Dataset Information

Complete blood count and C-reactive protein to predict positive blood culture among neonates using machine learning algorithms.

ABSTRACT:

Purpose

The authors aimed to develop a Machine-Learning (ML) algorithm that can predict positive blood culture in the neonatal intensive care unit, using complete blood count and C-reactive protein values.

Methods

The study was based on patients' electronic health records at a tertiary neonatal intensive care unit in São Paulo, Brazil. All blood cultures that had paired complete blood count and C-reactive protein measurements taken at the same time were included. To evaluate the machine learning model's performance, the authors used accuracy, Area Under the Receiver Operating Characteristics (AUROC), recall, precision, and F1-score.

Results

The dataset included 1181 blood cultures with paired complete blood count plus c-reactive protein and 1911 blood cultures with paired complete blood count only. The f1-score ranged from 0.14 to 0.43, recall ranged from 0.08 to 0.59, precision ranged from 0.29 to 1.00, and accuracy ranged from 0.688 to 0.864.

Conclusion

Complete blood count parameters and C-reactive protein levels cannot be used in ML models to predict bacteremia in newborns.

SUBMITTER: Matsushita FY

PROVIDER: S-EPMC9763374 | biostudies-literature | 2023

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Complete blood count and C-reactive protein to predict positive blood culture among neonates using machine learning algorithms.

Matsushita Felipe Yu FY Krebs Vera Lúcia Jornada VLJ de Carvalho Werther Brunow WB

Clinics (Sao Paulo, Brazil) 20221208

<h4>Purpose</h4>The authors aimed to develop a Machine-Learning (ML) algorithm that can predict positive blood culture in the neonatal intensive care unit, using complete blood count and C-reactive protein values.<h4>Methods</h4>The study was based on patients' electronic health records at a tertiary neonatal intensive care unit in São Paulo, Brazil. All blood cultures that had paired complete blood count and C-reactive protein measurements taken at the same time were included. To evaluate the m ...[more]

PMID: 36502550

Similar Datasets

Project description:BackgroundBiomarkers, such as leukocyte count, C-reactive protein (CRP), and procalcitonin (PCT), have been commonly used to predict the occurrence of life-threatening bacteremia and provide prognostic information, given the need for prompt intervention. However, such diagnosis methods require much time and money. Therefore, we propose a method with a high prediction capability using machine learning (ML) models based on complete blood count (CBC) and differential leukocyte count (DC) and compare its performance with traditional CRP or PCT biomarker methods and those of models incorporating CRP or PCT biomarkers.MethodsWe collected 366,586 daily blood culture (BC) results, of which 350,775 (93.2%), 308,803 (82.1%), and 23,912 (6.4%) cases were issued CBC/DC (CBC/DC group), CRP with CBC/DC (CRP&CBC/DC group), and PCT with CBC/DC (PCT&CBC/DC group), respectively. For the ML methods, conventional logistic regression and random forest models were selected, trained, applied, and validated for each group. Fivefold validation and prediction capability were also evaluated and reported.ResultsOverall, the ML methods, such as the random forest model, demonstrated promising performances. When trained with CBC/DC data, it achieved an area under the ROC curve (AUC) of 0.802, which is superior to the prediction conventionally made with CRP/PCT levels (0.699/0.731). Upon evaluating the performance enhanced by incorporating CRP or PCT biomarkers, it reported no substantial AUC increase with the addition of either CRP or PCT to CBC/DC data, which suggests the predicting power and applicability of using only CBC/DC data. Moreover, it showed competitive prognostic capability compared to the PCT test with similar all-cause in-hospital mortality (45.10% vs. 47.40%) and overall median survival time (27 vs. 25 days).ConclusionsThe ML models using only CBC/DC data yielded more accurate bacteremia predictions compared to those by methods using CRP and PCT data and reached similar prognostic performance as by PCT data. Thus, such models are potentially complementary and competitive with traditional CRP and PCT biomarkers for conducting and guiding antibiotic usage.

Project description:This study examines the prognostic impact of C-reactive protein (CRP) and white blood cell (WBC) counts in patients with cardiogenic shock (CS). Data regarding the prognostic impact of inflammatory biomarkers in CS are scarce. All consecutive patients with CS from 2019 to 2021 admitted to a cardiac intensive care unit (ICU) were included at one institution. Laboratory measurements were retrieved from the day of admission (i.e., day 1), as well as days 2, 3, 4, and 8. The primary endpoint was 30-day all-cause mortality. Statistical analyses included univariate t-tests, Spearman's correlations, C-statistics, Kaplan-Meier, and Cox regression analyses. From a total of 240 consecutive patients admitted with CS, 55% died within 30 days. CRP levels on days 3 to 8 were associated with reliable discrimination for 30-day all-cause mortality (area under the curve (AUC): 0.623-0.754), whereas CRP on day 1 was not (AUC = 0.514). In line, CRP > 100 mg/L on day 3 (56% vs. 37%; log-rank p = 0.023; HR = 1.702; 95% CI 1.060-2.735; p = 0.028) and especially a CRP increase of at least 200% from days 1 to day 3 (51% vs. 35%; log-rank p = 0.040; HR = 1.720; 95% CI 1.006-2.943; p = 0.048) were associated with an increased risk of all-cause mortality. Furthermore, WBC on day 1 discriminated 30-day all-cause mortality (AUC = 0.605; p = 0.005) with an increased risk of all-cause mortality in patients admitted with WBC > 10 × 106/mL (59% vs. 40%; log-rank p = 0.036; HR = 1.643; 95% CI 1.010-2.671; p = 0.045). In conclusion, WBC count on admission as well as CRP levels during the course of ICU treatment were associated with 30-day all-cause mortality. Specifically, an increase of CRP levels by at least 200% from day 1 to day 3 during the course of ICU treatment was associated with an increased risk of 30-day all-cause mortality. The present study is one of the first to describe the prognostic value of inflammatory biomarkers in consecutive all-comer CS patients treated at a cardiac ICU.

Dataset Information

Complete blood count and C-reactive protein to predict positive blood culture among neonates using machine learning algorithms.

Purpose

Methods

Results

Conclusion

Publications

Complete blood count and C-reactive protein to predict positive blood culture among neonates using machine learning algorithms.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets