Prediction of 30-day cardiac-related-emergency-readmissions using simple administrative hospital data

Effective hospital readmission prediction models using machine-learned features

BACKGROUND

Hospital readmissions are one of the costliest challenges facing healthcare systems, but conventional models fail to predict readmissions well. Many existing models use exclusively manually-engineered features, which are labor intensive and dataset-specific. Our objective was to develop and evaluate models to predict hospital readmissions using derived features that are automatically generated from longitudinal data using machine learning techniques.

METHODS

We studied patients discharged from acute care facilities in 2015 and 2016 in Alberta, Canada, excluding those who were hospitalized to give birth or for a psychiatric condition. We used population-level linked administrative hospital data from 2011 to 2017 to train prediction models using both manually derived features and features generated automatically from observational data. The target value of interest was 30-day all-cause hospital readmissions, with the success of prediction measured using the area under the curve (AUC) statistic.

RESULTS

Data from 428,669 patients (62% female, 38% male, 27% 65 years or older) were used for training and evaluating models: 24,974 (5.83%) were readmitted within 30 days of discharge for any reason. Patients were more likely to be readmitted if they utilized hospital care more, had more physician office visits, had more prescriptions, had a chronic condition, or were 65 years old or older. The LACE readmission prediction model had an AUC of 0.66 ± 0.0064 while the machine learning model's test set AUC was 0.83 ± 0.0045, based on learning a gradient boosting machine on a combination of machine-learned and manually-derived features.

CONCLUSION

Applying a machine learning model to the computer-generated and manual features improved prediction accuracy over the LACE model and a model that used only manually-derived features. Our model can be used to identify high-risk patients, for whom targeted interventions may potentially prevent readmissions.

A nomogram for predicting the readmission within 6 months after treatment in patients with acute coronary syndrome

Purpose

To explore predictors for readmission within 6 months of ACS patients, and to build a prediction model, and generate a nomogram.

Methods

The retrospective cohort study included 498 patients with ACS in the Second Medical Center of the Chinese People’s Liberation Army General Hospital between January 2016 and March 2019. Univariate and multivariate logistic regression with odds ratios (OR) and two-sided 95% confidence interval (CI) analysis were used to investigate predictors for readmission within 6 months. The cohort was randomly divided into training cohort to develop a prediction model, and the validation cohort to validate the model. The receiver operating characteristic curve (ROC) and the calibration curve was used to assess discriminative power and calibration.

Results

Eighty-three ACS patients were readmitted within six months, with a readmission rate of 16.67%. Predictors included ACS type, treatment, hypertension, SUA, length of stay, statins, and adverse events occurred during hospitalization were used to form a six-month readmission prediction model for readmission within 6 months in ACS patients. The area under the curve (AUC) of the model was 0.788 (95%CI: 0.735–0.878) and 0.775 (95%CI: 0.686–0.865) in the training cohort and the validation cohort, respectively. Calibration curves showed the good calibration of the prediction model. Decision-curve analyses and clinical impact curve also demonstrated that it was clinically valuable.

Conclusion

We used seven readily available predictors to develop a prediction model for readmission within six months after treatment in ACS patients, which could be used to identify high-risk patients for ACS readmission.

Supplementary Information

The online version contains supplementary material available at 10.1186/s12872-022-02873-6.

Predictive Modeling of Hospital Readmission: Challenges and Solutions

Hospital readmission prediction is a study to learn models from historical medical data to predict probability of a patient returning to hospital in a certain period, e.g. 30 or 90 days, after the discharge. The motivation is to help health providers deliver better treatment and post-discharge strategies, lower the hospital readmission rate, and eventually reduce the medical costs. Due to inherent complexity of diseases and healthcare ecosystems, modeling hospital readmission is facing many challenges. By now, a variety of methods have been developed, but existing literature fails to deliver a complete picture to answer some fundamental questions, such as what are the main challenges and solutions in modeling hospital readmission; what are typical features/models used for readmission prediction; how to achieve meaningful and transparent predictions for decision making; and what are possible conflicts when deploying predictive approaches for real-world usages. In this paper, we systematically review computational models for hospital readmission prediction, and propose a taxonomy of challenges featuring four main categories: (1) data variety and complexity; (2) data imbalance, locality and privacy; (3) model interpretability; and (4) model implementation. The review summarizes methods in each category, and highlights technical solutions proposed to address the challenges. In addition, a review of datasets and resources available for hospital readmission modeling also provides firsthand materials to support researchers and practitioners to design new approaches for effective and efficient hospital readmission prediction.

Predictive modeling for COVID-19 readmission risk using machine learning algorithms

Introduction

The COVID-19 pandemic overwhelmed healthcare systems with severe shortages in hospital resources such as ICU beds, specialized doctors, and respiratory ventilators. In this situation, reducing COVID-19 readmissions could potentially maintain hospital capacity. By employing machine learning (ML), we can predict the likelihood of COVID-19 readmission risk, which can assist in the optimal allocation of restricted resources to seriously ill patients.

Methods

In this retrospective single-center study, the data of 1225 COVID-19 patients discharged between January 9, 2020, and October 20, 2021 were analyzed. First, the most important predictors were selected using the horse herd optimization algorithms. Then, three classical ML algorithms, including decision tree, support vector machine, and k-nearest neighbors, and a hybrid algorithm, namely water wave optimization (WWO) as a precise metaheuristic evolutionary algorithm combined with a neural network were used to construct predictive models for COVID-19 readmission. Finally, the performance of prediction models was measured, and the best-performing one was identified.

Results

The ML algorithms were trained using 17 validated features. Among the four selected ML algorithms, the WWO had the best average performance in tenfold cross-validation (accuracy: 0.9705, precision: 0.9729, recall: 0.9869, specificity: 0.9259, F-measure: 0.9795).

Conclusions

Our findings show that the WWO algorithm predicts the risk of readmission of COVID-19 patients more accurately than other ML algorithms. The models developed herein can inform frontline clinicians and healthcare policymakers to manage and optimally allocate limited hospital resources to seriously ill COVID-19 patients.

Predicting hospital readmission risk in patients with COVID-19: A machine learning approach

Introduction

The Coronavirus 2019 (COVID-19) epidemic stunned the health systems with severe scarcities in hospital resources. In this critical situation, decreasing COVID-19 readmissions could potentially sustain hospital capacity. This study aimed to select the most affecting features of COVID-19 readmission and compare the capability of Machine Learning (ML) algorithms to predict COVID-19 readmission based on the selected features.

Material and methods

The data of 5791 hospitalized patients with COVID-19 were retrospectively recruited from a hospital registry system. The LASSO feature selection algorithm was used to select the most important features related to COVID-19 readmission. HistGradientBoosting classifier (HGB), Bagging classifier, Multi-Layered Perceptron (MLP), Support Vector Machine ((SVM) kernel = linear), SVM (kernel = RBF), and Extreme Gradient Boosting (XGBoost) classifiers were used for prediction. We evaluated the performance of ML algorithms with a 10-fold cross-validation method using six performance evaluation metrics.

Results

Out of the 42 features, 14 were identified as the most relevant predictors. The XGBoost classifier outperformed the other six ML models with an average accuracy of 91.7%, specificity of 91.3%, the sensitivity of 91.6%, F-measure of 91.8%, and AUC of 0.91%.

Conclusion

The experimental results prove that ML models can satisfactorily predict COVID-19 readmission. Besides considering the risk factors prioritized in this work, categorizing cases with a high risk of reinfection can make the patient triaging procedure and hospital resource utilization more effective.

Predictive modelling of hospital readmission: Evaluation of different preprocessing techniques on machine learning classifiers

Hospital readmission is a major cost for healthcare systems worldwide. If patients with a higher potential of readmission could be identified at the start, existing resources could be used more efficiently, and appropriate plans could be implemented to reduce the risk of readmission. Therefore, it is important to predict the right target patients. Medical data is usually noisy, incomplete, and inconsistent. Hence, before developing a prediction model, it is crucial to efficiently set up the predictive model so that improved predictive performance is achieved. The current study aims to analyse the impact of different preprocessing methods on the performance of different machine learning classifiers. The preprocessing applied by previous hospital readmission studies were compared, and the most common approaches highlighted such as missing value imputation, feature selection, data balancing, and feature scaling. The hyperparameters were selected using Bayesian optimisation. The different preprocessing pipelines were assessed using various performance metrics and computational costs. The results indicated that the preprocessing approaches helped improve the model’s prediction of hospital readmission.

Published models that predict hospital readmission: a critical appraisal

INTRODUCTION

The number of readmission risk prediction models available has increased rapidly, and these models are used extensively for health decision-making. Unfortunately, readmission models can be subject to flaws in their development and validation, as well as limitations in their clinical usefulness.

OBJECTIVE

To critically appraise readmission models in the published literature using Delphi-based recommendations for their development and validation.

METHODS

We used the modified Delphi process to create Critical Appraisal of Models that Predict Readmission (CAMPR), which lists expert recommendations focused on development and validation of readmission models. Guided by CAMPR, two researchers independently appraised published readmission models in two recent systematic reviews and concurrently extracted data to generate reference lists of eligibility criteria and risk factors.

RESULTS

We found that published models (n=81) followed 6.8 recommendations (45%) on average. Many models had weaknesses in their development, including failure to internally validate (12%), failure to account for readmission at other institutions (93%), failure to account for missing data (68%), failure to discuss data preprocessing (67%) and failure to state the model's eligibility criteria (33%).

CONCLUSIONS

The high prevalence of weaknesses in model development identified in the published literature is concerning, as these weaknesses are known to compromise predictive validity. CAMPR may support researchers, clinicians and administrators to identify and prevent future weaknesses in model development.

Development and Validation of a Nomogram to Predict the 180-Day Readmission Risk for Chronic Heart Failure: A Multicenter Prospective Study

Background: The existing prediction models lack the generalized applicability for chronic heart failure (CHF) readmission. We aimed to develop and validate a widely applicable nomogram for the prediction of 180-day readmission to the patients. Methods: We prospectively enrolled 2,980 consecutive patients with CHF from two hospitals. A nomogram was created to predict 180-day readmission based on the selected variables. The patients were divided into three datasets for development, internal validation, and external validation (mean age: 74.2 ± 14.1, 73.8 ± 14.2, and 71.0 ± 11.7 years, respectively; sex: 50.2, 48.8, and 55.2% male, respectively). At baseline, 102 variables were submitted to the least absolute shrinkage and selection operator (Lasso) regression algorithm for variable selection. The selected variables were processed by the multivariable Cox proportional hazards regression modeling combined with univariate analysis and stepwise regression. The model was evaluated by the concordance index (C-index) and calibration plot. Finally, the nomogram was provided to visualize the results. The improvement in the regression model was calculated by the net reclassification index (NRI) (with tenfold cross-validation and 200 bootstraps). Results: Among the selected 2,980 patients, 1,696 (56.9%) were readmitted within 180 days, and 1,502 (50.4%) were men. A nomogram was established by the results of Lasso regression, univariate analysis, stepwise regression and multivariate Cox regression, as well as variables with clinical significance. The values of the C-index were 0.75 [95% confidence interval (CI): 0.72-0.79], 0.75 [95% CI: 0.69-0.81], and 0.73 [95% CI: 0.64-0.83] for the development, internal validation, and external validation datasets, respectively. Calibration plots were provided for both the internal and external validation sets. Five variables including history of acute heart failure, emergency department visit, age, blood urea nitrogen level, and beta blocker usage were considered in the final prediction model. When adding variables involving hospital discharge way, alcohol taken and left bundle branch block, the calculated values of NRI demonstrated no significant improvements. Conclusions: A nomogram for the prediction of 180-day readmission of patients with CHF was developed and validated based on five variables. The proposed methodology can improve the accurate prediction of patient readmission and have the wide applications for CHF.

Composite Outcomes of Mortality and Readmission in Patients with Heart Failure: Retrospective Review of Administrative Datasets

Background

Controlling the quality of care through readmissions and mortality for patients with heart failure (HF) is a national priority for healthcare regulators in developed countries. In this longitudinal cohort study, using administrative data such as hospital discharge forms (HDFs), emergency departments (EDs) accesses, and vital statistics, we test new covariates for predicting mortality and readmissions of patients hospitalized for HF and discuss the use of combined outcome as an alternative.

Methods

Logistic models, with a stepwise selection method, were estimated on 70% of the sample and validated on the remaining 30% to evaluate 30-day mortality, 30-day readmissions, and the combined outcome. We followed an extraction method for any-cause mortality and unplanned readmission within 30 days after incident HF hospitalization. Data on patient admission and previous history were extracted by HDFs and ED dataset.

Results

Our principal findings demonstrate that the model’s discriminant ability is consistent with literature both for mortality (AUC=0.738, CI (0.729–0.748)) and readmissions (AUC=0.578, CI (0.562–0.594)). Additionally, the discriminant ability of the composite outcome model is satisfactory (AUC=0.675, CI (0.666–0.684)).

Conclusion

Hospitalization characteristics and patient history introduced in the logistic models do not improve their discriminant ability. The composite outcome prediction is led more by mortality than readmission, without improvements for the comprehension of the readmission phenomenon.

Multi-level models for heart failure patients' 30-day mortality and readmission rates: the relation between patient and hospital factors in administrative data

Background

This study aims at gathering evidence about the relation between 30-day mortality and 30-day unplanned readmission and patient and hospital factors. By definition, we refer to 30-day mortality and 30-day unplanned readmission as the number of deaths and non-programmed hospitalizations for any cause within 30 days after the incident heart failure (HF). In particular, the focus is on the role played by hospital-level factors.

Methods

A multi-level logistic model that combines patient- and hospital-level covariates has been developed to better disentangle the role played by the two groups of covariates. Later on, hospital outliers in term of better-than-expected/worst-than-expected performers have been identified by comparing expected cases vs. observed cases. Hospitals performance in terms of 30-day mortality and 30-day unplanned readmission rates have been visualized through the creation of funnel plots. Covariates have been selected coherently to past literature. Data comes from the hospital discharge forms for Heart Failure patients in the Lombardy Region (Northern Italy). Considering incident cases for HF in the timespan 2010–2012, 78,907 records for adult patients from 117 hospitals have been collected after quality checks.

Results

Our results show that 30-day mortality and 30-day unplanned readmissions are explained by hospital-level covariates, paving the way for the design and implementation of evidence-based improvement strategies. While the percentage of surgical DRG (OR = 1.001; CI (1.000–1.002)) and the hospital type of structure (Research hospitals vs. non-research public hospitals (OR = 0.62; CI (0.48–0.80)) and Non-research private hospitals vs. non-research hospitals OR = 0.75; CI (0.63–0.90)) are significant for mortality, the mean length of stay (OR = 0.96; CI (0.95–0.98)) is significant for unplanned readmission, showing that mortality and readmission rates might be improved through different strategies.

Conclusion

Our results confirm that hospital-level covariates do affect quality of care, and that 30-day mortality and 30-day unplanned readmission are affected by different managerial choices. This confirms that hospitals should be accountable for their “added value” to quality of care.

Predictive models for hospital readmission risk: A systematic review of methods

OBJECTIVES

Hospital readmission risk prediction facilitates the identification of patients potentially at high risk so that resources can be used more efficiently in terms of cost-benefit. In this context, several models for readmission risk prediction have been proposed in recent years. The goal of this review is to give an overview of prediction models for hospital readmission, describe the data analysis methods and algorithms used for building the models, and synthesize their results.

METHODS

Studies that reported the predictive performance of a model for hospital readmission risk were included. We defined the scope of the review and accordingly built a search query to select the candidate papers. This query string was used as input for the chosen search engines, namely PubMed and Google Scholar. For each study, we recorded the population, feature selection method, classification algorithm, sample size, readmission threshold, readmission rate and predictive performance of the model.

RESULTS

We identified 77 studies that met the inclusion criteria, out of 265 citations. In 68% of the studies (n = 52) logistic regression or other regression techniques were utilized as the main method. Ten (13%) studies used survival analysis for model construction, while 14 (18%) used machine learning techniques for classification, of which decision tree-based methods and SVM were the most utilized algorithms. Among these, only four studies reported the use of any class imbalance addressing technique, of which resampling is the most frequent (75%). The performance of the models varied significantly among studies, with Area Under the ROC Curve (AUC) values in the ranges between 0.54 and 0.92.

CONCLUSION

Logistic regression and survival analysis have been traditionally the most widely used techniques for model building. Nevertheless, machine learning techniques are becoming increasingly popular in recent years. Recent comparative studies suggest that machine learning techniques can improve prediction ability over traditional statistical approaches. Regardless, the lack of an appropriate benchmark dataset of hospital readmissions makes a comparison of models' performance across different studies difficult.

Claims data-driven modeling of hospital time-to-readmission risk with latent heterogeneity

Hospital readmission risk modeling is of great interest to both hospital administrators and health care policy makers, for reducing preventable readmission and advancing care service quality. To accommodate the needs of both stakeholders, a readmission risk model is preferable if it (i) exhibits superior prediction performance; (ii) identifies risk factors to help target the most at-risk individuals; and (iii) constructs composite metrics to evaluate multiple hospitals, hospital networks, and geographic regions. Existing work mainly addressed the first two features and it is challenging to address the third one because available medical data are fragmented across hospitals. To simultaneously address all three features, this paper proposes readmission risk models with incorporation of latent heterogeneity, and takes advantage of administrative claims data, which is less fragmented and involves larger patient cohorts. Different levels of latent heterogeneity are considered to quantify the effects of unobserved factors, provide composite measures for performance evaluation at various aggregate levels, and compensate less informative claims data. To demonstrate the prediction performances of the proposed models, a real case study is considered on a state-wide heart failure patient cohort. A systematic comparison study is then carried out to evaluate the performances of 49 risk models and their variants.

Patient and clinical characteristics that heighten risk for heart failure readmission

BACKGROUND

Within 30 days of hospital discharge, heart failure (HF) readmission rates nationally accumulate to more than 20%. Due to this high rate of unplanned re-hospitalization, predictive models are needed to identify patients who pose the highest readmission risk.

OBJECTIVE

To evaluate the diagnosis and timing and to identify patient and clinical characteristics associated with 30 day readmissions among HF patients.

METHODS

A retrospective analysis of electronic health records was conducted to study HF admissions during the period October 2008 to November 2014. Patients with a primary discharge diagnosis consistent with HF were included. Descriptive statistics were used to compare the readmitted and non-readmitted cohorts. Logistic regression was used to develop a predictive model to determine patient and clinical variables associated with 30 day readmission.

RESULTS

Characteristics of the study cohort (n = 2420) are: a mean age of 72, predominantly male (55%), white (55%), currently not employed (91%), and utilizing Medicare as a payer (68%). Overall, 42% were married. Over the study time period there were 394 (16.3%) 30 day readmissions after 2420 hospitalizations. The 3 most common reasons for readmission were HF (36.0%), renal disorders (8.4%), and other cardiac diseases (6.9%). Analysis showed that 11.9% of patients readmitted during days 0-3, 15.2% during days 4-7, 31.5% during days 8-15, and 41.4% during days 16-30. The final multivariate predictive model included 5 variables that were associated with an increased risk for 30-day readmission: employment status as retired or disabled, > 1 emergency department visit in the past 90 days, length of stay >5 days during index visit, and a BUN value > 45 mg/dL.

CONCLUSION

This study provides a deeper understanding of patient and clinical characteristics that are associated with readmission in HF. Evaluation of these characteristics will provide additional information to guide strategies meant to reduce HF readmission rates.

Roles of disease severity and post-discharge outpatient visits as predictors of hospital readmissions

Background

Risks prediction models of 30-day all-cause hospital readmissions are multi-factorial. Severity of illness (SOI) and risk of mortality (ROM) categorized by All Patient Refined Diagnosis Related Groups (APR-DRG) seem to predict hospital readmission but lack large sample validation. Effects of risk reduction interventions including providing post-discharge outpatient visits remain uncertain. We aim to determine the accuracy of using SOI and ROM to predict readmission and further investigate the role of outpatient visits in association with hospital readmission.

Methods

Hospital readmission data were reviewed retrospectively from September 2012 through June 2015. Patient demographics and clinical variables including insurance type, homeless status, substance abuse, psychiatric problems, length of stay, SOI, ROM, ICD-10 diagnoses and medications prescribed at discharge, and prescription ratio at discharge (number of medications prescribed divided by number of ICD-10 diagnoses) were analyzed using logistic regression. Relationships among SOI, type of hospital visits, time between hospital visits, and readmissions were also investigated.

Results

A total of 6011 readmissions occurred from 55,532 index admissions. The adjusted odds ratios of SOI and ROM predicting readmissions were 1.31 (SOI: 95 % CI 1.25–1.38) and 1.09 (ROM: 95 % CI 1.05–1.14) separately. Ninety percent (5381/6011) of patients were readmitted from the Emergency Department (ED) or Urgent Care Center (UCC). Average time interval from index discharge date to ED/UCC visit was 9 days in both the no readmission and readmission groups (p > 0.05). Similar hospital readmission rates were noted during the first 10 days from index discharge regardless of whether post-index discharge patient clinic visits occurred when time-to-event analysis was performed.

Conclusions

SOI and ROM significantly predict hospital readmission risk in general. Most readmissions occurred among patients presenting for ED/UCC visits after index discharge. Simply providing early post-discharge follow-up clinic visits does not seem to prevent hospital readmissions.

Utility of models to predict 28-day or 30-day unplanned hospital readmissions: an updated systematic review

OBJECTIVE

To update previous systematic review of predictive models for 28-day or 30-day unplanned hospital readmissions.

DESIGN

Systematic review.

SETTING/DATA SOURCE

CINAHL, Embase, MEDLINE from 2011 to 2015.

PARTICIPANTS

All studies of 28-day and 30-day readmission predictive model.

OUTCOME MEASURES

Characteristics of the included studies, performance of the identified predictive models and key predictive variables included in the models.

RESULTS

Of 7310 records, a total of 60 studies with 73 unique predictive models met the inclusion criteria. The utilisation outcome of the models included all-cause readmissions, cardiovascular disease including pneumonia, medical conditions, surgical conditions and mental health condition-related readmissions. Overall, a wide-range C-statistic was reported in 56/60 studies (0.21-0.88). 11 of 13 predictive models for medical condition-related readmissions were found to have consistent moderate discrimination ability (C-statistic ≥0.7). Only two models were designed for the potentially preventable/avoidable readmissions and had C-statistic >0.8. The variables 'comorbidities', 'length of stay' and 'previous admissions' were frequently cited across 73 models. The variables 'laboratory tests' and 'medication' had more weight in the models for cardiovascular disease and medical condition-related readmissions.

CONCLUSIONS

The predictive models which focused on general medical condition-related unplanned hospital readmissions reported moderate discriminative ability. Two models for potentially preventable/avoidable readmissions showed high discriminative ability. This updated systematic review, however, found inconsistent performance across the included unique 73 risk predictive models. It is critical to define clearly the utilisation outcomes and the type of accessible data source before the selection of the predictive model. Rigorous validation of the predictive models with moderate-to-high discriminative ability is essential, especially for the two models for the potentially preventable/avoidable readmissions. Given the limited available evidence, the development of a predictive model specifically for paediatric 28-day all-cause, unplanned hospital readmissions is a high priority.

Feasibility of 30-day hospital readmission prediction modeling based on health information exchange data

INTRODUCTION

Unplanned 30-day hospital readmission account for roughly $17 billion in annual Medicare spending. Many factors contribute to unplanned hospital readmissions and multiple models have been developed over the years to predict them. Most researchers have used insurance claims or administrative data to train and operationalize their Readmission Risk Prediction Models (RRPMs). Some RRPM developers have also used electronic health records data; however, using health informatics exchange data has been uncommon among such predictive models and can be beneficial in its ability to provide real-time alerts to providers at the point of care.

METHODS

We conducted a semi-systematic review of readmission predictive factors published prior to March 2013. Then, we extracted and merged all significant variables listed in those articles for RRPMs. Finally, we matched these variables with common HL7 messages transmitted by a sample of health information exchange organizations (HIO).

RESULTS

The semi-systematic review resulted in identification of 32 articles and 297 predictive variables. The mapping of these variables with common HL7 segments resulted in an 89.2% total coverage, with the DG1 (diagnosis) segment having the highest coverage of 39.4%. The PID (patient identification) and OBX (observation results) segments cover 13.9% and 9.1% of the variables. Evaluating the same coverage in three sample HIOs showed data incompleteness.

DISCUSSION

HIOs can utilize HL7 messages to develop unique RRPMs for their stakeholders; however, data completeness of exchanged messages should meet certain thresholds. If data quality standards are met by stakeholders, HIOs would be able to provide real-time RRPMs that not only predict intra-hospital readmissions but also inter-hospital cases.

CONCLUSION

A RRPM derived using HIO data exchanged through may prove to be a useful method to prevent unplanned hospital readmissions. In order for the RRPM derived from HIO data to be effective, hospitals must actively exchange clinical information through the HIO and develop actionable methods that integrate into the workflow of providers to ensure that patients at high-risk for readmission receive the care they need.

Predicting 30-day Hospital Readmission with Publicly Available Administrative Database. A Conditional Logistic Regression Modeling Approach

INTRODUCTION

This article is part of the Focus Theme of Methods of Information in Medicine on "Big Data and Analytics in Healthcare".

BACKGROUND

Hospital readmissions raise healthcare costs and cause significant distress to providers and patients. It is, therefore, of great interest to healthcare organizations to predict what patients are at risk to be readmitted to their hospitals. However, current logistic regression based risk prediction models have limited prediction power when applied to hospital administrative data. Meanwhile, although decision trees and random forests have been applied, they tend to be too complex to understand among the hospital practitioners.

OBJECTIVES

Explore the use of conditional logistic regression to increase the prediction accuracy.

METHODS

We analyzed an HCUP statewide inpatient discharge record dataset, which includes patient demographics, clinical and care utilization data from California. We extracted records of heart failure Medicare beneficiaries who had inpatient experience during an 11-month period. We corrected the data imbalance issue with under-sampling. In our study, we first applied standard logistic regression and decision tree to obtain influential variables and derive practically meaning decision rules. We then stratified the original data set accordingly and applied logistic regression on each data stratum. We further explored the effect of interacting variables in the logistic regression modeling. We conducted cross validation to assess the overall prediction performance of conditional logistic regression (CLR) and compared it with standard classification models.

RESULTS

The developed CLR models outperformed several standard classification models (e.g., straightforward logistic regression, stepwise logistic regression, random forest, support vector machine). For example, the best CLR model improved the classification accuracy by nearly 20% over the straightforward logistic regression model. Furthermore, the developed CLR models tend to achieve better sensitivity of more than 10% over the standard classification models, which can be translated to correct labeling of additional 400 - 500 readmissions for heart failure patients in the state of California over a year. Lastly, several key predictor identified from the HCUP data include the disposition location from discharge, the number of chronic conditions, and the number of acute procedures.

CONCLUSIONS

It would be beneficial to apply simple decision rules obtained from the decision tree in an ad-hoc manner to guide the cohort stratification. It could be potentially beneficial to explore the effect of pairwise interactions between influential predictors when building the logistic regression models for different data strata. Judicious use of the ad-hoc CLR models developed offers insights into future development of prediction models for hospital readmissions, which can lead to better intuition in identifying high-risk patients and developing effective post-discharge care strategies. Lastly, this paper is expected to raise the awareness of collecting data on additional markers and developing necessary database infrastructure for larger-scale exploratory studies on readmission risk prediction.

Transition Networks in a Cohort of Patients with Congestive Heart Failure: A Novel Application of Informatics Methods to Inform Care Coordination

BACKGROUND

Unnecessary hospital readmissions are one source of escalating costs that may be reduced through improved care coordination, but how best to design and evaluate coordination programs is poorly understood. Measuring patient flow between service visits could support decisions for coordinating care, particularly for conditions such as congestive heart failure (CHF) which have high morbidity, costs, and hospital readmission rates.

OBJECTIVES

To determine the feasibility of using network analysis to explore patterns of service delivery for patients with CHF in the context of readmissions.

METHODS

A retrospective cohort study used de-identified records for patients ≥18 years with an ICD-9 diagnosis code 428.0-428.9, and service visits between July 2011 and June 2012. Patients were stratified by admission outcome. Traditional and novel network analysis techniques were applied to characterize care patterns.

RESULTS

Patients transitioned between services in different order and frequency depending on admission status. Patient-to-service CoUsage networks were diffuse suggesting unstructured flow of patients with no obvious coordination hubs. In service-to-service Transition networks a specialty heart failure service was on the care path to the most other services for never admitted patients, evidence of how specialist care may prevent hospital admissions for some patients. For patients admitted once, transitions expanded for a clinic-based internal medicine service which clinical experts identified as a Patient Centered Medical Home implemented in the first month for which we obtained data.

CONCLUSIONS

We detected valid patterns consistent with a targeted care initiative, which experts could understand and explain, suggesting the method has utility for understanding coordination. The analysis revealed strong but complex patterns that could not be demonstrated using traditional linear methods alone. Network analysis supports measurement of real world health care service delivery, shows how transitions vary between services based on outcome, and with further development has potential to inform coordination strategies.

[Differential features of DRG 541 readmitting patients]

OBJECTIVE

Hospital readmission is considered an adverse outcome, and the hospital readmission ratio is an indicator of health care quality. Published studies show a wide variability and heterogeneity, with large groups of patients with different diagnoses and prognoses. The aim of the study was to analyse the differences between patients readmitted and those who were not, in patients grouped into the diagnosis related group (DRG) 541.

MATERIAL AND METHOD

A retrospective observational study was conducted on DRG 541 patients discharged in 2010. Readmission is defined as any admission into any hospital department, and for any reason at ≤30 days from discharge. An analysis was performed that included age, sex, day of discharge, month of discharge, number of diagnoses and drugs at discharge, respiratory depressant drugs, length of stay, requests for consultations/referrals, Charlson comorbidity index, feeding method, hospitalisations in the previous 6 months, albumin and haemoglobin levels and medical examinations within 30 days after discharge.

RESULTS

Of the 985 patients included in the study, 189 were readmitted. On multivariate analysis, significant variables were: Haemoglobin -0.6g/dl (95% confidence interval [95%CI] -0.9 to -0.3), gastrostomy feeding odds ratio (OR) 5.6 (95%CI: 1.5 to 21.6), hospitalisations in previous 6 months OR 1.9 (95%CI: 1.3 to 2.8), visits to emergency department OR 17.4 (95%CI: 11.3 to 26.8), medical checks after discharge OR 0.4 (95%CI: 0.2 to 0.8).

CONCLUSIONS

DRG 541 readmitting patients have some distinctive features that could allow early detection and prevent hospital readmission.

Is the readmission rate a valid quality indicator? A review of the evidence

INTRODUCTION

Hospital readmission rates are increasingly used for both quality improvement and cost control. However, the validity of readmission rates as a measure of quality of hospital care is not evident. We aimed to give an overview of the different methodological aspects in the definition and measurement of readmission rates that need to be considered when interpreting readmission rates as a reflection of quality of care.

METHODS

We conducted a systematic literature review, using the bibliographic databases Embase, Medline OvidSP, Web-of-Science, Cochrane central and PubMed for the period of January 2001 to May 2013.

RESULTS

The search resulted in 102 included papers. We found that definition of the context in which readmissions are used as a quality indicator is crucial. This context includes the patient group and the specific aspects of care of which the quality is aimed to be assessed. Methodological flaws like unreliable data and insufficient case-mix correction may confound the comparison of readmission rates between hospitals. Another problem occurs when the basic distinction between planned and unplanned readmissions cannot be made. Finally, the multi-faceted nature of quality of care and the correlation between readmissions and other outcomes limit the indicator's validity.

CONCLUSIONS

Although readmission rates are a promising quality indicator, several methodological concerns identified in this study need to be addressed, especially when the indicator is intended for accountability or pay for performance. We recommend investing resources in accurate data registration, improved indicator description, and bundling outcome measures to provide a more complete picture of hospital care.

Predicting unplanned readmission after myocardial infarction from routinely collected administrative hospital data

Objective Readmission rates are high following acute myocardial infarction (AMI), but risk stratification has proved difficult because known risk factors are only weakly predictive. In the present study, we applied hospital data to identify the risk of unplanned admission following AMI hospitalisations. Methods The study included 1660 consecutive AMI admissions. Predictive models were derived from 1107 randomly selected records and tested on the remaining 553 records. The electronic medical record (EMR) model was compared with a seven-factor predictive score known as the HOSPITAL score and a model derived from Elixhauser comorbidities. All models were evaluated for the ability to identify patients at high risk of 30-day ischaemic heart disease readmission and those at risk of all-cause readmission within 12 months following the initial AMI hospitalisation. Results The EMR model has higher discrimination than other models in predicting ischaemic heart disease readmissions (area under the curve (AUC) 0.78; 95% confidence interval (CI) 0.71–0.85 for 30-day readmission). The positive predictive value was significantly higher with the EMR model, which identifies cohorts that were up to threefold more likely to be readmitted. Factors associated with readmission included emergency department attendances, cardiac diagnoses and procedures, renal impairment and electrolyte disturbances. The EMR model also performed better than other models (AUC 0.72; 95% CI 0.66–0.78), and with greater positive predictive value, in identifying 12-month risk of all-cause readmission. Conclusions Routine hospital data can help identify patients at high risk of readmission following AMI. This could lead to decreased readmission rates by identifying patients suitable for targeted clinical interventions. What is known about the topic? Many clinical and demographic risk factors are known for hospital readmissions following acute myocardial infarction, including multivessel disease, high baseline heart rate, hypertension, diabetes, obesity, chronic obstructive pulmonary disease and psychiatric morbidity. However, combining these risk factors into indices for predicting readmission had limited success. A recent study reported a C-statistic of 0.73 for predicting 30-day readmissions. In a recent American study, a simple seven-factor score was shown to predict hospital readmissions among medical patients. What does this paper add? This paper presents a way to predict readmissions following myocardial infarction using routinely collected administrative data. The model performed better than the recently described HOSPITAL score and a model derived from Elixhauser comorbidities. Moreover, the model uses only data generally available in most hospitals. What are the implications for practitioners? Routine hospital data available at discharges can be used to tailor preventative care for AMI patients, to improve institutional performance and to decrease the cost burden associated with AMI.

Red blood cell distribution width is a predictor of readmission in cardiac patients

BACKGROUND

Three-quarters of rehospitalizations ($44 billion yearly estimated cost) may be avoidable. A screening tool for the detection of potential readmission may facilitate more efficient case management.

HYPOTHESIS

An elevated red blood cell distribution width (RDW) is an independent predictor of hospital readmission in patients with unstable angina (UA) or non-ST-elevation myocardial infarction (NSTEMI).

METHODS

The study is a retrospective observational cohort analysis of adults admitted in 2007 with UA or NSTEMI. Data were gathered by review of inpatient medical records. The rate of 30-day nonelective readmission and time to nonelective readmission were recorded until November 1, 2011, and compared by RDW group using the 95th percentile (16.3%) as a cutoff.

RESULTS

The median follow-up time of the 503 subjects (average age, 65 ± 13 years; 56% male) was 3.8 years (interquartile range: 0.3-4.3 years). Those readmitted within 30 days were older, had more comorbidities and higher RDW and creatinine levels, and were more likely to have had an intervention. At 3.8 years of follow-up, subjects with high RDW (>16.3%) were more likely to be readmitted compared to those with normal RDW (≤16.3%) (72.28% vs 59.95%, P = 0.003). In multivariable analyses, high RDW was a statistically significant predictor of readmission in general (hazard ratio: 1.35 (95% confidence interval [CI]:1.02-1.79), P = 0.033) but not of 30-day rehospitalization (odds ratio: 1.34 (95% CI: 0.78-2.31), P = 0.292). Its area under the receiver operating characteristic curve was 0.54 (sensitivity 23% and specificity 85%).

CONCLUSIONS

An elevated RDW is an independent predictor of hospital readmission in patients with UA or NSTEMI.