Applicability of predictive models for 30-day unplanned hospital readmission risk in paediatrics: a systematic review

Decision tree model development and in silico validation for avoidable hospital readmissions at 30 days in a pediatric population

Introduction

Background and objective: identifying patients at high risk of avoidable readmission remains a challenge for healthcare professionals. Despite the recent interest in Machine Learning in this topic, studies are scarce and commonly using only black box algorithms. The aim of our study was to develop and validate in silico an interpretable predictive model using a decision tree inference to identify pediatric patients at risk of 30-day potentially avoidable readmissions. Methods: a retrospective cohort study was conducted with all patients under 18 years admitted to a tertiary university hospital. Demographic, clinical and nutritional data were collected from electronic databases. The outcome was the potentially avoidable 30-day readmissions. The J48 algorithm was used to develop the best-fit trees capable of classifying the outcome efficiently. Leave-one-out cross-validation was applied and we computed the area under the receiver operating curve (AUC). Results: the most important attributes of the model were C-reactive protein, hemoglobin and sodium levels, besides nutritional monitoring. We obtained an AUC of 0.65 and accuracy of 63.3 % for the full training and leave-one-out cross-validation. Conclusion: our model allows the identification of 30-day potentially avoidable readmissions through practical indicators facilitating timely interventions by the medical team, and might contribute to reduce this outcome.

Hospital readmission following acute illness among children 2-23 months old in sub-Saharan Africa and South Asia: a secondary analysis of CHAIN cohort

Background

Children in low and middle-income countries remain vulnerable following hospital-discharge. We estimated the incidence and correlates of hospital readmission among young children admitted to nine hospitals in sub-Saharan Africa and South Asia.

Methods

This was a secondary analysis of the CHAIN Network prospective cohort enrolled between 20th November 2016 and 31st January 2019. Children aged 2-23 months were eligible for enrolment, if admitted for an acute illness to one of the study hospitals. Exclusions were requiring immediate resuscitation, inability to tolerate oral feeds in their normal state of health, had suspected terminal illness, suspected chromosomal abnormality, trauma, admission for surgery, or their parent/caregiver was unwilling to participate and attend follow-up visits. Data from children discharged alive from the index admission were analysed for hospital readmission within 180-days from discharge. We examined ratios of readmission to post-discharge mortality rates. Using models with death as the competing event, we evaluated demographic, nutritional, clinical, and socioeconomic associations with readmission.

Findings

Of 2874 children (1239 (43%) girls, median (IQR) age 10.8 (6.8-15.6) months), 655 readmission episodes occurred among 506 (18%) children (198 (39%) girls): 391 (14%) with one, and 115 (4%) with multiple readmissions, with a rate of: 41.0 (95% CI 38.0-44.3) readmissions/1000 child-months. Median time to readmission was 42 (IQR 15-93) days. 460/655 (70%) and 195/655 (30%) readmissions occurred at index study hospital and non-study hospitals respectively. One-third (N = 213/655, 33%) of readmissions occurred within 30 days of index discharge. Sites with fewest readmissions had the highest post-discharge mortality. Most readmissions to study hospitals (371/450, 81%) were for the same illness as the index admission. Age, prior hospitalisation, chronic conditions, illness severity, and maternal mental health score, but not sex, nutritional status, or physical access to healthcare, were associated with readmission.

Interpretation

Readmissions may be appropriate and necessary to reduce post-discharge mortality in high mortality settings. Social and financial support, training on recognition of serious illness for caregivers, and improving discharge procedures, continuity of care and facilitation of readmission need to be tested in intervention studies. We propose the ratio of readmission to post-discharge mortality rates as a marker of overall post-discharge access and care.

Funding

The Bill & Melinda Gates Foundation (OPP1131320).

Factors associated with hospital admission and 30-day readmission for children less than 18 years of age in 2018 in France: a one-year nationwide observational study

BACKGROUND

Nationwide data for children for short-stay hospitalisation (SSH) and associated factors are scarce. This retrospective study of children in France < 18 years of age followed after their birth or birthday in 2018 focused on at least one annual SSH, stay < 1 night or ≥ 1 night, or 30-day readmission ≥ 1 night.

METHODS

Children were selected from the national health data system (SNDS), which includes data on long-term chronic disease (LTD) status with full reimbursement and complementary universal coverage based on low household income (CMUC). Uni and multivariate quasi-Poisson regression were applied for each outcome.

RESULTS

Among 13.211 million children (94.4% population, 51.2% boys), CMUC was identified for 17.5% and at least one LTD for 4% (0-<1 year: 1.5%; 14-<18 year: 5.2%). The most frequent LTDs were pervasive developmental diseases (0.53%), asthma (0.24%), epilepsy (0.17%), and type 1 diabetes (0.15%). At least one SSH was found for 8.8%: SSH < 1 night (4.9%), SSH ≥ 1 night (4.5%), readmission (0.4%). Children with at least one SSH were younger (median 6 vs. 9 years) and more often had CMUC (21%), a LTD (12%), an emergency department (ED) visit (56%), or various primary healthcare visits than all children. Those with a SSH ≥1 night vs. < 1 night were older (median: 9 vs. 4 years). They had the same frequency of LTD (13.4%) but more often an ED visit (78% vs. 42%). Children with readmissions were younger (median 3 years). They had the highest levels of CMUC (29.3%), LTD (34%), EDs in their municipality (35% vs. 29% for the whole population) and ED visits (87%). In adjusted analysis, each outcome was significantly less frequent among girls than boys and more frequent for children with CMUC. LTDs with the largest association with SSH < 1 night were cystic fibrosis, sickle cell diseases (SCD), diabetes type 1, those with SSH ≥1 night type 1 diabetes epilepsy and SCD, and those for readmissions lymphoid leukaemia, malignant neoplasm of the brain, and SCD. Among all SSH admissions of children < 10 years, 25.8% were potentially preventable.

CONCLUSION

Higher SSH and readmission rates were found for children with certain LTD living in low-income households, suggesting the need or increase of specific policy actions and research.

Data transforming: A concept analysis

PURPOSE

The aims of this study are to clarify the concept of how data retrieved from electronic health records (EHR) are transformed into nurses' tacit knowledge for evidence-based practice from a cognitive perspective at a macro-organizational level, and to identify this concept's attributes, antecedents, and consequences in the nursing field.

SOURCE

A literature review was conducted by performing a search on scientific databases using the key terms "data," "transform," "EHR," "nursing," "tacit knowledge," "organization," "data," "interpretation," and "healthcare." Forty-nine articles and four books were selected for the analysis. The process was audited by two independent experts to ensure neutrality and credibility.

CONCLUSION

Data transforming is a complex cognitive process among different groups of data stakeholders at a macro-organizational level. The concept of data transforming has three attributes: analytical, respectful, and social. The antecedents of these attributes are skillful, immersive, and mission-driven. They have either positive or negative consequences for frontline nurses. These findings not only add to the body of knowledge but also serve as an important impetus for further theory development and research in nursing.