Machine Learning Approaches for Electronic Health Records Phenotyping: A Methodical Review

Yang, Siyue; Varghese, Paul; Stephenson, Ellen; Tu, Karen; Gronsbell, Jessica

doi:10.1101/2022.04.23.22274218

Cited by 8 publications

(4 citation statements)

References 179 publications

(589 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This can be especially useful in urosepsis, where imaging can be used to identify the source of infection, such as a urinary tract obstruction or a kidney abscess. 4,[11][12][13] .…”

Section: Introductionmentioning

confidence: 99%

Biomarker identification and point-of-care assessment in urosepsis supported by machine learning

Wityk,

Cierpiak,

Raczak-Gutknecht

et al. 2024

Biophotonics in Point-of-Care III

View full text Add to dashboard Cite

Urinary Tract Infection (UTI): A common bacterial infection affecting the urinary system, leading to symptoms like frequent urination, burning sensation, and cloudy bloody urine. Urosepsis: A severe condition caused by untreated UTIs, where the infection spreads to the bloodstream, potentially leading to organ failure and life-threatening complications.Prompt treatment is vital. UTIs and the associated risk of urosepsis represent critical public health concerns. To address this, we present an innovative optical method supported by machine learning, specifically designed for mass screening of UTIs and urosepsis in urine samples. Our study involves obtaining spectra through spectroscopy measurements of artificial urine samples spiked with bacteria from solid cultures of clinical E. coli strains, allowing for the precise differentiation of infections. To ensure reliable classification, we rigorously tested 27 machine learning algorithms, achieving a remarkable accuracy rate of up to 97%.

show abstract

“…This can be especially useful in urosepsis, where imaging can be used to identify the source of infection, such as a urinary tract obstruction or a kidney abscess. 4,[11][12][13] .…”

Section: Introductionmentioning

confidence: 99%

Biomarker identification and point-of-care assessment in urosepsis supported by machine learning

Wityk,

Cierpiak,

Raczak-Gutknecht

et al. 2024

Biophotonics in Point-of-Care III

View full text Add to dashboard Cite

show abstract

“…To address this gap, researchers have developed machine learning algorithms intended to classify adult patients with PASC in large clinical databases [ 5 ]. In contrast with explicit rule-based definitions, machine learning algorithms have the advantage of being able to detect complex patterns involving thousands of covariates [ 6 ].…”

Section: Introductionmentioning

confidence: 99%

A machine learning-based phenotype for long COVID in children: An EHR-based study from the RECOVER program

et al. 2023

View full text Add to dashboard Cite

As clinical understanding of pediatric Post-Acute Sequelae of SARS CoV-2 (PASC) develops, and hence the clinical definition evolves, it is desirable to have a method to reliably identify patients who are likely to have post-acute sequelae of SARS CoV-2 (PASC) in health systems data. In this study, we developed and validated a machine learning algorithm to classify which patients have PASC (distinguishing between Multisystem Inflammatory Syndrome in Children (MIS-C) and non-MIS-C variants) from a cohort of patients with positive SARS- CoV-2 test results in pediatric health systems within the PEDSnet EHR network. Patient features included in the model were selected from conditions, procedures, performance of diagnostic testing, and medications using a tree-based scan statistic approach. We used an XGboost model, with hyperparameters selected through cross-validated grid search, and model performance was assessed using 5-fold cross-validation. Model predictions and feature importance were evaluated using Shapley Additive exPlanation (SHAP) values. The model provides a tool for identifying patients with PASC and an approach to characterizing PASC using diagnosis, medication, laboratory, and procedure features in health systems data. Using appropriate threshold settings, the model can be used to identify PASC patients in health systems data at higher precision for inclusion in studies or at higher recall in screening for clinical trials, especially in settings where PASC diagnosis codes are used less frequently or less reliably. Analysis of how specific features contribute to the classification process may assist in gaining a better understanding of features that are associated with PASC diagnoses.

show abstract

“…Unstructured variables in EHRs are usually dealt with using manual abstraction and proxy variables available as structured data 5 . Manual abstraction is time-consuming and not scalable, especially with the increase in EHR data 6 .…”

Section: Introductionmentioning

confidence: 99%

“…false positive)? * 13 5. 10 20How many patient charts would you be willing to review manually to prevent one patient who has GBM from being left out of the dataset (i.e.…”

mentioning

confidence: 99%

Selective prediction for extracting unstructured clinical data

Swaminathan

López

Wang

et al. 2022

Preprint

View full text Add to dashboard Cite

Background: Electronic health records represent a large data source for outcomes research, but the majority of EHR data is unstructured (e.g. free text of clinical notes) and not conducive to computational methods. While there are currently approaches to handle unstructured data, such as manual abstraction, structured proxy variables, and model-assisted abstraction, these methods are time-consuming, not scalable, and require clinical domain expertise. This paper aims to determine whether selective prediction, which gives a model the option to abstain from generating a prediction, can improve the accuracy and efficiency of unstructured clinical data abstraction. Methods: We trained selective prediction models to identify the presence of four distinct clinical variables in free-text pathology reports: primary cancer diagnosis of glioblastoma (GBM, n = 659), resection of rectal adenocarcinoma (RRA, n = 601), and two procedures for resection of rectal adenocarcinoma: abdominoperineal resection (APR, n = 601) and low anterior resection (LAR, n = 601). Data were manually abstracted from pathology reports and used to train L1-regularized logistic regression models using term-frequency-inverse-document-frequency features. Data points that the model was unable to predict with high certainty were manually abstracted. Findings: All four selective prediction models achieved a test-set sensitivity, specificity, positive predictive value, and negative predictive value above 0.91. The use of selective prediction led to sizable gains in automation (anywhere from 57% to 95% reduction in manual abstraction of charts across the four outcomes). For our GBM classifier, the selective prediction model saw improvements to sensitivity (0.94 to 0.96), specificity (0.79 to 0.96), PPV (0.89 to 0.98), and NPV (0.88 to 0.91) when compared to a non-selective classifier. Interpretation: Selective prediction using utility-based probability thresholds can facilitate unstructured data extraction by giving "easy" charts to a model and "hard" charts to human abstractors, thus increasing efficiency while maintaining or improving accuracy.

show abstract

Machine Learning Approaches for Electronic Health Records Phenotyping: A Methodical Review

Cited by 8 publications

References 179 publications

Biomarker identification and point-of-care assessment in urosepsis supported by machine learning

Biomarker identification and point-of-care assessment in urosepsis supported by machine learning

A machine learning-based phenotype for long COVID in children: An EHR-based study from the RECOVER program

Selective prediction for extracting unstructured clinical data

Contact Info

Product

Resources

About