Predictors of 90-Day Readmission in Children Undergoing Spinal Cord Tumor Surgery: A Nationwide Readmissions Database Analysis

Janjua, M. Burhan; Reddy, Sumanth; Samdani, Amer F.; Welch, William C.; Öztürk, Ali; Price, Angela V.; Weprin, Bradley E.; Swift, Dale M.

doi:10.1016/j.wneu.2019.03.245

Cited by 9 publications

(10 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Model prediction improvements were identified when adding clinical information and written discharge documentation compared with the available administrative data. Previous paediatric studies 3,[11][12][13][14][33][34][35] reported predictive model performance, with only one study 34 examining both clinical and administrative data by reviewing patients' medical record charts. Previous studies that have applied machine learning to paediatric readmission prediction obtained similar 13 or better performance 11,12 to the current study.…”

Section: Discussionmentioning

confidence: 99%

“…Logistic regression analysis methods are commonly employed in predicting paediatric unplanned hospital readmissions. Advanced machine learning analysis approaches have also been applied to adult 10 and paediatric [11][12][13][14] unplanned hospital readmissions, because of their potential to improve predictive model performance. 15 The commonly applied approaches included random forests, 16 least absolute selection and shrinkage operator (LASSO), 11,16,17 and gradient boosted decision trees.…”

Section: Introductionmentioning

confidence: 99%

“…[16][17][18] However, the number of paediatric studies remains limited, and have so far only analysed administrative data. [11][12][13][14] In a recently published study, 19 we developed a logistic regression model based on 16 administratively collected variables as electronic medical records were not available. The model was found with moderate discriminative ability for 30-day all-cause readmission at a tertiary paediatric hospital in Western Australia (WA) (C-statistic ¼ 0.645).…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Using machine learning to predict paediatric 30-day unplanned hospital readmissions: a case-control retrospective analysis of medical records, including written discharge documentation

et al. 2021

View full text Add to dashboard Cite

Objectives. To assess whether adding clinical information and written discharge documentation variables improves prediction of paediatric 30-day same-hospital unplanned readmission compared with predictions based on administrative information alone.Methods. A retrospective matched case-control study audited the medical records of patients discharged from a tertiary paediatric hospital in Western Australia (WA) between January 2010 and December 2014. A random selection of 470 patients with unplanned readmissions (out of 3330) were matched to 470 patients without readmissions based on age, sex, and principal diagnosis at the index admission. Prediction utility of three groups of variables (administrative, administrative and clinical, and administrative, clinical and written discharge documentation) were assessed using standard logistic regression and machine learning.Results. Inclusion of written discharge documentation variables significantly improved prediction of readmission compared with models that used only administrative and/or clinical variables in standard logistic regression analysis (x 2 17 ¼ 29.4, P ¼ 0.03). Highest prediction accuracy was obtained using a gradient boosted tree model (C-statistic ¼ 0.654), followed closely by random forest and elastic net modelling approaches. Variables highlighted as important for prediction included patients' social history (legal custody or patient was under the care of the Department for Child Protection), languages spoken other than English, completeness of nursing admission and discharge planning documentation, and timing of issuing discharge summary.Conclusions. The variables of significant social history, low English language proficiency, incomplete discharge documentation, and delay in issuing the discharge summary add value to prediction models.What is known about the topic? Despite written discharge documentation playing a critical role in the continuity of care for paediatric patients, limited research has examined its association with, and ability to predict, unplanned hospital readmissions. Machine learning approaches have been applied to various health conditions and demonstrated improved predictive accuracy. However, few published studies have used machine learning to predict paediatric readmissions.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Using machine learning to predict paediatric 30-day unplanned hospital readmissions: a case-control retrospective analysis of medical records, including written discharge documentation

et al. 2021

View full text Add to dashboard Cite

show abstract

“…Furthermore, the authors found that CNS, pulmonary, and infectious complications were among the five most common causes for 90-day readmission. 17 Abu-Bonsrah et al 15 found that 26.7% of the unplanned readmissions were due to surgical complications, with the most common being wound infections and cerebrospinal fluid leak. Similarly, in the Elsamadicy et al's 9 study of 135 patients, the authors showed that uncontrolled pain (16.7%), sensory motor deficits (13.3%), and fever (10.0%) were the most common reasons for 30-day readmission.…”

Section: Discussionmentioning

confidence: 99%

Thirty- and 90-day Readmissions After Spinal Surgery for Spine Metastases

Elsamadicy

Koo

David

et al. 2020

Spine

View full text Add to dashboard Cite

Study Design. Retrospective cohort study.Objective. The aim of this study was to investigate differences in 30-and 90-day readmissions for spine metastases treated with decompression and/or fusion spine surgery in a nationwide readmission database. Summary of Background Data. Patients with metastases to the spine represent a particularly vulnerable patient group that may encounter frequent readmissions. However, the 30-and 90day rates for readmission following surgery for spine metastases have not been well described. Methods. The Nationwide Readmission Database years 2013 to 2015 was queried. Patients were grouped by no readmission (non-R), readmission within 30 days (30-R), and readmission within 31 to 90 days (90-R). Weighted multivariate analysis assessed impact of treatment approach and clinical factors associated with 30-and 90-day readmissions. Results. There were a total of 4423 patients with a diagnosis of spine metastases identified who underwent spine surgery, of which 1657 (37.5%) encountered either a 30-or 90-day unplanned readmission (

show abstract

“…Univariable/multivariable logistic/linear regressions were performed, controlling for age, BMI, tumor size, the presence of other organ metastasis, and preoperative/postoperative RT and chemotherapy. The multivariable model was constructed in accordance with prior knowledge of potential confounders in outcomes after spinal metastasis surgery and based on the discussion with senior authors 20,21. We tried to incorporate demographics (age, BMI), disease severity (tumor size, the presence of other organ metastasis), and postoperative treatment modalities (RT/chemotherapy).…”

Section: Methodsmentioning

confidence: 99%

Unplanned Readmission Is Associated With Decreased Overall Survival and Performance After Metastatic Spine Surgery

Chanbour

Chen

Gangavarapu

et al. 2023

Spine

View full text Add to dashboard Cite

Study Design. Retrospective case-control study. Objective. In a cohort of patients undergoing metastatic spine surgery, we sought to: (1) identify risk factors associated with unplanned readmission, and (2) determine the impact of an unplanned readmission on long-term outcomes. Summary of Background Data. Factors affecting readmission after metastatic spine surgery remain relatively unexplored. Materials and Methods. A single-center, retrospective, case-control study was undertaken of patients undergoing spine surgery for extradural metastatic disease between 02/2010 and 01/2021. The primary outcome was 3-month unplanned readmission. Preoperative, perioperative, and tumor-specific variables were collected. Multivariable Cox regression was performed, controlling for tumor size, other organ metastasis, and preoperative/postoperative radiotherapy/chemotherapy. Results. A total of 357 patients underwent surgery for spinal metastases with a mean follow-up of 538.7±648.6 days. Unplanned readmission within 3 months of surgery occurred in 64/357 (21.9%) patients, 37 (57.8%) were medical, 27 (42.2%) surgical, and 21 (77.7%) were related to their spine surgery. No significant differences were found regarding demographics and preoperative variables, except for insurance, where most readmitted patients had private insurance compared with nonreadmitted patients (P=0.021). No significant difference was found in preoperative radiotherapy/chemotherapy. Regarding perioperative exposure variables, readmitted patients had a higher rate of postoperative complications (68.8% vs. 24.2%, P<0.001) and worse postoperative Karnofsky Performance Score (P=0.021) and Modified McCormick Scale (P=0.015) at the time of first follow-up. On multivariate logistic regression, postoperative complications were associated with increased readmissions (odds ratio=1.38, 95% CI=1.25–1.52, P<0.001). Regarding the impact of unplanned readmission on long-term tumor control, unplanned readmission was associated with shorter time to local recurrence (log-rank; P=0.029) and reduced overall survival (OS) (log-rank; P<0.001). On multivariate Cox regression, other organ metastasis [hazard ratio (HR)=1.48, 95% CI=1.13–1.93, P=0.004] and 3-month readmission (HR=1.75, 95% CI=1.28–2.39, P<0.001) were associated with worsened OS, with no impact on LR. Postoperative chemotherapy was significantly associated with longer OS (HR=0.59, 95% CI=0.45–0.77, P<0.001). Conclusions. Postoperative complications were associated with unplanned readmission following metastatic spine surgery. Furthermore, 3-month unplanned readmission was associated with a shorter time to local recurrence and decreased OS. These results help surgeons understand the drivers of readmissions and the impact of readmissions on patient outcomes. Level of Evidence. 3.

show abstract

Predictors of 90-Day Readmission in Children Undergoing Spinal Cord Tumor Surgery: A Nationwide Readmissions Database Analysis

Cited by 9 publications

References 29 publications

Using machine learning to predict paediatric 30-day unplanned hospital readmissions: a case-control retrospective analysis of medical records, including written discharge documentation

Using machine learning to predict paediatric 30-day unplanned hospital readmissions: a case-control retrospective analysis of medical records, including written discharge documentation

Thirty- and 90-day Readmissions After Spinal Surgery for Spine Metastases

Unplanned Readmission Is Associated With Decreased Overall Survival and Performance After Metastatic Spine Surgery

Contact Info

Product

Resources

About