Machine Learning to Calculate Heparin Dose in COVID-19 Patients with Active Cancer

Machine Learning: A New Approach for Dose Individualization

The application of machine learning (ML) has shown promising results in precision medicine due to its exceptional performance in dealing with complex multidimensional data. However, using ML for individualized dosing of medicines is still in its early stage, meriting further exploration. A systematic review of study designs and modeling details of using ML for individualized dosing of different drugs was performed. We have summarized the status of the study populations, predictive targets, and data sources for ML modeling, the selection of ML algorithms and features, and the evaluation and validation of their predictive performance. We also used the Prediction model Risk of Bias Assessment Tool (PROBAST) to assess the risk of bias of included studies. Currently, ML can be used for both a priori and a posteriori dose selection and optimization, and it can also assist the implementation of therapeutic drug monitoring. However, studies are mainly focused on drugs with narrow therapeutic windows, predominantly immunosuppressants (N = 23, 35.9%) and anti-infectives (N = 21, 32.8%), and there is currently only very limited attention for special populations, such as children (N = 22, 34.4%). Most studies showed poor methodological quality and a high risk of bias. The lack of external validation and clinical utility evaluation currently limits the further clinical implementation of ML for dose individualization. We therefore have proposed several ways to improve the clinical relevance of the studies and facilitate the translation of ML models into clinical practice.

Construction and validation of a predictive risk model for nosocomial infections with MDRO in NICUs: a multicenter observational study

Objectives

This study aimed to construct and validate a predictive risk model (PRM) for nosocomial infections with multi-drug resistant organism (MDRO) in neonatal intensive care units (NICUs), in order to provide a scientific and reliable prediction tool, and to provide reference for clinical prevention and control of MDRO infections in NICUs.

Methods

This multicenter observational study was conducted at NICUs of two tertiary children's hospitals in Hangzhou, Zhejiang Province. Using cluster sampling, eligible neonates admitted to NICUs of research hospitals from January 2018 to December 2020 (modeling group) or from July 2021 to June 2022 (validation group) were included in this study. Univariate analysis and binary logistic regression analysis were used to construct the PRM. H-L tests, calibration curves, ROC curves and decision curve analysis were used to validate the PRM.

Results

Four hundred and thirty-five and one hundred fourteen neonates were enrolled in the modeling group and validation group, including 89 and 17 neonates infected with MDRO, respectively. Four independent risk factors were obtained and the PRM was constructed, namely: P = 1/ (1+ e-X), X = -4.126 + 1.089× (low birth weight) +1.435× (maternal age ≥ 35 years) +1.498× (use of antibiotics >7 days) + 0.790× (MDRO colonization). A nomogram was drawn to visualize the PRM. Through internal and external validation, the PRM had good fitting degree, calibration, discrimination and certain clinical validity. The prediction accuracy of the PRM was 77.19%.

Conclusion

Prevention and control strategies for each independent risk factor can be developed in NICUs. Moreover, clinical staff can use the PRM to early identification of neonates at high risk, and do targeted prevention to reduce MDRO infections in NICUs.

Development, Validation and Comparison of Artificial Neural Network and Logistic Regression Models Predicting Eosinophilic Chronic Rhinosinusitis With Nasal Polyps

PURPOSE

Chronic rhinosinusitis with nasal polyps (CRSwNP) can be classified into eosinophilic CRSwNP (eCRSwNP) and non-eosinophilic CRSwNP (non-eCRSwNP) by tissue biopsy, which is difficult to perform preoperatively. Clinical biomarkers have predictive value for the classification of CRSwNP. We aimed to evaluate the application of artificial neural network (ANN) modeling in distinguishing different endotypes of CRSwNP based on clinical biomarkers.

METHODS

Clinical parameters were collected from 109 CRSwNP patients, and their predictive ability was analyzed. ANN and logistic regression (LR) models were developed in the training group (72 patients) and further tested in the test group (37 patients). The output variable was the diagnosis of eCRSwNP, defined as tissue eosinophil count > 10 per high-power field. The receiver operating characteristics curve was used to assess model performance.

RESULTS

A total of 15 clinical features from 60 healthy controls, 60 eCRSwNP and 49 non-eCRSwNP were selected as candidate predictors. Nasal nitric oxide levels, peripheral eosinophil absolute count, total immunoglobulin E, and ratio of bilateral computed tomography scores for the ethmoid sinus and maxillary sinus were identified as important features for modeling. Two ANN models based on 4 and 15 clinical features were developed to predict eCRSwNP, which showed better performance, with the area under the receiver operator characteristics significantly higher than those from the respective LR models (0.976 vs. 0.902, P = 0.048; 0.970 vs. 0.845, P = 0.011). All ANN models had better fits than single variable prediction models (all P < 0.05), and ANN model 1 had the best predictive performance among all models.

CONCLUSIONS

Machine learning models assist clinicians in predicting endotypes of nasal polyps before invasive detection. The ANN model has the potential to predict eCRSwNP with high sensitivity and specificity, and is superior to the LR model. ANNs are valuable for optimizing personalized patient management.

Editorial COVID-19 and Thrombosis 2023: New Waves of SARS-CoV-2 Infection, Triage Organization in Emergency Department and the Association of VOCs/VOI with Pulmonary Embolism

Nearly two years ago, the SARS-CoV-2 outbreak began, and our lives have changed significantly since then [...]

The pharmacology of anticoagulant drug treatment options in COVID-19 patients: reviewing real-world evidence in clinical practice

INTRODUCTION

The optimal anticoagulation strategy for venous thromboembolism (VTE) prevention among COVID-19 patients, hospitalized or in the community setting, is still challenging and largely based on real-world evidence.

AREAS COVERED

We analyzed real-world data regarding the safety and effectiveness of anticoagulant treatment, both parenteral and oral, for VTE prevention or atrial fibrillation (AF)/VTE treatment among COVID-19 patients.

EXPERT OPINION

The efficacy of low-molecular-weight heparin (LMWH) doses for VTE prevention correlates with COVID-19 disease status. LMWH prophylactic dose may be useful in COVID-19 patients at the early stage of the disease. LMWH intermediate or therapeutic dose is recommended in COVID-19 patients with an advanced stage of the disease. COVID-19 patients on VKAs therapy for atrial fibrillation (AF) and VTE should switch to NOACs in the community setting or LMWH in the hospital setting. No definitive data on de-novo starting of NOACs or VKAs therapy for VTE prevention in COVID-19 outpatients are available. In patients at high risk discharged after hospitalization due to COVID-19, thromboprophylaxis with NOACs may be considered.

Editorial: Unusual Clinical Presentation of COVID-19

Nearly two years ago, the SARS-CoV2 outbreak began, and our lives have changed significantly since then [...].