Predictive analytics support for complex chronic medical conditions: An experience-based co-design study of physician managers' needs and preferences.

PURPOSE: The literature suggests predictive technology applications in health care would benefit from physician and manager input during design and development. The aim was to explore the needs and preferences of physician managers regarding the role of predictive analytics in decision support for patients with the highly complex yet common combination of multiple chronic conditions of cardiovascular (Heart) and kidney (Nephrology) diseases and diabetes (HND). METHODS: This qualitative study employed an experience-based co-design model comprised of three data gathering phases: 1. Patient mapping through non-participant observations informed by process mining of electronic health records data, 2. Semi-structured experience-based interviews, and 3. A co-design workshop. Data collection was conducted with physician managers working at or collaborating with the HND center, Danderyd University Hospital (DSAB), in Stockholm, Sweden. HND center is an integrated practice unit offering comprehensive person-centered multidisciplinary care to stabilize disease progression, reduce visits, and develop treatment strategies that enables a transition to primary care. RESULTS: Interview and workshop data described a complex challenge due to the interaction of underlying pathophysiologies and the subsequent need for multiple care givers that hindered care continuity. The HND center partly met this challenge by coordinating care through multiple interprofessional and interdisciplinary shared decision-making interfaces. The large patient datasets were difficult to operationalize in daily practice due to data entry and retrieval issues. Predictive analytics was seen as a potentially effective approach to support decision-making, calculate risks, and improve resource utilization, especially in the context of complex chronic care, and the HND center a good place for pilot testing and development. Simplicity of visual interfaces, a better understanding of the algorithms by the health care professionals, and the need to address professional concerns, were identified as key factors to increase adoption and facilitate implementation. CONCLUSIONS: The HND center serves as a comprehensive integrated practice unit that integrates different medical disciplinary perspectives in a person-centered care process to address the needs of patients with multiple complex comorbidities. Therefore, piloting predictive technologies at the same time with a high potential for improving care represents an extreme, demanding, and complex case. The study findings show that health care professionals' involvement in the design of predictive technologies right from the outset can facilitate the implementation and adoption of such technologies, as well as enhance their predictive effectiveness and performance. Simplicity in the design of predictive technologies and better understanding of the concept and interpretation of the algorithms may result in implementation of predictive technologies in health care. Institutional efforts are needed to enhance collaboration among the health care professionals and IT professionals for effective development, implementation, and adoption of predictive analytics in health care.

A Prospective Multimodal Education Intervention for Providers Does Not Increase Hepatic Encephalopathy Treatment Rates.

BACKGROUND: Over 50% of hospitalizations from hepatic encephalopathy (HE) are preventable, but patients often do not receive medical treatment. AIMS: To use a multimodal education intervention (MMEI) to increase HE treatment rates and to evaluate (1) trends in HE treatment, (2) predictors of receiving treatment, and (3) the impact of treatment on hospitalization outcomes. METHODS: Prospective single-center cohort study of patients hospitalized with HE from April 1, 2020-September 30, 2022. The first 15 months were a control ("pre-MMEI"), the subsequent 15 months (MMEI) included three phases: (1) prior authorization resources, (2) electronic order set, and (3) in-person provider education. Treatment included receiving any drug (lactulose or rifaximin), or combination therapy. Treatment rates pre- vs. post-MMEI were compared using logistic regression. RESULTS: 471 patients were included. There were lower odds of receiving any drug post-MMEI (p = 0.03). There was no difference in receiving combination therapy pre- or post-MMEI (p = 0.32). Predictors of receiving any drug included alcohol-related or cryptogenic cirrhosis (p's < 0.001), and the presence of ascites (p = 0.005) and/or portal hypertension (p = 0.003). The only significant predictor of not receiving any drug treatment was having autoimmune cirrhosis (p < 0.001). Patients seen by internal medicine (p = 0.01) or who were intoxicated (p = 0.02) were less likely to receive rifaximin. Any treatment was associated with higher 30-day liver disease-specific readmission (p < 0.001). CONCLUSION: This MMEI did not increase HE treatment rates, suggesting that alternative strategies are needed to identify and address barriers to treatment.

Utility of the LACE index to assess risk of mortality and readmission in patients with spinal infections.

Retrospective cohort study. To assess the utility of the LACE index for predicting death and readmission in patients with spinal infections (SI). SIs are severe conditions, and their incidence has increased in recent years. The LACE (Length of stay, Acuity of admission, Comorbidities, Emergency department visits) index quantifies the risk of mortality or unplanned readmission. It has not yet been validated for SIs. LACE indices were calculated for all adult patients who underwent surgery for spinal infection between 2012 and 2021. Data were collected from a single academic teaching hospital. Outcome measures included the LACE index, mortality, and readmission rate within 30 and 90 days. In total, 164 patients were analyzed. Mean age was 64.6 (± 15.1) years, 73 (45%) were female. Ten (6.1%) patients died within 30 days and 16 (9.8%) died within 90 days after discharge. Mean LACE indices were 13.4 (± 3.6) and 13.8 (± 3.0) for the deceased patients, compared to 11.0 (± 2.8) and 10.8 (± 2.8) for surviving patients (p = 0.01, p < 0.001), respectively. Thirty-seven (22.6%) patients were readmitted ≤ 30 days and 48 (29.3%) were readmitted ≤ 90 days. Readmitted patients had a significantly higher mean LACE index compared to non-readmitted patients (12.9 ± 2.1 vs. 10.6 ± 2.9, < 0.001 and 12.8 ± 2.3 vs. 10.4 ± 2.8, p < 0.001, respectively). ROC analysis for either death or readmission within 30 days estimated a cut-off LACE index of 12.0 points (area under the curve [AUC] 95% CI, 0.757 [0.681-0.833]) with a sensitivity of 70% and specificity of 69%. Patients with SI had high LACE indices that were associated with high mortality and readmission rates. The LACE index can be applied to this patient population to predict the risk of early death or unplanned readmission.

Hospital readmissions after robotic hepatectomy for neoplastic disease: Analysis of risk factors, survival, and economical impact. A logistical regression and propensity score matched study.

BACKGROUND: As the first comprehensive investigation into hospital readmissions following robotic hepatectomy for neoplastic disease, this study aims to fill a critical knowledge gap by evaluating risk factors associated with readmission and their impact on survival and the financial burden. METHODS: The study analyzed a database of robotic hepatectomy patients, comparing readmitted and non-readmitted individuals post-operatively using 1:1 propensity score matching. Statistical methods included Chi-square, Mann-Whitney U, T-test, binomial logistic regression, and Kaplan-Meier analysis. RESULTS: Among 244 patients, 44 were readmitted within 90 days. Risk factors included hypertension (p â€‹= â€‹0.01), increased Child-Pugh score (p â€‹< â€‹0.01), and R1 margin status (p â€‹= â€‹0.05). Neoadjuvant chemotherapy correlated with lower readmission risk (p â€‹= â€‹0.045). Readmissions didn't significantly impact five-year survival (p â€‹= â€‹0.42) but increased fixed indirect hospital costs (p â€‹< â€‹0.01). CONCLUSIONS: Readmission post-robotic hepatectomy correlates with hypertension, higher Child-Pugh scores, and R1 margins. The use of neoadjuvant chemotherapy was associated with a lower admission rate due to less diffuse liver disease in these patients. While not affecting survival, readmissions elevate healthcare costs.

The Impact of Social Deprivation on Healthcare Utilization Patterns Following Rotator Cuff Repair.

BACKGROUND: Disparities in social determinants of health have been linked to worse patient reported outcomes, higher pain, and increased risk of revision surgery following rotator cuff repair. Identification of perioperative predictors of increased healthcare utilization is of particular interest to surgeons to improve outcomes and mitigate the total cost of care. The effect of social deprivation on healthcare utilization has not been fully characterized. METHODS: This is a retrospective review of a single institution's experience with primary rotator cuff repair between 2012-2020. Demographic variables (age, race, gender, ASA score) and healthcare utilization (hospital readmission, emergency department visits, follow-up visits, telephone calls) were recorded within 90 days of surgery. The Area Deprivation Index (ADI) was recorded, and patients were separated into terciles according to their relative level of social deprivation. Outcomes were then stratified based on ADI tercile and compared. RESULTS: A total of 1695 patients were included. The upper, middle, and lower terciles of ADI consisted of 410, 767, and 518 patients, respectively. The most deprived tercile had greater emergency department visitation and office visitation within 90 days of surgery relative to the least and intermediate deprived terciles. Higher levels of social deprivation were independent risk factors for increased ED visitation and follow-up visitation. There was no difference in 90-day readmission rates or telephone calls made between the least, intermediate, and most deprived patients. CONCLUSIONS: Patients with higher levels of deprivation demonstrated greater postoperative hospital utilization. We hope to use these results to identify risk factors for increased hospital use, guide clinical decision making, increase transparency, and manage patient outcomes following rotator cuff repair surgery.

Preventing Readmissions of Hepatic Encephalopathy: Strategies in the Acute Inpatient, Immediate Postdischarge, and Longitudinal Outpatient Setting.

Hepatic encephalopathy (HE) is a strong predictor of early hospital readmission in patients with cirrhosis. Early hospital readmission increases health care costs and is associated with worse survival. Herein we provide an overview of strategies to prevent hospital readmissions in patients with HE, divided into 3 contexts: (a) acute inpatient, (b) immediate postdischarge, and (c) longitudinal outpatient setting.

Risk factors for readmission after a cholecystectomy: a case-control study.

OBJECTIVE: The aim of this study was to assess the risk factors associated with 30-day hospital readmissions after a cholecystectomy. METHODS: We conducted a case-control study, with data obtained from UC-Christus from Santiago, Chile. All patients who underwent a cholecystectomy between January 2015 and December 2019 were included in the study. We identified all patients readmitted after a cholecystectomy and compared them with a randomized control group. Univariate and multivariate analyses were conducted to identify risk factors. RESULTS: Of the 4866 cholecystectomies performed between 2015 and 2019, 79 patients presented 30-day hospital readmission after the surgical procedure (1.6%). We identified as risk factors for readmission in the univariate analysis the presence of a solid tumor at the moment of cholecystectomy (OR = 7.58), high pre-operative direct bilirubin (OR = 2.52), high pre-operative alkaline phosphatase (OR = 3.25), emergency admission (OR = 2.04), choledocholithiasis on admission (OR = 4.34), additional surgical procedure during the cholecystectomy (OR = 4.12), and post-operative complications. In the multivariate analysis, the performance of an additional surgical procedure during cholecystectomy was statistically significant (OR = 4.24). CONCLUSION: Performing an additional surgical procedure during cholecystectomy was identified as a risk factor associated with 30-day hospital readmission.

OBJETIVO: El objetivo de este estudio fue evaluar los factores de riesgo asociados al reingreso hospitalario en los primeros 30 días post colecistectomía. MÉTODOS: Estudio de casos-controles con datos obtenidos del Hospital Clínico de la UC-Christus, Santiago, Chile. Se ­incluyeron las colecistectomías realizadas entre los años 2015-2019. Se consideraron como casos aquellos pacientes que reingresaron en los 30 primeros días posterior a una colecistectomía. Se realizó un análisis univariado y multivariado de diferentes posibles factores de riesgo. RESULTADOS: De un total de 4866 colecistectomías, 79 pacientes presentaron reingreso hospitalario. Los resultados estadísticamente significativos en el análisis univariado fueron; tumor sólido al momento de la colecistectomía (OR = 7.58) bilirrubina directa preoperatoria alterada (OR = 2.52), fosfatasa alcalina preoperatoria alterada (OR = 3.25), ingreso de urgencia (OR = 2.04), coledocolitiasis al ingreso (OR = 4.34) realización de otros procedimientos (OR = 4.12) y complicaciones postoperatorias. En el análisis multivariado sólo la realización de otro procedimiento durante la colecistectomía fue estadísticamente significativa (OR = 4.24). CONCLUSIÓN: La realización de otros procedimientos durante la colecistectomía es un factor de riesgo de reingreso hospitalario en los 30 días posteriores a la colecistectomía.

Reingreso hospitalario a 30 días en pacientes pediátricos con enfermedades crónicas complejas / Thirty-day readmissions in children with complex chronic conditions

Introducción: La tasa de reingreso hospitalario a 30 días del alta es una medida de calidad de la atención médica. Los pacientes pediátricos con enfermedades crónicas complejas tienen altas tasas de reingreso. La falla en la transición entre el cuidado hospitalario y domiciliario podría explicar este fenómeno. Objetivos: Estimar la tasa de incidencia de reingreso hospitalario a 30 días en pacientes pediátricos con enfermedades crónicas complejas, estimar cuántos son potencialmente prevenibles y explorar posibles factores asociados a reingreso. Materiales y método: Estudio de cohorte prospectivo incluyendo pacientes hospitalizados con enfermedades crónicas complejas de un mes a 18 años de edad. Se excluyeron pacientes con enfermedad oncológica y cardiopatías congénitas. Se evaluaron el reingreso a 30 días y el reingreso potencialmente prevenible. Se valoraron características sociodemográficas, geográficas, clínicas y de la transición hacia el cuidado domiciliario. Resultados: Se incluyeron 171 hospitalizaciones; dentro de los 30 días reingresaron 28 pacientes (16,4%; IC95% 11,6-22,7). De los 28 reingresos, 23 (82,1%; IC95% 64,4-92,1) fueron potencialmente prevenibles. La enfermedad respiratoria se asoció con mayor probabilidad de reingreso. No se encontró asociación entre el reingreso a 30 días y los factores de la transición al cuidado domiciliario evaluados. Conclusiones: La tasa de reingreso a 30 días en pacientes con enfermedad crónica compleja fue del 16,4%, y el 82,1% fueron potencialmente prevenibles. Únicamente la enfermedad respiratoria se comportó como factor de riesgo para reingreso a 30 días.(AU)

Introduction: The rate of hospital readmission within 30 days of discharge is a quality indicator in health care. Paediatric patients with complex chronic conditions have high readmission rates. Failure in the transition between hospital and home care could explain this phenomenon. Objectives: To estimate the incidence rate of 30-day hospital readmission in paediatric patients with complex chronic conditions, estimate how many are potentially preventable and explore factors associated with readmission. Materials and method: Cohort study including hospitalized patients with complex chronic conditions aged one month to 18 years. Patients with cancer or with congenital heart disease requiring surgical correction were excluded. The outcomes assessed were 30-day readmission rate and potentially preventable readmissions. We analysed sociodemographic, geographic, clinical and transition to home care characteristics as factors potentially associated with readmission. Results: The study included 171 hospitalizations, and 28 patients were readmitted within 30 days (16.4%; 95% CI, 11.6–22.7). Of the 28 readmissions, 23 were potentially preventable (82.1%; 95% CI, 64.4–92.1). Respiratory disease was associated with a higher probability of readmission. There was no association between 30-day readmission and the characteristics of the transition to home care. Conclusions: The 30-day readmission rate in patients with complex chronic disease was 16.4%, and 82.1% of readmissions were potentially preventable. Respiratory disease was the only identified risk factor for 30-day readmission.(AU)

Predictive validity of the Academy of Nutrition and Dietetics/American Society for Parenteral and Enteral Nutrition indicators to diagnose malnutrition tool in hospitalized adults: a cohort study.

BACKGROUND: The lack of a widely accepted, broadly validated tool for diagnosing malnutrition in hospitalized patients limits the ability to assess the integral role of nutrition as an input and outcome of health, disease, and treatment. OBJECTIVES: This study aimed to evaluate the predictive validity of the Academy of Nutrition and Dietetics/American Society for Parenteral and Enteral Nutrition (ASPEN) indicators to diagnose malnutrition (AAIM) tool and determine if it can be simplified. METHODS: A prospective cohort study was conducted from August 2019 to September 2022 with 32 hospitals in United States. At baseline, 290 adult patients were evaluated for a diagnosis of malnutrition using the AAIM tool, which assesses weight loss, inadequate energy intake, subcutaneous fat and muscle loss, edema, and hand grip strength. Healthcare outcomes were extracted from the medical record: composite incidence of emergency department (ED) visits and hospital readmissions within 90 d postdischarge; length of hospital stay (LOS); and Medicare Severity Disease Related Group (MS-DRG) relative weight (i.e., healthcare resource utilization). We used multilevel, multivariable negative binomial or generalized linear regression models to evaluate relationships between malnutrition diagnosis and healthcare outcomes. RESULTS: After adjusting for disease severity and acuity and sociodemographic characteristics, individuals diagnosed with severe malnutrition had a higher incidence rate of ED visits and hospital readmissions (incidence rate ratio: 1.89; 95% CI: 1.14, 3.13; P = 0.01), and individuals diagnosed with moderate malnutrition had a 25.2% longer LOS (95% CI: 2.0%, 53.7%; P = 0.03) and 15.1% greater healthcare resource utilization (95% CI: 1.6%, 31.9%; P = 0.03) compared with individuals with no malnutrition diagnosis. Observed relationships remained consistent when only considering malnutrition diagnoses supported by at least 2 of these indicators: weight loss, subcutaneous fat loss, muscle wasting, and inadequate energy intake. CONCLUSIONS: Findings from this multihospital study confirm the predictive validity of the original or simplified AAIM tool and support its routine use for hospitalized adult patients. This trial was registered at clinicaltrials.gov as NCT03928548 (https://classic. CLINICALTRIALS: gov/ct2/show/NCT03928548).

Evaluating Algorithmic Bias in 30-Day Hospital Readmission Models: Retrospective Analysis.

BACKGROUND: The adoption of predictive algorithms in health care comes with the potential for algorithmic bias, which could exacerbate existing disparities. Fairness metrics have been proposed to measure algorithmic bias, but their application to real-world tasks is limited. OBJECTIVE: This study aims to evaluate the algorithmic bias associated with the application of common 30-day hospital readmission models and assess the usefulness and interpretability of selected fairness metrics. METHODS: We used 10.6 million adult inpatient discharges from Maryland and Florida from 2016 to 2019 in this retrospective study. Models predicting 30-day hospital readmissions were evaluated: LACE Index, modified HOSPITAL score, and modified Centers for Medicare & Medicaid Services (CMS) readmission measure, which were applied as-is (using existing coefficients) and retrained (recalibrated with 50% of the data). Predictive performances and bias measures were evaluated for all, between Black and White populations, and between low- and other-income groups. Bias measures included the parity of false negative rate (FNR), false positive rate (FPR), 0-1 loss, and generalized entropy index. Racial bias represented by FNR and FPR differences was stratified to explore shifts in algorithmic bias in different populations. RESULTS: The retrained CMS model demonstrated the best predictive performance (area under the curve: 0.74 in Maryland and 0.68-0.70 in Florida), and the modified HOSPITAL score demonstrated the best calibration (Brier score: 0.16-0.19 in Maryland and 0.19-0.21 in Florida). Calibration was better in White (compared to Black) populations and other-income (compared to low-income) groups, and the area under the curve was higher or similar in the Black (compared to White) populations. The retrained CMS and modified HOSPITAL score had the lowest racial and income bias in Maryland. In Florida, both of these models overall had the lowest income bias and the modified HOSPITAL score showed the lowest racial bias. In both states, the White and higher-income populations showed a higher FNR, while the Black and low-income populations resulted in a higher FPR and a higher 0-1 loss. When stratified by hospital and population composition, these models demonstrated heterogeneous algorithmic bias in different contexts and populations. CONCLUSIONS: Caution must be taken when interpreting fairness measures' face value. A higher FNR or FPR could potentially reflect missed opportunities or wasted resources, but these measures could also reflect health care use patterns and gaps in care. Simply relying on the statistical notions of bias could obscure or underplay the causes of health disparity. The imperfect health data, analytic frameworks, and the underlying health systems must be carefully considered. Fairness measures can serve as a useful routine assessment to detect disparate model performances but are insufficient to inform mechanisms or policy changes. However, such an assessment is an important first step toward data-driven improvement to address existing health disparities.

Thirty-day readmissions in children with complex chronic conditions.

INTRODUCTION: The rate of hospital readmission within 30 days of discharge is a quality indicator in health care. Paediatric patients with complex chronic conditions have high readmission rates. Failure in the transition between hospital and home care could explain this phenomenon. OBJECTIVES: To estimate the incidence rate of 30-day hospital readmission in paediatric patients with complex chronic conditions, estimate how many are potentially preventable and explore factors associated with readmission. MATERIALS AND METHOD: Cohort study including hospitalised patients with complex chronic conditions aged 1 month to 18 years. Patients with cancer or with congenital heart disease requiring surgical correction were excluded. The outcomes assessed were 30-day readmission rate and potentially preventable readmissions. We analysed sociodemographic, geographic, clinical and transition to home care characteristics as factors potentially associated with readmission. RESULTS: The study included 171 hospitalizations, and 28 patients were readmitted within 30 days (16.4%; 95% CI, 11.6%-22.7%). Of the 28 readmissions, 23 were potentially preventable (82.1%; 95% CI, 64.4%-92.1%). Respiratory disease was associated with a higher probability of readmission. There was no association between 30-day readmission and the characteristics of the transition to home care. CONCLUSIONS: The 30-day readmission rate in patients with complex chronic disease was 16.4%, and 82.1% of readmissions were potentially preventable. Respiratory disease was the only identified risk factor for 30-day readmission.

Impact of pre- and peri-operative risk factors on length of stay and hospital readmission following minimally-invasive partial nephrectomy.

Objective: We conducted an analysis of the American College of Surgeons National Surgical Quality Improvement Program database for minimally-invasive partial nephrectomy cases reported with the goal to identify pre- and peri-operative variables associated with length of stay (LOS) greater than 3 days and readmission within 30 days. Methods: Records from 2008 to 2018 for "laparoscopy, surgical; partial nephrectomy" for prolonged LOS and readmission cohorts were compiled. Univariate analysis with Chi-square, t-tests, and multivariable logistic regression analysis with odds ratios (ORs), p-values, and 95% confidence intervals assessed statistical associations. Results: Totally, 20 306 records for LOS greater than 3 days and 15 854 for readmission within 30 days were available. Univariate and multivariable analysis exhibited similar results. For LOS greater than 3 days, undergoing non-elective surgery (OR=5.247), transfusion of greater than four units within 72 h prior to surgery (OR=5.072), pre-operative renal failure or dialysis (OR=2.941), and poor pre-operative functional status (OR=2.540) exhibited the strongest statistically significant associations. For hospital readmission within 30 days, loss in body weight greater than 10% in 6 months prior to surgery (OR=2.227) and bleeding disorders (OR=2.081) exhibited strongest statistically significant associations. Conclusion: Multiple pre- and peri-operative risk factors are independently associated with prolonged LOS and hospital readmission within 30 days of surgery using the American College of Surgeons National Surgical Quality Improvement Program data. Recognizing the risks factors that can potentially be improved prior to minimally-invasive partial nephrectomy is crucial to informing patient selection, optimization strategies, and patient education.

Association of hospital and market characteristics with 30-day readmission rates from 2009 to 2015.

Objectives: The US government implemented the Hospital Readmission Reduction Program on 1 October 2012 to reduce readmission rates through financial penalties to hospitals with excessive readmissions. We conducted a pooled cross-sectional analysis of US hospitals from 2009 to 2015 to determine the association of the Hospital Readmission Reduction Program with 30-day readmissions. Methods: We utilized multivariable linear regression with year and state fixed effects. The model was adjusted for hospital and market characteristics lagged by 1 year. Interaction effects of hospital and market characteristics with the Hospital Readmission Reduction Program indicator variable was also included to assess whether associations of Hospital Readmission Reduction Program with 30-day readmissions differed by these characteristics. Results: In multivariable adjusted analysis, the main effect of the Hospital Readmission Reduction Program was a 3.80 percentage point (p < 0.001) decrease in readmission rates in 2013-2015 relative to 2009-2012. Hospitals with lower readmission rates overall included not-for-profit and government hospitals, medium and large hospitals, those in markets with a larger percentage of Hispanic residents, and population 65 years and older. Higher hospital readmission rates were observed among those with higher licensed practical nurse staffing ratio, larger Medicare and Medicaid share, and less competition. Statistically significant interaction effects between hospital/market characteristics and the Hospital Readmission Reduction Program on the outcome of 30-day readmission rates were present. Teaching hospitals, rural hospitals, and hospitals in markets with a higher percentage of residents who were Black experienced larger decreases in readmission rates. Hospitals with larger registered nurse staffing ratios and in markets with higher uninsured rate and percentage of residents with a high school education or greater experienced smaller decreases in readmission rates. Conclusion: Findings of the current study support the effectiveness of the Hospital Readmission Reduction Program but also point to the need to consider the ability of hospitals to respond to penalties and incentives based on their characteristics during policy development.

Risk Factors for Hospital Readmission in Patients With Interstitial Lung Disease.

BACKGROUND: Little is known about the rates, causes, or risk factors for hospital readmission among patients with interstitial lung disease (ILD). We investigated the prevalence, features, and comorbidities of subjects hospitalized with ILD and their subsequent re-hospitalizations in this retrospective study. METHODS: A retrospective analysis of subjects enrolled in the University of Chicago ILD Natural History registry was conducted. Demographic data, comorbidities, and timing and cause of subsequent hospitalizations were collected from the medical record. The primary outcome was time to first readmission via a cause-specific Cox hazards model with a sensitivity analysis with the Fine-Gray cumulative hazard model; the secondary outcome was the number of hospitalizations per subject via a Poisson multivariable model. RESULTS: Among 1,796 patients with ILD, 443 subjects were hospitalized, with 978 total hospitalizations; 535 readmissions were studied, 282 (53%) for a respiratory indication. For the outcome of time to readmission, Black race was the only subject characteristic associated with an increased hazard of readmission in the Cox model (hazard ratio 1.50, P = .03) while Black race, hypersensitivity pneumonitis, and sarcoidosis were associated with increased hazard of readmission in the Fine-Gray model. Black race, female sex, atrial fibrillation, obstructive lung disease, and pulmonary hypertension were associated with an increased number of hospitalizations in the Poisson model. CONCLUSIONS: We demonstrated that hospital readmission from any cause was a common occurrence in subjects with ILD. Further efforts to improve quality of life among these subjects could focus on risk scores for readmission, mitigating racial health disparities, and treatment of comorbidities.

Characterizing Current and Optimal Involvement of Hospital Pharmacists in the Discharge Process: A Survey of Pharmacists in British Columbia.

Background: Transitions of care represent a vulnerable time when patients are at increased risk of medication errors. Medication-related problems constitute one of the main contributors to hospital readmissions. Discharge interventions carried out by pharmacists have been shown to reduce hospital readmissions. Although clinical pharmacists in British Columbia are involved in discharges, their degree of involvement and the interventions they prioritize in practice have not been fully elucidated. Objectives: To characterize the current involvement of BC hospital pharmacists at the time of discharge, to identify which discharge interventions they believe should be prioritized, and who they feel should be responsible for these interventions, as well as to identify strategies to optimize the discharge process. Methods: A survey of BC hospital pharmacists was conducted in January and February 2022. The survey included questions about pharmacists' current involvement at the time of discharge, interventions required for a successful discharge, solutions for optimizing the patient discharge process, and participants' baseline characteristics. Results: The survey response rate was 20% (101/500). Pharmacists reported performing all interventions for less than 60% of their patients. Interventions such as medication reconciliation on discharge, medication education, and ensuring adherence were considered very important for a successful discharge and were considered to be best performed by pharmacists. Solutions for optimizing the discharge process included improved staffing, weekend coverage, timely notification of discharge, and prescribing by pharmacists. Conclusions: Despite the belief that most interventions listed in the survey are necessary for successful discharge, various barriers prevented pharmacists from providing them to all patients. Increased resources and expanded scope of practice for pharmacists could reduce hospital readmissions and enable broader implementation of discharge interventions.

Contexte: Les transitions de soins sont une période vulnérable pendant laquelle les patients courent un risque accru d'erreurs médicamenteuses. Les problèmes liés aux médicaments constituent l'un des principaux contributeurs aux réadmissions à l'hôpital. Il a été démontré que les interventions au moment du congé effectuées par les pharmaciens réduisent les réadmissions à l'hôpital. Même si les pharmaciens cliniciens de la Colombie-Britannique participent aux congés, leur degré de participation et les interventions qu'ils privilégient dans la pratique n'ont pas été entièrement élucidés. Objectifs: Caractériser l'implication actuelle des pharmaciens des hôpitaux de la Colombie-Britannique au moment du congé; recenser les interventions à ce moment qui, selon eux, devraient être prioritaires et quel praticien, selon eux encore, devrait être responsable de ces interventions; enfin, déterminer des stratégies pour optimiser le processus de congé de l'hôpital. Méthodes: Une enquête auprès des pharmaciens hospitaliers de la Colombie-Britannique a été menée en janvier et février 2022. L'enquête comprenait des questions sur l'implication actuelle des pharmaciens au moment du congé du patient, les interventions requises pour sa réussite, les solutions pour optimiser son processus ainsi que les caractéristiques de base des participants. Résultats: Le taux de réponse à l'enquête était de 20 % (101/500). Les pharmaciens ont déclaré avoir effectué toutes les interventions auprès de moins de 60 % de leurs patients. Les interventions telles que le bilan comparatif des médicaments à la sortie, l'éducation sur les médicaments et l'assurance de l'observance étaient considérées comme très importantes pour la réussite du congé et les pharmaciens étaient considérés comme étant les mieux placés pour effectuer ces interventions. Les solutions suggérées pour optimiser le processus comprenaient un meilleur personnel, une couverture le week-end, une notification en temps opportun du congé et des prescriptions par les pharmaciens. Conclusions: Même si l'on croit que la plupart des interventions énumérées dans l'enquête sont nécessaires pour la réussite du congé hospitalier, divers obstacles ont empêché les pharmaciens de les proposer à tous les patients. Des ressources accrues et un champ d'exercice élargi pour les pharmaciens pourraient réduire les réadmissions à l'hôpital et permettre une mise en oeuvre élargie des interventions au moment du congé.

Machine Learning-Based Predictive Models for 90-Day Readmission of Total Joint Arthroplasty Using Comprehensive Electronic Health Records and Patient-Reported Outcome Measures.

Background: The Centers for Medicare & Medicaid Services currently incentivizes hospitals to reduce postdischarge adverse events such as unplanned hospital readmissions for patients who underwent total joint arthroplasty (TJA). This study aimed to predict 90-day TJA readmissions from our comprehensive electronic health record data and routinely collected patient-reported outcome measures. Methods: We retrospectively queried all TJA-related readmissions in our tertiary care center between 2016 and 2019. A total of 104-episode care characteristics and preoperative patient-reported outcome measures were used to develop several machine learning models for prediction performance evaluation and comparison. For interpretability, a logistic regression model was built to investigate the statistical significance, magnitudes, and directions of associations between risk factors and readmission. Results: Given the significant imbalanced outcome (5.8% of patients were readmitted), our models robustly predicted the outcome, yielding areas under the receiver operating characteristic curves over 0.8, recalls over 0.5, and precisions over 0.5. In addition, the logistic regression model identified risk factors predicting readmission: diabetes, preadmission medication prescriptions (ie, nonsteroidal anti-inflammatory drug, corticosteroid, and narcotic), discharge to a skilled nursing facility, and postdischarge care behaviors within 90 days. Notably, low self-reported confidence to carry out social activities accurately predicted readmission. Conclusions: A machine learning model can help identify patients who are at substantially increased risk of a readmission after TJA. This finding may allow for health-care providers to increase resources targeting these patients. In addition, a poor response to the "social activities" question may be a useful indicator that predicts a significant increased risk of readmission after TJA.

Impact of Program Changes Including Telemedicine and Telephonic Care During the COVID-19 Pandemic in Preventing 30-Day Hospital Readmission for Patients in a Care Transitions Program.

INTRODUCTION/OBJECTIVES: To describe health outcomes of older adults enrolled in the Mayo Clinic Care Transitions (MCCT) program before and during the COVID-19 pandemic compared to unenrolled patients. METHODS: We conducted a retrospective cohort study of adults (age >60 years) in the MCCT program compared to a usual care control group from January 1, 2019, to September 20, 2022. The MCCT program involved a home, telephonic, or telemedicine visit by an advanced care provider. Outcomes were 30- and 180-day hospital readmissions, emergency department (ED) visit, and mortality. We performed a subgroup analysis after March 1, 2020 (during the pandemic). We analyzed data with Cox proportional hazards regression models and hazard ratios (HRs) with 95% CIs. RESULTS: Of the 1,012 patients total, 354 were in the MCCT program and 658 were in the usual care group with a mean (SD) age of 81.1 (9.1) years overall. Thirty-day readmission was 16.9% (60 of 354) for MCCT patients and 14.7% (97 of 658) for usual care patients (HR, 1.24; 95% CI, 0.88-1.75). During the pandemic, the 30-day readmission rate was 15.1% (28 of 186) for MCCT patients and 14.9% (68 of 455) for usual care patients (HR, 1.20; 95% CI, 0.75-1.91). There was no difference between groups for 180-day hospitalization, 30- or 180-day ED visit, and 30- or 180-day mortality. CONCLUSIONS: Numerous factors involving patients, providers, and health care delivery systems during the pandemic most likely contributed to these findings.

Practice patterns and complications of hysterectomy for invasive cervical cancer after the Laparoscopic Approach to Cervical Cancer trial.

BACKGROUND: After the publication of the Laparoscopic Approach to Cervical Cancer trial, the standard surgical approach for early-stage cervical cancer is open radical hysterectomy. Only limited data were available regarding whether the change to open abdominal hysterectomy observed after the Laparoscopic Approach to Cervical Cancer trial led to an increase in postoperative complication rates as a consequence of the decrease in the use of the minimally invasive approach. OBJECTIVE: This study aimed to analyze whether there was a correlation between the publication of the Laparoscopic Approach to Cervical Cancer trial and an increase in the 30-day complications associated with surgical treatment of invasive cervical cancer. STUDY DESIGN: Data from the American College of Surgeons National Surgical Quality Improvement Program were used to compare the results in the pre-Laparoscopic Approach to Cervical Cancer period (January 2016 to December 2017) vs the results in the post-Laparoscopic Approach to Cervical Cancer period (January 2019 to December 2020). The rates of each surgical approach (open abdominal or minimally invasive) hysterectomy for invasive cervical cancer during the 2 periods were assessed. Subsequently, 30-day major complication, minor complication, unplanned hospital readmission, and intra- or postoperative transfusion rates before and after the publication of the Laparoscopic Approach to Cervical Cancer trial were compared. RESULTS: Overall, 3024 patients undergoing either open abdominal hysterectomy or minimally invasive hysterectomy for invasive cervical cancer were included in the study. Of the patients, 1515 (50.1%) were treated in the pre-Laparoscopic Approach to Cervical Cancer period, and 1509 (49.9%) were treated in the post-Laparoscopic Approach to Cervical Cancer period. The rate of minimally invasive approaches decreased significantly from 75.6% (1145/1515) in the pre-Laparoscopic Approach to Cervical Cancer period to 41.1% (620/1509) in the post-Laparoscopic Approach to Cervical Cancer period, whereas the rate of open abdominal approach increased from 24.4% (370/1515) in the pre-Laparoscopic Approach to Cervical Cancer period to 58.9% (889/1509) in the post-Laparoscopic Approach to Cervical Cancer period (P<.001). The overall 30-day major complications remained stable between the pre-Laparoscopic Approach to Cervical Cancer period (85/1515 [5.6%]) and the post-Laparoscopic Approach to Cervical Cancer period (74/1509 [4.9%]) (adjusted odds ratio, 0.85; 95% confidence interval, 0.61-1.17). The overall 30-day minor complications were similar in the pre-Laparoscopic Approach to Cervical Cancer period (103/1515 [6.8%]) vs the post-Laparoscopic Approach to Cervical Cancer period (120/1509 [8.0%]) (adjusted odds ratio, 1.17; 95% confidence interval, 0.89-1.55). The unplanned hospital readmission rate remained stable during the pre-Laparoscopic Approach to Cervical Cancer period (7.9% per 30 person-days) and during the post-Laparoscopic Approach to Cervical Cancer period (6.3% per 30 person-days) (adjusted hazard ratio, 0.78; 95% confidence interval, 0.58-1.04)]. The intra- and postoperative transfusion rates increased significantly from 3.8% (58/1515) in the pre-Laparoscopic Approach to Cervical Cancer period to 6.7% (101/1509) in the post-Laparoscopic Approach to Cervical Cancer period (adjusted odds ratio, 1.79; 95% confidence interval, 1.27-2.53). CONCLUSION: This study observed a significant shift in the surgical approach for invasive cervical cancer after the publication of the Laparoscopic Approach to Cervical Cancer trial, with a reduction in the minimally invasive abdominal approach and an increase in the open abdominal approach. The change in surgical approach was not associated with an increase in the rate of 30-day major or minor complications and unplanned hospital readmission, although it was associated with an increase in the transfusion rate.

An overview of reviews and synthesis across 440 studies examines the importance of hospital readmission predictors across various patient populations.

OBJECTIVES: The scientific literature contains an abundance of prediction models for hospital readmissions. However, no review has yet synthesized their predictors across various patient populations. Therefore, our aim was to examine predictors of hospital readmissions across 13 patient populations. STUDY DESIGN AND SETTING: An overview of systematic reviews was combined with a meta-analytical approach. Two thousand five hundred four different predictors were categorized using common ontologies to pool and examine their odds ratios and frequencies of use in prediction models across and within different patient populations. RESULTS: Twenty-eight systematic reviews with 440 primary studies were included. Numerous predictors related to prior use of healthcare services (odds ratio; 95% confidence interval: 1.64; 1.42-1.89), diagnoses (1.41; 1.31-1.51), health status (1.35; 1.20-1.52), medications (1.28; 1.13-1.44), administrative information about the index hospitalization (1.23; 1.14-1.33), clinical procedures (1.20; 1.07-1.35), laboratory results (1.18; 1.11-1.25), demographic information (1.10; 1.06-1.14), and socioeconomic status (1.07; 1.02-1.11) were analyzed. Diagnoses were frequently used (in 37.38%) and displayed large effect sizes across all populations. Prior use of healthcare services showed the largest effect sizes but were seldomly used (in 2.57%), whereas demographic information (in 13.18%) was frequently used but displayed small effect sizes. CONCLUSION: Diagnoses and patients' prior use of healthcare services showed large effects both across and within different populations. These results can serve as a foundation for future prediction modeling.

Machine learning for hospital readmission prediction in pediatric population.

BACKGROUND AND OBJECTIVE: Pediatric readmissions are a burden on patients, families, and the healthcare system. In order to identify patients at higher readmission risk, more accurate techniques, as machine learning (ML), could be a good strategy to expand the knowledge in this area. The aim of this study was to develop predictive models capable of identifying children and adolescents at high risk of potentially avoidable 30-day readmission using ML. METHODS: Retrospective cohort study was carried out with 9,080 patients under 18 years old admitted to a tertiary university hospital. Demographic, clinical, and biochemical data were collected from electronic databases. We randomly divided the dataset into training (75 %) and testing (25 %), applied downsampling, repeated cross-validation with five folds and ten repetitions, and the hyperparameter was optimized of each technique using a grid search via racing with ANOVA models. We applied six ML classification algorithms to build the predictive models, including classification and regression tree (CART), random forest (RF), gradient boosting machine (GBM), extreme gradient boosting (XGBoost), decision tree and logistic regression (LR). The area under the receiver operating curve (AUC), sensitivity, specificity, Youden's J-index and accuracy were used to evaluate the performance of each model. RESULTS: The avoidable 30-day hospital readmissions rate was 9.5 %. Some algorithms presented similar AUC, both in the dataset training and in the dataset testing, such as XGBoost, RF, GBM and CART. Considering the Youden's J-index, the algorithm that presented the best index was XGBoost with bagging imputation, with AUC of 0.814 (J-index of 0.484). Cancer diagnosis, age, red blood cells, leukocytes, red cell distribution width and sodium levels, elective admission, and multimorbidity were the most important characteristics to classify between readmission and non-readmission groups. CONCLUSION: Machine learning approaches, especially XGBoost, can predict potentially avoidable 30-day pediatric hospital readmission into tertiary assistance. If implemented in the computer hospital system, our model can help in the early and more accurate identification of patients at readmission risk, targeting health strategic interventions.