Machine learning-derived blood culture classification with both predictive and prognostic values in the intensive care unit : A retrospective cohort study
Copyright © 2023 The Author(s). Published by Elsevier Ltd.. All rights reserved..
OBJECTIVES: Diagnosis and management of intensive care unit (ICU)-acquired bloodstream infections are often based on positive blood culture results. This retrospective cohort study aimed to develop a classification model using data-driven characterisation to optimise the management of intensive care patients with blood cultures.
SETTING, METHODOLOGY/DESIGN: An unsupervised clustering model was developed based on the clinical characteristics of patients with blood cultures in the Medical Information Mart for Intensive Care (MIMIC)-IV database (n = 2451). It was tested using the data from the MIMIC-III database (n = 2047).
MAIN OUTCOME MEASURES: The prognosis, blood culture outcomes, antimicrobial interventions, and trajectories of infection indicators were compared between clusters.
RESULTS: Four clusters were identified using machine learning-based k-means clustering based on data obtained 48 h before the first blood culture sampling. Cluster γ was associated with the highest 28-day mortality rate, followed by clusters α, δ, and β. Cluster γ had a higher fungal isolation rate than cluster β (P < 0.05). Cluster δ was associated with a higher isolation rate of Gram-negative organisms and fungi (P < 0.05). Patients in clusters γ and δ underwent more femoral site vein catheter placements than those in cluster β (P < 0.001, all). Patients with a duration of antibiotics treatment of 4, 6, and 7 days in clusters α, δ, and γ, respectively, had the lowest 28-day mortality rate.
CONCLUSIONS: Machine learning identified four clusters of intensive care patients with blood cultures, which yielded different prognoses, blood culture outcomes, and optimal duration of antibiotic treatment. Such data-driven blood culture classifications suggest further investigation should be undertaken to optimise treatment and improve care.
IMPLICATIONS FOR CLINICAL PRACTICE: Intensive care unit-acquired bloodstream infections are heterogeneous. Meaningful classifications associated with outcomes should be described. Using machine learning and cluster analysis could help in understanding heterogeneity. Data-driven blood culture classification could identify distinct physiological states and prognoses before deciding on blood culture sampling, optimise treatment, and improve care.
Medienart: |
E-Artikel |
---|
Erscheinungsjahr: |
2024 2023 |
---|---|
Erschienen: |
2024 |
Enthalten in: |
Zur Gesamtaufnahme - volume:80 |
---|---|
Enthalten in: |
Intensive & critical care nursing - 80(2023) vom: 01. Feb., Seite 103549 |
Sprache: |
Englisch |
---|
Beteiligte Personen: |
Zhang, Jin [VerfasserIn] |
---|
Links: |
---|
Themen: |
Anti-Bacterial Agents |
---|
Anmerkungen: |
Date Completed 05.12.2023 Date Revised 05.12.2023 published: Print-Electronic Citation Status MEDLINE |
---|
doi: |
10.1016/j.iccn.2023.103549 |
---|
funding: |
|
---|---|
Förderinstitution / Projekttitel: |
|
PPN (Katalog-ID): |
NLM362984093 |
---|
LEADER | 01000naa a22002652 4500 | ||
---|---|---|---|
001 | NLM362984093 | ||
003 | DE-627 | ||
005 | 20231226092401.0 | ||
007 | cr uuu---uuuuu | ||
008 | 231226s2024 xx |||||o 00| ||eng c | ||
024 | 7 | |a 10.1016/j.iccn.2023.103549 |2 doi | |
028 | 5 | 2 | |a pubmed24n1209.xml |
035 | |a (DE-627)NLM362984093 | ||
035 | |a (NLM)37804818 | ||
035 | |a (PII)S0964-3397(23)00167-2 | ||
040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
041 | |a eng | ||
100 | 1 | |a Zhang, Jin |e verfasserin |4 aut | |
245 | 1 | 0 | |a Machine learning-derived blood culture classification with both predictive and prognostic values in the intensive care unit |b A retrospective cohort study |
264 | 1 | |c 2024 | |
336 | |a Text |b txt |2 rdacontent | ||
337 | |a ƒaComputermedien |b c |2 rdamedia | ||
338 | |a ƒa Online-Ressource |b cr |2 rdacarrier | ||
500 | |a Date Completed 05.12.2023 | ||
500 | |a Date Revised 05.12.2023 | ||
500 | |a published: Print-Electronic | ||
500 | |a Citation Status MEDLINE | ||
520 | |a Copyright © 2023 The Author(s). Published by Elsevier Ltd.. All rights reserved. | ||
520 | |a OBJECTIVES: Diagnosis and management of intensive care unit (ICU)-acquired bloodstream infections are often based on positive blood culture results. This retrospective cohort study aimed to develop a classification model using data-driven characterisation to optimise the management of intensive care patients with blood cultures | ||
520 | |a SETTING, METHODOLOGY/DESIGN: An unsupervised clustering model was developed based on the clinical characteristics of patients with blood cultures in the Medical Information Mart for Intensive Care (MIMIC)-IV database (n = 2451). It was tested using the data from the MIMIC-III database (n = 2047) | ||
520 | |a MAIN OUTCOME MEASURES: The prognosis, blood culture outcomes, antimicrobial interventions, and trajectories of infection indicators were compared between clusters | ||
520 | |a RESULTS: Four clusters were identified using machine learning-based k-means clustering based on data obtained 48 h before the first blood culture sampling. Cluster γ was associated with the highest 28-day mortality rate, followed by clusters α, δ, and β. Cluster γ had a higher fungal isolation rate than cluster β (P < 0.05). Cluster δ was associated with a higher isolation rate of Gram-negative organisms and fungi (P < 0.05). Patients in clusters γ and δ underwent more femoral site vein catheter placements than those in cluster β (P < 0.001, all). Patients with a duration of antibiotics treatment of 4, 6, and 7 days in clusters α, δ, and γ, respectively, had the lowest 28-day mortality rate | ||
520 | |a CONCLUSIONS: Machine learning identified four clusters of intensive care patients with blood cultures, which yielded different prognoses, blood culture outcomes, and optimal duration of antibiotic treatment. Such data-driven blood culture classifications suggest further investigation should be undertaken to optimise treatment and improve care | ||
520 | |a IMPLICATIONS FOR CLINICAL PRACTICE: Intensive care unit-acquired bloodstream infections are heterogeneous. Meaningful classifications associated with outcomes should be described. Using machine learning and cluster analysis could help in understanding heterogeneity. Data-driven blood culture classification could identify distinct physiological states and prognoses before deciding on blood culture sampling, optimise treatment, and improve care | ||
650 | 4 | |a Journal Article | |
650 | 4 | |a Blood culture | |
650 | 4 | |a Catheters | |
650 | 4 | |a Classification | |
650 | 4 | |a Cluster analysis | |
650 | 4 | |a Intensive Care | |
650 | 4 | |a Machine learning | |
650 | 4 | |a Prognosis | |
650 | 4 | |a Retrospective study | |
650 | 7 | |a Anti-Bacterial Agents |2 NLM | |
700 | 1 | |a Liu, Wanjun |e verfasserin |4 aut | |
700 | 1 | |a Xiao, Wenyan |e verfasserin |4 aut | |
700 | 1 | |a Liu, Yu |e verfasserin |4 aut | |
700 | 1 | |a Hua, Tianfeng |e verfasserin |4 aut | |
700 | 1 | |a Yang, Min |e verfasserin |4 aut | |
773 | 0 | 8 | |i Enthalten in |t Intensive & critical care nursing |d 1997 |g 80(2023) vom: 01. Feb., Seite 103549 |w (DE-627)NLM013113569 |x 1532-4036 |7 nnns |
773 | 1 | 8 | |g volume:80 |g year:2023 |g day:01 |g month:02 |g pages:103549 |
856 | 4 | 0 | |u http://dx.doi.org/10.1016/j.iccn.2023.103549 |3 Volltext |
912 | |a GBV_USEFLAG_A | ||
912 | |a GBV_NLM | ||
951 | |a AR | ||
952 | |d 80 |j 2023 |b 01 |c 02 |h 103549 |