Predicting 30-day all-cause readmissions from hospital inpatient discharge data

  title={Predicting 30-day all-cause readmissions from hospital inpatient discharge data},
  author={Chengliang Yang and Chris Delcher and Elizabeth A. Shenkman and Sanjay Ranka},
  journal={2016 IEEE 18th International Conference on e-Health Networking, Applications and Services (Healthcom)},
  • Chengliang YangC. Delcher S. Ranka
  • Published 1 September 2016
  • Medicine
  • 2016 IEEE 18th International Conference on e-Health Networking, Applications and Services (Healthcom)
Inpatient hospital readmissions for potentially avoidable conditions are problematic and costly. In this paper, we build machine learning models using variables widely available in health claims data to predict patients' 30-day readmission risks at the time of discharge. These models show high predictive power on a U.S. nationwide readmission database. They are also capable of providing interpretable risk factors globally at the population level and locally associated with each single discharge… 

Figures and Tables from this paper

Nationwide hospital admission data statistics and disease-specific 30-day readmission prediction

The study shows that hospital readmission rates vary significantly with respect to different disease types, gender, age groups, any other factors, and further designs a machine learning framework for disease-specific 30-day hospital readmissions prediction.

Analysis and prediction of unplanned intensive care unit readmission using recurrent neural networks with long short-term memory

The ability of machine learning models to improve the authors' ICU decision making accuracy is highlighted, and is a real-world example of precision medicine in hospitals.

A machine learning model to predict the risk of 30-day readmissions in patients with heart failure: a retrospective analysis of electronic medical records data

Deep learning techniques performed better than other traditional techniques in developing this EMR-based prediction model for 30-day readmissions in heart failure patients, enabling care teams to target interventions at their most high-risk patients and improving overall clinical outcomes.

Imbalanced Learning for Hospital Readmission Prediction using National Readmission Database

An imbalanced learning strategy to create features from patient hospital visit is designed, by combining patient demographic information, ICD-10 clinical modification (CM) and procedure codes (PCS), and Clinical Classification Software Refined (CCSR) conversion, and achieves good performance to predict patient readmission.

Using machine learning to predict paediatric 30-day unplanned hospital readmissions: a case-control retrospective analysis of medical records, including written discharge documentation.

The findings are presented of the first known study in Australia to assess and report that written discharge documentation and clinical information improves unplanned rehospitalisation prediction accuracy in a paediatric cohort compared with administrative data alone.

Development and Prospective Validation of a Machine Learning-Based Risk of Readmission Model in a Large Military Hospital

This work reflects significant collaborative efforts required to operationalize ML models in a complex clinical environment such as that seen in an integrated health care system and the importance of prospective model validation.

A point-wise linear model reveals reasons for 30-day readmission of heart failure patients

This is the first study on a deep-learning approach to explaining decisions behind readmission predictions and it provides an automatic patient stratification to explain cohorts of readmitted patients.

A framework for the estimation and reduction of hospital readmission penalties using predictive analytics

Focusing resources toward the potentially most expensive patients offers considerably better results than unfocused efforts and direct calculation to estimate readmission costs has shown to be a more efficient use of resources than current readmission reduction methods.



A Predictive Model to Identify Patients at Risk of Unplanned 30-Day Acute Care Hospital Readmission

  • K. Lemke
  • Medicine
    2013 IEEE International Conference on Healthcare Informatics
  • 2013
We tested an all-cause unplanned 30-day readmission risk model that produces timely risk scores from claims data and using the ACG predictive modeling framework. Our model achieves and AUC of. 75 on

A predictive analytics approach to reducing avoidable hospital readmission

A new readmission metric based on administrative data that can identify potentially avoidable readmissions from all other types of readmissions is developed that can directly incorporate patient's history of readmission and risk factors changes over time.

30 Day hospital readmission analysis

Analysis of the Nationwide Inpatient Sample dataset provided by HCUP to identify various clinical, demographic and socio-economic factors that play crucial roles in predicting the revenue loss due to readmissions enables the hospitals to compute the loss of revenue but also monitors their quality of service in a real-time fashion.

Mining high-dimensional administrative claims data to predict early hospital readmissions

An administrative claim-based algorithm to predict 30-day readmission using standardized billing codes and basic admission characteristics available before discharge is developed that is widely applicable to various patient cohorts and portable across institutions.

Electronic medical record-based multicondition models to predict the risk of 30 day readmission or death among adult medicine patients: validation and comparison to existing models

A new electronic multicondition model based on information derived from the EMR predicted mortality and readmission at 30 days, and was superior to previously published claims-based models.

A comparison of models for predicting early hospital readmissions

Predicting readmission of heart failure patients using automated follow-up calls

Patients at an elevated risk of readmission can be identified based on the trend of their responses to automated follow-up calls, and this presents a simple method for risk stratification based on patient self-assessment.

Dynamic Hierarchical Classification for Patient Risk-of-Readmission

DHC's algorithmic layering capability is trained and tested over two real world datasets and is currently integrated into the clinical decision support tools at MultiCare Health System (MHS), a major provider of healthcare services in the northwestern US.

An automated model using electronic medical record data identifies patients with cirrhosis at high risk for readmission.

  • A. SingalR. Rahimi Ruben Amarasingham
  • Medicine
    Clinical gastroenterology and hepatology : the official clinical practice journal of the American Gastroenterological Association
  • 2013