The role of specialized hospital units in infection and mortality risk reduction among patients with hematological cancers

Raïsa Carmen, Galit B. Yom-Tov, Inneke Van Nieuwenhuyse, Bram Foubert, Yishai Ofran

Research output: Contribution to journalArticleAcademicpeer-review

Abstract

Motivation

Patients with hematological malignancies are susceptible to life-threatening infections after chemotherapy. The current study aimed to evaluate whether management of such patients in dedicated inpatient and emergency wards could provide superior infection prevention and outcome.

Methods

We have developed an approach allowing to retrieve infection-related information from unstructured electronic medical records of a tertiary center. Data on 2,330 adults receiving 13,529 chemotherapy treatments for hematological malignancies were identified and assessed. Infection and mortality hazard rates were calculated with multivariate models. Patients were randomly divided into 80: 20 training and validation cohorts. To develop patient-tailored risk-prediction models, several machine-learning methods were compared using area under the curve (AUC).

Results

Of the tested algorithms, the probit model was found to most accurately predict the evaluated hazards and was implemented in an online calculator. The infection-prediction model identified risk factors for infection based on patient characteristics, treatment and history. Observation of patients with a high predicted infection risk in general wards appeared to increase their infection hazard (p = 0.009) compared to similar patients observed in hematology units. The mortality-risk model demonstrated that for infection events starting at home, admission through hematology services was associated with a lower mortality hazard compared to admission through the general emergency department (p = 0.007). Both models show that dedicated hematological facilities and emergency services improve patient outcome post-chemotherapy. The calculated numbers needed to treat were 30.27 and 31.08 for the dedicated emergency and observation facilities, respectively. Infection hazard risks were found to be non-monotonic in time.

Conclusions

The accuracy of the proposed mortality and infection risk-prediction models was high, with the AUC of 0.74 and 0.83, respectively. Our results demonstrate that temporal assessment of patient risks is feasible. This may enable physicians to move from one-point decision-making to a continuous dynamic observation, allowing a more flexible and patient-tailored admission policy.

Original languageEnglish
Article number0211694
Number of pages17
JournalPLOS ONE
Volume14
Issue number3
DOIs
Publication statusPublished - 20 Mar 2019

Keywords

  • PREDICTION
  • IMPACT
  • TIME
  • MANAGEMENT
  • SYMPTOMS
  • SURVIVAL
  • THERAPY
  • SEPSIS
  • COHORT
  • MODEL

Cite this

Carmen, Raïsa ; Yom-Tov, Galit B. ; Van Nieuwenhuyse, Inneke ; Foubert, Bram ; Ofran, Yishai. / The role of specialized hospital units in infection and mortality risk reduction among patients with hematological cancers. In: PLOS ONE. 2019 ; Vol. 14, No. 3.
@article{841c3e0163b144faaeb70ff333434ecc,
title = "The role of specialized hospital units in infection and mortality risk reduction among patients with hematological cancers",
abstract = "MotivationPatients with hematological malignancies are susceptible to life-threatening infections after chemotherapy. The current study aimed to evaluate whether management of such patients in dedicated inpatient and emergency wards could provide superior infection prevention and outcome.MethodsWe have developed an approach allowing to retrieve infection-related information from unstructured electronic medical records of a tertiary center. Data on 2,330 adults receiving 13,529 chemotherapy treatments for hematological malignancies were identified and assessed. Infection and mortality hazard rates were calculated with multivariate models. Patients were randomly divided into 80: 20 training and validation cohorts. To develop patient-tailored risk-prediction models, several machine-learning methods were compared using area under the curve (AUC).ResultsOf the tested algorithms, the probit model was found to most accurately predict the evaluated hazards and was implemented in an online calculator. The infection-prediction model identified risk factors for infection based on patient characteristics, treatment and history. Observation of patients with a high predicted infection risk in general wards appeared to increase their infection hazard (p = 0.009) compared to similar patients observed in hematology units. The mortality-risk model demonstrated that for infection events starting at home, admission through hematology services was associated with a lower mortality hazard compared to admission through the general emergency department (p = 0.007). Both models show that dedicated hematological facilities and emergency services improve patient outcome post-chemotherapy. The calculated numbers needed to treat were 30.27 and 31.08 for the dedicated emergency and observation facilities, respectively. Infection hazard risks were found to be non-monotonic in time.ConclusionsThe accuracy of the proposed mortality and infection risk-prediction models was high, with the AUC of 0.74 and 0.83, respectively. Our results demonstrate that temporal assessment of patient risks is feasible. This may enable physicians to move from one-point decision-making to a continuous dynamic observation, allowing a more flexible and patient-tailored admission policy.",
keywords = "PREDICTION, IMPACT, TIME, MANAGEMENT, SYMPTOMS, SURVIVAL, THERAPY, SEPSIS, COHORT, MODEL",
author = "Ra{\"i}sa Carmen and Yom-Tov, {Galit B.} and {Van Nieuwenhuyse}, Inneke and Bram Foubert and Yishai Ofran",
note = "data source: patient infection and mortality data of hospital in Israel",
year = "2019",
month = "3",
day = "20",
doi = "10.1371/journal.pone.0211694",
language = "English",
volume = "14",
journal = "PLOS ONE",
issn = "1932-6203",
publisher = "Public Library of Science",
number = "3",

}

The role of specialized hospital units in infection and mortality risk reduction among patients with hematological cancers. / Carmen, Raïsa; Yom-Tov, Galit B.; Van Nieuwenhuyse, Inneke ; Foubert, Bram; Ofran, Yishai.

In: PLOS ONE, Vol. 14, No. 3, 0211694, 20.03.2019.

Research output: Contribution to journalArticleAcademicpeer-review

TY - JOUR

T1 - The role of specialized hospital units in infection and mortality risk reduction among patients with hematological cancers

AU - Carmen, Raïsa

AU - Yom-Tov, Galit B.

AU - Van Nieuwenhuyse, Inneke

AU - Foubert, Bram

AU - Ofran, Yishai

N1 - data source: patient infection and mortality data of hospital in Israel

PY - 2019/3/20

Y1 - 2019/3/20

N2 - MotivationPatients with hematological malignancies are susceptible to life-threatening infections after chemotherapy. The current study aimed to evaluate whether management of such patients in dedicated inpatient and emergency wards could provide superior infection prevention and outcome.MethodsWe have developed an approach allowing to retrieve infection-related information from unstructured electronic medical records of a tertiary center. Data on 2,330 adults receiving 13,529 chemotherapy treatments for hematological malignancies were identified and assessed. Infection and mortality hazard rates were calculated with multivariate models. Patients were randomly divided into 80: 20 training and validation cohorts. To develop patient-tailored risk-prediction models, several machine-learning methods were compared using area under the curve (AUC).ResultsOf the tested algorithms, the probit model was found to most accurately predict the evaluated hazards and was implemented in an online calculator. The infection-prediction model identified risk factors for infection based on patient characteristics, treatment and history. Observation of patients with a high predicted infection risk in general wards appeared to increase their infection hazard (p = 0.009) compared to similar patients observed in hematology units. The mortality-risk model demonstrated that for infection events starting at home, admission through hematology services was associated with a lower mortality hazard compared to admission through the general emergency department (p = 0.007). Both models show that dedicated hematological facilities and emergency services improve patient outcome post-chemotherapy. The calculated numbers needed to treat were 30.27 and 31.08 for the dedicated emergency and observation facilities, respectively. Infection hazard risks were found to be non-monotonic in time.ConclusionsThe accuracy of the proposed mortality and infection risk-prediction models was high, with the AUC of 0.74 and 0.83, respectively. Our results demonstrate that temporal assessment of patient risks is feasible. This may enable physicians to move from one-point decision-making to a continuous dynamic observation, allowing a more flexible and patient-tailored admission policy.

AB - MotivationPatients with hematological malignancies are susceptible to life-threatening infections after chemotherapy. The current study aimed to evaluate whether management of such patients in dedicated inpatient and emergency wards could provide superior infection prevention and outcome.MethodsWe have developed an approach allowing to retrieve infection-related information from unstructured electronic medical records of a tertiary center. Data on 2,330 adults receiving 13,529 chemotherapy treatments for hematological malignancies were identified and assessed. Infection and mortality hazard rates were calculated with multivariate models. Patients were randomly divided into 80: 20 training and validation cohorts. To develop patient-tailored risk-prediction models, several machine-learning methods were compared using area under the curve (AUC).ResultsOf the tested algorithms, the probit model was found to most accurately predict the evaluated hazards and was implemented in an online calculator. The infection-prediction model identified risk factors for infection based on patient characteristics, treatment and history. Observation of patients with a high predicted infection risk in general wards appeared to increase their infection hazard (p = 0.009) compared to similar patients observed in hematology units. The mortality-risk model demonstrated that for infection events starting at home, admission through hematology services was associated with a lower mortality hazard compared to admission through the general emergency department (p = 0.007). Both models show that dedicated hematological facilities and emergency services improve patient outcome post-chemotherapy. The calculated numbers needed to treat were 30.27 and 31.08 for the dedicated emergency and observation facilities, respectively. Infection hazard risks were found to be non-monotonic in time.ConclusionsThe accuracy of the proposed mortality and infection risk-prediction models was high, with the AUC of 0.74 and 0.83, respectively. Our results demonstrate that temporal assessment of patient risks is feasible. This may enable physicians to move from one-point decision-making to a continuous dynamic observation, allowing a more flexible and patient-tailored admission policy.

KW - PREDICTION

KW - IMPACT

KW - TIME

KW - MANAGEMENT

KW - SYMPTOMS

KW - SURVIVAL

KW - THERAPY

KW - SEPSIS

KW - COHORT

KW - MODEL

U2 - 10.1371/journal.pone.0211694

DO - 10.1371/journal.pone.0211694

M3 - Article

VL - 14

JO - PLOS ONE

JF - PLOS ONE

SN - 1932-6203

IS - 3

M1 - 0211694

ER -