Predicting presumed serious infection among hospitalized children on central venous lines with machine learning

Tabaie, Azade; Orenstein, Evan; Nemati, Shamim; Basu, Rajit K.; Kandaswamy, Swaminathan; Clifford, Gari D.; Kamaleswaran, Rishikesan

doi:10.1016/j.compbiomed.2021.104289

Cited by 17 publications

(15 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Notably, these models outperformed CCI, which is the standard scoring system for mortality. The high performance of machine learning models demonstrates their potential in contributing to infection management by providing accurate information at very early stages of the infection 27 – 29 . Recent studies have shown machine learning models to outperform standard scoring systems 27 , 30 , 31 .…”

Section: Discussionmentioning

confidence: 99%

“…The high performance of machine learning models demonstrates their potential in contributing to infection management by providing accurate information at very early stages of the infection 27 – 29 . Recent studies have shown machine learning models to outperform standard scoring systems 27 , 30 , 31 . In line with these findings, our results show enhanced performance in comparison to the CCI score.…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Predicting bloodstream infection outcome using machine learning

Zoabi

Kehat

Lahav

et al. 2021

Sci Rep

View full text Add to dashboard Cite

Bloodstream infections (BSI) are a main cause of infectious disease morbidity and mortality worldwide. Early prediction of BSI patients at high risk of poor outcomes is important for earlier decision making and effective patient stratification. We developed electronic medical record-based machine learning models that predict patient outcomes of BSI. The area under the receiver-operating characteristics curve was 0.82 for a full featured inclusive model, and 0.81 for a compact model using only 25 features. Our models were trained using electronic medical records that include demographics, blood tests, and the medical and diagnosis history of 7889 hospitalized patients diagnosed with BSI. Among the implications of this work is implementation of the models as a basis for selective rapid microbiological identification, toward earlier administration of appropriate antibiotic therapy. Additionally, our models may help reduce the development of BSI and its associated adverse health outcomes and complications.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

Predicting bloodstream infection outcome using machine learning

Zoabi

Kehat

Lahav

et al. 2021

Sci Rep

View full text Add to dashboard Cite

show abstract

“…At present, scholars have an increasing enthusiasm for utilizing supervised ML to predict the occurrence of infection, including iatrogenic and non-iatrogenic (21,(25)(26)(27)(28)(29)(30)(31)(32)(33). Nonetheless, the study that forecasts the risk of LDRM in an early stage before the clinical diagnosis is limited, although we have proposed a prediction model using the traditional logistic regression algorithm (19).…”

Section: Discussionmentioning

confidence: 99%

Prediction of Lumbar Drainage-Related Meningitis Based on Supervised Machine Learning Algorithms

Wang

Cheng

et al. 2022

Front. Public Health

View full text Add to dashboard Cite

BackgroundLumbar drainage is widely used in the clinic; however, forecasting lumbar drainage-related meningitis (LDRM) is limited. We aimed to establish prediction models using supervised machine learning (ML) algorithms.MethodsWe utilized a cohort of 273 eligible lumbar drainage cases. Data were preprocessed and split into training and testing sets. Optimal hyper-parameters were archived by 10-fold cross-validation and grid search. The support vector machine (SVM), random forest (RF), and artificial neural network (ANN) were adopted for model training. The area under the operating characteristic curve (AUROC) and precision-recall curve (AUPRC), true positive ratio (TPR), true negative ratio (TNR), specificity, sensitivity, accuracy, and kappa coefficient were used for model evaluation. All trained models were internally validated. The importance of features was also analyzed.ResultsIn the training set, all the models had AUROC exceeding 0.8. SVM and the RF models had an AUPRC of more than 0.6, but the ANN model had an unexpectedly low AUPRC (0.380). The RF and ANN models revealed similar TPR, whereas the ANN model had a higher TNR and demonstrated better specificity, sensitivity, accuracy, and kappa efficiency. In the testing set, most performance indicators of established models decreased. However, the RF and AVM models maintained adequate AUROC (0.828 vs. 0.719) and AUPRC (0.413 vs. 0.520), and the RF model also had better TPR, specificity, sensitivity, accuracy, and kappa efficiency. Site leakage showed the most considerable mean decrease in accuracy.ConclusionsThe RF and SVM models could predict LDRM, in which the RF model owned the best performance, and site leakage was the most meaningful predictor.

show abstract

“…While biopathophysiologic links can indeed be created related to escalating PEEP (e.g., worsening microvascular/endothelial injury in the pulmonary vasculature potentially related to cytokine storm/inflammation as a response to a brewing infection or pulmonary edema from endovascular injury and leak and fluid delivery) – the beauty of a deep learning model approach is it reduces clinician bias that a variable (or set of variables) is or is not related to the outcome of interest. As the literature shows – many models have been able to identify constellations of variables that would go otherwise unheeded as heralds to a patient event ( 11 , 19 ).…”

Section: Methodsmentioning

confidence: 99%

“…While specific definitions for entities such as CLABSI and sepsis exist in pediatrics, they often have inadequate sensitivity for clinically important infections and may be difficult to generalize across electronic medical record (EMR) platforms (7,8). Presumed serious infection (PSI), which is used in both adult and pediatric sepsis surveillance systems, is defined as a blood culture being obtained (regardless of the result) followed by new antimicrobial agents started within 2 days of the blood culture (i.e., agents that were not being administered prior to the blood culture) that are administered for at least 4 consecutive days or until time of death or transfer to another hospital (9)(10)(11). This PSI definition captures suspicion for infection (as identified by obtaining a blood culture) along with sufficient antimicrobial use to distinguish empirical treatment of a suspected infection from definitive treatment.…”

Section: Introductionmentioning

confidence: 99%

Deep Learning Model to Predict Serious Infection Among Children With Central Venous Lines

et al. 2021

Self Cite

View full text Add to dashboard Cite

Objective: Predict the onset of presumed serious infection, defined as a positive blood culture drawn and new antibiotic course of at least 4 days (PSI*), among pediatric patients with Central Venous Lines (CVLs).Design: Retrospective cohort study.Setting: Single academic children's hospital.Patients: All hospital encounters from January 2013 to December 2018, excluding the ones without a CVL or with a length-of-stay shorter than 24 h.Measurements and Main Results: Clinical features including demographics, laboratory results, vital signs, characteristics of the CVLs and medications used were extracted retrospectively from electronic medical records. Data were aggregated across all hospitals within a single pediatric health system and used to train a deep learning model to predict the occurrence of PSI* during the next 48 h of hospitalization. The proposed model prediction was compared to prediction of PSI* by a marker of illness severity (PELOD-2). The baseline prevalence of line infections was 0.34% over all segmented 48-h time windows. Events were identified among cases using onset time. All data from admission till the onset was used for cases and among controls we used all data from admission till discharge. The benchmarks were aggregated over all 48 h time windows [N=748,380 associated with 27,137 patient encounters]. The model achieved an area under the receiver operating characteristic curve of 0.993 (95% CI = [0.990, 0.996]), the enriched positive predictive value (PPV) was 23 times greater than the base prevalence. Conversely, prediction by PELOD-2 achieved a lower PPV of 1.5% [0.9%, 2.1%] which was 5 times the baseline prevalence.Conclusion: A deep learning model that employs common clinical features in the electronic health record can help predict the onset of CLABSI in hospitalized children with central venous line 48 hours prior to the time of specimen collection.

show abstract

Predicting presumed serious infection among hospitalized children on central venous lines with machine learning

Cited by 17 publications

References 34 publications

Predicting bloodstream infection outcome using machine learning

Predicting bloodstream infection outcome using machine learning

Prediction of Lumbar Drainage-Related Meningitis Based on Supervised Machine Learning Algorithms

Deep Learning Model to Predict Serious Infection Among Children With Central Venous Lines

Contact Info

Product

Resources

About