An experimental study in automatically categorizing medical documents

Abstract

In this article, we evaluate the retrieval performance of an algorithm that automatically categorizes medical documents. The categorization, which consists in assigning an International Code of Disease (ICD) to the medical document under examination, is based on well‐known information retrieval techniques. The algorithm, which we proposed, operates in a fully automatic mode and requires no supervision or training data. Using a database of 20,569 documents, we verify that the algorithm attains levels of average precision in the 70–80% range for category coding and in the 60–70% range for subcategory coding. We also carefully analyze the case of those documents whose categorization is not in accordance with the one provided by the human specialists. The vast majority of them represent cases that can only be fully categorized with the assistance of a human subject (because, for instance, they require specific knowledge of a given pathology). For a slim fraction of all documents (0.77% for category coding and 1.4% for subcategory coding), the algorithm makes assignments that are clearly incorrect. However, this fraction corresponds to only one‐fourth of the mistakes made by the human specialists.

HealthMap: Global Infectious Disease Monitoring through Automated Classification and Visualization of Internet Media Reports

“…We will also explore more advanced techniques such as fuzzy matching and Bayesian machine learning for improving the resolution and accuracy of our automated classification algorithms, as well as categorizing alerts by relevancy, clustering similar alerts, and extracting other useful attributes. [27][28][29] On the human side, taking inspiration from the highly successful Wikipedia model, 30 we plan to work with networks of experts to evaluate community collaboration as a mechanism for alert acquisition and classification.…”

Clinical Assistant Diagnosis for Electronic Medical Record Based on Convolutional Neural Network

“…These four machine learning algorithms that we compared to have been applied to the auxiliary diagnosis of electronic medical records in some previous related works and have achieved good results 36–38 . From the results shown in Table 2 we can see that our model has achieved the best effect on each evaluation method.…”

Deploying Information Technology and Continuous Control Monitoring Systems in Hospitals to Prevent Medication Errors

“…Most medical organisations produce an abundance of medical documents that are used to support a variety of processes within these organisations (Ribeiro-Neto, Laender & Luciano 2001). The analysis of IT used in healthcare organisations is a very interesting field of research (Jamal, McKenzie & Clark 2009).…”