A Review of Automatic Phenotyping Approaches using Electronic Health Records

Alzoubi, Hadeel; Alzubi, Raid; Ramzan, Naeem; West, Daune; Al-Hadhrami, Tawfik; Alazab, Mamoun

doi:10.3390/electronics8111235

Cited by 45 publications

(36 citation statements)

References 98 publications

(128 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The duration of the drug exposure window can be determined by clinical knowledge or sensitivity analysis. Additionally, the performance metrics of a pharmacoinformatic study also depend on confounding control 37,38 . Longitudinal health data contain a variety of variables, including both categorical and numerical confounders.…”

Section: Discussionmentioning

confidence: 99%

“…Additionally, the performance metrics of a pharmacoinformatic study also depend on confounding control. 37 , 38 Longitudinal health data contain a variety of variables, including both categorical and numerical confounders. Both categorical confounders and numerical confounders can be controlled by using multivariable analysis.…”

Section: Discussionmentioning

confidence: 99%

“…Additionally, the performance metrics of pharmacoinformatics study also depend on confounding control (38,39). Longitudinal health data contain a variety of variables including both categorical and numerical confounders.…”

Section: Accepted Articlementioning

confidence: 99%

See 2 more Smart Citations

Random control selection for conducting high‐throughput adverse drug events screening using large‐scale longitudinal health data

Chiang

Zhang

Donneyong

et al. 2021

CPT Pharmacom & Syst Pharma

View full text Add to dashboard Cite

Case-control design based high-throughput pharmacoinformatics study using large-scale longitudinal health data is able to detect new adverse drug events (ADEs) signals. Existing control selection approaches for case-control design including dynamic/super control selection approach. Dynamic/super control selection approach requires all individuals to be evaluated at all ADE case index dates, as the individuals' eligibilities as control depend on ADE/enrolment history. Thus, using large-scale longitudinal health data, dynamic/super control selection approach requires extraordinarly high computational time. We proposed a random control selection approach in which ADE case index dates were matched by randomly generated control index dates. Random control selection approach doesn't depend on ADE/enrolment history. It is able to significantly reduce computational time to prepare case-control data sets, as it requires all individuals to be evaluated only once. We compared the performance metrics of all control selection approaches using two large-scale longitudinal health data and a drug-ADE gold standard including 399 drug-ADE pairs. The F-scores for random control selection approach were between 0.586 -0.600 compared to between 0.545 -0.562 for dynamic/super control selection approaches. Random control selection approach was approximately 1,000 times faster than dynamic/super control selection approach on preparing case-control data sets. With large-scale longitudinal health data, case-control design based pharmacoinformatics study using random control selection is able to generate comparable ADE signals than the existing control selection approaches. Random control selection approach also significantly reduces computational time to prepare the case-control data sets.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Random control selection for conducting high‐throughput adverse drug events screening using large‐scale longitudinal health data

Chiang

Zhang

Donneyong

et al. 2021

CPT Pharmacom & Syst Pharma

View full text Add to dashboard Cite

show abstract

“…Electronic medical records and disease registries are possible candidates along this line. An increasing number of phenotype algorithms [ 88 – 90 ] may well function as gold standards for CBA research when electronic medical records are available. Cancer registries can be used to conduct comprehensive CBA research for various cancers.…”

Section: Discussionmentioning

confidence: 99%

Claims-based algorithms for common chronic conditions were efficiently constructed using machine learning methods

et al. 2021

View full text Add to dashboard Cite

Identification of medical conditions using claims data is generally conducted with algorithms based on subject-matter knowledge. However, these claims-based algorithms (CBAs) are highly dependent on the knowledge level and not necessarily optimized for target conditions. We investigated whether machine learning methods can supplement researchers’ knowledge of target conditions in building CBAs. Retrospective cohort study using a claims database combined with annual health check-up results of employees’ health insurance programs for fiscal year 2016–17 in Japan (study population for hypertension, N = 631,289; diabetes, N = 152,368; dyslipidemia, N = 614,434). We constructed CBAs with logistic regression, k-nearest neighbor, support vector machine, penalized logistic regression, tree-based model, and neural network for identifying patients with three common chronic conditions: hypertension, diabetes, and dyslipidemia. We then compared their association measures using a completely hold-out test set (25% of the study population). Among the test cohorts of 157,822, 38,092, and 153,608 enrollees for hypertension, diabetes, and dyslipidemia, 25.4%, 8.4%, and 38.7% of them had a diagnosis of the corresponding condition. The areas under the receiver operating characteristic curve (AUCs) of the logistic regression with/without subject-matter knowledge about the target condition were .923/.921 for hypertension, .957/.938 for diabetes, and .739/.747 for dyslipidemia. The logistic lasso, logistic elastic-net, and tree-based methods yielded AUCs comparable to those of the logistic regression with subject-matter knowledge: .923-.931 for hypertension; .958-.966 for diabetes; .747-.773 for dyslipidemia. We found that machine learning methods can attain AUCs comparable to the conventional knowledge-based method in building CBAs.

show abstract

“…Natural Language Processing (NLP) is gaining relevance within the clinical documentation services to cope with extensive information conveyed by Electronic Health Records (EHRs). Healthcare data is getting increasingly larger and complex to process [1], but evidence shows its usefulness in such different sectors as Adverse Drug Reaction extraction [2,3] and identification of complex symptoms, assessed in several cohorts of patients in hemodialysis [4], as well as relevant symptoms in patients with schizophrenia [5], and breast cancer [6], and the creation of phenotypes to characterise patients [7,8].…”

Section: Introductionmentioning

confidence: 99%

Extreme Multi-Label ICD Classification: Sensitivity to Hospital Service and Time

2020

View full text Add to dashboard Cite

This work deals with clinical text mining for automatic classification of Electronic Health Records (EHRs) with respect to the International Classification of Diseases (ICD). ICD is the international standard for the identification of diseases and health conditions in EHRs and the foundation for reporting health statistics. Machine learning-based techniques have proven robust to infer classification models from EHRs. Since each EHR tends to involve multiple diseases, multi-label classification is required. The concern in this work is the versatility of the models inferred and their ability to generalise in two ways: as time goes ahead and across hospital services or health specialties. Indeed, in this work, we show the capabilities of a Bidirectional Recurrent Neural Network (RNN) with GRU units and ELMo embeddings on two corpora (a corpus comprising a set of EHRs within the Basque Health System, namely Osakidetza, and the well-known MIMIC-III corpus). To delve into and assess the versatility of the models, we focus on their resilience across hospital admissions taken over two different years and also across six distinct hospital services. In addition, we paid attention to the classification performance to estimate ICD codes of different granularity (e.g. with or without essential modifiers). Our best results are 39.55% and 47.28% F-Score for the Osakidetza and MIMIC-III datasets respectively, with the original main label-sets. Regarding the models evaluated per specialty, the most remarkable results are 57.00% and 72.74% F-Score, in the Cardiology and Nephrology medical services respectively. INDEX TERMS Extreme multi-label classification, Electronic Health Records, International Classification of Diseases, Classification across-time, Classification across hospital-services.

show abstract

A Review of Automatic Phenotyping Approaches using Electronic Health Records

Cited by 45 publications

References 98 publications

Random control selection for conducting high‐throughput adverse drug events screening using large‐scale longitudinal health data

Random control selection for conducting high‐throughput adverse drug events screening using large‐scale longitudinal health data

Claims-based algorithms for common chronic conditions were efficiently constructed using machine learning methods

Extreme Multi-Label ICD Classification: Sensitivity to Hospital Service and Time

Contact Info

Product

Resources

About