Information Extraction from Echocardiography Reports for a Clinical Follow-up Study-Comparison of Extracted Variables Intended for General Use in a Data Warehouse with Those Intended Specifically for the Study

A general text mining method to extract echocardiography measurement results from echocardiography documents

BACKGROUND

In everyday medical practice, the results of cardiac ultrasound examinations are generally recorded in unstructured text, from which extracting relevant information is an important and challenging task. This paper presents a generally applicable language and corpus-independent text mining method for extracting and structuring numerical measurement results and their descriptions from echocardiography reports.

METHOD

The developed method is based on generally applicable text mining preprocessing activities, it automatically identifies and standardizes the descriptions of the cardiac ultrasound measures, and it stores the extracted and standardized measurement descriptions with their measurement results in a structured form for later usage. The method does not contain any regular expression-based search and does not rely on information about the structure of the document.

RESULTS

The method has been tested on a document set containing more than 20,000 echocardiographic reports by examining the efficiency of extracting 12 echocardiography parameters considered important by experts. The method extracted and structured the echocardiography parameters under the study with good sensitivity (lowest value: 0.775, highest value: 1.0, average: 0.904) and excellent specificity (for all cases 1.0). The F1 score ranged between 0.873 and 1.0, and its average value was 0.948.

CONCLUSION

The presented case study has shown that the proposed method can extract measurement results from echocardiography documents with high confidence without performing a direct search or having detailed information about the data recording habits. Furthermore, it effectively handles spelling errors, abbreviations and the highly varied terminology used in descriptions. As it does not rely on any information related to the structure or the language of the documents or data recording habits, it can be applied for processing any free-text written medical texts.

Sex-specific bimodal clustering of left ventricular ejection fraction in patients with acute heart failure

Aims

There is an ongoing discussion whether the categorization of patients with heart failure according to left ventricular ejection fraction (LVEF) is scientifically justified and clinically relevant. Major efforts are directed towards the identification of appropriate cut‐off values to correctly allocate heart failure‐specific pharmacotherapy. Alternatively, an LVEF continuum without definite subgroups is discussed. This study aimed to evaluate the natural distribution of LVEF in patients presenting with acutely decompensated heart failure and to identify potential subgroups of LVEF in male and female patients.

Methods and results

We identified 470 patients (mean age 75 ± 11 years, n = 137 female) hospitalized for acute heart failure in whom LVEF could be quantified by Simpson's method in an in‐hospital echocardiogram. Non‐parametric modelling revealed a bimodal shape of the LVEF distribution. Parametric modelling identified two clusters suggesting two LVEF peaks with mean (variance) of 61% (9%) and 31% (10%), respectively. Sub‐differentiation by sex revealed a sex‐specific bimodal clustering of LVEF. The respective threshold differentiating between ‘high’ and ‘low’ LVEF was 45% in men and 52% in women.

Conclusions

In patients presenting with acute heart failure, LVEF clustered in two subgroups and exhibited profound sex‐specific distributional differences. These findings might enrich the scientific process to identify distinct subgroups of heart failure patients, which might each benefit from respectively tailored (pharmaco)therapies.

Automatic extraction of 12 cardiovascular concepts from German discharge letters using pre-trained language models

Objective

A vast amount of medical data is still stored in unstructured text documents. We present an automated method of information extraction from German unstructured clinical routine data from the cardiology domain enabling their usage in state-of-the-art data-driven deep learning projects.

Methods

We evaluated pre-trained language models to extract a set of 12 cardiovascular concepts in German discharge letters. We compared three bidirectional encoder representations from transformers pre-trained on different corpora and fine-tuned them on the task of cardiovascular concept extraction using 204 discharge letters manually annotated by cardiologists at the University Hospital Heidelberg. We compared our results with traditional machine learning methods based on a long short-term memory network and a conditional random field.

Results

Our best performing model, based on publicly available German pre-trained bidirectional encoder representations from the transformer model, achieved a token-wise micro-average F1-score of 86% and outperformed the baseline by at least 6%. Moreover, this approach achieved the best trade-off between precision (positive predictive value) and recall (sensitivity).

Conclusion

Our results show the applicability of state-of-the-art deep learning methods using pre-trained language models for the task of cardiovascular concept extraction using limited training data. This minimizes annotation efforts, which are currently the bottleneck of any application of data-driven deep learning projects in the clinical domain for German and many other European languages.