Improving Orthopedic Patient Outcomes: A Model to Predict 30-Day and 90-Day Readmission Rates Following Total Joint Arthroplasty

Greiwe, R. Michael; Spanyer, Jonathon; Nolan, Joseph R.; Rodgers, Renée N.; Hill, Misti A.; Harm, Richard G.

doi:10.1016/j.arth.2019.05.051

Cited by 13 publications

(10 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Our findings are consistent with prior evidence. Indeed, a retrospective study of 1663 patients undergoing TJA reported that being a man was associated with a higher likelihood of readmissions than being a woman [26], while similar studies have demonstrated that predictors of readmissions after TJA include advanced age, preexisting cardiovascular comorbidities including cardiac dysrhythmias, BMI, and gender [13,17]. To our knowledge, there are no studies about the association between cancer-related diagnoses and readmissions after TJA; however, the association between a history of oncologic diagnoses and lower readmission rates that we found may reflect a "monitoring effect" whereby those receiving oncologic care may receive medical care more regularly or communicate with medical providers more frequently, leading to more surveillance and care, as well as lower readmissions.…”

Section: Most Important Features For Predicting Unplanned Readmissionsmentioning

confidence: 99%

“…However, predicting hospital readmissions is challenging, given the many factors influencing readmissions, analytic complexities including discordance between administrative coding and clinician-informed diagnosis, and heterogeneity in reporting across different institutional and national databases [19]. Furthermore, prior research on predicting TJA readmissions has not uniformly evaluated predictive performance for randomized or independent holdout samples, meaning these studies are limited to evaluating in-sample associations, which may limit the generalizability of their findings and result in inflated model performance [4,13,15,18]. Many predictive models also use factors that are known only after discharge, information that would not be available in a prospective, preoperative context [20,25].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Machine Learning on Medicare Claims Poorly Predicts the Individual Risk of 30-Day Unplanned Readmission After Total Joint Arthroplasty, Yet Uncovers Interesting Population-level Associations With Annual Procedure Volumes

Kunze

Padgett

et al. 2023

Clin Orthop Relat Res

View full text Add to dashboard Cite

Background Unplanned hospital readmissions after total joint arthroplasty (TJA) represent potentially serious adverse events and remain a critical measure of hospital quality. Predicting the risk of readmission after TJA may provide patients and clinicians with valuable information for preoperative decision-making. Questions/purposes (1) Can nonlinear machine-learning models integrating preoperatively available patient, surgeon, hospital, and county-level information predict 30day unplanned hospital readmissions in a large cohort of nationwide Medicare beneficiaries undergoing TJA? (2) Which predictors are the most important in predicting 30day unplanned hospital readmissions? (3) What specific information regarding population-level associations can we obtain from interpreting partial dependency plots (plots describing, given our modeling choice, the potentially Each author certifies that there are no funding or commercial associations (consultancies, stock ownership, equity interest, patent/licensing arrangements, etc.) that might pose a conflict of interest in connection with the submitted article related to the author or any immediate family members. All ICMJE Conflict of Interest Forms for authors and Clinical Orthopaedics and Related Research® editors and board members are on file with the publication and can be viewed on request. Clinical Orthopaedics and Related Research® neither advocates nor endorses the use of any treatment, drug, or device. Readers are encouraged to always seek additional information, including FDA approval status, of any drug or device before clinical use.

show abstract

Section: Most Important Features For Predicting Unplanned Readmissionsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Machine Learning on Medicare Claims Poorly Predicts the Individual Risk of 30-Day Unplanned Readmission After Total Joint Arthroplasty, Yet Uncovers Interesting Population-level Associations With Annual Procedure Volumes

Kunze

Padgett

et al. 2023

Clin Orthop Relat Res

View full text Add to dashboard Cite

show abstract

“…Despite legislative support for quality improvements, more must be done. During our study period, readmission rates in the US did not show significant improvement [26,28]. This underscores the concept that legislation alone is insufficient to significantly impact readmissions [1].…”

Section: Discussionmentioning

confidence: 48%

“…As this model was developed to predict 30-day hospital readmissions, it may not be useful for predicting mortality or morbidity outcomes. However, these outcomes are vital, and future studies should consider similar models to predict other outcomes of interest [28]. The interactions among variables and their total contributions to the models should also be considered.…”

Section: Discussionmentioning

confidence: 99%

Which Factors Predict 30-Day Readmission After Total Hip and Knee Replacement Surgery?

Williams¹,

Pujalte²,

Li³

et al. 2022

Cureus

View full text Add to dashboard Cite

BackgroundThe Centers for Medicare and Medicaid Services enacted the Hospital Readmissions Reduction Program to impose penalties for diagnoses with high readmission rates. Despite several elective orthopedic procedures being included in this program, readmission rates have not declined, and associated costs have reached critical levels for total knee and total hip arthroplasty. Readmissions drastically impact patient outcomes. There are many known contributors to patient readmission rates, including infection, pain, and hematomas. However, evidence is inconclusive regarding other aspects, such as demographics, insurance, and discharge disposition. The purpose of this manuscript is to 1) measure hospital readmission rates for total knee and total hip arthroplasty, 2) evaluate the causes of readmissions, and 3) provide a predictive profile of risk factors associated with hospital readmissions. MethodsPatients who underwent total knee or total hip arthroplasty were identified through a retrospective database review. An electronic chart review extracted data concerning patient demographics, comorbidities, surgical information, 30-day outcomes, and reasons for 30-day readmissions. Continuous and categorical variables were assessed with the Wilcoxon rank-sum test and the Chi-square test, respectively. ResultsA total of 6,065 patients were included, with 269 (4.4%) having at least one surgery-related 30-day readmission. No differences in readmission were noted with age, sex, or ethnicity; however, differences were found in weight and body mass index. Statistically significant comorbidities were heart failure, chronic obstructive pulmonary disease, dialysis, and alcohol use or abuse. ConclusionOur research indicated that surgery type, length of stay, and heart failure most significantly impacted 30day readmission rates. By assessing readmission rates, we can take steps to optimize care for non-elective surgeries that will improve patient outcomes and cost-effectiveness.

show abstract

“…An orthopedic patient who suffered from musculoskeletal system problems so needs assistance from the orthopedic health team. One of these team members are an orthopedic nurse (Greiwe et al, 2019). Care bundle term refers to apply of creating chains of evidence-based medical management and nursing care to deal with incidental risks.…”

Section: Introductionmentioning

confidence: 99%

Effect of Application Bundle Skin Care on Nurses’ Performance and Orthopedic Patients’ Skin Outcome: Quasi-Experimental Study

Elasrag¹,

Elsabagh²,

Salih³

et al. 2020

ijrps

View full text Add to dashboard Cite

Treating severe pressure ulcers may consume considerable manpower, time, and medical resources. Pressure ulcers can be avoided and effectively treated when nurses conduct proper skin assessment and care for wounds appropriately. Research hypothesis: There was positive impact of bundle skincare training on nurses' performance and orthopedic patients' skin outcome. quasi-experimental design was utilized at orthopedic units at Shebin El Koum teaching Hospital and Menofia University Hospital. Tools used for data collection were Pre-designed Questionnaire contained on nurses' characteristics, Attitude Rating Scale and Nurses' knowledge, also used Observational Checklist and BRADEN scale. The subject composed of 45 nurses and 90 orthopedic patients. Mean score of total knowledge pre-intervention was 6.83±3.1, while at the post was 9.95±2.1. Also, a mean score of total practice pre-intervention was 7.11±2.6, while at the post was 11.83±3.4, and, a mean score of total attitude pre-intervention was 5.02±2.8, while at the post was 7.82±1.9. Mean score of BRADEN scale at pre-intervention was 12.81±3.04, while at the post was 13.45±1.99. Application bundle skin care had a positive effect on nurses' knowledge, practice and attitude related skincare for orthopedic patients. So, there was an improvement at BRADEN score of patients post-application bundle skincare. Age, gender and previous hospitalization, BMI, and length had positive predictor effect on pressure sore risk. Skincare bundle for orthopedic patients is acceptable and has the potential to improve nursing care.

show abstract

Improving Orthopedic Patient Outcomes: A Model to Predict 30-Day and 90-Day Readmission Rates Following Total Joint Arthroplasty

Cited by 13 publications

References 3 publications

Machine Learning on Medicare Claims Poorly Predicts the Individual Risk of 30-Day Unplanned Readmission After Total Joint Arthroplasty, Yet Uncovers Interesting Population-level Associations With Annual Procedure Volumes

Machine Learning on Medicare Claims Poorly Predicts the Individual Risk of 30-Day Unplanned Readmission After Total Joint Arthroplasty, Yet Uncovers Interesting Population-level Associations With Annual Procedure Volumes

Which Factors Predict 30-Day Readmission After Total Hip and Knee Replacement Surgery?

Effect of Application Bundle Skin Care on Nurses’ Performance and Orthopedic Patients’ Skin Outcome: Quasi-Experimental Study

Contact Info

Product

Resources

About