Predictors of 30-Day Unplanned Readmission After Carotid Artery Stenting Using Artificial Intelligence.
Ontology highlight
ABSTRACT: Introduction
This study aimed to describe the rates and causes of unplanned readmissions within 30 days following carotid artery stenting (CAS) and to use artificial intelligence machine learning analysis for creating a prediction model for short-term readmissions. The prediction of unplanned readmissions after index CAS remains challenging. There is a need to leverage deep machine learning algorithms in order to develop robust prediction tools for early readmissions.Methods
Patients undergoing inpatient CAS during the year 2017 in the US Nationwide Readmission Database (NRD) were evaluated for the rates, predictors, and costs of unplanned 30-day readmission. Logistic regression, support vector machine (SVM), deep neural network (DNN), random forest, and decision tree models were evaluated to generate a robust prediction model.Results
We identified 16,745 patients who underwent CAS, of whom 7.4% were readmitted within 30 days. Depression [p < 0.001, OR 1.461 (95% CI 1.231-1.735)], heart failure [p < 0.001, OR 1.619 (95% CI 1.363-1.922)], cancer [p < 0.001, OR 1.631 (95% CI 1.286-2.068)], in-hospital bleeding [p = 0.039, OR 1.641 (95% CI 1.026-2.626)], and coagulation disorders [p = 0.007, OR 1.412 (95% CI 1.100-1.813)] were the strongest predictors of readmission. The artificial intelligence machine learning DNN prediction model has a C-statistic value of 0.79 (validation 0.73) in predicting the patients who might have all-cause unplanned readmission within 30 days of the index CAS discharge.Conclusions
Machine learning derived models may effectively identify high-risk patients for intervention strategies that may reduce unplanned readmissions post carotid artery stenting.Central illustration
Figure 2: ROC and AUPRC analysis of DNN prediction model with other classification models on 30-day readmission data for CAS subjects.
SUBMITTER: Amritphale A
PROVIDER: S-EPMC8190015 | biostudies-literature |
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:Unplanned hospital readmissions following surgical interventions are associated with adverse events and contribute to increasing health care costs. Despite numerous studies defining risk factors following lower extremity bypass surgery, evidence regarding readmission after endovascular interventions is limited. This study aimed to identify predictors of 30-day unplanned readmission following infrainguinal endovascular interventions.We identified all patients undergoing an infrainguinal endovascular intervention in the targeted vascular module of the American College of Surgeons National Surgical Quality Improvement Program between 2012 and 2014. Perioperative outcomes were stratified by symptom status (chronic limb-threatening ischemia [CLI] vs claudication). Patients who died during index admission and those who remained in the hospital after 30 days were excluded. Indications for unplanned readmission related to the index procedure were evaluated. Multivariable logistic regression was used to identify preoperative and in-hospital (during index admission) risk factors of 30-day unplanned readmission.There were 4449 patients who underwent infrainguinal endovascular intervention, of whom 2802 (63%) had CLI (66% tissue loss) and 1647 (37%) had claudication. The unplanned readmission rates for CLI and claudication patients were 16% (n = 447) and 6.5% (n = 107), respectively. Mortality after index admission was higher for readmitted patients compared with those not readmitted (CLI, 3.4% vs 0.7% [P < .001]; claudication, 2.8% vs 0.1% [P < .01]). Approximately 50% of all unplanned readmissions were related to the index procedure. Among CLI patients, the most common indication for readmission related to the index procedure was wound or infection related (42%), whereas patients with claudication were mainly readmitted for recurrent symptoms of peripheral vascular disease (28%). In patients with CLI, predictors of unplanned readmission included diabetes (odds ratio, 1.3; 95% confidence interval, 1.01-1.6), congestive heart failure (1.6; 1.1-2.5), renal insufficiency (1.7; 1.3-2.2), preoperative dialysis (1.4; 1.02-1.9), tibial angioplasty/stenting (1.3; 1.04-1.6), in-hospital bleeding (1.9; 1.04-3.5), in-hospital unplanned return to the operating room (1.9; 1.1-3.5), and discharge other than to home (1.5; 1.1-2.0). Risk factors for those with claudication were dependent functional status (3.5; 1.4-8.7), smoking (1.6; 1.02-2.5), diabetes (1.5; 1.01-2.3), preoperative dialysis (3.6; 1.6-8.3), procedure time exceeding 120 minutes (1.8; 1.1-2.7), in-hospital bleeding (2.9; 1.2-7.4), and in-hospital unplanned return to the operating room (3.4; 1.2-9.4).Unplanned readmission after endovascular treatment is relatively common, especially in patients with CLI, and is associated with substantially increased mortality. Awareness of these risk factors will help providers identify patients at high risk who may benefit from early surveillance, and prophylactic measures focused on decreasing postoperative complications may reduce the rate of readmission.
| S-EPMC5293151 | biostudies-literature
Project description:BackgroundExisting readmission reduction solutions tend to focus on complementing inpatient care with enhanced care transition and postdischarge interventions. These solutions are initiated near or after discharge, when clinicians' impact on inpatient care is ending. Preventive intervention during hospitalization is an underexplored area that holds potential for reducing readmission risk. However, it is challenging to predict readmission risk at the early stage of hospitalization because few data are available.ObjectiveThe objective of this study was to build an early prediction model of unplanned 30-day hospital readmission using a large and diverse sample. We were also interested in identifying novel readmission risk factors and protective factors.MethodsWe extracted the medical records of 96,550 patients in 205 participating Cerner client hospitals across four US census regions in 2016 from the Health Facts database. The model was built with index admission data that can become available within 24 hours and data from previous encounters up to 1 year before the index admission. The candidate models were evaluated for performance, timeliness, and generalizability. Multivariate logistic regression analysis was used to identify readmission risk factors and protective factors.ResultsWe developed six candidate readmission models with different machine learning algorithms. The best performing model of extreme gradient boosting (XGBoost) achieved an area under the receiver operating characteristic curve of 0.753 on the development data set and 0.742 on the validation data set. By multivariate logistic regression analysis, we identified 14 risk factors and 2 protective factors of readmission that have never been reported.ConclusionsThe performance of our model is better than that of the most widely used models in US health care settings. This model can help clinicians identify readmission risk at the early stage of hospitalization so that they can pay extra attention during the care process of high-risk patients. The 14 novel risk factors and 2 novel protective factors can aid understanding of the factors associated with readmission.
| S-EPMC8077543 | biostudies-literature
Project description:OBJECTIVE:To evaluate the association between novel pre- and post-operative biomarker levels and 30-day unplanned readmission or mortality after paediatric congenital heart surgery. METHODS:Children aged 18 years or younger undergoing congenital heart surgery (n = 162) at Johns Hopkins Hospital from 2010 to 2014 were enrolled in the prospective cohort. Collected novel pre- and post-operative biomarkers include soluble suppression of tumorgenicity 2, galectin-3, N-terminal prohormone of brain natriuretic peptide, and glial fibrillary acidic protein. A model based on clinical variables from the Society of Thoracic Surgery database was developed and evaluated against two augmented models. RESULTS:Unplanned readmission or mortality within 30 days of cardiac surgery occurred among 21 (13%) children. The clinical model augmented with pre-operative biomarkers demonstrated a statistically significant improvement over the clinical model alone with a receiver-operating characteristics curve of 0.754 (95% confidence interval: 0.65-0.86) compared to 0.617 (95% confidence interval: 0.47-0.76; p-value: 0.012). The clinical model augmented with pre- and post-operative biomarkers demonstrated a significant improvement over the clinical model alone, with a receiver-operating characteristics curve of 0.802 (95% confidence interval: 0.72-0.89; p-value: 0.003). CONCLUSIONS:Novel biomarkers add significant predictive value when assessing the likelihood of unplanned readmission or mortality after paediatric congenital heart surgery. Further exploration of the utility of these novel biomarkers during the pre- or post-operative period to identify early risk of mortality or readmission will aid in determining the clinical utility and application of these biomarkers into routine risk assessment.
| S-EPMC6711799 | biostudies-literature
Project description:PURPOSE:Analyze associations between patients' characteristics and treatment factors with 30-day unplanned readmissions in hospitalized otolaryngology patients in the German Diagnosis Related Group (D-DRG) system. METHODS:A retrospective cohort study was performed on 15.271 otolaryngology admissions of 12.859 patients in 2015 in Thuringia, Germany. The medical records of the 1173 cases (7.6%) with readmission within 30-days were analyzed in detail. RESULTS:The 30-day readmission was planned in 747 cases (4.9%) and was unplanned in 422 cases (2.8%). The median interval between primary and next inpatient treatment was 11 days. The principal diagnosis was the same as during the primary index treatment in 72% of the cases. The most frequent reasons for readmission were: Need for non-surgical therapy (31.2%), need for further surgery (26.3%), post-surgical complaints (16.9%), and recurrence of primary complaints (10.7%). The multivariate analysis revealed that discharge due to patient's request against medical advice was a strong independent factor with high risk for unplanned readmission (Odds Ratio [OR] = 9.62]; confidence interval [CI] = 2.69-34.48). Surgery at index admission (OR = 3.33; CI = 1.86-5.96) was the second important independent risk factor for unplanned readmission. Unplanned readmission had more frequently a non-surgical treatment at readmission than a surgical treatment (OR = 3.92; CI = 2.24-6.84) and needed more frequently further diagnostics (OR = 2.34; CI = 1.34-4.11). The following index International Classification of Diseases (ICD) categories had the highest risk for unplanned readmission: Injury, poisoning and certain other consequences of external causes, ICD: S00-T98 (OR = 66.67; CI = 15.87-333.33), symptoms, signs, abnormal findings, ill-defined causes, not otherwise classified, ICD: R00-R99 (OR = 62.5; CI = 11.76-333.33), blood forming organ diseases, ICD: D50-D90 (OR = 21.276; CI = 3.508-125), and eye/ ear diseases, ICD: H00-H95 (OR = 12.66; CI = 4.29-37.03). CONCLUSIONS:The causes of unplanned 30-day readmission in German otolaryngology inpatients are multifactorial. Specific patient and treatment characteristics were identified to be targeted with health care interventions to decrease unplanned readmissions.
| S-EPMC6797198 | biostudies-literature
Project description:BackgroundUnplanned hospital readmissions are a major source of morbidity among dialysis patients, in whom the risk of hospital readmission is exceptionally high. The contribution of dialysis facility staffing to hospital readmission has been largely overlooked.MethodsUsing annual data of dialysis patients from the United States Renal Data System from 2010 to 2013, we assessed dialysis facilities with a significantly worse (SW) and facilities with a nonsignificant (NS) standardized readmission ratio (SRR). SRR estimates were risk adjusted for patient factors, past year comorbidities, and index hospitalization characteristics. Facility staffing variables were compared between 2 exposure groups: facilities with SW and NS SRRs. Four measures of staffing, including patient-to-staffing ratio, were compared between SW and matched NS facilities.ResultsAbout 136,000-148,000 dialysis patients with 269,000-319,000 index hospital discharges were used to identify facilities with SW and facilities with NS SRR annually. Approximately 3-4% of facilities were identified as having SW SRR among > 5,000 facilities annually. The percent of nurses-to-total staff was significantly lower in 2010 for SW facilities than in matched NS facilities (42.5 vs. 45.6%, p = 0.012), but this disparity was attenuated by 2013 (44.8 vs. 44.7%, p = 0.949). There was a higher patient-to-nurse ratio for SW facilities than for NS facilities (mean 16.4 vs. 15.2, p = 0.038) in 2010 as well, and the disparity was reduced by 2013. The trends were similar for patient-to-total staff and patient-to-registered nurse, but not statistically significant.ConclusionsThis study found that dialysis facilities with SW 30-day readmission rates had lower proportions of nurses-to-total staff and higher patient-to-nurse ratios, but this disparity improved in recent years. Additional research is warranted focusing on how evidence-based staffing at dialysis facilities can contribute to reduction of hospital readmission, and this knowledge is needed to inform clinical practice guidelines and policy decisions regarding optimal dialysis patient staffing.
| S-EPMC6587206 | biostudies-literature
Project description:Avoidable hospital readmissions not only contribute to the high costs of healthcare in the US, but also have an impact on the quality of care for patients. Large scale adoption of Electronic Health Records (EHR) has created the opportunity to proactively identify patients with high risk of hospital readmission, and apply effective interventions to mitigate that risk. To that end, in the past, numerous machine-learning models have been employed to predict the risk of 30-day hospital readmission. However, the need for an accurate and real-time predictive model, suitable for hospital setting applications still exists. Here, using data from more than 300,000 hospital stays in California from Sutter Health's EHR system, we built and tested an artificial neural network (NN) model based on Google's TensorFlow library. Through comparison with other traditional and non-traditional models, we demonstrated that neural networks are great candidates to capture the complexity and interdependency of various data fields in EHRs. LACE, the current industry standard, showed a precision (PPV) of 0.20 in identifying high-risk patients in our database. In contrast, our NN model yielded a PPV of 0.24, which is a 20% improvement over LACE. Additionally, we discussed the predictive power of Social Determinants of Health (SDoH) data, and presented a simple cost analysis to assist hospitalists in implementing helpful and cost-effective post-discharge interventions.
| S-EPMC5510858 | biostudies-other
Project description:ObjectivesAnemia, either chronic or newly developed in the hospital as a result of underlying disease and/or phlebotomy, is seen commonly among general medical inpatients, and its impact on the quality and efficiency of care is unknown.MethodsThis study investigated the relation among hemoglobin level, length of stay, and 30-day unplanned readmission rates in a cohort of 314 general medical inpatients 18 years old and older admitted to a teaching hospital during a period of 4 months in a large urban academic medical center, using retrospective chart review of the electronic health record.ResultsAnemia was common among this cohort of general medical inpatients (44.6%), and there was a statistically significant decrease in hemoglobin levels during their hospitalization. Anemic patients, as compared with nonanemic patients, had significantly longer mean and median length of stay. More important, the admission hemoglobin level and its change during hospitalization were significant predictors of increased length of stay. For every 1-U increase in admission hemoglobin level, the median length of stay was reduced by 0.5 days. For every 1-U increase in the level of hemoglobin change, the median length of stay was extended by 1.5 days. Likewise, the discharge hemoglobin level predicted the rate of 30-day unplanned readmission. For every 1-U decrease in discharge hemoglobin level, the readmission rate increased by nearly 4%. These relations remained after adjusting for common demographic and clinical variables, including age, sex, nutritional status, and number of comorbidities.ConclusionsAnemia is common among general medical inpatients and adversely affects their length of stay and 30-day unplanned readmission rate.
| S-EPMC7047646 | biostudies-literature
Project description:Study designSystematic review.ObjectivesSurgical procedures for lumbar degenerative diseases (LDD), which have emerged in the 21-century, are commonly practiced worldwide. Regarding financial burdens and health costs, readmissions within 30days following surgery are inconvenient. We performed a systematic review to integrate real-world evidence and report the current risk factors associated with 30-day readmission following surgery for LDD.MethodsThe Cochrane Library, Embase, and Medline electronic databases were searched from inception to April 2022 to identify relevant studies reporting risk factors for 30-day readmission following surgery for LDD.ResultsThirty-six studies were included in the review. Potential risk factors were identified in the included studies that reported multivariate analysis results, including age, race, obesity, higher American Society of Anesthesiologists score, anemia, bleeding disorder, chronic pulmonary disease, heart failure, dependent status, depression, diabetes, frailty, malnutrition, chronic steroid use, surgeries with anterior approach, multilevel spinal surgeries, perioperative transfusion, presence of postoperative complications, prolonged operative time, and prolonged length of stay.ConclusionsThere are several potential perioperative risk factors associated with unplanned readmission following surgery for LDD. Preoperatively identifying patients that are at increased risk of readmission is critical for achieving the best possible outcomes.
| S-EPMC9972270 | biostudies-literature
Project description:Readmission following COPD exacerbation is a common and challenging clinical problem. New approaches to predicting readmissions are required to help mitigate risk and develop novel interventions. We conducted a prospective cohort study in 82 COPD patients admitted due to an exacerbation of COPD. Lung function measures [spirometry, forced oscillation technique (FOT) indices and peak inspiratory flow rate (PIFR)], inflammatory biomarkers and patient-reported outcomes including previous exacerbation history, breathlessness, quality of life and frailty were measured at admission and discharge. We prospectively followed patients for 30 and 90 days to identify predictors for readmission. The readmission rate within 30 days was 38%, and 56% within 90 days. Previous exacerbations, higher COPD Assessment Test score at discharge, frailty, reduced PIFR and increased length of stay were significantly associated with 30-day readmission. PIFR at discharge and frailty had the highest predictive ability for 30-day readmission using area under receiver operating characteristic curves (AUC 0.86, 95% CI 0.78-0.95, p < 0.001 and AUC 0.81, 95% CI 0.71-0.90, p < 0.001, respectively). Ninety-day readmissions were significantly associated with previous exacerbations and hospitalisations, higher CAT score at discharge, frailty, depression, lower PIFR and greater expiratory flow limitation (EFL) in the supine position. The best predictive variable in multivariable analysis for both 30- and 90-day readmission was PIFR at discharge. PIFR, CAT score, frailty, and EFL were found to be associated with 30- and 90-day readmission following COPD exacerbation. These findings help identify those at highest risk and to optimise care prior to discharge.
| S-EPMC8504869 | biostudies-literature
Project description:Introduction:Constant technological progress in the field of carotid stenting translates into improved short- and long-term results of endovascular treatment. The introduction of a new generation, self-expanding, open-cell stent has provided a new treatment option in endovascular management of carotid stenosis. Aim:To evaluate 30-day and 1-year clinical outcomes of non-consecutive patients with high risk of carotid endarterectomy, who underwent 5F cylinder-tapered MER™ open-cell carotid stent implantation. Material and methods:It was a single-arm, prospective study conducted in four experienced catheterisation centres. The use of embolic protection devices was mandatory. The primary endpoint was stroke in 30-day follow-up. The secondary endpoints were 30-day and 1-year cumulative incidence of death, stroke and myocardial infarction, 1-year target vessel revascularisation, procedural success (residual stenosis ? 30%), restenosis rate (%DS ? 50%), and Serious Adverse Device Effect (SADE) rate in 1-year follow-up. Results:In total 100 patients were recruited for the study, with the majority being males (n = 61). The mean age was 68.3 ±8.2 years, and most of the patients were asymptomatic (n = 56). In 55 (55%) patients direct stenting was performed, with the use of proximal protection devices in 19 (19%) patients. Mean internal carotid artery/common carotid artery stenosis before and after stent implantation was 81.98 ±9.15% and 12.52 ±8.70%, respectively (p < 0.001). Procedural success was achieved in all cases. One ischaemic stroke was observed at 30 days (1%, primary endpoint). At 1-year follow-up two myocardial infarctions and three deaths occurred with no additional stroke. Conclusions:The OCEANUS study indicated the safety and efficacy of the MER™ stent during 30-day and 1-year follow-up in both symptomatic and asymptomatic patients. The majority of patients were event-free. However, larger cohort studies are needed to evaluate MER™ stents in detail.
| S-EPMC7189137 | biostudies-literature