Automating classification of free‐text electronic health records for epidemiological studies

Schuemie, Martijn J.; Şen, Emine; Jong, Geert W. ‘t; Soest, Eva M. van; Sturkenboom, Miriam; Kors, Jan A.

doi:10.1002/pds.3205

Cited by 31 publications

(27 citation statements)

References 16 publications

(15 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The advantage of using the assertion filter and bag-of-words feature representation on Dutch EMRs is presented in [24]. Since the total number of features was still very high even after preprocessing, which makes machine learning computationally expensive and may also hamper the predictive accuracy of the classifier, we performed chi-square feature selection [43].…”

Section: Methodsmentioning

confidence: 99%

“…We selected the four top-performing algorithms from a previous study [24], in which many well-known machine-learning algorithms were evaluated for the classification of EMRs in a similar experimental setting.…”

Section: Methodsmentioning

confidence: 99%

“…Machine-learning methods have been used for different classifications tasks based on electronic medical records such as identification of patients with various conditions [6,13-17], automatic coding [7,18,19], identifying candidates in need of therapy [20], identifying clinical entries of interest [21], and identifying smoking status [22,23]. Schuemie et al [24] compared several machine-learning methods for identifying patients with liver disorder from free-text medical records. These methods are usually not optimized for sensitivity but for accuracy.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Improving sensitivity of machine learning methods for automated case identification from free-text electronic medical records

Afzal

Schuemie

Blijderveen

et al. 2013

BMC Med Inform Decis Mak

View full text Add to dashboard Cite

BackgroundDistinguishing cases from non-cases in free-text electronic medical records is an important initial step in observational epidemiological studies, but manual record validation is time-consuming and cumbersome. We compared different approaches to develop an automatic case identification system with high sensitivity to assist manual annotators.MethodsWe used four different machine-learning algorithms to build case identification systems for two data sets, one comprising hepatobiliary disease patients, the other acute renal failure patients. To improve the sensitivity of the systems, we varied the imbalance ratio between positive cases and negative cases using under- and over-sampling techniques, and applied cost-sensitive learning with various misclassification costs.ResultsFor the hepatobiliary data set, we obtained a high sensitivity of 0.95 (on a par with manual annotators, as compared to 0.91 for a baseline classifier) with specificity 0.56. For the acute renal failure data set, sensitivity increased from 0.69 to 0.89, with specificity 0.59. Performance differences between the various machine-learning algorithms were not large. Classifiers performed best when trained on data sets with imbalance ratio below 10.ConclusionsWe were able to achieve high sensitivity with moderate specificity for automatic case identification on two data sets of electronic medical records. Such a high-sensitive case identification system can be used as a pre-filter to significantly reduce the burden of manual record validation.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Improving sensitivity of machine learning methods for automated case identification from free-text electronic medical records

Afzal

Schuemie

Blijderveen

et al. 2013

BMC Med Inform Decis Mak

View full text Add to dashboard Cite

show abstract

“…The era of RWD and RWE calls for closer collaborations with experts from computer science, data science, informatics, genomic research, and other disciplines. Data-adaptive techniques (such as machine learning) combined with thoughtful human input are increasingly being used to mine electronic health record databases [34, 35] and improve analytic methods commonly used in pharmacoepidemiology [36, 37]. The ability to collect more data from mobile devices enables exploration of new issues, e.g., the relation between weather and joint pain in patients with rheumatoid arthritis [38].…”

Section: Boldermentioning

confidence: 99%

Pharmacoepidemiology in the Era of Real-World Evidence

Toh

2017

Curr Epidemiol Rep

View full text Add to dashboard Cite

“…“spikes” and “sharp waves”), generalized periodic discharges, lateralized periodic discharges, and rhythmic delta activity [1]. To derive useful knowledge from these free-text reports, researchers typically have to perform weeks to months of intensive manual work to review and categorize these reports [7] [8]. Automated algorithms offer the advantages of saving human labor, increased speed and the ability to scale the process to larger datasets [11].…”

Section: Introductionmentioning

confidence: 99%

Automated information extraction from free-text EEG reports

Biswal

Nip

Moura

et al. 2015

2015 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)

View full text Add to dashboard Cite

In this study we have developed a supervised learning to automatically detect with high accuracy EEG reports that describe seizures and epileptiform discharges. We manually labeled 3,277 documents as describing one or more seizures vs no seizures, and as describing epileptiform discharges vs no epileptiform discharges. We then used Naïve Bayes to develop a system able to automatically classify EEG reports into these categories. Our system consisted of normalization techniques, extraction of key sentences, and automated feature selection using cross validation. As candidate features we used key words and special word patterns called elastic word sequences (EWS). Final feature selection was accomplished via sequential backward selection. We used cross validation to predict out of sample performance. Our automated feature selection procedure resulted in a classifier with 38 features for seizure detection, and 23 features for epileptiform discharge detection. The average [95% CI] area under the receiver operating curve was 99.05 [98.79, 99.32]% for detecting reports with seizures, and 96.15 [92.31, 100.00]% for detecting reports with epileptiform discharges. The methodology described herein greatly reduces the manual labor involved in identifying large cohorts of patients for retrospective neurophysiological studies of patients with epilepsy.

show abstract

Automating classification of free‐text electronic health records for epidemiological studies

Cited by 31 publications

References 16 publications

Improving sensitivity of machine learning methods for automated case identification from free-text electronic medical records

Improving sensitivity of machine learning methods for automated case identification from free-text electronic medical records

Pharmacoepidemiology in the Era of Real-World Evidence

Automated information extraction from free-text EEG reports

Contact Info

Product

Resources

About