Machine Learning For Risk Prediction After Heart Failure Emergency Department Visit or Hospital Admission Using Administrative Health Data.
<h4>Aims</h4>Patients visiting the emergency department (ED) or hospitalized for heart failure (HF) are at increased risk for subsequent adverse outcomes, however effective risk stratification remains challenging. We utilized a machine-learning (ML)-based approach to identify HF patients...
Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Public Library of Science (PLoS)
2024-10-01
|
| Series: | PLOS Digital Health |
| Online Access: | https://doi.org/10.1371/journal.pdig.0000636 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850075317227487232 |
|---|---|
| author | Nowell M Fine Sunil V Kalmady Weijie Sun Russ Greiner Jonathan G Howlett James A White Finlay A McAlister Justin A Ezekowitz Padma Kaul |
| author_facet | Nowell M Fine Sunil V Kalmady Weijie Sun Russ Greiner Jonathan G Howlett James A White Finlay A McAlister Justin A Ezekowitz Padma Kaul |
| author_sort | Nowell M Fine |
| collection | DOAJ |
| description | <h4>Aims</h4>Patients visiting the emergency department (ED) or hospitalized for heart failure (HF) are at increased risk for subsequent adverse outcomes, however effective risk stratification remains challenging. We utilized a machine-learning (ML)-based approach to identify HF patients at risk of adverse outcomes after an ED visit or hospitalization using a large regional administrative healthcare data system.<h4>Methods and results</h4>Patients visiting the ED or hospitalized with HF between 2002-2016 in Alberta, Canada were included. Outcomes of interest were 30-day and 1-year HF-related ED visits, HF hospital readmission or all-cause mortality. We applied a feature extraction method using deep feature synthesis from multiple sources of health data and compared performance of a gradient boosting algorithm (CatBoost) with logistic regression modelling. The area under receiver operating characteristic curve (AUC-ROC) was used to assess model performance. We included 50,630 patients with 93,552 HF ED visits/hospitalizations. At 30-day follow-up in the holdout validation cohort, the AUC-ROC for the combined endpoint of HF ED visit, HF hospital readmission or death for the Catboost and logistic regression models was 74.16 (73.18-75.11) versus 62.25 (61.25-63.18), respectively. At 1-year follow-up corresponding values were 76.80 (76.1-77.47) versus 69.52 (68.77-70.26), respectively. AUC-ROC values for the endpoint of all-cause death alone at 30-days and 1-year follow-up were 83.21 (81.83-84.41) versus 69.53 (67.98-71.18), and 85.73 (85.14-86.29) versus 69.40 (68.57-70.26), for the CatBoost and logistic regression models, respectively.<h4>Conclusions</h4>ML-based modelling with deep feature synthesis provided superior risk stratification for HF patients at 30-days and 1-year follow-up after an ED visit or hospitalization using data from a large administrative regional healthcare system. |
| format | Article |
| id | doaj-art-b23431938de744ca84471c81df40a7c0 |
| institution | DOAJ |
| issn | 2767-3170 |
| language | English |
| publishDate | 2024-10-01 |
| publisher | Public Library of Science (PLoS) |
| record_format | Article |
| series | PLOS Digital Health |
| spelling | doaj-art-b23431938de744ca84471c81df40a7c02025-08-20T02:46:20ZengPublic Library of Science (PLoS)PLOS Digital Health2767-31702024-10-01310e000063610.1371/journal.pdig.0000636Machine Learning For Risk Prediction After Heart Failure Emergency Department Visit or Hospital Admission Using Administrative Health Data.Nowell M FineSunil V KalmadyWeijie SunRuss GreinerJonathan G HowlettJames A WhiteFinlay A McAlisterJustin A EzekowitzPadma Kaul<h4>Aims</h4>Patients visiting the emergency department (ED) or hospitalized for heart failure (HF) are at increased risk for subsequent adverse outcomes, however effective risk stratification remains challenging. We utilized a machine-learning (ML)-based approach to identify HF patients at risk of adverse outcomes after an ED visit or hospitalization using a large regional administrative healthcare data system.<h4>Methods and results</h4>Patients visiting the ED or hospitalized with HF between 2002-2016 in Alberta, Canada were included. Outcomes of interest were 30-day and 1-year HF-related ED visits, HF hospital readmission or all-cause mortality. We applied a feature extraction method using deep feature synthesis from multiple sources of health data and compared performance of a gradient boosting algorithm (CatBoost) with logistic regression modelling. The area under receiver operating characteristic curve (AUC-ROC) was used to assess model performance. We included 50,630 patients with 93,552 HF ED visits/hospitalizations. At 30-day follow-up in the holdout validation cohort, the AUC-ROC for the combined endpoint of HF ED visit, HF hospital readmission or death for the Catboost and logistic regression models was 74.16 (73.18-75.11) versus 62.25 (61.25-63.18), respectively. At 1-year follow-up corresponding values were 76.80 (76.1-77.47) versus 69.52 (68.77-70.26), respectively. AUC-ROC values for the endpoint of all-cause death alone at 30-days and 1-year follow-up were 83.21 (81.83-84.41) versus 69.53 (67.98-71.18), and 85.73 (85.14-86.29) versus 69.40 (68.57-70.26), for the CatBoost and logistic regression models, respectively.<h4>Conclusions</h4>ML-based modelling with deep feature synthesis provided superior risk stratification for HF patients at 30-days and 1-year follow-up after an ED visit or hospitalization using data from a large administrative regional healthcare system.https://doi.org/10.1371/journal.pdig.0000636 |
| spellingShingle | Nowell M Fine Sunil V Kalmady Weijie Sun Russ Greiner Jonathan G Howlett James A White Finlay A McAlister Justin A Ezekowitz Padma Kaul Machine Learning For Risk Prediction After Heart Failure Emergency Department Visit or Hospital Admission Using Administrative Health Data. PLOS Digital Health |
| title | Machine Learning For Risk Prediction After Heart Failure Emergency Department Visit or Hospital Admission Using Administrative Health Data. |
| title_full | Machine Learning For Risk Prediction After Heart Failure Emergency Department Visit or Hospital Admission Using Administrative Health Data. |
| title_fullStr | Machine Learning For Risk Prediction After Heart Failure Emergency Department Visit or Hospital Admission Using Administrative Health Data. |
| title_full_unstemmed | Machine Learning For Risk Prediction After Heart Failure Emergency Department Visit or Hospital Admission Using Administrative Health Data. |
| title_short | Machine Learning For Risk Prediction After Heart Failure Emergency Department Visit or Hospital Admission Using Administrative Health Data. |
| title_sort | machine learning for risk prediction after heart failure emergency department visit or hospital admission using administrative health data |
| url | https://doi.org/10.1371/journal.pdig.0000636 |
| work_keys_str_mv | AT nowellmfine machinelearningforriskpredictionafterheartfailureemergencydepartmentvisitorhospitaladmissionusingadministrativehealthdata AT sunilvkalmady machinelearningforriskpredictionafterheartfailureemergencydepartmentvisitorhospitaladmissionusingadministrativehealthdata AT weijiesun machinelearningforriskpredictionafterheartfailureemergencydepartmentvisitorhospitaladmissionusingadministrativehealthdata AT russgreiner machinelearningforriskpredictionafterheartfailureemergencydepartmentvisitorhospitaladmissionusingadministrativehealthdata AT jonathanghowlett machinelearningforriskpredictionafterheartfailureemergencydepartmentvisitorhospitaladmissionusingadministrativehealthdata AT jamesawhite machinelearningforriskpredictionafterheartfailureemergencydepartmentvisitorhospitaladmissionusingadministrativehealthdata AT finlayamcalister machinelearningforriskpredictionafterheartfailureemergencydepartmentvisitorhospitaladmissionusingadministrativehealthdata AT justinaezekowitz machinelearningforriskpredictionafterheartfailureemergencydepartmentvisitorhospitaladmissionusingadministrativehealthdata AT padmakaul machinelearningforriskpredictionafterheartfailureemergencydepartmentvisitorhospitaladmissionusingadministrativehealthdata |