Search: onr:"swepub:oai:lup.lub.lu.se:3b82e946-9976-42b5-9c3b-12d5f9b4a56b" >
Improving risk pred...
Improving risk prediction in heart failure using machine learning
-
- Adler, Eric D. (author)
- University of California, San Diego
-
- Voors, Adriaan A. (author)
- University Medical Center Groningen,University of Groningen
-
- Klein, Liviu (author)
- University of California, San Francisco
-
show more...
-
- Macheret, Fima (author)
- University of California, San Diego
-
- Braun, Oscar O. (author)
- Lund University,Lunds universitet,Heart Failure and Mechanical Support,Forskargrupper vid Lunds universitet,Lund University Research Groups,Skåne University Hospital
-
- Urey, Marcus A. (author)
- University of California, San Diego
-
- Zhu, Wenhong (author)
- University of California, San Diego
-
- Sama, Iziah (author)
- University of Groningen,University Medical Center Groningen
-
- Tadel, Matevz (author)
- University of California, San Diego
-
- Campagnari, Claudio (author)
- University of California, Santa Barbara
-
- Greenberg, Barry (author)
- University of California, San Diego
-
- Yagil, Avi (author)
- University of California, San Diego
-
show less...
-
(creator_code:org_t)
- 2019-11-12
- 2020
- English 9 s.
-
In: European Journal of Heart Failure. - : Wiley. - 1388-9842 .- 1879-0844. ; 22:1, s. 139-147
- Related links:
-
http://dx.doi.org/10...
-
show more...
-
https://onlinelibrar...
-
https://lup.lub.lu.s...
-
https://doi.org/10.1...
-
show less...
Abstract
Subject headings
Close
- Background: Predicting mortality is important in patients with heart failure (HF). However, current strategies for predicting risk are only modestly successful, likely because they are derived from statistical analysis methods that fail to capture prognostic information in large data sets containing multi-dimensional interactions. Methods and results: We used a machine learning algorithm to capture correlations between patient characteristics and mortality. A model was built by training a boosted decision tree algorithm to relate a subset of the patient data with a very high or very low mortality risk in a cohort of 5822 hospitalized and ambulatory patients with HF. From this model we derived a risk score that accurately discriminated between low and high-risk of death by identifying eight variables (diastolic blood pressure, creatinine, blood urea nitrogen, haemoglobin, white blood cell count, platelets, albumin, and red blood cell distribution width). This risk score had an area under the curve (AUC) of 0.88 and was predictive across the full spectrum of risk. External validation in two separate HF populations gave AUCs of 0.84 and 0.81, which were superior to those obtained with two available risk scores in these same populations. Conclusions: Using machine learning and readily available variables, we generated and validated a mortality risk score in patients with HF that was more accurate than other risk scores to which it was compared. These results support the use of this machine learning approach for the evaluation of patients with HF and in other settings where predicting risk has been challenging.
Subject headings
- MEDICIN OCH HÄLSOVETENSKAP -- Klinisk medicin -- Kardiologi (hsv//swe)
- MEDICAL AND HEALTH SCIENCES -- Clinical Medicine -- Cardiac and Cardiovascular Systems (hsv//eng)
Keyword
- Heart failure
- Machine learning
- Outcomes
Publication and Content Type
- art (subject category)
- ref (subject category)
Find in a library
To the university's database
- By the author/editor
-
Adler, Eric D.
-
Voors, Adriaan A ...
-
Klein, Liviu
-
Macheret, Fima
-
Braun, Oscar O.
-
Urey, Marcus A.
-
show more...
-
Zhu, Wenhong
-
Sama, Iziah
-
Tadel, Matevz
-
Campagnari, Clau ...
-
Greenberg, Barry
-
Yagil, Avi
-
show less...
- About the subject
-
- MEDICAL AND HEALTH SCIENCES
-
MEDICAL AND HEAL ...
-
and Clinical Medicin ...
-
and Cardiac and Card ...
- Articles in the publication
-
European Journal ...
- By the university
-
Lund University