Background: Anticipating the need for non-home discharge (NHD) enables improved patient counseling and expedites placement, potentially reducing length of stay and hospital readmission. The objective of this study was to create a simple, preoperative, clinical prediction tool for NHD using The Society of Thoracic Surgeons General Thoracic Surgery Database (STS GTSD).
Methods: The STS GTSD was queried for patients who underwent elective anatomic lung cancer resection between 2009 and 2019. Exclusion criteria included age <18 years, percentage predicted diffusion capacity of the lung for carbon monoxide <20% or >150%, N3 or M1 disease, incomplete datasets, and mortality. The primary outcome was defined as discharge to an extended care, transitional care, rehabilitation center, or another hospital. Multivariable logistic regression was used to select risk factors and a nomogram for predicting risk of NHD was developed. The approach was cross-validated in 100 replications of a training set consisting of randomly selected two-thirds of the cohort and a validation set of remaining patients.
Results: A total of 35 948 patients from the STS GTSD met inclusion criteria. Final model variables used to derive the nomogram for NHD risk prediction included age (P < .001), percentage predicted diffusion capacity of the lung for carbon monoxide (P < .001), open surgery (P < .001), cerebrovascular history (P < .001), and Zubrod score (P < .001). The receiver operating characteristic curve, using sensitivities and specificities of the model, yielded area under the curve of 0.74. In 100 replicated cross-validations, out-of-sample area under the curve ranged from 0.72-0.76.
Conclusions: Using readily available preoperative variables, our nomogram prognosticates the risk of NHD after anatomic lung resection with good discriminatory ability. Such risk stratification can enable improved patient counseling and facilitate better planning of patients' postoperative needs.
Download full-text PDF |
Source |
|---|---|
| http://dx.doi.org/10.1016/j.athoracsur.2022.07.020 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Predicting Discharge Destination from Inpatient Rehabilitation Using Machine Learning.
Am J Phys Med Rehabil
December 2024
Department of Physical Medicine and Rehabilitation, Medical College of Wisconsin, 8701 W Watertown Plank Rd, Milwaukee, WI, 53226.
Predicting discharge destination for patients at inpatient rehabilitation facilities is important as it facilitates transitions of care and can improve healthcare resource utilization. This study aims to build on previous studies investigating discharges from inpatient rehabilitation by employing machine learning models to predict discharge disposition to home versus non-home and explore related factors. Fifteen machine learning models were tested.
View Article and Find Full Text PDFInpatient total thyroidectomy costs and outcomes vary regionally: A nationwide study.
Laryngoscope Investig Otolaryngol
February 2025
Objectives: While it is known that surgical costs continue to rise in the United States, there is little information about the specific underlying factors for this variation in many common procedures. This study investigates the influence of geographic location and hospital demographics on hospital cost and postoperative outcomes in adult patients undergoing total thyroidectomy (TT).
Methods: The National Inpatient Sample was queried for patients who underwent primary TT between 2016 and 2017.
Care Fragmentation Following Bariatric Operations: A National Analysis.
Am Surg
January 2025
Department of Surgery, University of California, Los Angeles, CA, USA.
Background: Although existing work has evaluated outcomes associated with care fragmentation (CF), these adverse consequences may be accentuated in patients undergoing bariatric operations. This retrospective study examined the association of CF with clinical and financial outcomes among patients receiving bariatric surgery.
Methods: All adult (≥18 years) records for bariatric operations were tabulated from the 2016-2021 Nationwide Readmissions Database.
The Adelaide Score: prospective implementation of an artificial intelligence system to improve hospital and cost efficiency.
ANZ J Surg
January 2025
Lyell McEwin Hospital, Adelaide, South Australia, Australia.
Background: The Adelaide Score is an artificial intelligence system that integrates objective vital signs and laboratory tests to predict likelihood of hospital discharge.
Methods: A prospective implementation trial was conducted at the Lyell McEwin Hospital in South Australia. The Adelaide Score was added to existing human, artificial intelligence, and other technological infrastructure for the first 28 days of April 2024 (intervention), and outcomes were compared using parametric, non-parametric and health economic analyses, to those in the first 28 days of April 2023 (control).
The economic burden of diabetes in spinal fusion surgery: a systematic review and meta-analysis.
Eur Spine J
January 2025
Departments of Neurological and Orthopedic Surgery, Thomas Jefferson University, Philadelphia, Pennsylvania, USA.
Purpose: This study aimed at comparing the costs of spinal fusion surgery between patients with and without diabetes.
Methods: Following PRISMA guidelines, a systematic search of four databases was conducted. A meta-analysis was performed on comparative studies examining diabetic versus non-diabetic adults undergoing cervical/lumbar fusion in terms of cost.
Want AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!