ETM: Enrichment by topic modeling for automated clinical sentence classification to detect patients’ disease history

Abstract

Given the rapid rate at which text data are being digitally gathered in the medical domain, there is growing need for automated tools that can analyze clinical notes and classify their sentences in electronic health records (EHRs). This study uses EHR texts to detect patients' disease history from clinical sentences. However, in EHRs, sentences are less topic-focused and shorter than that in general domain, which leads to the sparsity of co-occurrence patterns and the lack of semantic features. To tackle this challenge, current approaches for clinical sentence classification are dependent on external information to improve classification performance. However, this is implausible owing to a lack of universal medical dictionaries. This study proposes the ETM (enrichment by topic modeling) algorithm, based on latent Dirichlet allocation, to smoothen the semantic representations of short sentences. The ETM enriches text representation by incorporating probability distributions generated by an unsupervised algorithm into it. It considers the length of the original texts to enhance representation by using an internal knowledge acquisition procedure. When it comes to clinical predictive modeling, interpretability improves the acceptance of the model. Thus, for clinical sentence classification, the ETM approach employs an initial TFiDF (term frequency inverse document frequency) representation, where we use the support vector machine and neural network algorithms for the classification task. We conducted three sets of experiments on a data set consisting of clinical cardiovascular notes from the Netherlands to test the sentence classification performance of the proposed method in comparison with prevalent approaches. The results show that the proposed ETM approach outperformed state-of-the-art baselines.

Automatic Prediction of Recurrence of Major Cardiovascular Events: A Text Mining Study Using Chest X-Ray Reports

“…(i) Bag-of-Words . The BOW representation is the most commonly used representation for text mining applications [ 11 ]. Words in the reports were converted into a sparse multidimensional representation, which was leveraged for further classification and clustering purposes.…”

“…This method has the advantage of using an interpretable lower-dimensional representation of text and the disadvantage of lacking the capacity of methods that use all features of unstructured medical notes. We ran the experiments fitting the LDA topic model with Gibbs sampling [ 11 , 40 ] using 10 topics. Figure 3 shows two topics of the output of LDA applied to the X-ray radiology reports in the SMART study.…”

“…Unstructured texts contained within the EHRs are recognized as a rich but not easily accessible and usable source of medical information [1][2][3][4][5][6]. Recent studies have attempted to derive information from unstructured medical texts to classify disease codes [7][8][9][10], detect patient's disease history [11,12], and predict hospital readmission or clinical outcomes [13][14][15]. X-ray radiology reports are an example of such unstructured data describing radiologist's observations on patient's medical conditions associated with medical images.…”

Text Mining in Healthcare: Bringing Structure to Electronic Health Records

“…The BOW representation is the most commonly used representation for text mining applications (Bagheri et al, 2020b). Words in the reports were converted into a sparse multidimensional representation, which was leveraged for further classification and clustering purposes.…”

“…This method has the advantage of using an interpretable lower dimensional representation of text and the disadvantage of lacking the capacity of methods that use all features of unstructured medical notes. We ran the experiments fitting the LDA topic model with Gibbs sampling (Bagheri et al, 2020b;Blei et al, 2003) using 10 topics. Figure 4.3 shows two topics of the output of LDA applied to the x-ray radiology reports in the SMART study.…”