Examining the predictability and prognostication of multimorbidity among older Delayed-Discharge Patients: A Machine learning analytics

Developing a decision support tool to predict delayed discharge from hospitals using machine learning

BACKGROUND

The growing demand for healthcare services challenges patient flow management in health systems. Alternative Level of Care (ALC) patients who no longer need acute care yet face discharge barriers contribute to prolonged stays and hospital overcrowding. Predicting these patients at admission allows for better resource planning, reducing bottlenecks, and improving flow. This study addresses three objectives: identifying likely ALC patients, key predictive features, and preparing guidelines for early ALC identification at admission.

METHODS

Data from Nova Scotia Health (2015-2022) covering patient demographics, diagnoses, and clinical information was extracted. Data preparation involved managing outliers, feature engineering, handling missing values, transforming categorical variables, and standardizing. Data imbalance was addressed using class weights, random oversampling, and the Synthetic Minority Over-Sampling Technique (SMOTE). Three ML classifiers, Random Forest (RF), Artificial Neural Network (ANN), and eXtreme Gradient Boosting (XGB), were tested to classify patients as ALC or not. Also, to ensure accurate ALC prediction at admission, only features available at that time were used in a separate model iteration.

RESULTS

Model performance was assessed using recall, F1-Score, and AUC metrics. The XGB model with SMOTE achieved the highest performance, with a recall of 0.95 and an AUC of 0.97, excelling in identifying ALC patients. The next best models were XGB with random oversampling and ANN with class weights. When limited to admission-only features, the XGB with SMOTE still performed well, achieving a recall of 0.91 and an AUC of 0.94, demonstrating its effectiveness in early ALC prediction. Additionally, the analysis identified diagnosis 1, patient age, and entry code as the top three predictors of ALC status.

CONCLUSIONS

The results demonstrate the potential of ML models to predict ALC status at admission. The findings support real-time decision-making to improve patient flow and reduce hospital overcrowding. The ALC guideline groups patients first by diagnosis, then by age, and finally by entry code, categorizing prediction outcomes into three probability ranges: below 30%, 30-70%, and above 70%. This framework assesses whether ALC status can be accurately predicted at admission or during the patient's stay before discharge.

Setting the balance of care for older adults at risk of hospitalization and delayed discharge: A mixed-methods research protocol

INTRODUCTION

Delayed hospital discharge is a persistent care quality issue experienced across health systems worldwide and remains a priority area to be addressed in Canada. Often associated with a decrease in services while waiting to leave the hospital, delayed discharge from hospital can lead to increased frailty, physical and cognitive decline, and caregiver burnout. Optimizing availability of and timely access to community-based health and social care are avenues that could reduce initial admissions to the hospital and length of hospital stay, and facilitate hospital discharges.

METHODS

This research will explore the ways in which community resources could be leveraged to potentially avoid hospitalization and delayed hospital discharge for older adults using sequential mixed-methods including co-design. To better understand the characteristics and needs of older adults, the research team will first identify sub-populations of older adults (65 years old or older) at risk of hospitalization and delayed discharge using comprehensive, longitudinal administrative health data. From these health data, risk profiles and personas will be created and then shared with key partners (e.g., older adults, caregivers, healthcare providers, healthcare decision-makers), who will be engaged to identify, leverage, and create targeted care solutions. The barriers and facilitators to the implementation of these care solutions will then be explored.

DISCUSSION

Delayed hospital discharge has been a critical care quality issue across Canada for decades. The current research will provide health system leaders with an approach to better allocate services to older adults in order to avoid delayed hospital discharge and identify gaps in health and social care resources based on the characteristics, needs, and preferences of older adults, their caregivers, and providers.

Impact of sleep duration and dietary patterns on risk of metabolic syndrome in middle-aged and elderly adults: a cross-sectional study from a survey in Anhui, Eastern China

The aim of this study was to assess the sleep status of middle-aged and elderly adults in Bengbu City, Anhui Province, China, to identify the major dietary patterns, and to analyze the association of different sleep duration and dietary patterns with metabolic syndrome (MetS) and its related influencing factors, as well as to explore the predictive value of sleep duration and dietary patterns. A cross-sectional analysis was performed utilizing data collected from the Community-based Cardiovascular and Health Promotion Study 2019 (COCHPS 2019) conducted in Bengbu. The definition of MetS adhered to the criteria of Guidelines for the Prevention and Treatment of Dyslipidemia in Chinese Adults (2016 Revision). Dietary information was obtained using the Food Frequency Questionnaire (FFQ) to assess dietary intake over the past year. Principal component analysis (PCA) was performed to identify dominant dietary patterns. A logistic regression model was developed to analyze the associations among sleep duration, dietary patterns, and MetS, and a decision tree (DT) model was developed to compare factors affecting MetS and screen people at high risk for MetS. The prevalence of MetS was 13.4% among the 9132 middle-aged and elderly residents over 45 years of age included in COCHPS 2019. Participants were divided into short (< 6 h/d), normal (6-8 h/d), and long (> 8 h/d) groups based on their daily sleep duration. Three dietary patterns were identified by PCA, the fruit-milk pattern, the tubers-meat pattern, and the vegetable-cereal pattern. After adjusting for covariables, logistic regression analysis showed that long sleep duration was significantly negatively associated with MetS. The fruit-milk and vegetable-cereal patterns were negatively associated with MetS, whereas the tubers-meat pattern was positively correlated with MetS. The results of the DT model analysis showed that the vegetable-cereal pattern is the most important factor impacting MetS, followed by marital status, the tubers-meat pattern, the fruit-milk pattern, exercise, sleep duration, and gender. The DT model also screened out five types of MetS high-risk groups. The results of our study indicate that normal sleep duration and consumption of either a fruit-milk or vegetable-cereal diet may lower the likelihood of developing MetS in middle-aged and elderly adults.

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.

Outcomes of complex discharge planning in older adults with complex needs: a scoping review

In this scoping review, we aimed to evaluate the effectiveness of integrated multidisciplinary team discharge planning and identify common outcomes among older adults with complex needs, focusing on a safe transition from the hospital to the community. We performed a literature search for relevant articles using seven electronic databases and agreed search terms. Only articles published in English were included. In total, 23,772 articles were identified, with 27 articles meeting the inclusion criteria. A preponderance of patients aged ≥65 years and women was inferred based on population demographics. Initiatives on complex discharge planning were noted across most Western countries. Common outcomes of complex discharge planning were functionality (n = 11) including frailty (n = 4), quality of life (n = 11), and patient-centered factors including psychosocial needs (n = 9). Various outcomes from complex discharge planning initiatives and pathways were explored in this scoping review. None of the selected studies covered all nine domains of outcome assessment. Further research is needed involving follow-up studies after complex discharge planning interventions to assess their true effectiveness or value.

Construction of Xinjiang metabolic syndrome risk prediction model based on interpretable models

Background

We aimed to construct simple and practical metabolic syndrome (MetS) risk prediction models based on the data of inhabitants of Urumqi and to provide a methodological reference for the prevention and control of MetS.

Methods

This is a cross-sectional study conducted in the Xinjiang Uygur Autonomous Region of China. We collected data from inhabitants of Urumqi from 2018 to 2019, including demographic characteristics, anthropometric indicators, living habits and family history. Resampling technology was used to preprocess the data imbalance problems, and then MetS risk prediction models were constructed based on logistic regression (LR) and decision tree (DT). In addition, nomograms and tree diagrams of DT were used to explain and visualize the model.

Results

Of the 25,542 participants included in the study, 3,267 (12.8%) were diagnosed with MetS, and 22,275 (87.2%) were diagnosed with non-MetS. Both the LR and DT models based on the random undersampling dataset had good AUROC values (0.846 and 0.913, respectively). The accuracy, sensitivity, specificity, and AUROC values of the DT model were higher than those of the LR model. Based on a random undersampling dataset, the LR model showed that exercises such as walking (OR=0.769) and running (OR= 0.736) were protective factors against MetS. Age 60 ~ 74 years (OR=1.388), previous diabetes (OR=8.902), previous hypertension (OR=2.830), fatty liver (OR=3.306), smoking (OR=1.541), high systolic blood pressure (OR=1.044), and high diastolic blood pressure (OR=1.072) were risk factors for MetS; the DT model had 7 depth layers and 18 leaves, with BMI as the root node of the DT being the most important factor affecting MetS, and the other variables in descending order of importance: SBP, previous diabetes, previous hypertension, DBP, fatty liver, smoking, and exercise.

Conclusions

Both DT and LR MetS risk prediction models have good prediction performance and their respective characteristics. Combining these two methods to construct an interpretable risk prediction model of MetS can provide methodological references for the prevention and control of MetS.