International Validity of the HOSPITAL Score to Predict 30-Day Potentially Avoidable Hospital Readmissions

Effect of digital tools to promote hospital quality and safety on adverse events after discharge

OBJECTIVES

Post-discharge adverse events (AEs) are common and heralded by new and worsening symptoms (NWS). We evaluated the effect of electronic health record (EHR)-integrated digital tools designed to promote quality and safety in hospitalized patients on NWS and AEs after discharge.

MATERIALS AND METHODS

Adult general medicine patients at a community hospital were enrolled. We implemented a dashboard which clinicians used to assess safety risks during interdisciplinary rounds. Post-implementation patients were randomized to complete a discharge checklist whose responses were incorporated into the dashboard. Outcomes were assessed using EHR review and 30-day call data adjudicated by 2 clinicians and analyzed using Poisson regression. We conducted comparisons of each exposure on post-discharge outcomes and used selected variables and NWS as independent predictors to model post-discharge AEs using multivariable logistic regression.

RESULTS

A total of 260 patients (122 pre, 71 post [dashboard], 67 post [dashboard plus discharge checklist]) enrolled. The adjusted incidence rate ratios (aIRR) for NWS and AEs were unchanged in the post- compared to pre-implementation period. For patient-reported NWS, aIRR was non-significantly higher for dashboard plus discharge checklist compared to dashboard participants (1.23 [0.97,1.56], P = .08). For post-implementation patients with an AE, aIRR for duration of injury (>1 week) was significantly lower for dashboard plus discharge checklist compared to dashboard participants (0 [0,0.53], P < .01). In multivariable models, certain patient-reported NWS were associated with AEs (3.76 [1.89,7.82], P < .01).

DISCUSSION

While significant reductions in post-discharge AEs were not observed, checklist participants experiencing a post-discharge AE were more likely to report NWS and had a shorter duration of injury.

CONCLUSION

Interventions designed to prompt patients to report NWS may facilitate earlier detection of AEs after discharge.

CLINICALTRIALS.GOV

NCT05232656.

A prediction model based on random survival forest analysis of the overall survival of elderly female papillary thyroid carcinoma patients: a SEER-based study

OBJECTIVE

Papillary thyroid carcinoma (PTC) is a common malignancy whose incidence is three times greater in females than in males. The prognosis of ageing patients is poor. This research was designed to construct models to predict the overall survival of elderly female patients with PTC.

METHODS

We developed prediction models based on the random survival forest (RSF) algorithm and traditional Cox regression. The data of 4539 patients were extracted from the Surveillance, Epidemiology, and End Results (SEER) database. Twelve variables were analysed to establish the models. The C-index and the Brier score were selected to evaluate the discriminatory ability of the models. Time-dependent receiver operating characteristic (ROC) curves were also drawn to evaluate the accuracy of the models. The clinical benefits of the two models were compared on the basis of the DCA curve. In addition, the Shapley Additive Explanations (SHAP) plot was used to visualize the contribution of the variables in the RSF model.

RESULTS

The C-index of the RSF model was 0.811, which was greater than that of the Cox model (0.781). According to the Brier score and the area under the ROC curve (AUC), the RSF model performed better than the Cox model. On the basis of the DCA curve, the RSF model demonstrated fair clinical benefit. The SHAP plot showed that age was the most important variable contributing to the outcome of PTC in elderly female patients.

CONCLUSIONS

The RSF model we developed performed better than the Cox model and might be valuable for clinical practice.

Implementing primary care follow-up for high-risk vascular surgery patients

BACKGROUND

The Centers for Medicare and Medicaid Services consider the 30-day hospital readmission rate an outcome of care measure; a high rate is associated with high-cost and bed utilization.

PURPOSE

The Division of Vascular Surgery at a large academic medical center implemented a 15-week quality improvement project in the fall of 2022 to reduce readmissions among patients deemed high-risk for readmission and discharged to home.

METHODS

The discharging provider utilized the "HOSPITAL Score for Readmission" tool to identify patients at high-risk for unplanned 30-day readmission to receive the intervention, which included follow-up with a primary care provider (PCP) within two weeks of hospital discharge to address non-surgical medical conditions that may have been exacerbated during the hospital stay. A hospital based transitional care clinic bridged medical care for identified patients without an established PCP or whose PCP could not accommodate an appointment until PCP assumption of care. Discharging providers included 11 nurse practitioners and 2 surgery residents; each received a one-on-one educational teaching session and a weekly reminder e-mail through week 9.

RESULTS

A total of 158 vascular surgery patients (low and high-risk) were discharged home over 15 weeks with 30 patients (19%) having an unplanned readmission within 30-days from discharge. Adherence issues with the intervention among staff allowed for the high-risk group to be divided into those who did not receive the intervention versus those who did. The high-risk patients who did not receive the intervention had a higher readmission rate (30.4%) than the high-risk patients who did receive the intervention (21.4%).

CONCLUSIONS

Numerous acute and chronic medical problems were treated at the PCP/transitional care clinic visits, which may have contributed to the reduction in rate of readmissions occurring within 30-days for those patients. Increased usage of the transitional care clinic identified a gap that patients continue to require assistance with establishing care with a PCP and further process change in the future is needed to ensure successful transition for all patients.

Inpatient opioid prescribing patterns and their effect on rehospitalisations: a nested case-control study using data from a Swiss public acute hospital

AIMS OF THE STUDY

Opioid prescriptions have increased in Switzerland, even though current guidelines warn of their harms. If opioids for postoperative analgesia are not tapered before hospital discharge, patients are at risk of adverse events such as constipation, drowsiness, dependence, tolerance and withdrawal. The aim of this study was to investigate and quantify the potential association between opioids prescribed at discharge from hospital and rehospitalisation.

METHODS

We conducted a nested case-control study using routinely collected electronic health records from a Swiss public acute hospital. Cases were patients aged 65 years or older admitted between November 2014 and December 2018, with documented opioid administration on the day of discharge and rehospitalisation within 18 or 30 days after discharge. Each case was matched to five controls for age, sex, year of hospitalisation and Charlson Comorbidity Index. We calculated odds ratios for 18-day and 30-day rehospitalisation based on exposure to opioids using a conditional logistic regression adjusted for potential confounders. Secondary analyses included stratifications into morphine-equivalent doses of <50 mg, 50-89 mg and ≥90 mg, and co-prescriptions of gabapentinoids and benzodiazepines.

RESULTS

Of 22,471 included patients, 3144 rehospitalisations were identified, of which 1698 were 18-day rehospitalisations and 1446 were 30-day rehospitalisations. Documented opioid administration on the day of discharge was associated with 30-day rehospitalisation after adjustment for confounders (adjusted odds ratio 1.48; 95% CI 1.25-1.75, p <0.001), while no difference was observed in the likelihood of 18-day rehospitalisation. The combined prescription of opioids with benzodiazepines or gabapentinoids and morphine-equivalent doses >50 mg were rare.

CONCLUSIONS

Patients receiving opioids on the day of discharge were 48% more likely to be readmitted to hospital within 30 days. Clinicians should aim to discontinue opioids started in hospital before discharge if possible. Patients receiving an opioid prescription should be educated and monitored as part of opioid stewardship programmes.

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.

Machine Learning-Based Prediction of Readmission Risk in Cardiovascular and Cerebrovascular Conditions Using Patient EMR Data

The primary objective of this study was to develop a risk-based readmission prediction model using the EMR data available at discharge. This model was then validated with the LACE plus score. The study cohort consisted of about 310,000 hospital admissions of patients with cardiovascular and cerebrovascular conditions. The EMR data of the patients consisted of lab results, vitals, medications, comorbidities, and admit/discharge settings. These data served as the input to an XGBoost model v1.7.6, which was then used to predict the number of days until the next readmission. Our model achieved remarkable results, with a precision score of 0.74 (±0.03), a recall score of 0.75 (±0.02), and an overall accuracy of approximately 82% (±5%). Notably, the model demonstrated a high accuracy rate of 78.39% in identifying the patients readmitted within 30 days and 80.81% accuracy for those with readmissions exceeding six months. The model was able to outperform the LACE plus score; of the people who were readmitted within 30 days, only 47.70 percent had a LACE plus score greater than 70, and, for people with greater than 6 months, only 10.09 percent had a LACE plus score less than 30. Furthermore, our analysis revealed that the patients with a higher comorbidity burden and lower-than-normal hemoglobin levels were associated with increased readmission rates. This study opens new doors to the world of differential patient care, helping both clinical decision makers and healthcare providers make more informed and effective decisions. This model is comparatively more robust and can potentially substitute the LACE plus score in cardiovascular and cerebrovascular settings for predicting the readmission risk.

Multimodal Machine Learning for Prediction of 30-Day Readmission Risk in Elderly Population

BACKGROUND

Readmission within 30 days is a prevalent issue among elderly patients, linked to unfavorable health outcomes. Our objective was to develop and validate multimodal machine learning models for predicting 30-day readmission risk in elderly patients discharged from internal medicine departments.

METHODS

This was a retrospective cohort study which included elderly patients aged 75 or older, who were hospitalized at the Hadassah Medical Center internal medicine departments between 2014 and 2020. Three machine learning algorithms were developed and employed to predict 30-day readmission risk. The primary measures were predictive model performance scores, specifically area under the receiver operator curve (AUROC), and average precision.

RESULTS

This study included 19,569 admissions. Of them, 3258 (16.65%) resulted in 30-day readmission. Our 3 proposed models demonstrated high accuracy and precision on an unseen test set, with AUROC values of 0.87, 0.89, and 0.93, respectively, and average precision values of 0.76, 0.78, and 0.81. Feature importance analysis revealed that the number of admissions in the past year, history of 30-day readmission, Charlson score, and admission length were the most influential variables. Notably, the natural language processing score, representing the probability of readmission according to a textual-based model trained on social workers' assessment letters during hospitalization, ranked among the top 10 contributing factors.

CONCLUSIONS

Leveraging multimodal machine learning offers a promising strategy for identifying elderly patients who are at high risk for 30-day readmission. By identifying these patients, machine learning models may facilitate the effective execution of preventive actions to reduce avoidable readmission incidents.

Can prediction models for hospital readmission be improved by incorporating patient-reported outcome measures? A systematic review and narrative synthesis

PURPOSE

To investigate the roles, challenges, and implications of using patient-reported outcome measures (PROMs) in predicting the risk of hospital readmissions.

METHODS

We systematically searched four bibliometric databases for peer-reviewed studies published in English between 1 January 2000 and 15 June 2023 and used validated PROMs to predict readmission risks for adult populations. Reported studies were analysed and narratively synthesised in accordance with the CHARMS and PRISMA guidelines.

RESULTS

Of the 2858 abstracts reviewed, 23 studies met predefined eligibility criteria, representing diverse geographic regions and medical specialties. Among those, 19 identified the positive contributions of PROMs in predicting readmission risks. Seven studies utilised generic PROMs exclusively, eleven used generic and condition-specific PROMs, while 5 focussed solely on condition-specific PROMs. Logistic regression was the most used modelling approach, with 13 studies aiming at predicting 30-day all-cause readmission risks. The c-statistic, ranging from 0.54 to 0.84, was reported in 22/23 studies as a measure of model discrimination. Nine studies reported model calibration in addition to c-statistic. Thirteen studies detailed their approaches to dealing with missing data.

CONCLUSION

Our study highlights the potential of PROMs to enhance predictive accuracy in readmission models, while acknowledging the diversity in data collection methods, readmission definitions, and model evaluation approaches. Recognizing that PROMs serve various purposes beyond readmission reduction, our study supports routine data collection and strategic integration of PROMs in healthcare practices to improve patient outcomes. To facilitate comparative analysis and broaden the use of PROMs in the prediction framework, it is imperative to consider the methodological aspects involved.

Analysis of Clinical Criteria for Discharge Among Patients Hospitalized for COVID-19: Development and Validation of a Risk Prediction Model

BACKGROUND

Patients hospitalized with COVID-19 can clinically deteriorate after a period of initial stability, making optimal timing of discharge a clinical and operational challenge.

OBJECTIVE

To determine risks for post-discharge readmission and death among patients hospitalized with COVID-19.

DESIGN

Multicenter retrospective observational cohort study, 2020-2021, with 30-day follow-up.

PARTICIPANTS

Adults admitted for care of COVID-19 respiratory disease between March 2, 2020, and February 11, 2021, to one of 180 US hospitals affiliated with the HCA Healthcare system.

MAIN MEASURES

Readmission to or death at an HCA hospital within 30 days of discharge was assessed. The area under the receiver operating characteristic curve (AUC) was calculated using an internal validation set (33% of the HCA cohort), and external validation was performed using similar data from six academic centers associated with a hospital medicine research network (HOMERuN).

KEY RESULTS

The final HCA cohort included 62,195 patients (mean age 61.9 years, 51.9% male), of whom 4704 (7.6%) were readmitted or died within 30 days of discharge. Independent risk factors for death or readmission included fever within 72 h of discharge; tachypnea, tachycardia, or lack of improvement in oxygen requirement in the last 24 h; lymphopenia or thrombocytopenia at the time of discharge; being ≤ 7 days since first positive test for SARS-CoV-2; HOSPITAL readmission risk score ≥ 5; and several comorbidities. Inpatient treatment with remdesivir or anticoagulation were associated with lower odds. The model's AUC for the internal validation set was 0.73 (95% CI 0.71-0.74) and 0.66 (95% CI 0.64 to 0.67) for the external validation set.

CONCLUSIONS

This large retrospective study identified several factors associated with post-discharge readmission or death in models which performed with good discrimination. Patients 7 or fewer days since test positivity and who demonstrate potentially reversible risk factors may benefit from delaying discharge until those risk factors resolve.

Is it legitimate to use unplanned hospitalizations as a quality indicator for cancer patients? A retrospective French cohort study with special attention to the influence of social deprivation

PURPOSE

Readmission indicators are used around the world to assess the quality of hospital care. We aimed to assess the relevance of this type of indicator in oncology, especially for socially deprived patients. Our objectives were (1) to assess the proportion of unplanned hospitalizations (UHs) in cancer patients, (2) to assess the proportion of UHs that were avoidable, i.e., related to poor care quality, and (3) to analyze cancer patients the effect of patients' deprivation level on the type of UH (avoidable UHs vs. unavoidable UHs).

METHODS

In a French university hospital, we selected all hospitalizations over a year for a random sample of cancer patients. Based on medical records, we identified those among UHs due to avoidable health problems. We assessed the association between social deprivation, home-to-hospital distance, or home-to-general practitioner with the type of UH (avoidable vs. unavoidable) via a multivariate binary logit estimation.

RESULTS

Among 2349 hospitalizations (355 patients), there were 383 UHs (16 %), among which 38% were avoidable. Among UHs, the European Deprivation Index was significantly associated with the risk of avoidable UHs, with a lower risk of avoidable UH for patients with medium or high social deprivation.

CONCLUSION

Our results suggest that the use of UHs rate as a quality indicator is questionable in oncology. Indeed, the majority of UHs were not avoidable. Furthermore, within UHs, those involving patients with medium or high social deprivation are more often unavoidable in comparison with other patients.

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.

The Early HOSPITAL Score to Predict 30-Day Readmission Soon After Hospitalization: a Prospective Multicenter Study

BACKGROUND

The simplified HOSPITAL score is an easy-to-use prediction model to identify patients at high risk of 30-day readmission before hospital discharge. An earlier stratification of this risk would allow more preparation time for transitional care interventions.

OBJECTIVE

To assess whether the simplified HOSPITAL score would perform similarly by using hemoglobin and sodium level at the time of admission instead of discharge.

DESIGN

Prospective national multicentric cohort study.

PARTICIPANTS

In total, 934 consecutively discharged medical inpatients from internal general services.

MAIN MEASURES

We measured the composite of the first unplanned readmission or death within 30 days after discharge of index admission and compared the performance of the simplified score with lab at discharge (simplified HOSPITAL score) and lab at admission (early HOSPITAL score) according to their discriminatory power (Area Under the Receiver Operating characteristic Curve (AUROC)) and the Net Reclassification Improvement (NRI).

KEY RESULTS

During the study period, a total of 3239 patients were screened and 934 included. In total, 122 (13.2%) of them had a 30-day unplanned readmission or death. The simplified and the early versions of the HOSPITAL score both showed very good accuracy (Brier score 0.11, 95%CI 0.10-0.13). Their AUROC were 0.66 (95%CI 0.60-0.71), and 0.66 (95%CI 0.61-0.71), respectively, without a statistical difference (p value 0.79). Compared with the model at discharge, the model with lab at admission showed improvement in classification based on the continuous NRI (0.28; 95%CI 0.08 to 0.48; p value 0.004).

CONCLUSION

The early HOSPITAL score performs, at least similarly, in identifying patients at high risk for 30-day unplanned readmission and allows a readmission risk stratification early during the hospital stay. Therefore, this new version offers a timely preparation of transition care interventions to the patients who may benefit the most.

Association of pharmacologic thromboprophylaxis with clinically relevant bleeding and hospital-acquired anemia in medical inpatients: the risk stratification for hospital-acquired venous thromboembolism in medical patients study

BACKGROUND

Pharmacologic thromboprophylaxis (pTPX) might exacerbate the risk of clinically relevant bleeding (CRB) and hospital-acquired anemia (HAA) in older multimorbid inpatients.

OBJECTIVES

We aimed to evaluate the association of pTPX use with CRB and HAA.

METHODS

We used data from a prospective cohort study conducted in 3 Swiss university hospitals. Adult patients admitted to internal medicine wards with no therapeutic anticoagulation were included. pTPX use was ascertained during hospitalization. Outcomes were in-hospital CRB and HAA. We calculated incidence rates by status of pTPX. We assessed the association of pTPX with CRB using survival analysis and with HAA using logistic regression, adjusted for infection, length of stay, and the International Medical Prevention Registry on Venous Thromboembolism bleeding risk score.

RESULTS

Among 1305 patients (mean age, 63.7 years; 44% women, 90% at low risk of bleeding), 809 (62%) received pTPX. The incidence of CRB was 2.4 per 1000 patient-days and was not significantly higher in patients with pTPX than in those without. We found no significant association between pTPX and CRB. HAA was frequent (20.2%) and higher in patients with pTPX than in those without (23.2% vs 15.3%). The incidence of HAA was 21.2 per 1000 patient-days and did not significantly differ between patients with pTPX and those without. We found an association between pTPX and HAA (adjusted odds ratio, 1.4; 95% CI, 1.0-2.1).

CONCLUSION

Our study confirmed the safety of pTPX in medical inpatients at low risk of bleeding but identified an association between pTPX and HAA. Adherence to guidelines that recommend administering pTPX to medical inpatients at increased venous thromboembolism risk and low bleeding risk is necessary.

A novel risk score predicting 30-day hospital re-admission of patients with acute stroke by machine learning model

BACKGROUND

The 30-day hospital re-admission rate is a quality measure of hospital care to monitor the efficiency of the healthcare system. The hospital re-admission of acute stroke (AS) patients is often associated with higher mortality rates, greater levels of disability and increased healthcare costs. The aim of our study was to identify predictors of unplanned 30-day hospital re-admissions after discharge of AS patients and define an early re-admission risk score (RRS).

METHODS

This observational, retrospective study was performed on AS patients who were discharged between 2014 and 2019. Early re-admission predictors were identified by machine learning models. The performances of these models were assessed by receiver operating characteristic curve analysis.

RESULTS

Of 7599 patients with AS, 3699 patients met the inclusion criteria, and 304 patients (8.22%) were re-admitted within 30 days from discharge. After identifying the predictors of early re-admission by logistic regression analysis, RRS was obtained and consisted of seven variables: hemoglobin level, atrial fibrillation, brain hemorrhage, discharge home, chronic obstructive pulmonary disease, one and more than one hospitalization in the previous year. The cohort of patients was then stratified into three risk categories: low (RRS = 0-1), medium (RRS = 2-3) and high (RRS >3) with re-admission rates of 5%, 8% and 14%, respectively.

CONCLUSIONS

The identification of risk factors for early re-admission after AS and the elaboration of a score to stratify at discharge time the risk of re-admission can provide a tool for clinicians to plan a personalized follow-up and contain healthcare costs.

Increasing illness severity of skilled nursing facility patients over time: Implications for readmission penalties

BACKGROUND

Current financial penalties for rehospitalization of skilled nursing facilities (SNFs) patients are based in part on the studies by Ouslander et al., 2011, and Mor et al., 2010, demonstrating that many SNF hospitalizations were avoidable. With increasing age, complex illness severity, and use of SNFs for subacute rehabilitation, readmission metrics and financial penalties based on previous data may be due for reevaluation.

METHODS

Retrospective electronic medical record (EMR) review of 21,591 admissions and discharges between 2010 and 2019 inclusive. Data extracted included demographics, LACE, Charlson comorbidity index (CCI), and simplified HOSPITAL score parameters. The scores were calculated for the study years from the extracted data. Patients readmitted to the hospital within 30 days were identified.

RESULTS

Mean yearly score of all three indices rose steadily: LACE score 10.76-12.04 (0.43 estimated annual increase, 95% CI [0.39, 0.46]), CCI 4.26-5.05 (0.31 estimated annual increase, 95% CI [0.27, 0.34]), and simplified HOSPITAL score 3.46-4.03 (0.21 estimated annual increase, 95% CI [0.18, 0.24]). The estimated probability of readmission across observed CCI scores ranged from 15.4% to 15.9%, 95% CI bounds (10.8%, 22.7%). The estimated probability of readmission across observed LACE scores ranged from 4.7% to 36.3%, 95% CI bounds (3.4%, 54.7%). The estimated probability of readmission across observed HOSPITAL scores ranged from 5.8% to 54.1%, 95% CI bounds (6.2%, 66.0%).

CONCLUSIONS AND IMPLICATIONS

The study confirms anecdotal experience that the illness acuity of patients admitted to SNFs increased progressively over time and was associated with an increased risk of 30-day readmissions to the hospital. Our study suggests that the use of clinically validated readmission risk assessment tools instead of the Skilled Nursing Facility Value-Based Purchasing Program (SNF VBP) current risk adjustors may be a more accurate reflection of the current illness severity of a facility's patient population at the time of payment adjustment.

Development of Multivariable Prediction Models for the Identification of Patients Admitted to Hospital with an Exacerbation of COPD and the Prediction of Risk of Readmission: A Retrospective Cohort Study using Electronic Medical Record Data

BACKGROUND

Approximately 20% of patients who are discharged from hospital for an acute exacerbation of COPD (AECOPD) are readmitted within 30 days. To reduce this, it is important both to identify all individuals admitted with AECOPD and to predict those who are at higher risk for readmission.

OBJECTIVES

To develop two clinical prediction models using data available in electronic medical records: 1) identifying patients admitted with AECOPD and 2) predicting 30-day readmission in patients discharged after AECOPD.

METHODS

Two datasets were created using all admissions to General Internal Medicine from 2012 to 2018 at two hospitals: one cohort to identify AECOPD and a second cohort to predict 30-day readmissions. We fit and internally validated models with four algorithms.

RESULTS

Of the 64,609 admissions, 3,620 (5.6%) were diagnosed with an AECOPD. Of those discharged, 518 (15.4%) had a readmission to hospital within 30 days. For identification of patients with a diagnosis of an AECOPD, the top-performing models were LASSO and a four-variable regression model that consisted of specific medications ordered within the first 72 hours of admission. For 30-day readmission prediction, a two-variable regression model was the top performing model consisting of number of COPD admissions in the previous year and the number of non-COPD admissions in the previous year.

CONCLUSION

We generated clinical prediction models to identify AECOPDs during hospitalization and to predict 30-day readmissions after an acute exacerbation from a dataset derived from available EMR data. Further work is needed to improve and externally validate these models.

Machine learning vs. conventional methods for prediction of 30-day readmission following percutaneous mitral edge-to-edge repair

BACKGROUND

Identifying predictors of readmissions after mitral valve transcatheter edge-to-edge repair (MV-TEER) is essential for risk stratification and optimization of clinical outcomes.

AIMS

We investigated the performance of machine learning [ML] algorithms vs. logistic regression in predicting readmissions after MV-TEER.

METHODS

We utilized the National-Readmission-Database to identify patients who underwent MV-TEER between 2015 and 2018. The database was randomly split into training (70 %) and testing (30 %) sets. Lasso regression was used to remove non-informative variables and rank informative ones. The top 50 informative predictors were tested using 4 ML models: ML-logistic regression [LR], Naive Bayes [NB], random forest [RF], and artificial neural network [ANN]/For comparison, we used a traditional statistical method (principal component analysis logistic regression PCA-LR).

RESULTS

A total of 9425 index hospitalizations for MV-TEER were included. Overall, the 30-day readmission rate was 14.6 %, and heart failure was the most common cause of readmission (32 %). The readmission cohort had a higher burden of comorbidities (median Elixhauser score 5 vs. 3) and frailty score (3.7 vs. 2.9), longer hospital stays (3 vs. 2 days), and higher rates of non-home discharges (17.4 % vs. 8.5 %). The traditional PCA-LR model yielded a modest predictive value (area under the curve [AUC] 0.615 [0.587-0.644]). Two ML algorithms demonstrated superior performance than the traditional PCA-LR model; ML-LR (AUC 0.692 [0.667-0.717]), and NB (AUC 0.724 [0.700-0.748]). RF (AUC 0.62 [0.592-0.677]) and ANN (0.65 [0.623-0.677]) had modest performance.

CONCLUSION

Machine learning algorithms may provide a useful tool for predicting readmissions after MV-TEER using administrative databases.

Clinical outcome prediction using observational supervision with electronic health records and audit logs

OBJECTIVE

Audit logs in electronic health record (EHR) systems capture interactions of providers with clinical data. We determine if machine learning (ML) models trained using audit logs in conjunction with clinical data ("observational supervision") outperform ML models trained using clinical data alone in clinical outcome prediction tasks, and whether they are more robust to temporal distribution shifts in the data.

MATERIALS AND METHODS

Using clinical and audit log data from Stanford Healthcare, we trained and evaluated various ML models including logistic regression, support vector machine (SVM) classifiers, neural networks, random forests, and gradient boosted machines (GBMs) on clinical EHR data, with and without audit logs for two clinical outcome prediction tasks: major adverse kidney events within 120 days of ICU admission (MAKE-120) in acute kidney injury (AKI) patients and 30-day readmission in acute stroke patients. We further tested the best performing models using patient data acquired during different time-intervals to evaluate the impact of temporal distribution shifts on model performance.

RESULTS

Performance generally improved for all models when trained with clinical EHR data and audit log data compared with those trained with only clinical EHR data, with GBMs tending to have the overall best performance. GBMs trained with clinical EHR data and audit logs outperformed GBMs trained without audit logs in both clinical outcome prediction tasks: AUROC 0.88 (95% CI: 0.85-0.91) vs. 0.79 (95% CI: 0.77-0.81), respectively, for MAKE-120 prediction in AKI patients, and AUROC 0.74 (95% CI: 0.71-0.77) vs. 0.63 (95% CI: 0.62-0.64), respectively, for 30-day readmission prediction in acute stroke patients. The performance of GBM models trained using audit log and clinical data degraded less in later time-intervals than models trained using only clinical data.

CONCLUSION

Observational supervision with audit logs improved the performance of ML models trained to predict important clinical outcomes in patients with AKI and acute stroke, and improved robustness to temporal distribution shifts.

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.

Risk factors for medication-related short-term readmissions in adults - a scoping review

BACKGROUND

Hospital readmissions due to medication-related problems occur frequently, burdening patients and caregivers emotionally and straining health care systems economically. In times of limited health care resources, interventions to mitigate the risk of medication-related readmissions should be prioritized to patients most likely to benefit. Focusing on general internal medicine patients, this scoping review aims to identify risk factors associated with drug-related 30-day hospital readmissions.

METHODS

We began by searching the Medline, Embase, and CINAHL databases from their inception dates to May 17, 2022 for studies reporting risk factors for 30-day drug-related readmissions. We included all peer-reviewed studies, while excluding literature reviews, conference abstracts, proceeding papers, editorials, and expert opinions. We also conducted backward citation searches of the included articles. Within the final sample, we analyzed the types and frequencies of risk factors mentioned.

RESULTS

After deduplication of the initial search results, 1159 titles and abstracts were screened for full-text adjudication. We read 101 full articles, of which we included 37. Thirteen more were collected via backward citation searches, resulting in a final sample of 50 articles. We identified five risk factor categories: (1) patient characteristics, (2) medication groups, (3) medication therapy problems, (4) adverse drug reactions, and (5) readmission diagnoses. The most commonly mentioned risk factors were polypharmacy, prescribing problems-especially underprescribing and suboptimal drug selection-and adherence issues. Medication groups associated with the highest risk of 30-day readmissions (mostly following adverse drug reactions) were antithrombotic agents, insulin, opioid analgesics, and diuretics. Preventable medication-related readmissions most often reflected prescribing problems and/or adherence issues.

CONCLUSIONS

This study's findings will help care teams prioritize patients for interventions to reduce medication-related hospital readmissions, which should increase patient safety. Further research is needed to analyze surrogate social parameters for the most common drug-related factors and their predictive value regarding medication-related readmissions.

Development and validation of predictive models for unplanned hospitalization in the Basque Country: analyzing the variability of non-deterministic algorithms

BACKGROUND

The progressive ageing in developed countries entails an increase in multimorbidity. Population-wide predictive models for adverse health outcomes are crucial to address these growing healthcare needs. The main objective of this study is to develop and validate a population-based prognostic model to predict the probability of unplanned hospitalization in the Basque Country, through comparing the performance of a logistic regression model and three families of machine learning models.

METHODS

Using age, sex, diagnoses and drug prescriptions previously transformed by the Johns Hopkins Adjusted Clinical Groups (ACG) System, we predict the probability of unplanned hospitalization in the Basque Country (2.2 million inhabitants) using several techniques. When dealing with non-deterministic algorithms, comparing a single model per technique is not enough to choose the best approach. Thus, we conduct 40 experiments per family of models - Random Forest, Gradient Boosting Decision Trees and Multilayer Perceptrons - and compare them to Logistic Regression. Models' performance are compared both population-wide and for the 20,000 patients with the highest predicted probabilities, as a hypothetical high-risk group to intervene on.

RESULTS

The best-performing technique is Multilayer Perceptron, followed by Gradient Boosting Decision Trees, Logistic Regression and Random Forest. Multilayer Perceptrons also have the lowest variability, around an order of magnitude less than Random Forests. Median area under the ROC curve, average precision and positive predictive value range from 0.789 to 0.802, 0.237 to 0.257 and 0.485 to 0.511, respectively. For Brier Score the median values are 0.048 for all techniques. There is some overlap between the algorithms. For instance, Gradient Boosting Decision Trees perform better than Logistic Regression more than 75% of the time, but not always.

CONCLUSIONS

All models have good global performance. The only family that is consistently superior to Logistic Regression is Multilayer Perceptron, showing a very reliable performance with the lowest variability.

Interventions to Reduce Hospital Readmissions in Older African Americans: A Systematic Review of Studies Including African American Patients

OBJECTIVES

This systematic review aims to summarize interventions that effectively reduced hospital readmission rates for African Americans (AAs) aged 65 and older.

METHODS

The Preferred Reporting Items for Systematic Reviews and Meta-Analyses guidelines were followed for this review. Studies were identified by searching PubMed for clinical trials on reducing hospital readmission among older patients published between 1 January 1990 and 31 January 2020. Eligibility criteria for the included studies were mean or median age ≥ 65 years, AAs included in the study, randomized clinical trial or quasi-experimental design, presence of an intervention, and hospital readmission as an outcome.

RESULTS

There were 5270 articles identified and 11 were included in the final review based on eligibility criteria. The majority of studies were conducted in academic centers, were multi-center trials, and included over 200 patients, and 6-90% of participants were older AAs. The length of intervention ranged from 1 week to over a year, with readmission assessed between 30 days and 1 year. Four studies which reported interventions that significantly reduced readmissions included both inpatient (e.g., discharge planning prior to discharge) and outpatient care components (e.g., follow-ups after discharge), and the majority used a multifaceted approach.

CONCLUSION

Findings from the review suggest successful interventions to reduce readmissions among AAs aged 65 and older should include inpatient and outpatient care components at a minimum. This systematic review showed limited evidence of interventions successfully decreasing readmission in older AAs, suggesting a need for research in the area to reduce readmission disparities and improve overall health.

Predicting Colorectal Surgery Readmission Risk: a Surgery-Specific Predictive Model

Most current predictive models for risk of readmission were primarily designed from non-surgical patients and often utilize administrative data alone. Models built upon comprehensive data sources specific to colorectal surgery may be key to implementing interventions aimed at reducing readmissions. This study aimed to develop a predictive model for risk of 30-day readmission specific to colorectal surgery patients including administrative, clinical, laboratory, and socioeconomic status (SES) data. Patients admitted to the colorectal surgery service who underwent surgery and were discharged from an academic tertiary hospital between 2017 and 2019 were included. A total of 1549 patients met eligibility criteria for this retrospective split-sample cohort study. The 30-day readmission rate of the cohort was 19.62%. A multivariable logistic regression was developed (C=0.70, 95% CI 0.61-0.73), which outperformed two internationally used readmission risk prediction indices (C=0.58, 95% CI 0.52-0.65) and (C=0.60, 95% CI 0.53-0.66). Tailored surgery-specific readmission models with comprehensive data sources outperform the most used readmission indices in predicting 30-day readmission in colorectal surgery patients. Model performance is improved by using more comprehensive datasets that include administrative and socioeconomic details about a patient, as well as clinical information used for decision-making around the time of discharge.

Effectiveness of Transition Care Intervention Targeted to High-Risk Patients to Reduce Readmissions: Study Protocol for the TARGET-READ Multicenter Randomized-Controlled Trial

Hospital readmissions within 30 days represent a burden for the patients and the entire health care system. Improving the care around hospital discharge period could decrease the risk of avoidable readmissions. We describe the methods of a trial that aims to evaluate the effect of a structured multimodal transitional care intervention targeted to higher-risk medical patients on 30-day unplanned readmissions and death. The TARGET-READ study is an investigator-initiated, pragmatic single-blinded randomized multicenter controlled trial with two parallel groups. We include all adult patients at risk of hospital readmission based on a simplified HOSPITAL score of ≥4 who are discharged home or nursing home after a hospital stay of one day or more in the department of medicine of the four participating hospitals. The patients randomized to the intervention group will receive a pre-discharge intervention by a study nurse with patient education, medication reconciliation, and follow-up appointment with their referring physician. They will receive short follow-up phone calls at 3 and 14 days after discharge to ensure medication adherence and follow-up by the ambulatory care physician. A blind study nurse will collect outcomes at 1 month by phone call interview. The control group will receive usual care. The TARGET-READ study aims to increase the knowledge about the efficacy of a bundled intervention aimed at reducing 30-day hospital readmission or death in higher-risk medical patients.

Evaluation, Description and Magnitude of Readmission Phenomenon in Azienda Ospedaliero Universitaria Pisana (AOUP) for Chronic-Degenerative Diseases in the Period 2018-2021

BACKGROUND

Readmissions are hospitalizations following a previous hospitalization (called index hospitalization) of the same patient that occurred in the same facility or nursing home. They may be a consequence of the progression of the natural history of a disease, but they may also reveal a previous suboptimal stay, or ineffective management of the underlying clinical condition. Preventing avoidable readmissions has the potential to improve both a patient's quality of life, by avoiding exposure to the risks of re-hospitalization, and the financial well-being of health care systems.

METHODS

We investigated the magnitude of 30 day repeat hospitalizations for the same Major Diagnostic Category (MDC) in the Azienda Ospedaliero Universitaria Pisana (AOUP) over the period from 2018 to 2021. Records were divided into only admissions, index admissions and repeated admission. The length of the stay of all groups was compared using analysis of variance and subsequent multi-comparison tests.

RESULTS

Results showed a reduction in readmissions over the period examined (from 5.36% in 2018 to 4.46% in 2021), likely due to reduced access to care during the COVID-19 pandemic. We also observed that readmissions predominantly affect the male sex, older age groups, and patients with medical Diagnosis Related Groups (DRGs). The length of stay of readmissions was longer than that of index hospitalization (difference of 1.57 days, 95% CI 1.36-1.78 days, p < 0.001). The length of stay of index hospitalization is longer than that of single hospitalization (difference of 0.62 days, 95% CI 0.52-0.72 days, p < 0.001).

CONCLUSIONS

A patient who goes for readmission thus has an overall hospitalization duration of almost two and a half times the length of the stay of a patient with single hospitalization, considering both index hospitalization and readmission. This represents a heavy use of hospital resources, about 10,200 more inpatient days than single hospitalizations, corresponding to a 30-bed ward working with an occupancy rate of 95%. Knowledge of readmissions is an important piece of information in health planning and a useful tool for monitoring the quality of models of patient care.

Predictors for Unplanned Readmissions within 18 Days after Hospital Discharge: a Retrospective Cohort Study

Since the introduction of the reimbursement system based on diagnosis-related groups (DRG) in Swiss hospitals in 2012, most readmissions occurring within 18 days and appertaining to the same major diagnostic category (MDC) are merged and thus often reimbursed to a lesser extent. While readmissions reflect increased distress for patients and their relatives, the causes are mainly patient-related and difficult to influence. However, it may be possible to identify cases at higher risk for readmission. Therefore, the aim of this study was to find predictors for early readmissions in the same MDC, to identify high-risk index hospitalizations and possibly prevent unnecessary readmissions. The data of all patients admitted to the Clinic of Internal Medicine at the University Hospital of Basel, Switzerland, hospitalized for longer than 24 hours during the pre-DRG period between October 2009 and September 2010 were retrospectively collected. Data were examined for predictors of unplanned readmission within 18 days under the same MDC ('relevant readmission') by means of logistic regression. 7479 patients (median age 67.8 years, 56% male) were admitted to the Clinic of Internal Medicine, with 232 patients (3.1%) being readmitted at least once. Logistic regression revealed male sex (p =0.035) and a high number of prescribed drugs at discharge (p <0.005) as patient-related predictors. The MDCs respiratory system, cardiovascular system, and gastrointestinal/hepatobiliary system were identified as high-risk categories (each p <0.005). Age and length of index hospital stay added no significant explanatory value to the regression model. Unplanned readmissions under the same MDC within 18 days were infrequent and not related to patients' age or length of hospital stay. Overall, multimorbid patients, and hospitalizations regarding the cardiovascular, respiratory, or gastrointestinal system appear to be most at risk and should therefore be specifically targeted in the prevention of early readmissions.

[Predictors for Early Unplanned Readmissions]

Predictors for Early Unplanned Readmissions Abstract. Unplanned rehospitalizations represent a major burden for patients, their relatives and the healthcare system. Since the introduction of the SwissDRG in 2012, financial incentives for hospitals have been promoted to forestall readmissions. Not every patient is at risk for rehospitalization. Affected patients can be identified by predictors from various areas in order to implement adequate interventions and avoid readmissions. Predictors can be directly related to patients as in the case of polypharmacy, multiple comorbidities or related to gender, but also provider-related and system-related. Early follow-up visits or a pre-discharge medication review are cited as effective interventions.

Evaluating Social Determinants of Health in a Mobile Integrated Healthcare-Community Paramedicine Program

In 2018, the University of Maryland Medical Center and the Baltimore City Fire Department implemented a community paramedicine program to help medically or socially complex patients transition from hospital to home and avoid hospital utilization. This study describes how patients' social determinants of health (SDoH) needs were identified, and measures the association between needs and hospital utilization. SDoH needs were categorized into ten domains. Multinomial logistic regression was used to measure association between identified SDoH domains and predicted risk of readmission. Poisson regression was used to measure association between SDoH domains and actual 30-day hospital utilization. The most frequently identified SDoH needs were in the Coordination of Healthcare (37.7%), Durable Medical Equipment (18.8%), and Medication (16.3%) domains. Compared with low-risk patients, patients with an intermediate risk of readmission were more likely to have needs within the Coordination of Healthcare (RRR [95% CI] 1.12 [1.01, 1.24], p = 0.032) and Durable Medical Equipment (RRR = 1.13 [1.00, 1.27], p = 0.046) domains. Patients with the highest risk for readmission were more likely to have needs in the Utilities domain (RRR = 1.76 [0.97, 3.19], p = 0.063). Miscellaneous domain needs, such as requiring a social security card, were associated with increased 30-day hospital utilization (IRR = 1.23 [0.96, 1.57], p = 0.095). SDoH needs within the Coordination of Healthcare, Durable Medical Equipment, and Utilities domains were associated with higher predicted 30-day readmission, while identification documentation and social services needs were associated with actual readmission. These results suggest where to allocate resources to effectively diminish hospital utilization.

Predicting 30-day all-cause hospital readmission using multimodal spatiotemporal graph neural networks

Reduction in 30-day readmission rate is an important quality factor for hospitals as it can reduce the overall cost of care and improve patient post-discharge outcomes. While deep-learning-based studies have shown promising empirical results, several limitations exist in prior models for hospital readmission prediction, such as: (a) only patients with certain conditions are considered, (b) do not leverage data temporality, (c) individual admissions are assumed independent of each other, which ignores patient similarity, (d) limited to single modality or single center data. In this study, we propose a multimodal, spatiotemporal graph neural network (MM-STGNN) for prediction of 30-day all-cause hospital readmission, which fuses in-patient multimodal, longitudinal data and models patient similarity using a graph. Using longitudinal chest radiographs and electronic health records from two independent centers, we show that MM-STGNN achieved an area under the receiver operating characteristic curve (AUROC) of 0.79 on both datasets. Furthermore, MM-STGNN significantly outperformed the current clinical reference standard, LACE+ (AUROC=0.61), on the internal dataset. For subset populations of patients with heart disease, our model significantly outperformed baselines, such as gradient-boosting and Long Short-Term Memory models (e.g., AUROC improved by 3.7 points in patients with heart disease). Qualitative interpretability analysis indicated that while patients' primary diagnoses were not explicitly used to train the model, features crucial for model prediction may reflect patients' diagnoses. Our model could be utilized as an additional clinical decision aid during discharge disposition and triaging high-risk patients for closer post-discharge follow-up for potential preventive measures.

Risk factors for hospital outcomes in pulmonary embolism: A retrospective cohort study

Background

Pulmonary embolism (PE) is not only a life-threatening disease but also a public health issue with significant economic burden. The aim of the study was to identify factors-including the role of primary care-that predict length of hospital stay (LOHS), mortality and re-hospitalization within 6 months of patients admitted for PE.

Method

A retrospective cohort study was conducted with patients presenting to a Swiss public hospital with PE diagnosed at the hospital between November 2018 and October 2020. Multivariable logistic and zero-truncated negative binomial regression analyses were performed to assess risk factors for mortality, re-hospitalization and LOHS. Primary care variables encompassed whether patients were sent by their general practitioner (GP) to the emergency department and whether a GP follow-up assessment after discharge was recommended. Further analyzed variables were pulmonary embolism severity index (PESI) score, laboratory values, comorbidities, and medical history.

Results

A total of 248 patients were analyzed (median 73 years and 51.6% females). On average patients were hospitalized for 5 days (IQR 3-8). Altogether, 5.6% of these patients died in hospital, and 1.6% died within 30 days (all-cause mortality), 21.8% were re-hospitalized within 6 months. In addition to high PESI scores, we detected that, patients with an elevated serum troponin, as well as with diabetes had a significantly longer hospital stay. Significant risk factors for mortality were elevated NT-proBNP and PESI scores. Further, high PESI score and LOHS were associated with re-hospitalization within 6 months. PE patients who were sent to the emergency department by their GPs did not show improved outcomes. Follow-up with GPs did not have a significant effect on re-hospitalization.

Conclusion

Defining the factors that are associated with LOHS in patients with PE has clinical implications and may help clinicians to allocate adequate resources in the management of these patients. Serum troponin and diabetes in addition to PESI score might be of prognostic use for LOHS. In this single-center cohort study, PESI score was not only a valid predictive tool for mortality but also for long-term outcomes such as re-hospitalization within 6 months.

Accuracy of the Simplified HOSPITAL Score to Predict Nonelective Readmission in a Brazilian Tertiary Care Public Teaching Hospital

BACKGROUND AND OBJECTIVES

Predictive models to identify patients at high risk of readmission have gained the attention of health care teams, which have focused the strategies to reduce unnecessary readmissions on the "at-risk" patients. The HOSPITAL score includes 7 predictor variables with a C-statistic of 0.70 or more when applied to international datasets. Its simplified version retains a C-statistic at around the same level, but only incipient external validation has been attempted to date. The primary objective of this study was to evaluate the prognostic accuracy of the simplified HOSPITAL score to predict nonelective hospital readmissions in a tertiary care public teaching hospital in Brazil.

METHODS

We used a retrospective cohort that included all patients discharged from the internal medicine service of a Brazilian tertiary care public teaching hospital in 2018. We excluded patients who died before index discharge, were transferred to another institution, left against medical advice, or were readmitted electively. We calculated the simplified HOSPITAL score for each admission, and admissions were divided into low (0-4 points) or high risk (≥ 5 points) of nonelective 30-day readmission. We estimated accuracy, area under the receiver operating characteristic curve (AUC), and observed/expected (O/E) readmission ratio; the latter using the mid-P exact test with Miettinen's modification at a 95% confidence interval (CI). A P value < .05 was considered significant.

RESULTS

A total of 4472 hospital discharges were analyzed during the study period after application of the exclusion criteria. The nonelective 30-day readmission rate was 14.0% (n = 625). Of all patients discharged, 3173 (71.0%) were considered to be at low risk and 1299 (29.0%) at high risk of readmission according to the simplified HOSPITAL score. The AUC was 0.68 (95% CI: 0.66-0.71; P < .001). The nonelective 30-day readmission rate was 9.2% in the low-risk group (expected: 9.2%; O/E: 1.0 [95% CI: 0.89-1.12]) and 25.7% in the high-risk group (expected: 27.2%; O/E: 0.95 [95% CI: 0.85-1.05]) ( P < .001). At a cut-off of 5 points, the score had a sensitivity of 53.4%, specificity of 74.9%, positive predictive value of 25.7%, and negative predictive value (NPV) of 90.8%.

CONCLUSIONS

The parameters of the score were almost identical to the original study, with better applicability to exclude low-risk patients given its high NPV. Additional adjustments are still needed for better applicability in daily clinical practice.

Early prediction of 30- and 14-day all-cause unplanned readmissions

BACKGROUND

An unplanned readmission is a dual metric for both the cost and quality of medical care.

METHODS

We employed the random forest (RF) method to build a prediction model using a large dataset from patients' electronic health records (EHRs) from a medical center in Taiwan. The discrimination abilities between the RF and regression-based models were compared using the areas under the ROC curves (AUROC).

RESULTS

When compared with standardized risk prediction tools, the RF constructed using data readily available at admission had a marginally yet significantly better ability to identify high-risk readmissions within 30 and 14 days without compromising sensitivity and specificity. The most important predictor for 30-day readmissions was directly related to the representing factors of index hospitalization, whereas for 14-day readmissions the most important predictor was associated with a higher chronic illness burden.

CONCLUSIONS

Identifying dominant risk factors based on index admission and different readmission time intervals is crucial for healthcare planning.

Hospital Admission and Discharge: Lessons Learned from a Large Programme in Southwest Germany

Introduction

In the context of a GP-based care programme, we implemented an admission, discharge and follow-up programme.

Description

The VESPEERA programme consists of three sets of components: pre-admission interventions, in-hospital interventions and post-discharge interventions. It was aimed at all patients with a hospital stay participating in the GP-based care programme and was implemented in 7 hospitals and 72 general practices in southwest Germany using a range of strategies. Its' effectiveness was evaluated using readmissions within 90 days after discharge as primary outcome. Questionnaires with staff were used to explore the implementation process.

Discussion

A statistically significant effect was not found, but the effect size was similar to other interventions. Intervention fidelity was low and contextual factors affecting the implementation, amongst others, were available resources, external requirements such as legal regulations and networking between care providers. Lessons learned were derived that can aid to inform future political or scientific initiatives.

Conclusion

Structured information transfer at hospital admission and discharge makes sense but the added value in the context of a GP-based programme seems modest. Primary care teams should be involved in pre- and post-hospital care.

Development and Validation of an Integrated Suite of Prediction Models for All-Cause 30-Day Readmissions of Children and Adolescents Aged 0 to 18 Years

IMPORTANCE

Readmission is often considered a hospital quality measure, yet no validated risk prediction models exist for children.

OBJECTIVE

To develop and validate a tool identifying patients before hospital discharge who are at risk for subsequent readmission, applicable to all ages.

DESIGN, SETTING, AND PARTICIPANTS

This population-based prognostic analysis used electronic health record-derived data from a freestanding children's hospital from January 1, 2016, to December 31, 2019. All-cause 30-day readmission was modeled using 3 years of discharge data. Data were analyzed from June 1 to November 30, 2021.

MAIN OUTCOMES AND MEASURES

Three models were derived as a complementary suite to include (1) children 6 months or older with 1 or more prior hospitalizations within the last 6 months (recent admission model [RAM]), (2) children 6 months or older with no prior hospitalizations in the last 6 months (new admission model [NAM]), and (3) children younger than 6 months (young infant model [YIM]). Generalized mixed linear models were used for all analyses. Models were validated using an additional year of discharges.

RESULTS

The derivation set contained 29 988 patients with 48 019 hospitalizations; 50.1% of these admissions were for children younger than 5 years and 54.7% were boys. In the derivation set, 4878 of 13 490 admissions (36.2%) in the RAM cohort, 2044 of 27 531 (7.4%) in the NAM cohort, and 855 of 6998 (12.2%) in the YIM cohort were followed within 30 days by a readmission. In the RAM cohort, prior utilization, current or prior procedures indicative of severity of illness (transfusion, ventilation, or central venous catheter), commercial insurance, and prolonged length of stay (LOS) were associated with readmission. In the NAM cohort, procedures, prolonged LOS, and emergency department visit in the past 6 months were associated with readmission. In the YIM cohort, LOS, prior visits, and critical procedures were associated with readmission. The area under the receiver operating characteristics curve was 83.1 (95% CI, 82.4-83.8) for the RAM cohort, 76.1 (95% CI, 75.0-77.2) for the NAM cohort, and 80.3 (95% CI, 78.8-81.9) for the YIM cohort.

CONCLUSIONS AND RELEVANCE

In this prognostic study, the suite of 3 prediction models had acceptable to excellent discrimination for children. These models may allow future improvements in tailored discharge preparedness to prevent high-risk readmissions.

Using Machine Learning to Predict Likelihood and Cause of Readmission After Hospitalization for Chronic Obstructive Pulmonary Disease Exacerbation

Background

Chronic obstructive pulmonary disease (COPD) is a leading cause of hospital readmissions. Few existing tools use electronic health record (EHR) data to forecast patients’ readmission risk during index hospitalizations.

Objective

We used machine learning and in-hospital data to model 90-day risk for and cause of readmission among inpatients with acute exacerbations of COPD (AE-COPD).

Design

Retrospective cohort study.

Participants

Adult patients admitted for AE-COPD at the University of Chicago Medicine between November 7, 2008 and December 31, 2018 meeting International Classification of Diseases (ICD)-9 or −10 criteria consistent with AE-COPD were included.

Methods

Random forest models were fit to predict readmission risk and respiratory-related readmission cause. Predictor variables included demographics, comorbidities, and EHR data from patients’ index hospital stays. Models were derived on 70% of observations and validated on a 30% holdout set. Performance of the readmission risk model was compared to that of the HOSPITAL score.

Results

Among 3238 patients admitted for AE-COPD, 1103 patients were readmitted within 90 days. Of the readmission causes, 61% (n = 672) were respiratory-related and COPD (n = 452) was the most common. Our readmission risk model had a significantly higher area under the receiver operating characteristic curve (AUROC) (0.69 [0.66, 0.73]) compared to the HOSPITAL score (0.63 [0.59, 0.67]; p = 0.002). The respiratory-related readmission cause model had an AUROC of 0.73 [0.68, 0.79].

Conclusion

Our models improve on current tools by predicting 90-day readmission risk and cause at the time of discharge from index admissions for AE-COPD. These models could be used to identify patients at higher risk of readmission and direct tailored post-discharge transition of care interventions that lower readmission risk.

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.

Prediction of 30-day risk of acute exacerbation of readmission in elderly patients with COPD based on support vector machine model

Background

Acute exacerbation of chronic obstructive pulmonary disease (COPD) is an important event in the process of disease management. Early identification of high-risk groups for readmission and appropriate measures can avoid readmission in some groups, but there is still a lack of specific prediction tools. The predictive performance of the model built by support vector machine (SVM) has been gradually recognized by the medical field. This study intends to predict the risk of acute exacerbation of readmission in elderly COPD patients within 30 days by SVM, in order to provide scientific basis for screening and prevention of high-risk patients with readmission.

Methods

A total of 1058 elderly COPD patients from the respiratory department of 13 general hospitals in Ningxia region of China from April 2019 to August 2020 were selected as the study subjects by convenience sampling method, and were followed up to 30 days after discharge. Discuss the influencing factors of patient readmission, and built four kernel function models of Linear-SVM, Polynomial-SVM, Sigmoid-SVM and RBF-SVM based on the influencing factors. According to the ratio of training set and test set 7:3, they are divided into training set samples and test set samples, Analyze and Compare the prediction efficiency of the four kernel functions by the precision, recall, accuracy, F1 index and area under the ROC curve (AUC).

Results

Education level, smoking status, coronary heart disease, hospitalization times of acute exacerbation of COPD in the past 1 year, whether long-term home oxygen therapy, whether regular medication, nutritional status and seasonal factors were the influencing factors for readmission. The training set shows that Linear-SVM, Polynomial-SVM, Sigmoid-SVM and RBF-SVM precision respectively were 69.89, 78.07, 79.37 and 84.21; Recall respectively were 50.78, 69.53, 78.74 and 88.19; Accuracy respectively were 83.92, 88.69, 90.81 and 93.82; F1 index respectively were 0.59, 0.74, 0.79 and 0.86; AUC were 0.722, 0.819, 0.866 and 0.918. Test set precision respectively were86.36, 87.50, 80.77 and 88.24; Recall respectively were51.35, 75.68, 56.76 and 81.08; Accuracy respectively were 85.11, 90.78, 85.11 and 92.20; F1 index respectively were 0.64, 0.81, 0.67 and 0.85; AUC respectively were 0.742, 0.858, 0.759 and 0.885.

Conclusions

This study found the factors that may affect readmission, and the SVM model constructed based on the above factors achieved a certain predictive effect on the risk of readmission, which has certain reference value.

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.

Comparison of LACE and HOSPITAL Readmission Risk Scores for CMS Target and Nontarget Conditions

This study evaluated the utility and performance of the LACE index and HOSPITAL score with consideration of the type of diagnoses and assessed the accuracy of these models for predicting readmission risks in patient cohorts from 2 large academic medical centers. Admissions to 2 hospitals from 2011 to 2015, derived from the Vizient Clinical Data Base and regional health information exchange, were included in this study (291 886 encounters). Models were assessed using Bayesian information criterion and area under the receiver operating characteristic curve. They were compared in CMS diagnosis-based cohorts and in 2 non-CMS cancer diagnosis-based cohorts. Overall, both models for readmission risk performed well, with LACE performing slightly better (area under the receiver operating characteristic curve 0.73 versus 0.69; P ≤ 0.001). HOSPITAL consistently outperformed LACE among 4 CMS target diagnoses, lung cancer, and colon cancer. Both LACE and HOSPITAL predict readmission risks well in the overall population, but performance varies by salient, diagnosis-based risk factors.

A hybrid approach for risk stratification and predictive modelling of 30-days unplanned readmission of comorbid patients with diabetes

OBJECTIVES

When comorbid patients with diabetes have 30-days Unplanned Readmission (URA), they attract more burdens to the healthcare system due to increased cost of treatment, insurance penalties to hospitals, and unavailable bed spaces for new patients. This paper, therefore, aims to develop a risk stratification and a predictive model for identifying patients at various risk severities of 30-days URA.

METHODS

Patients records of comorbid patients with diabetes treated with different medications were collected from different hospitals and analysed with Principal Component Analysis (PCA) and Multivariate Logistic Regression (MLR) to determine the probability of 30-days URA, which is classified into very low, low, moderate, high, and very high. The risk classes are later modelled using ANOVA feature selection to identify the optimal predictors and the best random forest (RF) hyperparameters for 30-days URA risk stratification. Synthetic Minority Oversampling Technique (SMOTE) was used to balance the risk classes while employing a10-fold cross-validation.

RESULTS

After analysing 17,933 episodes of comorbid diabetes patients' treatment, 10.71% are identified to have 30-days URA with 61.95% of patients at moderate risk, 35.5% at low risk, 2.25% at very low risk, 0.37% at high risk, and 0.08% at very high risk. The predictive accuracy of RF is: - recall: 0.947 ± 0.035, precision: 0.951 ± 0.033, F1-score: 0.947 ± 0.035, AUC: 0.994 ± 0.007 and Average Precision (AP) of 0.99. The predictive accuracies of the risk classes measured with F1-score are: - very low: 0.985 ± 0.019, low risk: 0.871 ± 0.079, moderate: 0.881 ± 0.093, high: 0.999 ± 0.003, and very high: 1.000 ± 0.00.

CONCLUSION

This study identified the risk severity of comorbid patients with diabetes treated with different medications, making it easier to identify those that will be prioritized on hospitalization to minimize 30-days URA. By relying on the technique developed, vulnerable patients to 30-days URA can be given better post-discharge monitoring to build critical self-management skills that will minimize the cost of diabetes care and improve the quality of life.

Associations between post-discharge medical consultations and 30-day unplanned hospital readmission: A prospective observational cohort study

BACKGROUND

The period following hospital discharge is one of significant vulnerability. Little is known about the relationship between post-discharge healthcare use and the risk of readmission.

OBJECTIVES

To explore associations between medical consultations and other healthcare use parameters and the risk of 30-day unplanned hospital readmission.

METHODS

Between July 2017 and March 2018, we monitored all adult internal medicine patients for 30 days after their discharge from four mid-sized hospitals. Using follow-up telephone calls, we assessed their post-discharge healthcare use: consultations with general practitioners (GPs) and specialist physicians, emergency room (ER) visits, and home visits by nurses. The binary outcome was defined as any unplanned hospital readmission within 30 days of discharge, and this was analyzed using logistic regression.

RESULTS

Of 934 patients discharged, 111 (12%) experienced at least one unplanned hospital readmission within 30 days. Attending at least one GP consultation decreased the odds of readmission by half (adjusted OR: 0.5; 95%CI: 0.3-0.7), whereas attending at least one specialist consultation doubled those odds (aOR: 2.0; 95%CI: 1.2-3.3). GP consultations also reduced the odds of the combined risk of an ER visit or unplanned hospital readmission (aOR: 0.5; 95%CI: 0.3-0.7). ER visits were also associated with a higher readmission risk after adjusting for confounding factors (aOR: 10.0; 95%CI: 6.0-16.8).

CONCLUSION

GP consultations were associated with fewer ER visits and unplanned hospital readmissions.

Evaluation of a patient-centered integrated care program for individuals with frequent hospital readmissions and multimorbidity

Managing patients with multimorbidity and frequent hospital readmissions is a challenge. Integrated care programs that consider their needs and allow for personalized care are necessary for their early identification and management. This work aims to describe these patients' clinical characteristics and evaluate a program designed to reducing readmissions. This prospective study analyzed all patients with ≥ 3 admissions to a medical department in the previous year who were included in the Internal Medicine Department chronic care program at the Lucus Augusti University Hospital (Lugo, Spain) between April 1, 2019 and April 30, 2021. A multidimensional assessment, personalized care plan, and proactive follow-up with a case manager nurse were provided via an advanced hospital system. Clinical and demographic variables and data on healthcare system use were analyzed at 6 and 12 months before and after inclusion. Descriptive and survival analyses were performed. One hundred sixty-one patients were included. Program participants were elderly (mean 81.4 (SD 11) years), had multimorbidity (10.2 (3) chronic diseases) and polypharmacy (10.6 (3.5) drugs), frequently used the healthcare system, and were highly complex. Most were included for heart failure. The program led to significant reductions in admissions and emergency department visits (p = .0001). A total of 44.7% patients died within 1 year. The PROFUND Index showed good predictive ability (p = .013), with high values associated with mortality (RR 1.15, p = .001). Patients with frequent hospital readmissions are highly complex and need special care. A personalized integrated care program reduced admissions and allowed for individualized decision-making.

Differences in Social Hardships in Women and Men with Acute Myocardial Infarction: Impact on 30-Day Readmission

Background:

Studies have shown that women with acute myocardial infarction (AMI) have a higher prevalence of unfavorable social variables then men and have a worse outcome. Less is known regarding the impact of these social variables on 30-day readmission after AMI.

Materials and Methods:

We analyzed adult patients with AMI enrolled in a Quality Improvement Program intended to improve the peri-discharge care of patients with an AMI, and decrease all-cause 30-day unplanned readmissions. We compared clinical and social variables by gender. Multivariate logistic regression, with separate adjustment for clinical and for social variable, was used to measure adjusted odds for readmission by gender.

Results:

Among 208 patients included in our project 68 (32.7%) were women. Only 30.9% of women were married or had domestic partner at the time of the interview and only 16.2% were employed. Nearly half of women (48.5%) needed help with medical care, and 39.7% of women did not speak English as their first language. These variables were significantly different by gender. Rates of 30-day readmissions were higher in women than men (22.1% vs. 7.8%, p = 0.024). After adjusting for clinical variables this difference by gender in 30-day readmissions remained significant (odds ratio [OR] 3.34 95% confidence interval [CI] 1.1–11.1, p = 0.049). However, when adjusting for social variables, this difference was no longer noted (OR 0.87 95% CI 0.27–2.78, p = 0.822).

Conclusion:

Women with AMI are more likely than men to have unfavorable social factors that can impact recovery from AMI and women have a higher 30-day readmission rate. The higher 30-day readmissions in women appears to be influenced by these social factors. Health care interventions aimed at reducing 30-day readmission after AMI should focus on eliciting a detailed social history and providing aid for those requiring additional social support at home.

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.

Intervention by a clinical pharmacist carried out at discharge of elderly patients admitted to the internal medicine department: influence on readmissions and costs

BACKGROUND

Patient education on pharmacological treatment could reduce readmissions. Our objective was to carry out a pharmacist intervention focused on providing information about high-risk medications to chronic patients and to analyse its influence on readmissions and costs.

METHODS

A single-centre study with an intervention group and a retrospective control group was conducted. The intervention was carried out in all polymedicated patients ≥ 65 years who were admitted to internal medicine and signed the informed consent between June 2017 and February 2018. Patients discharged to nursing homes or long-term hospitals were excluded. The control group were all the patients who were admitted during the same months of 2014 who met the same inclusion criteria. The patients were classified according to the HOSPITAL score as having a low, intermediate, or high risk of potentially avoidable readmission. Outcome measures were 30-day readmission and cost data. To analyse the effect of the intervention on readmission, a logistic regression was performed.

RESULTS

The study included 589 patients (286 intervention group; 303 control group). The readmission rate decreased from 20.13% to 16.43% in the intervention group [OR = 0.760 95% CI (0.495-1.166); p = 0.209)]. The incremental cost for the intervention to prevent one readmission was €3,091.19, and the net cost saving was €1,301.26. In the intermediate- and high-risk groups, readmissions were reduced 10.91% and 10.00%, and the net cost savings were €3,3143.15 and €3,248.71, respectively.

CONCLUSIONS

The pharmacist intervention achieved savings in the number of readmissions, and the net cost savings were greater in patients with intermediate and high risks of potentially avoidable readmission according to the HOSPITAL score.

Why did you come back to the hospital? A qualitative analysis of 72-hour readmissions

OBJECTIVES

Readmissions occurring within a few days of discharge are more likely due to a problem from the patient's original admission and may be preventable by interventions in the hospital setting. As part of a quality improvement project intended to reduce readmissions within 72 hours of discharge our objective was to explore patient and physician perspectives of reasons for readmissions and to identify potential indicators of readmission during the index admission.

METHODS

A retrospective chart review of all readmissions within 72 hours between 2/1/2019 and 6/7/2019 in our healthcare system comprised of an academic medical center and 2 smaller community hospitals. As part of a hospital protocol, patients readmitted within 30 days were interviewed by a social worker regarding reasons for readmission and their perspective on what might have prevented it. These answers, physician notes relevant to the reason for readmission and the clinical course of the index admission were abstracted from patient charts. For the subset of patients identified by themselves or their physicians as potentially benefitting from a longer hospitalization, their index admission was reviewed for indicators of readmission. Reasons for readmission, potential preventive measures, and indicators of readmission were independently reviewed by two authors then grouped into common themes by consensus.

RESULTS

One hundred and thirty-one patients readmitted within 72 hours were identified. Most patients were readmitted for infection related, cardiac or pulmonary reasons. Extending the initial admission was the most common factor suggested by both patients and physicians to prevent readmission. Focusing on 70 patients who may have benefited from a longer admission, indicators included patients not returning to their baseline health status, inadequate management of a known issue, or new symptoms developing during the index admission.

CONCLUSIONS

Patients should be evaluated for indicators of readmission, which may help guide decisions to discharge patients and decrease rates of 72-hour readmissions.