AI Article Synopsis
Article Abstract
Background: Rib fractures (RFx) remain the most prevalent injury in an elderly population that will increase from 40 to 81 million for the next 30 years. We sought to create an accurate cost-effective algorithm to triage elderly patients with RFx that accounted for both frailty and trauma burden.
Methods: Retrospective analysis evaluated 400 patients older than 55 years with RFx admitted to a level 1 trauma center from 2007 to 2012. Comorbidities included chronic obstructive pulmonary disease, congestive heart failure, tobacco use, obesity, and nutrition and functional status. Trauma burden included RFx, tube thoracostomy, pulmonary contusions, and spine and extremity fractures. Patients with Glasgow Coma Scale scores lower than 13, thoracoabdominal surgery, or deaths from other causes were excluded. Comparative analysis used bivariate and logistic regression. Variables contributing to intubation (INT) and pneumonia (PNA) were then used to create a scoring system to predict the need for intensive care unit (ICU) admission.
Results: Six variables increased the risk for INT or PNA: chronic obstructive pulmonary disease, low albumin, assisted status, tube thoracostomy, Injury Severity Score, and RFx (p < 0.05). These six variables and congestive heart failure (odds ratio, 1.9; p = 0.06) were used to create a predictive model with the following scores assigned respectively: 1.4, 1.1, 1, 0.9, 0.1(n), 0.1(n), and 0.6. A score lower than 3.7 had a sensitivity and specificity of 78.5% and 78.9%. The negative predictive value was 94.5% for INT or PNA, suggesting a low risk for ICU requirement. Ninety-two ICU admissions had a score lower than 3.7. Forty had no other indication for ICU admission aside from RFx. These patients had an average ICU length of stay of 1.7 days, resulting in an increased cost of $2,200 per patient.
Conclusion: A scoring system combining frailty and trauma burden may provide more accurate and cost-effective triage of the elderly trauma patient with RFx. Further prospective studies are required to verify our scoring system.
Level Of Evidence: Prognostic and epidemiologic study, level III.
Download full-text PDF |
Source |
|---|---|
| http://dx.doi.org/10.1097/TA.0000000000000619 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Enhancing Post-Surgical Wound Care in Anorectal Diseases: A Comparative Study of Advanced Convolutional Neural Network (CNN) Architectures for Image Classification and Analysis.
Ann Ital Chir
December 2024
Department of Colorectal Surgery, Hubei Provincial Hospital of Traditional Chinese Medicine Affiliated to Hubei University of Chinese Medicine, 430071 Wuhan, Hubei, China.
Aim: Anorectal diseases, often requiring surgical intervention and careful post-operative wound management, pose substantial challenges in healthcare. This study presents a novel application of artificial intelligence, specifically machine learning, aimed at improving the classification and analysis of post-surgical wound images. By doing so, it seeks to enhance patient outcomes through personalized and optimized wound care strategies.
View Article and Find Full Text PDFPrognostic Factors, Predictive Modeling, and Treatment Patterns in Breast Cancer Patients with Bone Metastasis Receiving First-Line Chemotherapy: A Population-Based Study.
Ann Ital Chir
December 2024
The Orthopedics Department, Affiliated Jinhua Hospital, Zhejiang University School of Medicine, 321000 Jinhua, Zhejiang, China.
Aim: The prognostic factors and a nomogram applicable to breast cancer (BC) patients with bone metastasis (BM) who received first-line chemotherapy have not been extensively studied. This study aimed to identify prognostic factors and construct a prognostic nomogram to predict overall survival (OS) in this population.
Methods: Data for BC patients with BM undergoing first-line chemotherapy were retrieved from the Surveillance, Epidemiology, and End Results (SEER) database from 2010 to 2016.
Free Energy-Based Refinement of DNA Force Field via Modification of Multiple Nonbonding Energy Terms.
J Chem Inf Model
December 2024
Department of Chemistry and Institute of Functional Materials, Pusan National University, Busan 46241, South Korea.
The amber-OL21 force field (ff) was developed to better describe noncanonical DNA, including Z-DNA. Despite its improvements for DNA simulations, this study found that OL21's scope of application was limited by embedded ff artifacts. In a benchmark set of seven DNA molecules, including two double-stranded DNAs transitioning between B- and Z-DNA and five single-stranded DNAs folding into mini-dumbbell or G-quadruplex structures, the free energy landscapes obtained using OL21 revealed several issues: Z-DNA was overly stabilized; misfolded states in mini-dumbbell DNAs were most stable; DNA GQ folding was consistently biased toward an antiparallel topology.
View Article and Find Full Text PDFMachine Learning Prediction of Physicochemical Properties in Lithium-Ion Battery Electrolytes With Active Learning Applied to Graph Neural Networks.
J Comput Chem
January 2025
Department of Chemistry, Birla Institute of Technology Mesra, Ranchi, India.
Accurate prediction of physicochemical properties, such as electronic energy, enthalpy, free energy, and average vibrational frequencies, is critical for optimizing lithium-ion battery (LIB) performance. Traditional methods like density functional theory (DFT) are computationally expensive and inefficient for large-scale screening. In this study, we apply active learning on top of graph neural networks (GNNs) to efficiently predict these properties.
View Article and Find Full Text PDFHeterogeneous blood pressure treatment effects on cognitive decline in type 2 diabetes: A machine learning analysis of a randomized clinical trial.
Diabetes Obes Metab
December 2024
Department of Endocrine and Metabolic Diseases, Shanghai Institute of Endocrine and Metabolic Diseases, Ruijin Hospital, Shanghai Jiaotong University School of Medicine, Shanghai, China.
Aim: We aimed to identify the characteristics of patients with diabetes who can derive cognitive benefits from intensive blood pressure (BP) treatment using machine learning methods.
Materials And Methods: Using data from the Action to Control Cardiovascular Risk in Diabetes Memory in Diabetes (ACCORD-MIND) study, 1349 patients with type 2 diabetes who underwent BP treatment (intensive treatment targeting a systolic BP <120 mmHg vs. standard treatment targeting <140 mmHg) were included in the machine learning analysis.
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!