitive function, and metabolic or nutritional derangements (e.g., hypoalbuminemia) may influence discharge destination after ICU admission [ 16 – 18 ]. Notably, while many of these identified risk factors are potentially modifiable, easily and/or rapidly correcting them can be a challenge in the clinical setting.…”

Section: Introductionmentioning

confidence: 99%

Admission vitamin D status is associated with discharge destination in critically ill surgical patients

Brook

Camargo

Christopher

et al. 2015

Ann. Intensive Care

View full text Add to dashboard Cite

BackgroundDischarge destination after critical illness is increasingly recognized as a valuable patient-centered outcome. Recently, vitamin D status has been shown to be associated with important outcomes such as length of stay (LOS) and mortality in intensive care unit (ICU) patients. Our goal was to investigate whether vitamin D status on ICU admission is associated with discharge destination.MethodsWe performed a retrospective analysis from an ongoing prospective cohort study of vitamin D status in critical illness. Patients were recruited from two surgical ICUs at a single teaching hospital in Boston, Massachusetts. All patients had 25-hydroxyvitamin D (25OHD) levels measured within 24 h of ICU admission. Discharge destination was dichotomized as non-home or home. Locally weighted scatterplot smoothing (LOWESS) was used to graph the relationship between 25OHD levels and discharge destination. To investigate the association between 25OHD level and discharge destination, we performed logistic regression analyses, controlling for age, sex, race, body mass index, socioeconomic status, acute physiology and chronic health evaluation II score, need for emergent vs. non-emergent surgery, vitamin D supplementation status, and hospital LOS.Results300 patients comprised the analytic cohort. Mean 25OHD level was 19 (standard deviation 8) ng/mL and 41 % of patients had a non-home discharge destination. LOWESS analysis demonstrated a near-inverse linear relationship between vitamin D status and non-home discharge destination to 25OHD levels around 10 ng/mL, with rapid flattening of the curve between levels of 10 and 20 ng/mL. Overall, 25OHD level at the outset of critical illness was inversely associated with non-home discharge destination (adjusted OR, 0.88; 95 % CI 0.82–0.95). When vitamin D status was dichotomized, patients with 25OHD levels <20 ng/mL had an almost 3-fold risk of a non-home discharge destination (adjusted OR, 2.74; 95 % CI 1.23–6.14) compared to patients with 25OHD levels ≥20 ng/mL.ConclusionsOur results suggest that vitamin D status may be a modifiable risk factor for non-home discharge destination in surgical ICU patients. Future randomized, controlled trials are needed to determine whether vitamin D supplementation in surgical ICU patients can improve clinical outcomes such as the successful rate of discharge to home after critical illness

show abstract

Predicting Discharge to a Long-Term Acute Care Hospital After Admission to an Intensive Care Unit

Cited by 23 publications

References 37 publications

Predicting Discharge Dates From the NICU Using Progress Note Data

Predicting Discharge Dates From the NICU Using Progress Note Data

The course and outcome of patients older than 79 years treated in intensive care unit

Admission vitamin D status is associated with discharge destination in critically ill surgical patients

Contact Info

Product

Resources

About