Predicting 28-day all-cause unplanned hospital re-admission of patients with alcohol use disorders: a machine learning approach

TL;DR

This study uses machine learning to predict 28-day hospital re-admissions for patients with alcohol use disorders, identifying key risk factors and showing the effectiveness of the Clinical Bio-BERT model.

Contribution

The study introduces the Clinical Bio-BERT model as a novel and highly sensitive tool for predicting re-admissions in patients with alcohol use disorders.

Findings

Patients aged 45–49 or 70–79, males, and polysubstance users had higher re-admission risks.

Interactions with emergency departments or drug and alcohol services reduced re-admission risks by 71% and 79%.

Clinical Bio-BERT outperformed other models with a sensitivity of 0.724.

Abstract

Patients with alcohol use disorders have a high hospital re-admission rate, adding to the strain on the healthcare system. To address this issue, this study aimed to predict 28-day unplanned hospital re-admission for these patients.

From linked de-identified datasets, patients with alcohol use disorders who had hospital re-admissions between 2015 and 2018 were identified. Univariate and multiple logistic regression were conducted to select variables for inclusion in five machine learning models—logistic regression (baseline), random forest, support vector machine, long-short term memory and clinical bio bidirectional encoder representation of transformers (Clinical Bio-BERT)—to predict the 28-day re-admission.

Eight hundred and sixty-nine patients with alcohol use disorders incurred 2254 hospital admissions. Patients aged 45–49 or 70–74 or 75–79 were 4–5 times more likely to be re-admitted than those in other age groups; males were 36% more likely than females; patients who use polysubstance were 3.3 times more likely than otherwise. Patients with “respiratory system disorders” or “hepatobiliary system and pancreas disorders” had 60% higher risk than otherwise. Interaction with emergency department or drug and alcohol service after discharge reduced the risk by 71% and 79%, respectively. The 10-variable Clinical Bio-BERT demonstrated the highest sensitivity (.724).

Patients with alcohol use disorders with the following characteristics were more likely to have unplanned re-admissions within 28 days: male, aged 45–49 or 70–74 or 75–79, with “respiratory system disorders” or “hepatobiliary system and pancreas disorders”, or patients who use polysubstance. Interactions with emergency department or drug and alcohol service after discharge had reduced risk of hospital re-admission.

Short Summary:
 For patients with alcohol use disorders, being male, aged 45–49 or 70–74 or 75–79, with “respiratory system disorders” or “hepatobiliary system and pancreas disorders”, or patients who use polysubstance are more likely to be re-admitted within 28 days.Patients who interact with the emergency department or community-based drug and alcohol service after a hospital discharge have a reduced risk of hospital re-admission within 28 days.The Clinical Bio-BERT model is highly sensitivity on predicting re-admissions of patients with alcohol use disorders, in comparison with random forest, support vector machine and long-short term memory.

For patients with alcohol use disorders, being male, aged 45–49 or 70–74 or 75–79, with “respiratory system disorders” or “hepatobiliary system and pancreas disorders”, or patients who use polysubstance are more likely to be re-admitted within 28 days.

Patients who interact with the emergency department or community-based drug and alcohol service after a hospital discharge have a reduced risk of hospital re-admission within 28 days.

The Clinical Bio-BERT model is highly sensitivity on predicting re-admissions of patients with alcohol use disorders, in comparison with random forest, support vector machine and long-short term memory.

Figures