Effects of discharge planning services and unplanned readmissions on post-hospital mortality in older patients: a time-varying survival analysis

Influence of physical function and frailty on unplanned readmission in middle-aged and older patients discharged from a hospital: a follow-up study

BACKGROUND

Unplanned readmissions are associated with increased mortality among older patients. This study investigated the effects of changes in physical function and frailty on unplanned readmissions in middle-aged and older patients after discharge.

METHODS

This longitudinal study recruited participants through convenience sampling from the general wards of a medical center in northern Taiwan. They were aged 50 years or older and identified as being at high risk for readmission or mortality following discharge. Baseline data were collected through interviews conducted the day before discharged, while follow-up data were obtained through interviews at 1, 2, and 3 months post-discharge. Generalized estimating equation (GEE) was used for statistical analysis, incorporating all tracked variables, including physical function and frailty.

RESULTS

A total of 230 participants were recruited, each followed three times after discharge. The unplanned readmission rates at 1, 2, and 3 months post-discharge were 2%, 8%, and 14%, respectively. Participants with poorer physical function (odds ratio [OR] = 1.60 [1.27-2.02]) and more severe frailty symptoms (OR = 3.16 [1.45-6.83]) had significantly higher odds of unplanned readmission. The interaction between the time and frailty indicated a significantly lower likelihood of unplanned readmission over time (OR = 0.73 [0.54-0.98]).

CONCLUSIONS

Declining physical function and frailty are key risk factors for unplanned readmission in older patients. Effective strategies to reduce this risk include monitoring physical function and frailty symptoms and providing supportive care services.

Factors influencing communication issues during hospital discharge for older adults in 11 high-income countries: a secondary analysis of the 2021 International Health Policy Survey

OBJECTIVES

To determine the prevalence of hospital discharge communication problems with older adults, compare them across countries and determine factors associated with those problems.

DESIGN

Secondary analysis of cross-sectional survey data.

SETTING

2021 Commonwealth Fund International Health Policy (IHP) Survey of Older Adults conducted across 11 high-income countries, including Australia, Canada, France, Germany, the Netherlands, New Zealand, Norway, Sweden, Switzerland, the UK and the USA.

PARTICIPANTS

4501 respondents aged 60 and older in the USA and 65 and older in all other included countries who were hospitalised at least once in the past 2 years before the survey and answered discharge communication-related questions.

PRIMARY OUTCOME MEASURE

Our primary outcome measure is poor discharge communication (PDC), a composite variable of three IHP questions related to written information, doctor follow-up and medicines discussed.

RESULTS

Overall PDC rate was 19.2% (864/4501), although rates varied by nation. PDC was highest in Norway (31.5%) and lowest in the USA (7.5%). Gender, education, income and the presence of at least one chronic disease were not statistically associated with PDC.

CONCLUSIONS

Given the high rate of PDC observed, hospital discharge teams and leadership should carefully examine communication during the hospital discharge process to ensure minimisation of care gaps, particularly regarding medication, since this was the most reported problem.

Trends in Veteran hospitalizations and associated readmissions and emergency department visits during the MISSION Act era

OBJECTIVE

To examine changes in hospitalization trends and healthcare utilization among Veterans following Maintaining Internal Systems and Strengthening Integrated Outside Networks (MISSION) Act implementation.

DATA SOURCES AND STUDY SETTING

VA Corporate Data Warehouse and Centers for Medicare and Medicaid Services datasets.

STUDY DESIGN

Retrospective cohort study to compare 7- and 30-day rates for unplanned readmission and emergency department visits following index hospital stays based on payor type (VHA facility stay, VA-funded stay in community facility [CC], or Medicare-funded community stay [CMS]). Segmented regression models were used to compare payors and estimate changes in outcome levels and slopes following MISSION Act implementation.

DATA COLLECTION/EXTRACTION METHODS

Veterans with active VA primary care utilization and ≥1 acute hospitalization between January 1, 2016 and December 31, 2021.

PRINCIPAL FINDINGS

Monthly index stays increased for all payors until MISSION Act implementation, when VHA and CMS admissions declined while CC admissions accelerated and overtook VHA admissions. In December 2021, CC admissions accounted for 54% of index admissions, up from 25% in January 2016. From adjusted models, just prior to implementation (May 2019), Veterans with CC admissions had 47% greater risk of 7-day readmission (risk ratio [RR]: 1.47, 95% confidence interval [CI]: 1.43, 1.51) and 20% greater risk of 30-day readmission (RR: 1.20, 95% CI: 1.19, 1.22) compared with those with VHA admissions; both effects persisted post-implementation. Pre-implementation CC admissions were also associated with higher 7- and 30-day ED visits, but both risks were substantially lower by study termination (RR: 0.90, 95% CI: 0.88, 0.91) and (RR: 0.89, 95% CI: 0.87, 0.90), respectively.

CONCLUSIONS

MISSION Act implementation was associated with substantial shifts in treatment site and federal payor for Veteran hospitalizations. Post-implementation readmission risk was estimated to be higher for those with CC and CMS index admissions, while post-implementation risk of ED utilization following CC admissions was estimated to be lower compared with VHA index admissions. Reasons for this divergence require further investigation.

A systematic literature review of predicting patient discharges using statistical methods and machine learning

Discharge planning is integral to patient flow as delays can lead to hospital-wide congestion. Because a structured discharge plan can reduce hospital length of stay while enhancing patient satisfaction, this topic has caught the interest of many healthcare professionals and researchers. Predicting discharge outcomes, such as destination and time, is crucial in discharge planning by helping healthcare providers anticipate patient needs and resource requirements. This article examines the literature on the prediction of various discharge outcomes. Our review discovered papers that explore the use of prediction models to forecast the time, volume, and destination of discharged patients. Of the 101 reviewed papers, 49.5% looked at the prediction with machine learning tools, and 50.5% focused on prediction with statistical methods. The fact that knowing discharge outcomes in advance affects operational, tactical, medical, and administrative aspects is a frequent theme in the papers studied. Furthermore, conducting system-wide optimization, predicting the time and destination of patients after discharge, and addressing the primary causes of discharge delay in the process are among the recommendations for further research in this field.

A nursing note-aware deep neural network for predicting mortality risk after hospital discharge

BACKGROUND

ICU readmissions and post-discharge mortality pose significant challenges. Previous studies used EHRs and machine learning models, but mostly focused on structured data. Nursing records contain crucial unstructured information, but their utilization is challenging. Natural language processing (NLP) can extract structured features from clinical text. This study proposes the Crucial Nursing Description Extractor (CNDE) to predict post-ICU discharge mortality rates and identify high-risk patients for unplanned readmission by analyzing electronic nursing records.

OBJECTIVE

Developed a deep neural network (NurnaNet) with the ability to perceive nursing records, combined with a bio-clinical medicine pre-trained language model (BioClinicalBERT) to analyze the electronic health records (EHRs) in the MIMIC III dataset to predict the death of patients within six month and two year risk.

DESIGN

A cohort and system development design was used.

SETTING(S)

Based on data extracted from MIMIC-III, a database of critically ill in the US between 2001 and 2012, the results were analyzed.

PARTICIPANTS

We calculated patients' age using admission time and date of birth information from the MIMIC dataset. Patients under 18 or over 89 years old, or who died in the hospital, were excluded. We analyzed 16,973 nursing records from patients' ICU stays.

METHODS

We have developed a technology called the Crucial Nursing Description Extractor (CNDE), which extracts key content from text. We use the logarithmic likelihood ratio to extract keywords and combine BioClinicalBERT. We predict the survival of discharged patients after six months and two years and evaluate the performance of the model using precision, recall, the F1-score, the receiver operating characteristic curve (ROC curve), the area under the curve (AUC), and the precision-recall curve (PR curve).

RESULTS

The research findings indicate that NurnaNet achieved good F1-scores (0.67030, 0.70874) within six months and two years. Compared to using BioClinicalBERT alone, there was an improvement in performance of 2.05 % and 1.08 % for predictions within six months and two years, respectively.

CONCLUSIONS

CNDE can effectively reduce long-form records and extract key content. NurnaNet has a good F1-score in analyzing the data of nursing records, which helps to identify the risk of death of patients after leaving the hospital and adjust the regular follow-up and treatment plan of relevant medical care as soon as possible.

A Neurosurgical Readmissions Reduction Program in an Academic Hospital Leveraging Machine Learning, Workflow Analysis, and Simulation

BACKGROUND

 Predicting 30-day hospital readmissions is crucial for improving patient outcomes, optimizing resource allocation, and achieving financial savings. Existing studies reporting the development of machine learning (ML) models predictive of neurosurgical readmissions do not report factors related to clinical implementation.

OBJECTIVES

 Train individual predictive models with good performance (area under the receiver operating characteristic curve or AUROC > 0.8), identify potential interventions through semi-structured interviews, and demonstrate estimated clinical and financial impact of these models.

METHODS

 Electronic health records were utilized with five ML methodologies: gradient boosting, decision tree, random forest, ridge logistic regression, and linear support vector machine. Variables of interest were determined by domain experts and literature. The dataset was split divided 80% for training and validation and 20% for testing randomly. Clinical workflow analysis was conducted using semi-structured interviews to identify possible intervention points. Calibrated agent-based models (ABMs), based on a previous study with interventions, were applied to simulate reductions of the 30-day readmission rate and financial costs.

RESULTS

 The dataset covered 12,334 neurosurgical intensive care unit (NSICU) admissions (11,029 patients); 1,903 spine surgery admissions (1,641 patients), and 2,208 traumatic brain injury (TBI) admissions (2,185 patients), with readmission rate of 13.13, 13.93, and 23.73%, respectively. The random forest model for NSICU achieved best performance with an AUROC score of 0.89, capturing potential patients effectively. Six interventions were identified through 12 semi-structured interviews targeting preoperative, inpatient stay, discharge phases, and follow-up phases. Calibrated ABMs simulated median readmission reduction rates and resulted in 13.13 to 10.12% (NSICU), 13.90 to 10.98% (spine surgery), and 23.64 to 21.20% (TBI). Approximately $1,300,614.28 in saving resulted from potential interventions.

CONCLUSION

 This study reports the successful development and simulation of an ML-based approach for predicting and reducing 30-day hospital readmissions in neurosurgery. The intervention shows feasibility in improving patient outcomes and reducing financial losses.

Patient and family perceptions of a discharge bedside board

Objective

To explore patient and family perspectives of a discharge bedside board for supporting engagement in patient care and discharge planning to inform tool revision.

Methods

This qualitative descriptive study included 45 semi-structured interviews with a purposeful sample of English-speaking patients (n = 44; mean age 58.5 years) and their family members (n = 5) across seven adult inpatient units at a tertiary acute care hospital in mid-western Canada. Thematic (interviews), content (board, organization procedure document), and framework-guided integrated (all data) analyses were performed.

Results

Four themes were generated from interview data: understanding the board, included essential information to guide care, balancing information on the board, and maintaining a sense of connection. Despite application inconsistencies, documented standard procedures aligned with recommended board (re)orientation, timely patient-friendly content, attention to privacy, and patient-provider engagement strategies.

Conclusion

Findings indicate the tool supported consultation and some involvement level engagement in patient care and discharge. Board information was usually valued, however, perceived procedural gaps in tool education, privacy, and the quality of tool-related communication offer opportunities to strengthen patients' and families' tool experience.

Innovation

Novel application of a continuum engagement framework in the exploration of multiple data sources generated significant insights to guide tool revision.

Utilizing Design Thinking for Effective Multidisciplinary Diabetes Management

(1) Background: Design thinking, as a human-centered design method, represents a unique framework to support the planning, testing, and evaluation of new clinical spaces for diabetic care throughout all phases of construction. This approach prioritizes the needs and experiences of diabetic patients to create innovative and effective healthcare environments. By applying design-thinking principles, healthcare facilities can optimize the design and functionality of their clinical spaces, ensuring a patient-centered approach to diabetic care. This holistic and personalized approach can ultimately enhance the overall quality of diabetic care provided to patients. (2) Methods: The study used the action research method and progressively explored diabetes patients' needs and preferences for care, subsequently developing creative solutions to achieve the goals. There were six doctors, seven nursing staffs, four case managers and three family members who participated in the design-thinking workshop. (3) Results: The participating trainees in this study developed unique and innovative solutions during the iterative process of "divergent thinking" and "focused thinking", including diabetes dietary guidelines for food ordering and delivery platforms, and the design of accompanying health-education picture books to enable patients to learn the care process and precautions before, during, and after discharge. (4) Conclusions: This continuing education model promoted sharing among participants, improved collaboration and mutual learning, and increased motivation through goal setting.

Health professionals' experience of implementing and delivering a 'Community Care' programme in metropolitan Melbourne: a qualitative reflexive thematic analysis

OBJECTIVES

To explore the experiences of health professionals involved in delivering a multidisciplinary Community Care programme that provides a transitional care coordination service for patients visiting a tertiary hospital service in Melbourne, Australia.

DESIGN

Reflexive thematic analysis was used to identify themes from descriptions of delivering the programme, including its perceived strengths and challenges.

PARTICIPANTS

12 healthcare professionals from four disciplines working in the Community Care programme were interviewed.

RESULTS

Four themes were identified: (1) 'increasingly complex', depicts the experience of delivering care to patients with increasingly complex health needs; (2) 'plugging unexpected gaps', describes meeting patient's healthcare needs; (3) 'disconnected', explains system-based issues which made participants feel disconnected from the wider health service; (4) 'a misunderstood programme', illustrates that a poor understanding of the programme within the health service is a barrier to patient enrolment which may have been exacerbated by a service name change.

CONCLUSIONS

The healthcare professionals involved in this study described the experience of providing care to patients as challenging, but felt they made a positive difference. By unravelling the patients' health problems in context of their surroundings, they were able to recognise the increasingly complex patients' health needs. The disconnection they faced to integrate within the wider healthcare system made their role at times difficult. This disconnection was partly contributed to by the fact that they felt the programme was misunderstood.