CoChat
Sign Up
Cited by 287Machine Learning in HealthcareArtificial Intelligence in HealthcareHeart Failure Treatment and Management

The DOI matches its Crossref record; 42 of the 42 references it cites were found in a registry or an index.

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

Open access
Golas, Sara Bersche, Shibahara, Takuma, Agboola, Stephen, Otaki, Hiroko, Sato, Jumpei, Nakae, Tatsuya, Hisamitsu, Toru, Kojima, Go, Felsted, Jennifer, Kakarmath, Sujay, Kvedar, Joseph, Jethwani, Kamal·2018·BMC Medical Informatics and Decision Making
DOI 10.1186/s12911-018-0620-zPMC PMC6013959
Open this paper in CoChat — free accountOpen PDF

Abstract

BACKGROUND: Heart failure is one of the leading causes of hospitalization in the United States. Advances in big data solutions allow for storage, management, and mining of large volumes of structured and semi-structured data, such as complex healthcare data. Applying these advances to complex healthcare data has led to the development of risk prediction models to help identify patients who would benefit most from disease management programs in an effort to reduce readmissions and healthcare cost, but the results of these efforts have been varied. The primary aim of this study was to develop a 30-day readmission risk prediction model for heart failure patients discharged from a hospital admission. METHODS: We used longitudinal electronic medical record data of heart failure patients admitted within a large healthcare system. Feature vectors included structured demographic, utilization, and clinical data, as well as selected extracts of un-structured data from clinician-authored notes. The risk prediction model was developed using deep unified networks (DUNs), a new mesh-like network structure of deep learning designed to avoid over-fitting. The model was validated with 10-fold cross-validation and results compared to models based on logistic regression, gradient boosting, and maxout networks. Overall model performance was assessed using concordance statistic. We also selected a discrimination threshold based on maximum projected cost saving to the Partners Healthcare system. RESULTS: Data from 11,510 patients with 27,334 admissions and 6369 30-day readmissions were used to train the model. After data processing, the final model included 3512 variables. The DUNs model had the best performance after 10-fold cross-validation. AUCs for prediction models were 0.664 ± 0.015, 0.650 ± 0.011, 0.695 ± 0.016 and 0.705 ± 0.015 for logistic regression, gradient boosting, maxout networks, and DUNs respectively. The DUNs model had an accuracy of 76.4% at the classification threshold that corresponded with maximum cost saving to the hospital. CONCLUSIONS: Deep learning techniques performed better than other traditional techniques in developing this EMR-based prediction model for 30-day readmissions in heart failure patients. Such models can be used to identify heart failure patients with impending hospitalization, enabling care teams to target interventions at their most high-risk patients and improving overall clinical outcomes.

Overview

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1186/s12911-018-0620-z

Cites

42 of 42 references verified0 citation errors · 0 not checkable

Statistics

Figures

Fig. 1 Network architectures of deep neural network and deep unified networks. Demonstrates the network architecture of deep unified networks (right side) compared to deep neural networks (left side)
Fig. 1 Network architectures of deep neural network and deep unified networks. Demonstrates the network architecture of deep unified networks (right side) compared to deep neural networks (left side)CC BY · PubMed Central
Fig. 2 Patient selection flowchart. Summarizes the patient selection process
Fig. 2 Patient selection flowchart. Summarizes the patient selection processCC BY · PubMed Central
Fig. 3 ROC curves of 10-fold CV. Demonstrates the ROC curve for each predictive modeling technique
Fig. 3 ROC curves of 10-fold CV. Demonstrates the ROC curve for each predictive modeling techniqueCC BY · PubMed Central
Fig. 4 Layer importance of DUNs. Shows the boxplot distributions of the attention unit output (Y axis) against each layer number (X axis)
Fig. 4 Layer importance of DUNs. Shows the boxplot distributions of the attention unit output (Y axis) against each layer number (X axis)CC BY · PubMed Central
Fig. 5 Projected net savings from readmission reduction by using prediction models to select CCCP enrollees. Shows the net savings from readmission reduction, calculated by changing the number of CCCP enrollees along with the classification threshold, using the ROC curves of 10-fold CV of 1) DUNs, 2) maxout networks, 3) logistic regression, and 4) gradient boosting as shown in Fig. 3
Fig. 5 Projected net savings from readmission reduction by using prediction models to select CCCP enrollees. Shows the net savings from readmission reduction, calculated by changing the number of CCCP enrollees along with the classification threshold, using the ROC curves of 10-fold CV of 1) DUNs, 2) maxout networks, 3) logistic regression, and 4) gradient boosting as shown in Fig. 3CC BY · PubMed Central

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Show all 42 references

Cited by

Sorted by citations

See all 287

Related

Metadata

Authors
Golas, S. B., Shibahara, T., Agboola, S., Otaki, H., Sato, J., Nakae, T., Hisamitsu, T., Kojima, G., Felsted, J., Kakarmath, S., Kvedar, J., & Jethwani, K.
Affiliations
  • Partners HealthCare Connected Health (US)
  • Hitachi (Japan) (JP)
  • Harvard University (US)
Corresponding author
Golas, Sara Bersche
ORCID
Venue
BMC Medical Informatics and Decision Making
Publisher
Springer Science and Business Media LLC
Published
2018-06-22
Volume
18
Issue
1
Pages
44-44
ISSN
1472-6947 (ISSN-L)
DOI
10.1186/s12911-018-0620-z
PMC
PMC6013959
OpenAlex
W2808897169
Cited by
287
References
42
Citations by year
2026: 17 · 2025: 39 · 2024: 37 · 2023: 37 · 2022: 40 · 2021: 59 · 2020: 35 · 2019: 21 · 2018: 2
FWCI
16.47
Type
journal article
Language
en
Open access
Licence
Locations
  • BMC Medical Informatics and Decision Making (publishedVersion, cc-by)
  • Europe PMC (PubMed Central) (publishedVersion, other-oa)
  • PubMed Central (publishedVersion, cc-by)
  • PubMed (publishedVersion)
  • DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
Funders
Central Research Laboratory, Hitachi, Ltd.
Topics
  • Physical Sciences › Computer Science › Artificial Intelligence › Machine Learning in Healthcare
  • Health Sciences › Health Professions › Health Information Management › Artificial Intelligence in Healthcare
  • Health Sciences › Medicine › Cardiology and Cardiovascular Medicine › Heart Failure Treatment and Management
Keywords
heart failure, 30-day readmission, readmission prediction, electronic health records, clinical notes, hospital readmission, healthcare cost reduction, disease management programs, deep learning prediction
MeSH terms
Deep Learning, Aged, Aged, 80 and over, Female, Heart Failure, Humans, Male, Middle Aged, Models, Theoretical, Patient Readmission, Prognosis, Retrospective Studies, Electronic Health Records

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review