Development and Validation of a Machine Learning Model to Estimate Bacterial Sepsis Among Immunocompromised Recipients of Stem Cell Transplant

Lind, Margaret L; Mooney, Stephen J.; Carone, Marco; Althouse, Benjamin M.; Liu, Catherine; Evans, Laura; Patel, Kevin; Vo, Phuong; Pergam, Steven A.; Phipps, Amanda I.

doi:10.1001/jamanetworkopen.2021.4514

Cited by 11 publications

(4 citation statements)

References 38 publications

(83 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The study population was divided into a training set and a test set at a ratio of 80:20 using stratified random sampling 21 . To avoid AA methods overfitting the test set, we applied fivefold cross-validation to the training set in validating procedure, and the area under the receiver operating curve (AUC) was averaged over all the data fold sets 22 , 23 . The stratified cross-validation method ensures that each training and test fold has a similar distribution of outcomes with the entire dataset to reduce bias in the training and evaluating processes.…”

Section: Methodsmentioning

confidence: 99%

Artificial intelligence model comparison for risk factor analysis of patent ductus arteriosus in nationwide very low birth weight infants cohort

Kim

Kwon

et al. 2021

Sci Rep

View full text Add to dashboard Cite

Despite the many comorbidities and high mortality rate in preterm infants with patent ductus arteriosus (PDA), therapeutic strategies vary depending on the clinical setting, and most studies of the related risk factors are based on small sample populations. We aimed to compare the performance of artificial intelligence (AI) analysis with that of conventional analysis to identify risk factors associated with symptomatic PDA (sPDA) in very low birth weight infants. This nationwide cohort study included 8369 very low birth weight (VLBW) infants. The participants were divided into an sPDA group and an asymptomatic PDA or spontaneously close PDA (nPDA) group. The sPDA group was further divided into treated and untreated subgroups. A total of 47 perinatal risk factors were collected and analyzed. Multiple logistic regression was used as a standard analytic tool, and five AI algorithms were used to identify the factors associated with sPDA. Combining a large database of risk factors from nationwide registries and AI techniques achieved higher accuracy and better performance of the PDA prediction tasks, and the ensemble methods showed the best performances.

show abstract

Section: Methodsmentioning

confidence: 99%

Artificial intelligence model comparison for risk factor analysis of patent ductus arteriosus in nationwide very low birth weight infants cohort

Kim

Kwon

et al. 2021

Sci Rep

View full text Add to dashboard Cite

show abstract

“…However, few studies reported on prediction models of non-adherence to medication in patients with T2D. Intelligence technology is becoming more prevalent in healthcare as a tool to improve practice patterns and patient outcomes ( 29 – 31 ). With technology development, ensemble models have been commonly used to explore disease progression in the field of molecular biology ( 32 – 36 ).…”

Section: Discussionmentioning

confidence: 99%

Development and assessment of novel machine learning models to predict medication non-adherence risks in type 2 diabetics

Yang

et al. 2022

Front. Public Health

View full text Add to dashboard Cite

BackgroundMedication adherence is the main determinant of effective management of type 2 diabetes, yet there is no gold standard method available to screen patients with high-risk non-adherence. Developing machine learning models to predict high-risk non-adherence in patients with T2D could optimize management.MethodsThis cross-sectional study was carried out on patients with T2D at the Sichuan Provincial People's Hospital from April 2018 to December 2019 who were examined for HbA1c on the day of the survey. Demographic and clinical characteristics were extracted from the questionnaire and electronic medical records. The sample was randomly divided into a training dataset and a test dataset with a radio of 8:2 after data preprocessing. Four imputing methods, five sampling methods, three screening methods, and 18 machine learning algorithms were used to groom data and develop and validate models. Bootstrapping was performed to generate the validation set for external validation and univariate analysis. Models were compared on the basis of predictive performance metrics. Finally, we validated the sample size on the best model.ResultsThis study included 980 patients with T2D, of whom 184 (18.8%) were defined as medication non-adherence. The results indicated that the model used modified random forest as the imputation method, random under sampler as the sampling method, Boruta as the feature screening method and the ensemble algorithms and had the best performance. The area under the receiver operating characteristic curve (AUC), F1 score, and area under the precision-recall curve (AUPRC) of the best model, among a total of 1,080 trained models, were 0.8369, 0.7912, and 0.9574, respectively. Age, present fasting blood glucose (FBG) values, present HbA1c values, present random blood glucose (RBG) values, and body mass index (BMI) were the most significant contributors associated with risks of medication adherence.ConclusionWe found that machine learning methods could be used to predict the risk of non-adherence in patients with T2D. The proposed model was well performed to identify patients with T2D with non-adherence and could help improve individualized T2D management.

show abstract

“…This full decision support assessment had superior prognostic accuracy for high-risk bacteremia and short-term mortality. This has the potential to inform timely sepsis detection in this patient population [51].…”

Section: Risk-assessment Strategies and Future Methods To Guide Antib...mentioning

confidence: 99%

Neutropenia and antibiotics: when, what, how and why?

Dickter

Logan

Taplitz

2023

Current Opinion in Infectious Diseases

View full text Add to dashboard Cite

Purpose of review Our aim is to review recent literature on antibiotic use in patients with neutropenia. Recent findings Prophylactic antibiotics are associated with risks and have limited mortality benefit. While early antibiotic use in febrile neutropenia (FN) is critical, early de-escalation or discontinuation may be safe in many patients. Summary With an increasing understanding of potential risks and benefits of use and improved risk assessment, paradigms of antibiotic use in neutropenic patients are changing.

show abstract

Development and Validation of a Machine Learning Model to Estimate Bacterial Sepsis Among Immunocompromised Recipients of Stem Cell Transplant

Cited by 11 publications

References 38 publications

Artificial intelligence model comparison for risk factor analysis of patent ductus arteriosus in nationwide very low birth weight infants cohort

Artificial intelligence model comparison for risk factor analysis of patent ductus arteriosus in nationwide very low birth weight infants cohort

Development and assessment of novel machine learning models to predict medication non-adherence risks in type 2 diabetics

Neutropenia and antibiotics: when, what, how and why?

Contact Info

Product

Resources

About