Evaluating the predictive strength of the LACE index in identifying patients at high risk of hospital readmission following an inpatient episode: a retrospective cohort study

Impact of Social Risk Screening on Discharge Care Processes and Postdischarge Outcomes: A Pragmatic Mixed-Methods Clinical Trial During the COVID-19 Pandemic

BACKGROUND

Social risk screening during inpatient care is required in new CMS regulations, yet its impact on inpatient care and patient outcomes is unknown.

OBJECTIVES

To evaluate whether implementing a social risk screening protocol improves discharge processes, patient-reported outcomes, and 30-day service use.

RESEARCH DESIGN

Pragmatic mixed-methods clinical trial.

SUBJECTS

Overall, 4130 patient discharges (2383 preimplementation and 1747 postimplementation) from general medicine and surgical services at a 528-bed academic medical center in the Intermountain United States and 15 attending physicians.

MEASURES

Documented family interaction, late discharge, patient-reported readiness for hospital discharge and postdischarge coping difficulties, readmission and emergency department visits within 30 days postdischarge, and coded interviews with inpatient physicians.

RESULTS

A multivariable segmented regression model indicated a 19% decrease per month in odds of family interaction following intervention implementation (OR=0.81, 95% CI=0.76-0.86, P<0.001), and an additional model found a 32% decrease in odds of being discharged after 2 pm (OR=0.68, 95% CI=0.53-0.87, P=0.003). There were no postimplementation changes in patient-reported discharge readiness, postdischarge coping difficulties, or 30-day hospital readmissions, or ED visits. Physicians expressed concerns about the appropriateness, acceptability, and feasibility of the structured social risk assessment.

CONCLUSIONS

Conducted in the immediate post-COVID timeframe, reduction in family interaction, earlier discharge, and provider concerns with structured social risk assessments likely contributed to the lack of intervention impact on patient outcomes. To be effective, social risk screening will require patient/family and care team codesign its structure and processes, and allocation of resources to assist in addressing identified social risk needs.

Assessing racial bias in healthcare predictive models: Practical lessons from an empirical evaluation of 30-day hospital readmission models

OBJECTIVE

Despite increased availability of methodologies to identify algorithmic bias, the operationalization of bias evaluation for healthcare predictive models is still limited. Therefore, this study proposes a process for bias evaluation through an empirical assessment of common hospital readmission models. The process includes selecting bias measures, interpretation, determining disparity impact and potential mitigations.

METHODS

This retrospective analysis evaluated racial bias of four common models predicting 30-day unplanned readmission (i.e., LACE Index, HOSPITAL Score, and the CMS readmission measure applied as is and retrained). The models were assessed using 2.4 million adult inpatient discharges in Maryland from 2016 to 2019. Fairness metrics that are model-agnostic, easy to compute, and interpretable were implemented and apprised to select the most appropriate bias measures. The impact of changing model's risk thresholds on these measures was further assessed to guide the selection of optimal thresholds to control and mitigate bias.

RESULTS

Four bias measures were selected for the predictive task: zero-one-loss difference, false negative rate (FNR) parity, false positive rate (FPR) parity, and generalized entropy index. Based on these measures, the HOSPITAL score and the retrained CMS measure demonstrated the lowest racial bias. White patients showed a higher FNR while Black patients resulted in a higher FPR and zero-one-loss. As the models' risk threshold changed, trade-offs between models' fairness and overall performance were observed, and the assessment showed all models' default thresholds were reasonable for balancing accuracy and bias.

CONCLUSIONS

This study proposes an Applied Framework to Assess Fairness of Predictive Models (AFAFPM) and demonstrates the process using 30-day hospital readmission model as the example. It suggests the feasibility of applying algorithmic bias assessment to determine optimized risk thresholds so that predictive models can be used more equitably and accurately. It is evident that a combination of qualitative and quantitative methods and a multidisciplinary team are necessary to identify, understand and respond to algorithm bias in real-world healthcare settings. Users should also apply multiple bias measures to ensure a more comprehensive, tailored, and balanced view. The results of bias measures, however, must be interpreted with caution and consider the larger operational, clinical, and policy context.

Synergistic effects of social determinants of health and race-ethnicity on 30-day all-cause readmission disparities: a retrospective cohort study

OBJECTIVE

The objective of this study is to assess the effects of social determinants of health (SDOH) and race-ethnicity on readmission and to investigate the potential for geospatial clustering of patients with a greater burden of SDOH that could lead to a higher risk of readmission.

DESIGN

A retrospective study of inpatients at five hospitals within Henry Ford Health (HFH) in Detroit, Michigan from November 2015 to December 2018 was conducted.

SETTING

This study used an adult inpatient registry created based on HFH electronic health record data as the data source. A subset of the data elements in the registry was collected for data analyses that included readmission index, race-ethnicity, six SDOH variables and demographics and clinical-related variables.

PARTICIPANTS

The cohort was composed of 248 810 admission patient encounters with 156 353 unique adult patients between the study time period. Encounters were excluded if they did not qualify as an index admission for all payors based on the Centers for Medicare and Medicaid Service definition.

MAIN OUTCOME MEASURE

The primary outcome was 30-day all-cause readmission. This binary index was identified based on HFH internal data supplemented by external validated readmission data from the Michigan Health Information Network.

RESULTS

Race-ethnicity and all SDOH were significantly associated with readmission. The effect of depression on readmission was dependent on race-ethnicity, with Hispanic patients having the strongest effect in comparison to either African Americans or non-Hispanic whites. Spatial analysis identified ZIP codes in the City of Detroit, Michigan, as over-represented for individuals with multiple SDOH.

CONCLUSIONS

There is a complex relationship between SDOH and race-ethnicity that must be taken into consideration when providing healthcare services. Insights from this study, which pinpoint the most vulnerable patients, could be leveraged to further improve existing models to predict risk of 30-day readmission for individuals in future work.

Causes for 30-day readmissions and accuracy of the LACE index in regional Victoria, Australia

BACKGROUND

Clinicians and funders continue to search for ways to reduce costs without sacrificing quality of care. Ongoing research should focus on innovative care models that identify patients at high-risk for hospitalisation and thereby reduce healthcare costs.

AIMS AND OBJECTIVES

This study examined readmission rates, comorbidity profiles and the performance of the LACEi (Length of stay, Acuity of admission, Charlson Comorbidity Index, ED admissions in the previous 6 months index) to predict the risk of 30-day readmissions in a regional population. Furthermore, we tested a novel clinician-orientated classification for the causes of 30-day readmissions.

DESIGN

Using a nested case-control design, data were extracted from administrative health records using 30-day readmission status as the outcome. We defined cases as discharges within 30 days before readmission and controls without a discharge within 30 days before admission between 1 July 2020 and 30 June 2022.

SETTING

The study was conducted at South West Healthcare in Victoria, Australia.

PARTICIPANTS

All adult medical patients were discharged alive from the facility. We excluded planned readmissions, surgical and obstetric admissions, dialysis, transfers to alternative facilities and discharges against medical advice.

MAIN OUTCOME MEASURES

Thirty-day readmission rate, comorbidity profile for all admissions, LACEi for all admissions, the performance of the LACEi in our setting and the causes leading to readmission using a clinician-orientated classification tool.

RESULTS

Comorbidity burden, male sex and age > 65 years were associated with increased readmission risk but not length of stay. The LACEi demonstrated modest predictive ability to identify high-risk patients for readmissions (area under the receiver operating characteristic curve = 0.59). Additional variables were needed to increase accuracy. The novel classification identified 42% of readmissions as potentially avoidable.

CONCLUSION

Our study identified comorbidity burden, male sex and age ≥ 65 years as critical indicators for readmission risk. Although the LACEi showed moderate predictive ability, additional variables were needed for increased accuracy. Over 40% of readmissions were potentially avoidable, and nearly two thirds occurred within 14 days of discharge from the hospital.

Interpretable (not just posthoc-explainable) medical claims modeling for discharge placement to reduce preventable all-cause readmissions or death

We developed an inherently interpretable multilevel Bayesian framework for representing variation in regression coefficients that mimics the piecewise linearity of ReLU-activated deep neural networks. We used the framework to formulate a survival model for using medical claims to predict hospital readmission and death that focuses on discharge placement, adjusting for confounding in estimating causal local average treatment effects. We trained the model on a 5% sample of Medicare beneficiaries from 2008 and 2011, based on their 2009-2011 inpatient episodes (approximately 1.2 million), and then tested the model on 2012 episodes (approximately 400 thousand). The model scored an out-of-sample AUROC of approximately 0.75 on predicting all-cause readmissions-defined using official Centers for Medicare and Medicaid Services (CMS) methodology-or death within 30-days of discharge, being competitive against XGBoost and a Bayesian deep neural network, demonstrating that one need-not sacrifice interpretability for accuracy. Crucially, as a regression model, it provides what blackboxes cannot-its exact gold-standard global interpretation, explicitly defining how the model performs its internal "reasoning" for mapping the input data features to predictions. In doing so, we identify relative risk factors and quantify the effect of discharge placement. We also show that the posthoc explainer SHAP provides explanations that are inconsistent with the ground truth model reasoning that our model readily admits.

Predicting readmission for heart failure patients by echocardiographic assessment of elevated left atrial pressure

BACKGROUND

Pathophysiologically, an elevated left ventricular (LV) filling pressure is the major reason for heart failure (HF) readmission. The 2016 American Society of Echocardiography (ASE)/European Association of Cardiovascular Imaging (EACVI) guidelines provide a simplified algorithm for the echocardiographic assessment of LV filling pressure; however, this algorithm is yet to be sufficiently validated.

MATERIALS AND METHODS

We retrospectively studied 139 consecutive patients with acute decompensated HF. High estimated left atrial pressure (eLAP) was defined according to the 2016 ASE/EACVI guidelines. Univariate and multivariate logistic regression analyses were performed to identify significant risk factors for HF readmission within one year of discharge.

RESULTS

Across the study cohort, 68 patients (49%) did not have a high eLAP, 32 (23%) had an indeterminate eLAP, and 39 (28%) had a high eLAP. The number of HF readmission events within one year in the without high eLAP, indeterminate, and high eLAP groups were 4 (7.5%), 5 (18.5%), and 10 (33.3%), respectively. The HF readmission rate was significantly higher in patients with high eLAP than in those without high eLAP. Multivariate analysis revealed high eLAP (odds ratio, 5.924; 95% confidence interval, 1.664-21.087; P = 0.006) as a significant risk factor for HF readmission within one year. Furthermore, the exploratory analysis of the two-year outcomes revealed a similar finding: patients with high eLAP had a significantly higher rate of readmission for HF.

CONCLUSIONS

The present study demonstrated that echocardiographic assessment of elevated LAP based on the 2016 ASE/EACVI guidelines is clinically valid for predicting readmission in patients with HF.

Heart Failure Emergency Readmission Prediction Using Stacking Machine Learning Model

Heart failure is a devastating disease that has high mortality rates and a negative impact on quality of life. Heart failure patients often experience emergency readmission after an initial episode, often due to inadequate management. A timely diagnosis and treatment of underlying issues can significantly reduce the risk of emergency readmissions. The purpose of this project was to predict emergency readmissions of discharged heart failure patients using classical machine learning (ML) models based on Electronic Health Record (EHR) data. The dataset used for this study consisted of 166 clinical biomarkers from 2008 patient records. Three feature selection techniques were studied along with 13 classical ML models using five-fold cross-validation. A stacking ML model was trained using the predictions of the three best-performing models for final classification. The stacking ML model provided an accuracy, precision, recall, specificity, F1-score, and area under the curve (AUC) of 89.41%, 90.10%, 89.41%, 87.83%, 89.28%, and 0.881, respectively. This indicates the effectiveness of the proposed model in predicting emergency readmissions. The healthcare providers can intervene pro-actively to reduce emergency hospital readmission risk and improve patient outcomes and decrease healthcare costs using the proposed model.

Factors Affecting the Effectiveness of Discharge Planning Implementation: A Case-Control Cohort Study

BACKGROUND

In many hospitals, a discharge planning team works with the medical team to provide case management to ensure high-quality patient care and improve continuity of care from the hospital to the community. However, a large-scale database analysis of the effectiveness of overall discharge planning efforts is lacking.

PURPOSE

This study was designed to investigate the clinical factors that impact the efficacy of discharge planning in terms of hospital length of stay, readmission rate, and survival status.

METHODS

A retrospective study was conducted based on patient medical records and the discharge plans applied to patients hospitalized in a regional medical center between 2017 and 2018. The medical information system database and the care service management information system maintained by the Ministry of Health and Welfare were used to collect data and explore patients' medical care and follow-up status.

RESULTS

Clinical factors such as activities of daily living ≤ 60, having indwelling catheters, having poor control of chronic diseases, and insufficient caregiver capacity were found to be associated with longer hospitalization stays. In addition, men and those with indwelling catheters were found to have a higher risk of readmission within 30 days of discharge. Moreover, significantly higher mortality was found after discharge in men, those ≥ 75 years old, those with activities of daily living ≤ 60, those with indwelling catheters, those with pressure ulcers or unclean wounds, those with financial problems, those with caregivers with insufficient capacity, and those readmitted 14-30 days after discharge.

CONCLUSIONS

The findings of this study indicate that implementing case management for discharge planning does not substantially reduce the length of hospital stay nor does it affect patients' readmission status or prognosis after discharge. However, age, underlying comorbidities, and specific disease factors decrease the efficacy of discharge planning. Therefore, active discharge planning interventions should be provided to ensure transitional care for high-risk patients.

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.

The Predictive Validity of Functional Outcome Measures With Discharge Destination for Hospitalized Medical Patients

Objective

To investigate the predictive validity for discharge to home or facility of 4 functional mobility outcome measures.

Design

Retrospective, observational study.

Setting

Urban, academic hospital in the United States.

Participants

Adult patients (N=3999) admitted to medical units between June 1, 2019, and February 29, 2020, with 2 or more recorded scores on each of 4 tools: Activity Measure for Post-Acute Care (AM-PAC) 6-Clicks Basic Mobility and Daily Activity, Henry Ford Mobility Level, and The Johns Hopkins Highest Level of Mobility.

Interventions

Not applicable.

Main Outcome Measures

Mobility scores and discharge destination.

Results

For the 3999 subjects, 51.4% went home at discharge and had higher mean scores on each measure than those not returning home. Both early (I) and later (II) time point for each measure had positive predictability for discharge home. AM-PAC 6-Clicks had the highest confidence intervals for early and later recorded scores. The c-statistic value for Basic Mobility I (cut point=16) was 0.74 and for II (cut point=18) was, 0.79. The value for Daily Activity I (cut point=18) was 0.75 and for Daily Activity II (cut point=18) was 0.80). The Johns Hopkins Highest Level of Mobility and Henry Ford Mobility Level measures were less discriminative at initial score (c-statistic 0.704 and 0.665, respectively) and final score (c-statistic 0.74 and 0.75, respectively).

Conclusions

Functional outcome measures have good predictive validity for discharge destination. The AM-PAC Basic mobility score appears to have a slightly higher confidence interval than the other tools in this study design.

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.

A bias evaluation checklist for predictive models and its pilot application for 30-day hospital readmission models

OBJECTIVE

Health care providers increasingly rely upon predictive algorithms when making important treatment decisions, however, evidence indicates that these tools can lead to inequitable outcomes across racial and socio-economic groups. In this study, we introduce a bias evaluation checklist that allows model developers and health care providers a means to systematically appraise a model's potential to introduce bias.

MATERIALS AND METHODS

Our methods include developing a bias evaluation checklist, a scoping literature review to identify 30-day hospital readmission prediction models, and assessing the selected models using the checklist.

RESULTS

We selected 4 models for evaluation: LACE, HOSPITAL, Johns Hopkins ACG, and HATRIX. Our assessment identified critical ways in which these algorithms can perpetuate health care inequalities. We found that LACE and HOSPITAL have the greatest potential for introducing bias, Johns Hopkins ACG has the most areas of uncertainty, and HATRIX has the fewest causes for concern.

DISCUSSION

Our approach gives model developers and health care providers a practical and systematic method for evaluating bias in predictive models. Traditional bias identification methods do not elucidate sources of bias and are thus insufficient for mitigation efforts. With our checklist, bias can be addressed and eliminated before a model is fully developed or deployed.

CONCLUSION

The potential for algorithms to perpetuate biased outcomes is not isolated to readmission prediction models; rather, we believe our results have implications for predictive models across health care. We offer a systematic method for evaluating potential bias with sufficient flexibility to be utilized across models and applications.

LACE Index to Predict the High Risk of 30-Day Readmission in Patients With Acute Myocardial Infarction at a University Affiliated Hospital

Background

The LACE index (length of stay, acuity of admission, comorbidity index, and emergency room visit in the past 6 months) has been used to predict the risk of 30-day readmission after hospital discharge in both medical and surgical patients. This study aimed to utilize the LACE index to predict the risk of 30-day readmission in hospitalized patients with acute myocardial infraction (AMI).

Methods

This was a retrospective study. Data were extracted from the hospital's electronic medical records of patients admitted with AMI between 2015 and 2019. LACE index was built on admission patient demographic data, and clinical and laboratory findings during the index of admission. The multivariate logistic regression was performed to determine the association and the risk prediction ability of the LACE index, and 30-day readmission were analyzed by receiver operator characteristic curves with C-statistic.

Results

Of the 3,607 patients included in the study, 5.7% (205) were readmitted within 30 days of discharge from the hospital. The adjusted odds ratio based on logistic regression of all baseline variables showed a statistically significant association with the LACE score and revealed an increased risk of readmission within 30 days of hospital discharge. However, patients with high LACE scores (≥10) had a significantly higher rate of emergency revisits within 30 days from the index discharge than those with low LACE scores. Despite this, analysis of the receiver operating characteristic curve indicated that the LACE index had favorable discrimination ability C-statistic 0.78 (95%CI; 0.75–0.81). The Hosmer–Lemeshow goodness- of-fit test P value was p = 0.920, indicating that the model was well-calibrated to predict risk of the 30-day readmission.

Conclusion

The LACE index demonstrated the good discrimination power to predict the risk of 30-day readmissions for hospitalized patients with AMI. These results can help clinicians to predict the risk of 30-day readmission at the early stage of hospitalization and pay attention during the care of high-risk patients. Future work is to be focused on additional factors to predict the risk of 30-day readmissions; they should be considered to improve the model performance of the LACE index with other acute conditions by using administrative data.

Ability of the LACE Index to Predict 30-Day Readmissions in Patients with Acute Myocardial Infarction

Aims: This study aimed to utilize the existing LACE index (length of stay, acuity of admission, comorbidity index and emergency room visit in the past six months) to predict the risk of 30-day readmission and to find the associated factors in patients with AMI. Methods: This was a retrospective study and LACE index scores were calculated for patients admitted with AMI between 2015 and 2019. Data were utilized from the hospital’s electronic medical record. Multivariate logistic regression was performed to find the association between covariates and 30-day readmission. The risk prediction ability of the LACE index for 30-day readmission was analyzed by receiver operating characteristic curves with the C statistic. Results: A total of 205 (5.7%) patients were readmitted within 30 days. The odds ratio of older age group (OR = 1.78, 95% CI: 1.54–2.05), admission via emergency ward (OR = 1.45; 95% CI: 1.42–1.54) and LACE score ≥10 (OR = 2.71; 95% CI: 1.03–4.37) were highly associated with 30-day readmissions and statistically significant. The receiver operating characteristic curve C statistic of the LACE index for AMI patients was 0.78 (95% CI: 0.75–0.80) and showed favorable discrimination in the prediction of 30-day readmission. Conclusion: The LACE index showed a good discrimination to predict the risk of 30-day readmission for hospitalized patients with AMI. Further study would be recommended to focus on additional factors that can be used to predict the risk of 30-day readmission; this should be considered to improve the model performance of the LACE index for other acute conditions by using the national-based administrative data.

A novel interpretable machine learning system to generate clinical risk scores: An application for predicting early mortality or unplanned readmission in a retrospective cohort study

Risk scores are widely used for clinical decision making and commonly generated from logistic regression models. Machine-learning-based methods may work well for identifying important predictors to create parsimonious scores, but such 'black box' variable selection limits interpretability, and variable importance evaluated from a single model can be biased. We propose a robust and interpretable variable selection approach using the recently developed Shapley variable importance cloud (ShapleyVIC) that accounts for variability in variable importance across models. Our approach evaluates and visualizes overall variable contributions for in-depth inference and transparent variable selection, and filters out non-significant contributors to simplify model building steps. We derive an ensemble variable ranking from variable contributions across models, which is easily integrated with an automated and modularized risk score generator, AutoScore, for convenient implementation. In a study of early death or unplanned readmission after hospital discharge, ShapleyVIC selected 6 variables from 41 candidates to create a well-performing risk score, which had similar performance to a 16-variable model from machine-learning-based ranking. Our work contributes to the recent emphasis on interpretability of prediction models for high-stakes decision making, providing a disciplined solution to detailed assessment of variable importance and transparent development of parsimonious clinical risk scores.

REadmission PREvention in SepSis: Development and Validation of a Prediction Model

ABSTRACT

Hospital 30-day readmissions remain a major quality and cost indicator. Traditional readmission risk scores, such as LACE (length of stay, acuity of admission, Charlson comorbidity index, and emergency department visits), may be suboptimal in special patient populations, such as those with sepsis. As sepsis survivorship improves, there is a need to determine which variables might be associated with a decrease in 30-day readmission. We completed a retrospective analysis reviewing patients with sepsis who had unplanned 30-day readmissions. Multivariate regression analysis was performed for the REadmission PREvention in SepSis (REPRESS) model, which evaluated age, length of stay, Charlson disease count, Richmond Agitation-Sedation Scale score, discharge to a skilled nursing facility, and mobility for predictive significance in hospital readmission. Our REPRESS model performed better when compared with LACE for predicting readmission risk in a sepsis population.

LACE Index to Predict the High Risk of 30-Day Readmission: A Systematic Review and Meta-Analysis

The LACE index accounts for: Length of stay (L), Acuity of admission (A), Comorbidities (C), and recent Emergency department use (E). This study aimed to explore the LACE index to predict the high risk of 30-day readmission in patients with diverse disease conditions by an updated systematic review. A systematic review carried out by electronic databases from 2011−2021. The studies included a LACE index score for 30-day of readmission and patients with all types of diseases and were published in the English language. The meta-analysis was performed by using a random-effects model with a 95% confidence interval. Of 3300 records, a total of 16 studies met the inclusion criteria. The country of publication was primarily the USA (n = 7) and study designs were retrospective and perspective cohorts. The average mean age was 64 years. The C-statistics was 0.55 to 0.81. The pooled random effects of relative risk readmission were overall (RR, 0.20; 95% CI, 0.12−0.34) and it was favorable. The subgroup analysis of the opted disease-based relative risk of readmissions of all causes, cardiovascular and pulmonary diseases, and neurological diseases were consistent and statistically significant at p < 0.001 level. Current evidence of this review suggested that incorporating a high-risk LACE index showed favorable to risk prediction and could be applied to predict 30-day readmission with chronic conditions. Future study would be planned to predict the high risk of 30-day readmission in acute clinical care for utility, and applicability of promising LACE index in South Korean hospitals.

HOSPITAL Score and LACE Index to Predict Mortality in Multimorbid Older Patients

Background

Estimating life expectancy of older adults informs whether to pursue future investigation and therapy. Several models to predict mortality have been developed but often require data not immediately available during routine clinical care. The HOSPITAL score and the LACE index were previously validated to predict 30-day readmissions but may also help to assess mortality risk. We assessed their performance to predict 1-year and 30-day mortality in hospitalized older multimorbid patients with polypharmacy.

Methods

We calculated the HOSPITAL score and LACE index in patients from the OPERAM (OPtimising thERapy to prevent Avoidable hospital admissions in the Multimorbid elderly) trial (patients aged ≥ 70 years with multimorbidity and polypharmacy, admitted to hospital across four European countries in 2016–2018). Our primary and secondary outcomes were 1-year and 30-day mortality. We assessed the overall accuracy (scaled Brier score, the lower the better), calibration (predicted/observed proportions), and discrimination (C-statistic) of the models.

Results

Within 1 year, 375/1879 (20.0%) patients had died, including 94 deaths within 30 days. The overall accuracy was good and similar for both models (scaled Brier score 0.01–0.08). The C-statistics were identical for both models (0.69 for 1-year mortality, p = 0.81; 0.66 for 30-day mortality, p = 0.94). Calibration showed well-matching predicted/observed proportions.

Conclusion

The HOSPITAL score and LACE index showed similar performance to predict 1-year and 30-day mortality in older multimorbid patients with polypharmacy. Their overall accuracy was good, their discrimination low to moderate, and the calibration good. These simple tools may help predict older multimorbid patients’ mortality after hospitalization, which may inform post-hospitalization intensity of care.

Effectiveness of the rural transitions nurse program for Veterans: A multicenter implementation study

BACKGROUND

Veterans are often transferred from rural areas to urban VA Medical Centers for care. The transition from hospital to home is vulnerable to postdischarge adverse events.

OBJECTIVE

To evaluate the effectiveness of the rural Transitions Nurse Program (TNP).

DESIGN, SETTING, AND PARTICIPANTS

National hybrid-effectiveness-implementation study, within site propensity-matched cohort in 11 urban VA hospitals. 3001 Veterans were enrolled in TNP from April 2017 to September 2019, and 6002 matched controls.

INTERVENTION AND OUTCOMES

The intervention was led by a transitions nurse who assessed discharge readiness, provided postdischarge communication with primary care providers (PCPs), and called the Veteran within 72 h of discharge home to assess needs, and encourage follow-up appointment attendance. Controls received usual care. The primary outcomes were PCP visits within 14 days of discharge and all-cause 30-day readmissions. Secondary outcomes were 30-day emergency department (ED) visits and 30-day mortality. Patients were matched by length of stay, prior hospitalizations and PCP visits, urban/rural status, and 32 Elixhauser comorbidities.

RESULTS

The 3001 Veterans enrolled in TNP were more likely to see their PCP within 14 days of discharge than 6002 matched controls (odds ratio = 2.24, 95% confidence interval [CI] = 2.05-2.45). TNP enrollment was not associated with reduced 30-day ED visits or readmissions but was associated with reduced 30-day mortality (hazard ratio = 0.33, 95% CI = 0.21-0.53). PCP and ED visits did not have a significant mediating effect on outcomes. The observational design, potential selection bias, and unmeasurable confounders limit causal inference.

CONCLUSIONS

TNP was associated with increased postdischarge follow-up and a mortality reduction. Further investigation to understand the reduction in mortality is needed.

Prediction value of the LACE index to identify older adults at high risk for all-cause mortality in South Korea: a nationwide population-based study

Background

As a tool to predict early hospital readmission, little is known about the association between LACE index and all-cause mortality in older adults. We aimed to validate the LACE index to predict all-cause mortality in older adults and also analyzed the LACE index outcome of all-cause mortality depending on the disease and age of the participants.

Methods

We used the National Health Insurance Service (NHIS) cohort, a nationwide claims database of Koreans. We enrolled 7491 patients who were hospitalized at least once between 2003 and 2004, aged ≥65 years as of the year of discharge, and subsequently followed-up until 2015. We estimated the LACE index using the NHI database. The Cox proportional hazards model was used to estimate the hazard ratio (HR) for all-cause mortality. Furthermore, we investigated all-cause mortality according to age and underlying disease when the LACE index was ≥10 and < 10, respectively.

Results

In populations over 65 years of age, patients with LACE index ≥10 had significantly higher risks of all-cause mortality than in those with LACE index < 10. (HR, 1.44; 95% confidence interval, 1.35–1.54). For those patients aged 65–74 years, the HR of all-cause mortality was found to be higher in patients with LACE index≥10 than in those with LACE index < 10 in almost all the diseases except CRF and mental illnesses. And those patients aged ≥75 years, the HR of all- cause mortality was found to be higher in patients with LACE index ≥10 than in those with LACE index < 10 in the diseases of pneumonia and MACE.

Conclusion

This is the first study to validate the predictive power of the LACE index to identify older adults at high risk for all-cause mortality using nationwide cohort data. Our findings have policy implications for selecting or managing patients who need post-discharge management.

Supplementary Information

The online version contains supplementary material available at 10.1186/s12877-022-02848-4.

Medications and Patient Factors Associated With Increased Readmission for Alcohol-Related Diagnoses

Objective

To investigate medication factors and patient characteristics associated with readmissions following alcohol-related hospitalizations.

Patients and Methods

Adult patients admitted from September 1, 2016, through August 31, 2019, who had an alcohol-related hospitalization were identified through electronic health records. Patient characteristics and medications of interest administered during hospitalization or prescribed at discharge were identified. Medications of interest included US Food and Drug Administration–approved medications for alcohol use disorder, benzodiazepines, barbiturates, gabapentin, opioids, and muscle relaxants. The primary outcome was to identify medications and patient factors associated with 30-day alcohol-related readmission. Secondary outcomes included medications and patient characteristics associated with multiple alcohol-related readmissions within a year from the index admission (ie, two or more readmissions) and factors associated with 30-day all-cause readmission.

Results

Characteristics of the 932 patients included in this study associated with a 30-day alcohol-related readmission included younger age, severity of alcohol withdrawal, history of psychiatric disorder, marital status, and the number of prior alcohol-related admission in the previous year. Benzodiazepine or barbiturate use during hospitalization or upon discharge was associated with 30-day alcohol-related readmission (P=.006). Gabapentin administration during hospitalization or upon discharge was not associated with 30-day alcohol-related readmission (P=.079).

Conclusion

The findings reinforce current literature identifying patient-specific factors associated with 30-day readmissions. Gabapentin use was not associated with readmissions; however, there was an association with benzodiazepine/barbiturate use.

Predicting hospital readmission risk: A prospective observational study to compare primary care providers' assessments with the LACE readmission risk index

Purpose

This study aims to determine if the primary care provider (PCP) assessment of readmission risk is comparable to the validated LACE tool at predicting readmission to hospital.

Methods

A prospective observational study of recently discharged adult patients clustered by PCPs in the primary care setting. Physician readmission risk assessment was determined via a questionnaire after the PCP reviewed the hospital discharge summary. LACE scores were calculated using administrative data and the discharge summary. The sensitivity and specificity of the physician assessment and the LACE tool in predicting readmission risk, agreement between the 2 assessments and the area under receiver operating characteristic (AUROC) curves were calculated.

Results

217 patient readmission encounters were included in this study from September 2017 till June 2018. The rate of readmission within 30 days was 14.7%, and 217 discharge summaries were used for analysis. The weighted kappa coefficient was 0.41 (95% CI: 0.30–0.51) demonstrating a moderate level of agreement. Sensitivity of physician assessment was 0.31 (95% CI: 0.22–0.40) and specificity was 0.80 (95% CI: 0.77–0.83). The sensitivity of the LACE assessment was 0.42 (95% CI: 0.25–0.59) and specificity was 0.79 (95% CI: 0.73–0.85). The AUROC for the LACE readmission risk was 0.65 (95% C.I. 0.55–0.76) demonstrating modest predictive power and was 0.57 (95% C.I. 0.46–0.68) for physician assessment, demonstrating low predictive power.

Conclusion

The LACE index shows moderate discriminatory power in identifying high-risk patients for readmission when compared to the PCP’s assessment. If this score can be provided to the PCP, it may help identify patients who requires more intensive follow-up after discharge.

External validation of the modified LACE+, LACE+, and LACE scores to predict readmission or death after hospital discharge

BACKGROUND

Unplanned hospital readmissions are common adverse events. The LACE+ score has been used to identify patients at the highest risk of unplanned readmission or death, yet the external validity of this score remains uncertain.

METHODS

We constructed a cohort of patients admitted to hospital between 1 October 2014 and 31 January 2017 using population-based data from British Columbia (Canada). The primary outcome was a composite of urgent hospital readmission or death within 30 days of index discharge. The primary analysis sought to optimize clinical utility and international generalizability by focusing on the modified LACE+ (mLACE+) score, a variation of the LACE+ score which excludes the Case Mix Group score. Predictive performance was assessed using model calibration and discrimination.

RESULTS

Among 368,154 hospitalized individuals, 31,961 (8.7%) were urgently readmitted and 5428 (1.5%) died within 30 days of index discharge (crude composite risk of readmission or death, 9.95%). The mLACE+ score exhibited excellent calibration (calibration-in-the-large and calibration slope no different than ideal) and adequate discrimination (c-statistic, 0.681; 95%CI, 0.678 to 0.684). Higher risk dichotomized mLACE+ scores were only modestly associated with the primary outcome (positive likelihood ratio 1.95, 95%CI 1.93 to 1.97). Predictive performance of the mLACE+ score was similar to that of the LACE+ and LACE scores.

CONCLUSION

The mLACE+, LACE+ and LACE scores predict hospital readmission with excellent calibration and adequate discrimination. These scores can be used to target interventions designed to prevent unplanned hospital readmission.

Assessing and Augmenting Predictive Models for Hospital Readmissions With Novel Variables in an Urban Safety-net Population

BACKGROUND

The performance of existing predictive models of readmissions, such as the LACE, LACE+, and Epic models, is not established in urban safety-net populations. We assessed previously validated predictive models of readmission performance in a socially complex, urban safety-net population, and if augmentation with additional variables such as the Area Deprivation Index, mental health diagnoses, and housing access improves prediction. Through the addition of new variables, we introduce the LACE-social determinants of health (SDH) model.

METHODS

This retrospective cohort study included adult admissions from July 1, 2016, to June 30, 2018, at a single urban safety-net health system, assessing the performance of the LACE, LACE+, and Epic models in predicting 30-day, unplanned rehospitalization. The LACE-SDH development is presented through logistic regression. Predictive model performance was compared using C-statistics.

RESULTS

A total of 16,540 patients met the inclusion criteria. Within the validation cohort (n=8314), the Epic model performed the best (C-statistic=0.71, P<0.05), compared with LACE-SDH (0.67), LACE (0.65), and LACE+ (0.61). The variables most associated with readmissions were (odds ratio, 95% confidence interval) against medical advice discharge (3.19, 2.28-4.45), mental health diagnosis (2.06, 1.72-2.47), and health care utilization (1.94, 1.47-2.55).

CONCLUSIONS

The Epic model performed the best in our sample but requires the use of the Epic Electronic Health Record. The LACE-SDH performed significantly better than the LACE and LACE+ models when applied to a safety-net population, demonstrating the importance of accounting for socioeconomic stressors, mental health, and health care utilization in assessing readmission risk in urban safety-net patients.

Prediction of Hospital Readmission from Longitudinal Mobile Data Streams

Hospital readmissions impose an extreme burden on both health systems and patients. Timely management of the postoperative complications that result in readmissions is necessary to mitigate the effects of these events. However, accurately predicting readmissions is very challenging, and current approaches demonstrated a limited ability to forecast which patients are likely to be readmitted. Our research addresses the challenge of daily readmission risk prediction after the hospital discharge via leveraging the abilities of mobile data streams collected from patients devices in a probabilistic deep learning framework. Through extensive experiments on a real-world dataset that includes smartphone and Fitbit device data from 49 patients collected for 60 days after discharge, we demonstrate our framework's ability to closely simulate the readmission risk trajectories for cancer patients.

Hepatopancreatobiliary readmission score out performs administrative LACE+ index as a predictive tool of readmission

BACKGROUND

This study aims to compare the LACE + readmission index to a novel hepatopancreatobiliary readmission risk score (HRRS) in predicting post-operative hepatopancreatobiliary (HPB) cancer patient readmissions.

METHODS

A retrospective review of 104 postoperative HPB cancer patients from January 2017 to July of 2019 was performed. Univariable and multivariable analyses were utilized.

RESULTS

The LACE + index did not predict 30-day (OR 1.01, 95% CI, 0.97-1.05, p = 0.81, c-statistic = 0.52) or 90-day (OR 1.02, 95% CI, 0.98-1.05, p = 0.43) readmission. Patients readmitted within 30 days had significantly increased HRRS scores compared to those who were not (0 vs 34, p < 0.001). A single unit increase in HRRS corresponded to a 6.5% increased risk of readmission; (OR 1.065, 95% CI, 1.038-1.094, p < 0.0001). HRRS independently predicted 30-day (OR 1.07, 95% CI, 1.04-1.11, p < 0.0001) and 90-day postoperative readmission (OR 1.05, 95% CI 1.03-1.08, p < 0.0001).

CONCLUSIONS

HRRS better predicts postoperative readmissions for HPB surgical patients compared to LACE+. Accurate assessment of postoperative readmission must include readmission scores focused on clinically relevant perioperative parameters.

Comparison of Back-Propagation Neural Network, LACE Index and HOSPITAL Score in Predicting All-Cause Risk of 30-Day Readmission

Background

The main purpose of this study is to predict the all-cause risk of 30-day readmission by employing the back-propagation neural network (BPNN) in comparison with traditional risk assessment tools of LACE index and HOSPITAL scores.

Methods

This was a retrospective cohort study from January 1st, 2018 to December 31st, 2019. A total of 55,688 hospitalizations from a medical center in Taiwan were examined. The LACE index (length of stay, acute admission, Charlson comorbidity index score, emergency department visits in previous 6 months) and HOSPITAL score (hemoglobin level at discharge, discharge from an Oncology service, sodium level at discharge, procedure during hospital stay, Index admission type, number of hospital admissions during the previous year, length of stay) are calculated. We employed variables from LACE index and HOSPITAL score as the input vector of BPNN for comparison purposes.

Results

The BPNN constructed in the current study has a considerably better ability with a C statistics achieved 0.74 (95% CI 0.73 to 0.75), which is statistically significant larger than that of the other two models using DeLong’s test. Also, it was possible to achieve higher sensitivity (70.32%) without penalizing the specificity (71.76%) and accuracy (71.68%) at its optimal threshold, which is at the 20% of patients with the highest predicted risk. Moreover, it is much more informative than the other two methods because of a considerably higher LR+ and a lower LR-.

Conclusion

Our findings suggest that more attention should be paid to methods based on non-linear classification systems, as they lead to substantial differences in risk-scores.

Prediction of Adverse Outcomes Within 90 Days of Surgery in a Heterogeneous Orthopedic Surgery Population

INTRODUCTION

The LACE+ index has been shown to predict readmissions; however, LACE+ has not been validated for extended postoperative outcomes in an orthopedic surgery population. The purpose of this study is to examine whether LACE+ scores predict unplanned readmissions and adverse outcomes following orthopedic surgery. Use of the LACE1 index to proactively identify at-risk patients may enable actions to reduce preventable readmissions.

METHODS

LACE+ scores were retrospectively calculated at the time of discharge for all consecutive orthopedic surgery patients (n = 18,893) at a multicenter health system over 3 years (2016-2018). Coarsened exact matching was used to match patients based on characteristics not assessed in the LACE+ index. Outcome differences between matched patients in different LACE quartiles (i.e. Q4 vs. Q3, Q2, and Q1) were analyzed.

RESULTS

Higher LACE+ scores significantly predicted readmission and emergency department visits within 90 days of discharge and for 30-90 days after discharge for all studied quartiles. Higher LACE+ scores also significantly predicted reoperations, but only between Q4 and Q3 quartiles.

CONCLUSIONS

The results suggest that the LACE+ risk-prediction tool may accurately predict patients with a high likelihood of adverse outcomes after a broad array of orthopedic procedures.

LACE index predicts age-specific unplanned readmissions and mortality after hospital discharge

Background

The LACE index scoring tool (Length of stay, Acuity of admission, Co-morbidities and Emergency department visits) has been designed to predict hospital readmissions. We evaluated the ability of the LACE index to predict age-specific frequent admissions and mortality.

Methods

Analysis of prospectively collected data of alive-discharge episodes between 01/04/2017 and 31/03/2019 in an NHS hospital. Data on 14,878 men and 17,392 women of mean age 64.0 years, SD = 20.5, range 18.0–106.7 years were analysed. The association of the LACE index with frequency of all-cause readmissions within 28 days of discharge and over a 2-year period, and with all-cause mortality within 30 days or within 6 months after discharge from hospital were evaluated.

Results

Within LACE index scores of 0–4, 5–9 or ≥ 10, the proportions of readmission ≥ 2 times within 28 days of discharge were 0.1, 1.3 and 9.2% (χ² = 3070, p < 0.001) and over a 2-year period were 1.7, 4.8 and 19.1% (χ² = 3364, p < 0.001). Compared with a LACE index score of 0–4, a score ≥ 10 increased the risk (adjusted for age, sex and frequency of admissions) of death within 6 months of discharge by 6.8-fold (5.1–9.0, p < 0.001) among all ages, and most strongly in youngest individuals (18.0–49.9 years): adjusted odds ratio = 16.1 (5.7–45.8, p < 0.001). For those aged 50–59.9, 60–69.9, 70–79.9 and ≥ 80 years, odds ratios reduced progressively to 9.6, 7.7, 5.1 and 2.3, respectively. Similar patterns were observed for the association of LACE index with mortality within 30 days of hospital discharge.

Conclusions

The LACE index predicts short-term and long-term frequent admissions and short-term and medium-term mortality, most pronounced among younger individuals, after hospital discharge.

Predicting patient outcomes after far lateral lumbar discectomy

INTRODUCTION

The LACE+ (Length of Stay, Acuity of Admission, Charlson Comorbidity Index (CCI) Score, Emergency Department (ED) visits within the previous 6 months) index has never been tested in a purely spine surgery population. This study assesses the ability of LACE + to predict adverse patient outcomes following discectomy for far lateral disc herniation (FLDH).

PATIENTS AND METHODS

Data were obtained for patients (n = 144) who underwent far lateral lumbar discectomy at a single, multi-hospital academic medical center (2013-2020). LACE + scores were calculated for all patients with complete information (n = 100). The influence of confounding variables was assessed and controlled with stepwise regression. Logistic regression was used to test the ability of LACE + to predict risk of unplanned hospital readmission, ED visits, outpatient office visits, and reoperation after surgery.

RESULTS

Mean age of the population was 61.72 ± 11.55 years, 69 (47.9 %) were female, and 126 (87.5 %) were non-Hispanic white. Patients underwent either open (n = 92) or endoscopic (n = 52) surgery. Each point increase in LACE + score significantly predicted, in the 30-day (30D) and 30-90-day (30-90D) post-discharge window, higher risk of readmission (p = 0.005, p = 0.009; respectively) and ED visits (p = 0.045). Increasing LACE + also predicted, in the 30D and 90-day (90D) post-discharge window, risk of reoperation (p = 0.022, p = 0.016; respectively), and repeat neurosurgical intervention (p = 0.026, p = 0.026; respectively). Increasing LACE + score also predicted risk of reoperation (p = 0.011) within 30 days of initial surgery.

CONCLUSIONS

LACE + may be suitable for characterizing risk of adverse perioperative events for patients undergoing far lateral discectomy.

Development and Implementation of a Complex Health System Intervention Targeting Transitions of Care from Hospital to Post-acute Care

BACKGROUND

Failure of effective transitions of care following hospitalization can lead to excess days in the hospital, readmissions, and adverse events. Evidence identifies both patient and system factors that influence poor care transitions, yet health systems struggle to translate evidence into complex interventions that have a meaningful impact on care transitions.

OBJECTIVE

We report on our experience developing, pilot testing, and evaluating a complex intervention (Addressing Complex Transitions program, or ACT program) that aims to improve care transitions for complex patients.

DESIGN

Following the Medical Research Council (MRC) framework, we engaged in iterative, stakeholder-driven work to develop a complex care intervention, assess feasibility and pilot methods, evaluate the intervention in practice, and facilitate ongoing implementation monitoring and dissemination.

PARTICIPANTS

Patients receiving care from UW Medicine's health system including 4 hospitals and 20-site Post-Acute Care network.

INTERVENTION

Literature review and prospective data collection activities informed ACT program design. ACT program components include a tailored risk calculator that provides real-time scoring of transitions of care risk factors, a multidisciplinary team with the capacity to address complex barriers to safe transitions, and enhanced discharge workflows to improve care transitions for complex patients.

KEY MEASURES

Program evaluation metrics included estimated hospital days saved and program acceptance by care team members.

KEY RESULTS

During the 6-month pilot, 565 patients were screened and 97 enrolled in the ACT program. An estimated 664 hospital days were saved for the index admission of ACT program participants. Analysis of pre/post-hospital utilization for ACT program participants showed an estimated 3227 fewer hospital days after ACT program enrollment.

CONCLUSIONS

Health systems need to address increasingly difficult challenges in care delivery. The use of evidence-based frameworks, such as the MRC framework, can guide systems to design complex interventions that respond to their local context and stakeholder needs.

LACE Score-Based Risk Management Tool for Long-Term Home Care Patients: A Proof-of-Concept Study in Taiwan

Background: Effectively predicting and reducing readmission in long-term home care (LTHC) is challenging. We proposed, validated, and evaluated a risk management tool that stratifies LTHC patients by LACE predictive score for readmission risk, which can further help home care providers intervene with individualized preventive plans. Method: A before-and-after study was conducted by a LTHC unit in Taiwan. Patients with acute hospitalization within 30 days after discharge in the unit were enrolled as two cohorts (Pre-Implement cohort in 2017 and Post-Implement cohort in 2019). LACE score performance was evaluated by calibration and discrimination (AUC, area under receiver operator characteristic (ROC) curve). The clinical utility was evaluated by negative predictive value (NPV). Results: There were 48 patients with 87 acute hospitalizations in Pre-Implement cohort, and 132 patients with 179 hospitalizations in Post-Implement cohort. These LTHC patients were of older age, mostly intubated, and had more comorbidities. There was a significant reduction in readmission rate by 44.7% (readmission rate 25.3% vs. 14.0% in both cohorts). Although LACE score predictive model still has room for improvement (AUC = 0.598), it showed the potential as a useful screening tool (NPV, 87.9%; 95% C.I., 74.2–94.8). The reduction effect is more pronounced in infection-related readmission. Conclusion: As real-world evidence, LACE score-based risk management tool significantly reduced readmission by 44.7% in this LTHC unit. Larger scale studies involving multiple homecare units are needed to assess the generalizability of this study.

Heart Failure with Preserved Ejection Fraction and 30-Day Readmission

OBJECTIVE

Several studies identify heart failure (HF) as a potential risk for hospital readmission; however, studies on predictability of heart failure readmission is limited. The objective of this work was to investigate whether a specific type of heart failure (HFpEF or HFrEF) has a higher association to the rate of 30-day hospital readmission and compare their predictability with the two risk scores: HOSPITAL score and LACE index.

DESIGN

Retrospective study from single academic center.

METHODS

Sample size included adult patients from an academic hospital in a two-year period (2015 - 2017). Exclusion criteria included death, transfer to another hospital, and unadvised leave from hospital. Baseline characteristics, diagnosis-related group, and ICD diagnosis codes were obtained. Variables affecting HOSPITAL score and LACE index and types of heart failure present were also extracted. Qualitative variables were compared using Pearson chi² or Fisher's exact test (reported as frequency) and quantitative variables using non-parametric Mann-Whitney U test (reported as mean ± standard deviation). Variables from univariate analysis with P values of 0.05 or less were further analyzed using multivariate logistic regression. Odds ratio was used to measure potential risk.

RESULTS

The sample size of adult patients in the study period was 1,916. All eligible cohort of patients who were readmitted were analyzed. Cumulative score indicators of HOSPITAL Score, LACE index (including the Charlson Comorbidity Index) predicted 30-day readmissions with P values of <0.001. The P value of HFpEF was found to be significant in the readmitted group (P < 0.001) compared to HFrEF (P = 0.141). Multivariate logistic regression further demonstrated the association of HFpEF with higher risk of readmission with odds ratio of 1.77 (95% CI: 1.25 - 2.50) and P value of 0.001.

CONCLUSIONS

Our data from an academic tertiary care center supports HFpEF as an independent risk factor for readmission. Multidisciplinary management of HFpEF may be an important target for interventions to reduce hospital readmissions.

Readmission Risk Factors and Heart Failure With Preserved Ejection Fraction

Context

Cases of heart failure with preserved ejection fraction (HFpEF) exacerbations continue to affect patients' quality of life and cause significant financial burden on our healthcare system.

Objective

To identify risk factors for readmission in patients discharged with a diagnosis of HFpEF.

Methods

Electronic health records of patients over 18 years of age with a primary diagnosis of HFpEF treated between August 1, 2017 and March 1, 2018 in a community hospital were retrospectively reviewed. The study population included patients with HFpEF greater than 40% who were screened but did not qualify for the ongoing CONNECT- HF trial being conducted by Duke Clinical Research. To be included, subjects had to fall into 1 of 2 classifications (NYHA Class II-IV or ACC/AHA Stage B-D) and have a life expectancy greater than 6 months. Patients were excluded if they had terminal illness other than HF, a prior heart transplant or were on a transplant list, a current or planned placement of a left ventricular assist device, chronic kidney disease requiring hemodialysis, inability to use mobile applications, or inability to participate in longitudinal follow up. Readmission rate was analyzed at 30 and 90 days along with patients' demographics and associated comorbidities, including peripheral vascular disease, anemia, pulmonary hypertension, arrythmia, and valvular heart disease. Patients were risk stratified using the LACE index readmission score and the Charlson comorbidity index.

Results

Of the 492 cases of HFpEF identified during the 7-month study period, 212 patients were included. The majority of patients were women (126; 59.4%), had a median body mass index above 30 kg/m2 (123; 58%), and had pulmonary hypertension (94; 44.3%), anemia (146; 68.8%), and arrhythmia (101, 47.6%). Forty-five (21.2%) patients were readmitted for HFpEF within 90 days of initial discharge; 32 of those (71.1%) were readmitted within 30 days of initial discharge. Patients with higher LACE and Charlson comorbidity index scores were more likely to be readmitted within 90 days. Peripheral vascular disease (P=.002), tricuspid regurgitation (P=.001), pulmonary hypertension (P=.049), and anemia (P=.029) were risk factors associated with readmissions. Use of ACEi/ARBs (P=.017) was associated with fewer readmissions.

Conclusion

Anemia, peripheral vascular disease, pulmonary hypertension, and valvular heart disease are not only postulated mechanisms of HFpEF, but also important risk factors for readmission. These study findings affirm the need for continued research of the pathophysiology and associated comorbidities of the HFpEF population to improve quality of life and lower healthcare costs.

Composite score for prediction of 30-day orthopedic surgery outcomes

The LACE+ (Length of stay, Acuity of admission, Charlson Comorbidity Index score, and Emergency department visits in the past 6 months) risk-prediction tool has never been tested in an orthopedic surgery population. LACE+ may help physicians more effectively identify and support high-risk orthopedics patients after hospital discharge. LACE+ scores were retrospectively calculated for all consecutive orthopedic surgery patients (n = 18 893) at a multi-center health system over 3 years (2016-2018). Coarsened exact matching was employed to create "matched" study groups with different LACE+ score quartiles (Q1, Q2, Q3, Q4). Outcomes were compared between quartiles. In all, 1444 patients were matched between Q1 and Q4 (n = 2888); 2079 patients between Q2 and Q4 (n = 4158); 3032 patients between Q3 and Q4 (n = 6064). Higher LACE+ scores significantly predicted 30D readmission risk for Q4 vs Q1 and Q4 vs Q3 (P < .001). Larger LACE+ scores also significantly predicted 30D risk of ED visits for Q4 vs Q1, Q4 vs Q2, and Q4 vs Q3 (P < .001). Increased LACE+ score also significantly predicted 30D risk of reoperation for Q4 vs Q1 (P = .018), Q4 vs Q2 (P < .001), and Q4 vs Q3 (P < .001).

Implementation of Artificial Intelligence-Based Clinical Decision Support to Reduce Hospital Readmissions at a Regional Hospital

BACKGROUND

Hospital readmissions are a key quality metric, which has been tied to reimbursement. One strategy to reduce readmissions is to direct resources to patients at the highest risk of readmission. This strategy necessitates a robust predictive model coupled with effective, patient-centered interventions.

OBJECTIVE

The aim of this study was to reduce unplanned hospital readmissions through the use of artificial intelligence-based clinical decision support.

METHODS

A commercially vended artificial intelligence tool was implemented at a regional hospital in La Crosse, Wisconsin between November 2018 and April 2019. The tool assessed all patients admitted to general care units for risk of readmission and generated recommendations for interventions intended to decrease readmission risk. Similar hospitals were used as controls. Change in readmission rate was assessed by comparing the 6-month intervention period to the same months of the previous calendar year in exposure and control hospitals.

RESULTS

Among 2,460 hospitalizations assessed using the tool, 611 were designated by the tool as high risk. Sensitivity and specificity for risk assignment were 65% and 89%, respectively. Over 6 months following implementation, readmission rates decreased from 11.4% during the comparison period to 8.1% (p < 0.001). After accounting for the 0.5% decrease in readmission rates (from 9.3 to 8.8%) at control hospitals, the relative reduction in readmission rate was 25% (p < 0.001). Among patients designated as high risk, the number needed to treat to avoid one readmission was 11.

CONCLUSION

We observed a decrease in hospital readmission after implementing artificial intelligence-based clinical decision support. Our experience suggests that use of artificial intelligence to identify patients at the highest risk for readmission can reduce quality gaps when coupled with patient-centered interventions.

Validation of the LACE Index (Length of Stay, Acuity of Admission, Comorbidities, Emergency Department Use) in the Adult Neurosurgical Patient Population

BACKGROUND

The LACE index (Length of stay, Acuity of admission, Comorbidities, Emergency department use) quantifies the risk of mortality or unplanned readmission within 30 d after hospital discharge. The index was validated originally in a large, general population and, subsequently, in several specialties, not including neurosurgery.

OBJECTIVE

To determine if the LACE index accurately predicts mortality and unplanned readmission of neurosurgery patients within 30 d of discharge.

METHODS

We performed a retrospective, cohort study of consecutive neurosurgical procedures between January 1 and September 29, 2017 at our institution. The LACE index and other clinical data were abstracted. Data analysis included univariate and multivariate logistic regressions.

RESULTS

Of the 1,054 procedures on 974 patients, 52.7% were performed on females. Mean age was 54.2 ± 15.4 yr. At time of discharge, the LACE index was low (1-4) in 58.3% of patients, moderate (5-9) in 32.4%, and high (10-19) in 9.3%. Rates of readmission and mortality within 30 d were 7.0, 11.4, and 14.3% in the low-, moderate-, and high-risk groups, respectively. Moderate-risk (odds ratio [OR] 1.62, 95% CI 1.02-2.56, P = .04) and high-risk LACE indexes (OR 2.20, 95% CI 1.15-4.19, P = .02) were associated with greater odds of readmission or mortality, adjusting for all variables. Additionally, longer operations (OR 1.11, 95% CI 1.02-1.21, P = .02) had greater odds of readmission. Specificity of the high-risk score to predict 30-d readmission or mortality was 91.2%.

CONCLUSION

A moderate- or high-risk LACE index can be applied to neurosurgical populations to predict 30-d readmission and mortality. Longer operations are potential predictors of readmission or mortality.

Risk factors for unplanned hospital readmissions within 30 days of discharge among medical oncology patients: A retrospective medical record review

PURPOSE

This study aimed to identify the risk factors for unplanned hospital readmissions (UHR) within 30 days of discharge among medical oncology patients at a tertiary hospital in Singapore.

METHODS

This study is a retrospective, case-control medical record review of patients admitted to a medical oncology unit at a tertiary hospital between 1 June and October 31, 2017. During the study period, there were 1559 adult patients discharged alive from the medical oncology unit. Of this, 359 patients had experienced at least a 30-day UHR (cases). The cases were matched to those without a 30-day UHR (controls) by their primary reason for index admission and discharge date. After matching, 312 medical records (cases: 156; controls: 156) were analysed.

RESULTS

Of the 156 cases with a 30-day UHR, 46.2% (n = 72) were readmitted within the first 10 days of discharge. The top reasons contributing to the UHR were non-neutropenic infection (n = 41) and pain (n = 23). Multivariate analyses identified three independent risk factors that were associated with the 30-day UHR: (1) single marital status, (2) emergency department visit(s) in the past six months, and (3) recent decline in activities of daily living.

CONCLUSION

The study results can guide risk stratification to identify medical oncology patients at high risk for 30-day UHR. In addition, the results warrant the need to refine the inpatient assessments and discharge planning, as well as ensure the accurate referral to and allocation of community and outpatient resources so as to reduce the risk of UHR.

The LACE+ Index as a Predictor of 90-Day Supratentorial Tumor Surgery Outcomes

BACKGROUND

The LACE+ (Length of stay, Acuity of admission, Charlson Comorbidity Index [CCI] score, and Emergency department [ED] visits in the past 6 mo) index risk-prediction tool has never been successfully tested in a neurosurgery population.

OBJECTIVE

To assess the ability of LACE+ to predict adverse outcomes after supratentorial brain tumor surgery.

METHODS

LACE+ scores were retrospectively calculated for all patients (n = 624) who underwent surgery for supratentorial tumors at the University of Pennsylvania Health System (2017-2019). Confounding variables were controlled with coarsened exact matching. The frequency of unplanned hospital readmission, ED visits, and death was compared for patients with different LACE+ score quartiles (Q1, Q2, Q3, and Q4).

RESULTS

A total of 134 patients were matched between Q1 and Q4; 152 patients were matched between Q2 and Q4; and 192 patients were matched between Q3 and Q4. Patients with higher LACE+ scores were significantly more likely to be readmitted within 90 d (90D) of discharge for Q1 vs Q4 (21.88% vs 46.88%, P = .005) and Q2 vs Q4 (27.03% vs 55.41%, P = .001). Patients with larger LACE+ scores also had significantly increased risk of 90D ED visits for Q1 vs Q4 (13.33% vs 30.00%, P = .027) and Q2 vs Q4 (22.54% vs 39.44%, P = .039). LACE+ score also correlated with death within 90D of surgery for Q2 vs Q4 (2.63% vs 15.79%, P = .003) and with death at any point after surgery/during follow-up for Q1 vs Q4 (7.46% vs 28.36%, P = .002), Q2 vs Q4 (15.79% vs 31.58%, P = .011), and Q3 vs Q4 (18.75% vs 31.25%, P = .047).

CONCLUSION

LACE+ may be suitable for characterizing risk of certain perioperative events in a patient population undergoing supratentorial brain tumor resection.

Updates in heart failure 30-day readmission prevention

Heart failure (HF) and HF 30-day readmission rates have been a major focus of efforts to reduce health care cost in the recent era. Since the implementation of the Affordable Care Act (ACA) in 2012 and the Hospital Readmission Reduction Program (HRRP), concerted efforts have focused on reduction of 30-day HF readmissions and other admission diagnoses targeted by the HRRP. Hospitals and organizations have instituted wide-ranging programs to reduce short-term readmissions, but the data supporting these programs is often mixed. In this review, we will discuss the challenges associated with reducing HF readmissions and summarize the rationale and effect of specific programs on HF 30-day readmission rates, ranging from medical therapy and adherence to remote hemodynamic monitoring. Finally, we will review the effect that the focus on reducing 30-day HF readmissions has had on the care of the HF patient.

Use of electronic medical records in development and validation of risk prediction models of hospital readmission: systematic review

OBJECTIVE

To provide focused evaluation of predictive modeling of electronic medical record (EMR) data to predict 30 day hospital readmission.

DESIGN

Systematic review.

DATA SOURCE

Ovid Medline, Ovid Embase, CINAHL, Web of Science, and Scopus from January 2015 to January 2019.

ELIGIBILITY CRITERIA FOR SELECTING STUDIES

All studies of predictive models for 28 day or 30 day hospital readmission that used EMR data.

OUTCOME MEASURES

Characteristics of included studies, methods of prediction, predictive features, and performance of predictive models.

RESULTS

Of 4442 citations reviewed, 41 studies met the inclusion criteria. Seventeen models predicted risk of readmission for all patients and 24 developed predictions for patient specific populations, with 13 of those being developed for patients with heart conditions. Except for two studies from the UK and Israel, all were from the US. The total sample size for each model ranged between 349 and 1 195 640. Twenty five models used a split sample validation technique. Seventeen of 41 studies reported C statistics of 0.75 or greater. Fifteen models used calibration techniques to further refine the model. Using EMR data enabled final predictive models to use a wide variety of clinical measures such as laboratory results and vital signs; however, use of socioeconomic features or functional status was rare. Using natural language processing, three models were able to extract relevant psychosocial features, which substantially improved their predictions. Twenty six studies used logistic or Cox regression models, and the rest used machine learning methods. No statistically significant difference (difference 0.03, 95% confidence interval -0.0 to 0.07) was found between average C statistics of models developed using regression methods (0.71, 0.68 to 0.73) and machine learning (0.74, 0.71 to 0.77).

CONCLUSIONS

On average, prediction models using EMR data have better predictive performance than those using administrative data. However, this improvement remains modest. Most of the studies examined lacked inclusion of socioeconomic features, failed to calibrate the models, neglected to conduct rigorous diagnostic testing, and did not discuss clinical impact.

Assess the Performance and Cost-Effectiveness of LACE and HOSPITAL Re-Admission Prediction Models as a Risk Management Tool for Home Care Patients: An Evaluation Study of a Medical Center Affiliated Home Care Unit in Taiwan

The LACE index and HOSPITAL score models are the two most commonly used prediction models identifying patients at high risk of readmission with limited information for home care patients. This study compares the effectiveness of these two models in predicting 30-day readmission following acute hospitalization of such patients in Taiwan. A cohort of 57 home care patients were enrolled and followed-up for one year. We compared calibration, discrimination (area under the receiver operating curve, AUC), and net reclassification improvement (NRI) to identify patients at risk of 30-day readmission for both models. Moreover, the cost-effectiveness of the models was evaluated using microsimulation analysis. A total of 22 readmissions occurred after 87 acute hospitalizations during the study period (readmission rate = 25.2%). While the LACE score had poor discrimination (AUC = 0.598, 95% confidence interval (CI) = 0.488–0.702), the HOSPITAL score achieved helpful discrimination (AUC = 0.691, 95% CI = 0.582–0.785). Moreover, the HOSPITAL score had improved the risk prediction in 38.3% of the patients, compared with the LACE index (NRI = 0.383, 95% CI = 0.068–0.697, p = 0.017). Both prediction models effectively reduced readmission rates compared to an attending physician’s model (readmission rate reduction: LACE, 39.2%; HOSPITAL, 43.4%; physician, 10.1%; p < 0.001). The HOSPITAL score provides a better prediction of readmission and has potential as a risk management tool for home care patients.

Multicentre, prospective observational study of the correlation between the Glasgow Admission Prediction Score and adverse outcomes

OBJECTIVES

To assess whether the Glasgow Admission Prediction Score (GAPS) is correlated with hospital length of stay, 6-month hospital readmission and 6-month all-cause mortality. This study represents a 6-month follow-up of patients who were included in an external validation of the GAPS' ability to predict admission at the point of triage.

SETTING

Sampling was conducted between February and May 2016 at two separate emergency departments (EDs) in Sheffield and Glasgow.

PARTICIPANTS

Data were collected prospectively at triage for consecutive adult patients who presented to the ED within sampling times. Any patients who avoided formal triage were excluded from the study. In total, 1420 patients were recruited.

PRIMARY OUTCOMES

GAPS was calculated following triage and did not influence patient management. Length of hospital stay, hospital readmission and mortality against GAPS were modelled using survival analysis at 6 months.

RESULTS

Of the 1420 patients recruited, 39.6% of these patients were initially admitted to hospital. At 6 months, 30.6% of patients had been readmitted and 5.6% of patients had died. For those admitted at first presentation, the chance of being discharged fell by 4.3% (95% CI 3.2% to 5.3%) per GAPS point increase. Cox regression indicated a 9.2% (95% CI 7.3% to 11.1%) increase in the chance of 6-month hospital readmission per point increase in GAPS. An association between GAPS and 6-month mortality was demonstrated, with a hazard increase of 9.0% (95% CI 6.9% to 11.2%) for every point increase in GAPS.

CONCLUSION

A higher GAPS is associated with increased hospital length of stay, 6-month hospital readmission and 6-month all-cause mortality. While GAPS's primary application may be to predict admission and support clinical decision making, GAPS may provide valuable insight into inpatient resource allocation and bed planning.

Exploring instruments used to evaluate potentially inappropriate medication use in hospitalised elderly patients in Kosovo

OBJECTIVES

A number of instruments are used to identify potentially inappropriate medications (PIMs) in the elderly. In this study we identify PIMs in elderly patients and aim to compare three different instruments used to assess PIMs.

METHODS

In this prospective cohort study, we compared medications of elderly patients against three commonly used instruments: Beers' list, PRISCUS and STOPP/START, at the point of hospital admission and discharge in the nephrology clinic of Kosovo's largest hospital. Readmission risk was evaluated using the LACE Index and correlations with the number of PIMs and PIMs criteria were analysed.

RESULTS

Of 184 patients admitted to the nephrology clinic, 84 met study inclusion criteria. Patients had a median of three drugs at admission and four at discharge. Hospital readmission risk was high with median LACE Index being 11 (63% of patients). A higher number of PIMs was associated at the point of discharge compared with admission for all three tools (Beers' list: 29% vs 38 %, P=0.04; STOPP/STRART: 20% vs 23%, P<0.001; PRISCUS list: 12% vs 21%, P<0.001). The number of drugs at admission predicted the number of PIMs at discharge only when using Beers' criteria (P=0.006). At discharge, each increase in medication was associated with an increase in PIMs based on Beers' [0.134; (P=0.007)] and STOPP/START criteria [0.130; (P=0.005)]. Nitrofurantoin was the main PIM identified with Beers' and PRISCUS list in comparison to proton- pump-inhibitors being the most prevalent agents identified with STOPP/START criteria.

CONCLUSIONS

There are differences when using Beers' criteria, STOPP/START criteria and PRISCUS list during identification of PIMs in elderly patients with high readmission risk. These differences should be considered when identifying PIMs in hospital settings.