Diabetes mellitus and blood glucose variability increases the 30-day readmission rate after kidney transplantation.

INTRODUCTION: Inpatient hyperglycemia is an established independent risk factor among several patient cohorts for hospital readmission. This has not been studied after kidney transplantation. Nearly one-third of patients who have undergone a kidney transplant reportedly experience 30-day readmission. METHODS: Data on first-time solitary kidney transplantations were retrieved between September 2015 and December 2018. Information was linked to the electronic health records to determine diagnosis of diabetes mellitus and extract glucometric and insulin therapy data. Univariate logistic regression analysis and the XGBoost algorithm were used to predict 30-day readmission. We report the average performance of the models on the testing set on bootstrapped partitions of the data to ensure statistical significance. RESULTS: The cohort included 1036 patients who received kidney transplantation; 224 (22%) experienced 30-day readmission. The machine learning algorithm was able to predict 30-day readmission with an average area under the receiver operator curve (AUC) of 78% with (76.1%, 79.9%) 95% confidence interval (CI). We observed statistically significant differences in the presence of pretransplant diabetes, inpatient-hyperglycemia, inpatient-hypoglycemia, minimum and maximum glucose values among those with higher 30-day readmission rates. The XGBoost model identified the index admission length of stay, presence of hyper- and hypoglycemia, the recipient and donor body mass index (BMI) values, presence of delayed graft function, and African American race as the most predictive risk factors of 30-day readmission. Additionally, significant variations in the therapeutic management of blood glucose by providers were observed. CONCLUSIONS: Suboptimal glucose metrics during hospitalization after kidney transplantation are associated with an increased risk for 30-day hospital readmission. Optimizing hospital blood glucose management, a modifiable factor, after kidney transplantation may reduce the risk of 30-day readmission.

Impact of early primary care physician follow-up on hospital readmission following gastrointestinal cancer surgery.

BACKGROUND: We sought to examine the association between primary care physician (PCP) follow-up on readmission following gastrointestinal (GI) cancer surgery. METHODS: Patients who underwent surgery for GI cancer were identified using the Surveillance, Epidemiology and End Results (SEER) database. Multivariable regression was performed to examine the association between early PCP follow-up and hospital readmission. RESULTS: Among 60 957 patients who underwent GI cancer surgery, 19 661 (32.7%) visited a PCP within 30-days after discharge. Of note, patients who visited PCP were less likely to be readmitted within 90 days (PCP visit: 17.4% vs. no PCP visit: 28.2%; p < 0.001). Median postsurgical expenditures were lower among patients who visited a PCP (PCP visit: $4116 [IQR: $670-$13 860] vs. no PCP visit: $6700 [IQR: $870-$21 301]; p < 0.001). On multivariable analysis, PCP follow-up was associated with lower odds of 90-day readmission (OR: 0.52, 95% CI: 0.50-0.55) (both p < 0.001). Moreover, patients who followed up with a PCP had lower risk of death at 90-days (HR: 0.50, 95% CI: 0.40-0.51; p < 0.001). CONCLUSION: PCP follow-up was associated with a reduced risk of readmission and mortality following GI cancer surgery. Care coordination across in-hospital and community-based health platforms is critical to achieve optimal outcomes for patients.

Predictors of hospital readmission rate in geriatric patients.

BACKGROUND: Hospital readmissions among older adults are associated with progressive functional worsening, increased institutionalization and mortality. AIM: Identify the main predictors of readmission in older adults. METHODS: We examined readmission predictors in 777 hospitalized subjects (mean age 84.40 ± 6.77 years) assessed with Comprehensive Geriatric Assessment (CGA), clinical, anthropometric and biochemical evaluations. Comorbidity burden was estimated by Charlson Comorbidity Index (CCI). Median follow-up was 365 days. RESULTS: 358 patients (46.1%) had a second admission within 365 days of discharge. Estimated probability of having a second admission was 0.119 (95%C.I. 0.095-0.141), 0.158 (95%C.I. 0.131-0.183), and 0.496 (95%C.I. 0.458-0.532) at 21, 30 and 356 days, respectively. Main predictors of readmission at 1 year were length of stay (LOS) > 14 days (p < 0.001), albumin level < 30 g/l (p 0.018), values of glomerular filtration rate (eGFR) < 40 ml/min (p < 0.001), systolic blood pressure < 115 mmHg (p < 0.001), CCI ≥ 6 (p < 0.001), and cardiovascular diagnoses. When the joint effects of selected prognostic variables were accounted for, LOS > 14 days, worse renal function, systolic blood pressure < 115 mmHg, higher comorbidity burden remained independently associated with higher readmission risk. DISCUSSION: Selected predictors are associated with higher readmission risk, and the relationship evolves with time. CONCLUSIONS: This study highlights the importance of performing an accurate CGA, since defined domains and variables contained in the CGA (i.e., LOS, lower albumin and systolic blood pressure, poor renal function, and greater comorbidity burden), when combined altogether, may offer a valid tool to identify the most fragile patients with clinical and functional impairment enhancing their risk of unplanned early and late readmission.

The impact on thirty day readmissions for patients hospitalized for acute exacerbations of chronic obstructive pulmonary disease admitted to an observation unit versus an inpatient medical unit: A retrospective observational study.

OBJECTIVES: We aimed to evaluate the utility of an Observation Unit (OU) in management of acute exacerbations of chronic obstructive pulmonary disease (AECOPD) and to identify the clinical characteristics of patients readmitted within 30-days for AECOPD following index admission to the OU or inpatient floor from the OU. METHODS: This is a retrospective observational study of patients admitted from January to December 2017 for AECOPD to an OU in an urban-based tertiary care hospital. Primary outcome was rate of 30-day readmission after admission for AECOPD for patients discharged from the OU versus inpatient service after failing OU management. Regression analyses were used to define risk factors. RESULTS: 163 OU encounters from 92 unique patients were included. There was a lower readmission rate (33%) for patients converted from OU to inpatient care versus patients readmitted after direct discharge from the OU (44%). Patients with 30-day readmissions were more likely to be undomiciled, with history of congestive heart failure (CHF), pulmonary embolism (PE), or had previous admissions for AECOPD. Patients with >6 annual OU visits for AECOPD had higher rates of substance abuse, psychiatric diagnosis, and prior PE; when these patients were excluded, the 30-day readmission rate decreased to 13.5%. CONCLUSION: Patients admitted for AECOPD with a history of PE, CHF, prior AECOPD admissions, and socioeconomic deprivation are at higher risk of readmission and should be prioritized for direct inpatient admission. Further prospective studies should be conducted to determine the clinical impact of this approach on readmission rates.

A validation study of the high acuity readmission risk pediatric screen (HARRPS) tool©: Predicting readmission risk within the pediatric population.

BACKGROUND: The initial research study of the High Acuity Readmission Risk Pediatric Screen (HARRPS) Tool © focused on using retrospective data to apply weighted values to the questions within the tool, identify overall risk score, and attribute risk categories (low, moderate, high risk) to the overall risk score. This study focused on validating the data from the initial study, as well as cross examining the need to include admission diagnosis within the tool. METHOD: Study was a single-centered, retrospective chart review study using a different subset of patients from the initial study. Pediatric patients with thirty-day readmissions were compared to pediatric patients without a thirty-day readmission over a twelve-month period. Utilized same statistical software and methodology from initial study to identify if readmission risk probability could be replicated with a different population. RESULTS: The initial study performed in 2018 demonstrated a c-statistic score/ area under the curve (AUC) of 0.68 [95% CI: 0.67, 0.69]. In addition, the initial study demonstrated as risk score increases, the probability of readmission gradually increased until a patient had a risk score of seven or greater, at which point readmission risk plateaued. This resulted in low, moderate, and high readmission risk categories. The current study performed using data from 2019 demonstrated an improved c-statistic score / AUC of 0.83 [95% CI: 0.80, 0.87] with admission diagnosis included, and a c-statistic score / AUC of 0.80 [95% CI: 0.76, 0.83] without the admission diagnosis included. The analysis of overall risk score demonstrated a substantial difference in how to interpret final readmission risk scores. Both the initial study and validation study were consistent in demonstrating a risk score of three or less was associated with low readmission risk. However, in the validation study, there was no substantial difference between moderate or high risk, leading to updating the tool from 3 risk categories into 2 risk categories of low risk and at risk of readmission. CONCLUSION: Based on the finding from the validation study, the admission diagnosis was removed from the HARRPS Tool© as the difference in c-statistic score was nominal, and the risk categories were changed from three categories (low, moderate, high risk) to two categories of low risk (score 0-2) and at risk of readmission for a score of 3+. The ability of the HARRPS Tool© to predict readmission risk preforms best with a c-statistic = 0.80, outperforming the following tools: LACE (0.65), LACE -SDH (0.67), LACE + (0.61), Epic's readmission risk model (0.69), and SQLAPE ® (0.71) (Ryan, et al., 2021; Hwang, et al., 2021).

Real-world effectiveness of long-acting injectable antipsychotics to reduce 90-day and annual readmission in psychotic disorders: insights from a state psychiatric hospital.

BACKGROUND: To evaluate the effectiveness of long-acting injectable antipsychotics (LAI-a) in reducing the 90-day and annual readmission rates in schizophrenia inpatients. METHODS: We conducted a cross-sectional study and included 180 adult patients with psychotic disorders discharged from 2018 to 2019 at a state psychiatric hospital. Descriptive statistics were used to measure the differences between the readmit and nonreadmit cohorts. Logistic regression model was used to measure the odds ratio (OR) for 90-day and annual readmission and was controlled for potential readmission risk factors. RESULTS: A lower proportion of patients receiving LAI-a were readmitted within 90-day (28.6%) and 1-year (32.4%) periods. Patients receiving LAI-a had lower odds of association for 90-day (OR 0.36, 95% confidence intervals [CI] 0.139-0.921) and annual (OR 0.35, 95% CI 0.131-0.954) readmissions compared to those discharged on oral antipsychotics. A higher proportion of inpatients who received fluphenazine LAI had 90-day (25%) and annual (18.2%) readmissions compared to other LAI-a. CONCLUSION: Utilization of LAI-a in patients with psychotic disorders can decrease both 90-day and annual psychiatric readmissions by 64% to 65%. Physicians should prefer LAI-a to reduce the readmission rate and improve the quality of life, and decrease the healthcare-related financial burden.

Prospective evaluation of social risks, physical function, and cognitive function in prediction of non-elective rehospitalization and post-discharge mortality.

BACKGROUND: Increasing evidence suggests that social factors and problems with physical and cognitive function may contribute to patients' rehospitalization risk. Understanding a patient's readmission risk may help healthcare providers develop tailored treatment and post-discharge care plans to reduce readmission and mortality. This study aimed to evaluate whether including patient-reported data on social factors; cognitive status; and physical function improves on a predictive model based on electronic health record (EHR) data alone. METHODS: We conducted a prospective study of 1,547 hospitalized adult patients in 3 Kaiser Permanente Northern California hospitals. The main outcomes were non-elective rehospitalization or death within 30 days post-discharge. Exposures included patient-reported social factors and cognitive and physical function (obtained in a pre-discharge interview) and EHR-derived data for comorbidity burden, acute physiology, care directives, prior utilization, and hospital length of stay. We performed bivariate comparisons using Chi-square, t-tests, and Wilcoxon rank-sum tests and assessed correlations between continuous variables using Spearman's rho statistic. For all models, the results reported were obtained after fivefold cross validation. RESULTS: The 1,547 adult patients interviewed were younger (age, p = 0.03) and sicker (COPS2, p < 0.0001) than the rest of the hospitalized population. Of the 6 patient-reported social factors measured, 3 (not living with a spouse/partner, transportation difficulties, health or disability-related limitations in daily activities) were significantly associated (p < 0.05) with the main outcomes, while 3 (living situation concerns, problems with food availability, financial problems) were not. Patient-reported cognitive (p = 0.027) and physical function (p = 0.01) were significantly lower in patients with the main outcomes. None of the patient-reported variables, singly or in combination, improved predictive performance of a model that included acute physiology and longitudinal comorbidity burden (area under the receiver operator characteristic curve was 0.716 for both the EHR model and maximal performance of a random forest model including all predictors). CONCLUSIONS: In this insured population, incorporating patient-reported social factors and measures of cognitive and physical function did not improve performance of an EHR-based model predicting 30-day non-elective rehospitalization or mortality. While incorporating patient-reported social and functional status data did not improve ability to predict these outcomes, such data may still be important for improving patient outcomes.

Scoping review: Social support impacts hospital readmission rates.

AIMS AND OBJECTIVES: To review and synthesise the current literature on social support and hospital readmission rates. BACKGROUND: Hospital readmission rates have not declined significantly since 2010 despite efforts to identify and implement strategies to reduce readmissions. After discharge, patients often report the need for help at home with personal care, medical care and/or transportation. Social factors can positively or negatively affect the transition from hospital to home and the extended recovery period experienced by patients. METHODS: Published primary studies in peer-reviewed journals, written in English, assessing the adult medical/surgical population and discussing social support and hospital readmission rates were included. A Preferred Reporting Items for Systematic reviews and Meta-Analyses extension for Scoping Reviews (PRISMA-ScR) was completed for this scoping review. RESULTS: The search resulted in 2919 articles. After removing duplicates and reviewing content for the inclusion and exclusion criteria, 23 articles were selected for review. Social support is provided by those within one's social circle. There are several types of social support and depending on the needs to the patient, the type of social required and provided is different. CONCLUSIONS: The most common form of social support needed at home for people recovering after a hospitalisation was instrumental support, tangible care in the form of assistance with daily personal and medical care, and transportation. Patients who lacked adequate social support after discharge were at an increased risk of hospital readmission. RELEVANCE TO CLINICAL PRACTICE: Identifying factors, such as social support, that may impact hospital readmission rates is important for quality hospital to home care transitions. Assessing patients' needs and available social support to meet those needs may be an essential part of the discharge planning process to decrease the risk of hospital readmission.

Readmission After Emergency General Surgery: NSQIP Review of Risk, Cause and Ideal Follow-Up.

BACKGROUND: The Emergency General Surgery (EGS) population is particularly at high risk for readmission. Currently, no system exists to predict which EGS patients are most at risk. We hypothesized that a subset of EGS patients could be identified with increased 30-day unplanned readmission. We also hypothesized that a majority of readmissions occur sooner than the conventional 2-week follow-up period. METHODS: National Surgical Quality Improvement Program (NSQIP) nonelective general surgery patients were analyzed. Multivariable logistic regression identified factors with increased odds of unplanned readmission. AAST EGS Diagnosis Categories were used to categorize postop ICD-9 codes, and the top 10 CPT codes in each group were analyzed. Readmission rate, the reason for unplanned readmission, and time to readmission were analyzed. RESULTS: A total of 383,726 patients were identified with a readmission rate of 8.1% within 30 d of their primary procedure. The top 50 CPT codes accounted for 84% of EGS readmissions. Increased readmission risk was demonstrated for underweight patients (OR = 1.15, P < 0.05). High-risk hospital characteristics were LOS >2 d, any inpatient pulmonary complications, and discharge to any facility or rehab (all P < 0.05). Surgical site infections cause nearly 25% of readmissions. Intestinal procedures are most frequently readmitted (22% of EGS readmissions), with colorectal procedures having the higher odds of readmission. Most readmissions occur <10 d after discharge. CONCLUSIONS: A high-risk subpopulation exists within EGS, and most readmissions occur sooner than a typical 2-week follow-up. Early interventions for high-risk EGS subpopulations may allow for early intervention and reduction of unnecessary healthcare utilization.

Quality of life after hospitalization predicts one-year readmission risk in a large Swiss cohort of medical in-patients.

PURPOSE: Estimating the probability of readmission following hospitalization using prediction scores can be complex. Quality of life (QoL) may provide an easy and effective alternative. METHODS: Secondary analysis of the prospective "TRIAGE" cohort. All medical in-patients admitted to a Swiss tertiary care institution (2016-2019) ≥18 years with a length of stay of ≥2 days (23,309 patients) were included. EQ-5D VAS, EQ-5D index, and Barthel index were assessed at a single telephone interview 30-day after admission. Patients lost to follow-up were excluded. Readmission was defined as a non-elective hospital stay at our institution >24 h within 1 year after discharge and assessed using area under the curve (AUC) analysis with adjustment for confounders. RESULTS: 12,842 patients (43% females, median age 68, IQR 55-78) were included. Unadjusted discrimination was modest at 0.59 (95% CI 0.56-0.62) for EQ-5D VAS. Partially adjusted discrimination (for gender) was identical. Additional adjustment for insurance, Charlson comorbidity index, length of stay, and native language increased the AUC to 0.66 (95% CI 0.63-0.69). Results were robust irrespective of time to event (12, 6 or 3 months). A cut-off in the unadjusted model of EQ-5D VAS of 55 could separate cases with a specificity of 80% and a sensitivity of 30%. CONCLUSION: QoL at day 30 after admission can predict one-year readmission risk with similar precision as more intricate tools. It might help for identification of high-risk patients and the design of tailored prevention strategies.

Prediction of Readmission in Geriatric Patients From Clinical Notes: Retrospective Text Mining Study.

BACKGROUND: Prior literature suggests that psychosocial factors adversely impact health and health care utilization outcomes. However, psychosocial factors are typically not captured by the structured data in electronic medical records (EMRs) but are rather recorded as free text in different types of clinical notes. OBJECTIVE: We here propose a text-mining approach to analyze EMRs to identify older adults with key psychosocial factors that predict adverse health care utilization outcomes, measured by 30-day readmission. The psychological factors were appended to the LACE (Length of stay, Acuity of the admission, Comorbidity of the patient, and Emergency department use) Index for Readmission to improve the prediction of readmission risk. METHODS: We performed a retrospective analysis using EMR notes of 43,216 hospitalization encounters in a hospital from January 1, 2017 to February 28, 2019. The mean age of the cohort was 67.51 years (SD 15.87), the mean length of stay was 5.57 days (SD 10.41), and the mean intensive care unit stay was 5% (SD 22%). We employed text-mining techniques to extract psychosocial topics that are representative of these patients and tested the utility of these topics in predicting 30-day hospital readmission beyond the predictive value of the LACE Index for Readmission. RESULTS: The added text-mined factors improved the area under the receiver operating characteristic curve of the readmission prediction by 8.46% for geriatric patients, 6.99% for the general hospital population, and 6.64% for frequent admitters. Medical social workers and case managers captured more of the psychosocial text topics than physicians. CONCLUSIONS: The results of this study demonstrate the feasibility of extracting psychosocial factors from EMR clinical notes and the value of these notes in improving readmission risk prediction. Psychosocial profiles of patients can be curated and quantified from text mining clinical notes and these profiles can be successfully applied to artificial intelligence models to improve readmission risk prediction.

The importance of sex as a risk factor for hospital readmissions due to pulmonary diseases.

BACKGROUND: Pulmonary diseases are a common and costly cause of 30-day readmissions. Few studies have focused on the difference in risk for rehospitalization between men and women in older patients. In this study we analyzed the association between sex and the risk of readmission in a cohort of patients admitted to the hospital for chronic obstructive pulmonary disease (COPD) exacerbation and other major pulmonary diseases. METHODS: This was a retrospective cohort study based on administrative data collected in the Veneto Region in 2016. We included 14,869 hospital admissions among residents aged ≥65 years for diagnosis related groups (DRGs) of the most common disorders of the respiratory system: bronchitis and asthma, pneumonia, pulmonary edema, respiratory failure, and COPD. Multilevel logistic regressions were performed to test the association between 30-day hospital readmission and sex, adjusting for confounding factors. RESULTS: For bronchitis and asthma, male patients had significantly higher odds of 30-day readmission than female patients (adjusted odds ratio (aOR), 2.07; 95% confidence interval (CI), 1.11-3.87). The odds of readmission for men were also significantly higher for pneumonia (aOR, 1.40; 95% CI, 1.13-1.72), for pulmonary edema and respiratory failure (aOR, 1.28; 95% CI, 1.05-1.55), and for COPD (aOR, 1.34; 95% CI, 1.00-1.81). CONCLUSIONS: This study found that male sex is a major risk factors for readmission in patients aged more than 65 years with a primary pulmonary diagnosis. More studies are needed to understand the underlying determinants of this phenomena and to provide targets for future interventions.

Usefulness of systolic blood pressure combined with heart rate measured on admission to identify 1-year all-cause mortality risk in elderly patients firstly hospitalized due to acute heart failure.

BACKGROUND: Systolic blood pressure (SBP) and heart rate (HR) are well-known prognostic factors in heart failure (HF). AIMS: Our objective was to assess the value of the combination of admission SBP and HR to estimate 1-year mortality risks in elderly patients admitted due to a first episode of acute HF (AHF). METHODS: During a 36-month period, we retrospectively reviewed 901 consecutive patients aged ≥ 75 admitted because of a first episode of AHF. According to admission SBP-HR combinations, three groups were defined: "low-risk" (HR < 70 bpm and SBP ≥ 140 mmHg), "moderate-risk" (HR < 70 bpm and SBP < 140 mmHg or HR ≥ 70 bmp and SBP ≥ 120 mmHg), and "high-risk" (HR ≥ 70 bpm and SBP < 120 mmHg). We analyzed all-cause mortality using Cox mortality analysis. RESULTS: One-year mortality ranged from 16.5% for patients in the low-risk group to 50% for those in the high-risk group (p < 0.0001). Multivariate Cox regression for 1-year mortality showed hazard risk (HzR) ratios, compared to that (HzR 1) of the low-risk reference group, of 1.759 (95% CI 1.035-2.988, p = 0.037) for moderate-risk, and 3.171 (95% CI 1.799-5.589, p = 0.0001) for high-risk group. Prior use of a high number of chronic therapies (HzR 1.045), lower admission diastolic BP (HzR 0.986) and higher admission serum potassium values (HzR 1.534) were also significantly associated with mortality. CONCLUSION: In elderly population firstly hospitalized due to AHF, the simple combined admission measurement of SBP and HR predicts higher risk for 1-year all-cause mortality.

Retrospective Chart Review: Readmission Prediction Ability of the High Acuity Readmission Risk Pediatric Screen (HARRPS) Tool.

BACKGROUND: Nurse Case Managers utilize adult based readmission risk tools upon admission to identify readmission risk. An evidence-based pediatric readmission tool could not be identified to replicate in the pediatric space, therefore the High Acuity Readmission Risk Pediatric Screen (HARRPS) Tool was developed to fill this gap. The research aim was to develop a risk score algorithm that accurately predicts pediatric readmissions and provide a predictive validation of the HARRPS Tool. METHOD: This was a single-centered, retrospective chart review study which compared pediatric patients with thirty-day readmissions to those without thirty-day readmissions over a twelve-month period. Sample size ratio of 1:2 was determined via power analysis with an overall sample size of 5371. Each category from the HARRPS Tool was appropriately weighted based upon data from this study to then produce an overall, patient-level risk score, which was summed [allowable range: 0, 14] across all components. Cross validation was used to ascertain the readmission risk predictability. RESULTS: Of the 5306 patients included in the final analysis, 1343 (25.3%) had a thirty-day readmission. Out of nine risk components analyzed, eight were consistent with the literature review findings. Patients with a score of seven or higher had a 54.9% predicted probability of a thirty-day readmission, compared to 13.6% for patients with a risk score of zero. The c-statistic score of the HARRPS Tool was determined to be 0.68 [95% CI, 0.67, 0.69]. Overall, the HARRPS Tool was favorable and provides initial credibility of the tool's predictive power for the general pediatric population.

Readmission Risk Assessment Technologies and the Anchoring and Adjustment Heuristic.

Approximately 23% of patients discharged from primary healthcare facilities are readmitted within 30 days at an annual cost of roughly $42 billion. To remedy this problem, healthcare providers are attempting to deploy readmission risk estimation tools, but how they might be used in the traditional, human-expert-centered decision process is not well understood. One such tool estimates readmission risk based on 50 patient-specific factors. This paper reports on a study performed in collaboration with Order of St. Francis Healthcare to determine how healthcare workers' own risk estimates are influenced by the tool, specifically testing the hypothesis that they will first anchor towards tool results while making adjustments based on their expertise, and then make further adjustments when additional human expert opinions are presented. Task analysis was performed, fictional patient scenarios were developed, and a survey of 56 subjects in two stratified groups of case managers was conducted. Data from the control and experiment groups were analyzed using ANOVA/GLM and t-tests. Results indicate that the healthcare workers' risk estimates were influenced by the anchor provided by the tool, then adjusted based on their expertise. The workers further adjusted their estimates in response to new expert human inputs. Thus, a reliance on both the predictive model and human expertise was observed.

Comparison of methods for early-readmission prediction in a high-dimensional heterogeneous covariates and time-to-event outcome framework.

BACKGROUND: Choosing the most performing method in terms of outcome prediction or variables selection is a recurring problem in prognosis studies, leading to many publications on methods comparison. But some aspects have received little attention. First, most comparison studies treat prediction performance and variable selection aspects separately. Second, methods are either compared within a binary outcome setting (where we want to predict whether the readmission will occur within an arbitrarily chosen delay or not) or within a survival analysis setting (where the outcomes are directly the censored times), but not both. In this paper, we propose a comparison methodology to weight up those different settings both in terms of prediction and variables selection, while incorporating advanced machine learning strategies. METHODS: Using a high-dimensional case study on a sickle-cell disease (SCD) cohort, we compare 8 statistical methods. In the binary outcome setting, we consider logistic regression (LR), support vector machine (SVM), random forest (RF), gradient boosting (GB) and neural network (NN); while on the survival analysis setting, we consider the Cox Proportional Hazards (PH), the CURE and the C-mix models. We also propose a method using Gaussian Processes to extract meaningfull structured covariates from longitudinal data. RESULTS: Among all assessed statistical methods, the survival analysis ones obtain the best results. In particular the C-mix model yields the better performances in both the two considered settings (AUC =0.94 in the binary outcome setting), as well as interesting interpretation aspects. There is some consistency in selected covariates across methods within a setting, but not much across the two settings. CONCLUSIONS: It appears that learning withing the survival analysis setting first (so using all the temporal information), and then going back to a binary prediction using the survival estimates gives significantly better prediction performances than the ones obtained by models trained "directly" within the binary outcome setting.

Perioperative Orthopedic Surgical Home: Optimizing Total Joint Arthroplasty Candidates and Preventing Readmission.

BACKGROUND: It is well recognized that unplanned readmissions following total joint arthroplasty (TJA) are more prevalent in patients with comorbidities. However, few investigators have delayed surgery and medically optimized patients prior to surgery. In its current form, the Perioperative Orthopedic Surgical Home (POSH) is a surgeon-led screening and optimization initiative targeting 8 common modifiable comorbidities. METHODS: A total of 4188 patients who underwent TJA between January 2014 and December 2016 were retrospectively screened by the Readmission Risk Assessment tool (RRAT) score. one thousand one hundred and ninety four subjects had a preoperative RRAT score ≥3 and were eligible for inclusion. Patients were then separated into 2 cohorts based on whether they were enrolled into the POSH initiative (POSH; n = 216) or continued with surgery (non-POSH; n = 978) despite their risk. RESULTS: Since the implementation of the POSH initiative, patients with RRAT scores ranging from 3 to 5 have experienced lower 30-day (1.6% vs 5.3%, P = .03) and 90-day (3.2% vs 7.4%, P < .05) readmission rates when compared to the non-POSH cohort. Only 15.3% of medically optimized patients enrolled in the POSH initiative were discharged to a post-acute care facility, whereas 23.4% of non-POSH patients were discharged to a post-acute care facility (P = .01). There were no differences in length of stay and infection rates between the 2 cohorts. Moreover, 90-day episode-of-care costs were 14.9% greater among non-POSH Medicare TJA recipients and 32.6% higher if a readmission occurred. CONCLUSION: The identification and medical optimization of comorbidities prior to surgical intervention may enhance the value of care TJA candidates receive. A standardized multidisciplinary approach to the medical optimization of high-risk TJA candidates may improve patient engagement and perioperative outcomes, while reducing cost associated with TJA. LEVEL OF EVIDENCE: Level III, Retrospective Cohort Study.

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

BACKGROUND: Over the next 10-15 years, there is expected to be an exponential increase in the number of total joint arthroplasties in the American population. This, combined with rising costs of total joint arthroplasty and more recent changes to the reimbursement payment models, increases the demand to perform quality, cost-effective total joint arthroplasties. The purpose of this study is to build models that could be used to estimate the 30-day and 90-day readmission rates for patients undergoing total joint arthroplasty. METHODS: A retrospective review of patients admitted to a single hospital, over the course of 56 months, for total joint arthroplasty was performed. The goal is to identify patients with readmission in a 30-day or 90-day period following discharge from the hospital. Binary logistic regression was used to build predictive models that estimate the likelihood of readmission based on a patient's risk factors. RESULTS: Of 5732 patients identified for this study, 237 were readmitted within 30 days, while 547 were readmitted within 90 days. Age, body mass index, gender, discharge disposition, occurrence of cardiac dysrhythmias and heart failure, emergency department visits, psychiatric diagnoses, and medication counts were all found to be associated with 30-day admission rates. Similar associations were found at 90 days, with the exclusion of age and psychiatric drug use, and the inclusion of intravenous drug abuse, narcotic medications, and total joint arthroplasty within 12 months. CONCLUSION: There are patient variables, or risk factors, that serve to predict the likelihood of readmission following total joint arthroplasty.

Prediction of 30-Day Readmission for COPD Patients Using Accelerometer-Based Activity Monitoring.

Chronic obstructive pulmonary disease (COPD) claimed 3.0 million lives in 2016 and ranked 3rd among the top 10 global causes of death. Moreover, once diagnosed and discharged from the hospital, the 30-day readmission risk in COPD patients is found to be the highest among all chronic diseases. The existing diagnosis methods, such as Global Initiative for Chronic Obstructive Lung Disease (GOLD) 2019, Body-mass index, airflow Obstruction, Dyspnea, and Exercise (BODE) index, modified Medical Research Council (mMRC), COPD assessment test (CAT), 6-minute walking distance, which are adopted currently by physicians cannot predict the potential readmission of COPD patients, especially within the 30 days after discharge from the hospital. In this paper, a statistical model was proposed to predict the readmission risk of COPD patients within 30-days by monitoring their physical activity (PA) in daily living with accelerometer-based wrist-worn wearable devices. This proposed model was based on our previously reported PA models for activity index (AI) and regularity index (RI) and it introduced a new parameter, quality of activity (QoA), which incorporates previously proposed parameters, such as AI and RI, with other activity-based indices to predict the readmission risk. Data were collected from continuous PA monitoring of 16 COPD patients after hospital discharge as test subjects and readmission prediction criteria were proposed, with a 63% sensitivity and a 37.78% positive prediction rate. Compared to other clinical assessment, diagnosis, and prevention methods, the proposed model showed significant improvement in predicting the 30-day readmission risk.

Predicting 7-day, 30-day and 60-day all-cause unplanned readmission: a case study of a Sydney hospital.

BACKGROUND: The identification of patients at high risk of unplanned readmission is an important component of discharge planning strategies aimed at preventing unwanted returns to hospital. The aim of this study was to investigate the factors associated with unplanned readmission in a Sydney hospital. We developed and compared validated readmission risk scores using routinely collected hospital data to predict 7-day, 30-day and 60-day all-cause unplanned readmission. METHODS: A combination of gradient boosted tree algorithms for variable selection and logistic regression models was used to build and validate readmission risk scores using medical records from 62,235 live discharges from a metropolitan hospital in Sydney, Australia. RESULTS: The scores had good calibration and fair discriminative performance with c-statistic of 0.71 for 7-day and for 30-day readmission, and 0.74 for 60-day. Previous history of healthcare utilization, urgency of the index admission, old age, comorbidities related to cancer, psychosis, and drug-abuse, abnormal pathology results at discharge, and being unmarried and a public patient were found to be important predictors in all models. Unplanned readmissions beyond 7 days were more strongly associated with longer hospital stays and older patients with higher number of comorbidities and higher use of acute care in the past year. CONCLUSIONS: This study demonstrates similar predictors and performance to previous risk scores of 30-day unplanned readmission. Shorter-term readmissions may have different causal pathways than 30-day readmission, and may, therefore, require different screening tools and interventions. This study also re-iterates the need to include more informative data elements to ensure the appropriateness of these risk scores in clinical practice.