Improving Prediction Performance Using Hierarchical Analysis of Real-Time Data

A Sepsis Case Study

Franco Van Wyk, Anahita Khojandi, Rishikesan Kamaleswaran

Research output: Contribution to journalArticle

Abstract

This paper presents a novel method for hierarchical analysis of machine learning algorithms to improve predictions of at risk patients, thus further enabling prompt therapy. Specifically, we develop a multi-layer machine learning approach to analyze continuous, high-frequency data. We illustrate the capabilities of this approach for early identification of patients at risk of sepsis, a potentially life-threatening complication of an infection, using high-frequency (minute-by-minute) physiological data collected from bedside monitors. In our analysis of a cohort of 586 patients, the model obtained from analyzing the output of a previously developed sepsis prediction model resulted in improved outcomes. Specifically, the original model failed to predict 11.76 ± 4.26% of sepsis patients earlier than Systemic Inflammatory Response Syndrome (SIRS) criteria, commonly used to identify patients at risk for rapid physiological deterioration resulting from sepsis. In contrast, the multi-layer model only failed to predict 3.21 ± 3.11% of sepsis patients earlier than SIRS. In addition, sepsis patients were predicted on average 204.87 ± 7.90 minutes earlier than SIRS criteria using the multi-layer model, which can potentially help reduce mortality and morbidity if implemented in the ICU.

Original languageEnglish (US)
Article number8624374
Pages (from-to)978-986
Number of pages9
JournalIEEE Journal of Biomedical and Health Informatics
Volume23
Issue number3
DOIs
StatePublished - May 1 2019

Fingerprint

Sepsis
Systemic Inflammatory Response Syndrome
Learning systems
Intensive care units
Learning algorithms
Deterioration
Cohort Studies
Morbidity
Mortality
Infection

All Science Journal Classification (ASJC) codes

  • Biotechnology
  • Computer Science Applications
  • Electrical and Electronic Engineering
  • Health Information Management

Cite this

Improving Prediction Performance Using Hierarchical Analysis of Real-Time Data : A Sepsis Case Study. / Van Wyk, Franco; Khojandi, Anahita; Kamaleswaran, Rishikesan.

In: IEEE Journal of Biomedical and Health Informatics, Vol. 23, No. 3, 8624374, 01.05.2019, p. 978-986.

Research output: Contribution to journalArticle

@article{4f6108de46c64a588c6a3a62e363fb1a,
title = "Improving Prediction Performance Using Hierarchical Analysis of Real-Time Data: A Sepsis Case Study",
abstract = "This paper presents a novel method for hierarchical analysis of machine learning algorithms to improve predictions of at risk patients, thus further enabling prompt therapy. Specifically, we develop a multi-layer machine learning approach to analyze continuous, high-frequency data. We illustrate the capabilities of this approach for early identification of patients at risk of sepsis, a potentially life-threatening complication of an infection, using high-frequency (minute-by-minute) physiological data collected from bedside monitors. In our analysis of a cohort of 586 patients, the model obtained from analyzing the output of a previously developed sepsis prediction model resulted in improved outcomes. Specifically, the original model failed to predict 11.76 ± 4.26{\%} of sepsis patients earlier than Systemic Inflammatory Response Syndrome (SIRS) criteria, commonly used to identify patients at risk for rapid physiological deterioration resulting from sepsis. In contrast, the multi-layer model only failed to predict 3.21 ± 3.11{\%} of sepsis patients earlier than SIRS. In addition, sepsis patients were predicted on average 204.87 ± 7.90 minutes earlier than SIRS criteria using the multi-layer model, which can potentially help reduce mortality and morbidity if implemented in the ICU.",
author = "{Van Wyk}, Franco and Anahita Khojandi and Rishikesan Kamaleswaran",
year = "2019",
month = "5",
day = "1",
doi = "10.1109/JBHI.2019.2894570",
language = "English (US)",
volume = "23",
pages = "978--986",
journal = "IEEE Journal of Biomedical and Health Informatics",
issn = "2168-2194",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "3",

}

TY - JOUR

T1 - Improving Prediction Performance Using Hierarchical Analysis of Real-Time Data

T2 - A Sepsis Case Study

AU - Van Wyk, Franco

AU - Khojandi, Anahita

AU - Kamaleswaran, Rishikesan

PY - 2019/5/1

Y1 - 2019/5/1

N2 - This paper presents a novel method for hierarchical analysis of machine learning algorithms to improve predictions of at risk patients, thus further enabling prompt therapy. Specifically, we develop a multi-layer machine learning approach to analyze continuous, high-frequency data. We illustrate the capabilities of this approach for early identification of patients at risk of sepsis, a potentially life-threatening complication of an infection, using high-frequency (minute-by-minute) physiological data collected from bedside monitors. In our analysis of a cohort of 586 patients, the model obtained from analyzing the output of a previously developed sepsis prediction model resulted in improved outcomes. Specifically, the original model failed to predict 11.76 ± 4.26% of sepsis patients earlier than Systemic Inflammatory Response Syndrome (SIRS) criteria, commonly used to identify patients at risk for rapid physiological deterioration resulting from sepsis. In contrast, the multi-layer model only failed to predict 3.21 ± 3.11% of sepsis patients earlier than SIRS. In addition, sepsis patients were predicted on average 204.87 ± 7.90 minutes earlier than SIRS criteria using the multi-layer model, which can potentially help reduce mortality and morbidity if implemented in the ICU.

AB - This paper presents a novel method for hierarchical analysis of machine learning algorithms to improve predictions of at risk patients, thus further enabling prompt therapy. Specifically, we develop a multi-layer machine learning approach to analyze continuous, high-frequency data. We illustrate the capabilities of this approach for early identification of patients at risk of sepsis, a potentially life-threatening complication of an infection, using high-frequency (minute-by-minute) physiological data collected from bedside monitors. In our analysis of a cohort of 586 patients, the model obtained from analyzing the output of a previously developed sepsis prediction model resulted in improved outcomes. Specifically, the original model failed to predict 11.76 ± 4.26% of sepsis patients earlier than Systemic Inflammatory Response Syndrome (SIRS) criteria, commonly used to identify patients at risk for rapid physiological deterioration resulting from sepsis. In contrast, the multi-layer model only failed to predict 3.21 ± 3.11% of sepsis patients earlier than SIRS. In addition, sepsis patients were predicted on average 204.87 ± 7.90 minutes earlier than SIRS criteria using the multi-layer model, which can potentially help reduce mortality and morbidity if implemented in the ICU.

UR - http://www.scopus.com/inward/record.url?scp=85065430489&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85065430489&partnerID=8YFLogxK

U2 - 10.1109/JBHI.2019.2894570

DO - 10.1109/JBHI.2019.2894570

M3 - Article

VL - 23

SP - 978

EP - 986

JO - IEEE Journal of Biomedical and Health Informatics

JF - IEEE Journal of Biomedical and Health Informatics

SN - 2168-2194

IS - 3

M1 - 8624374

ER -