Applying Convolutional Neural Networks to Predict the ICD-9 Codes of Medical Records

Abstract

The International Statistical Classification of Disease and Related Health Problems (ICD) is an international standard system for categorizing and reporting diseases, injuries, disorders, and health conditions. Most previously-proposed disease predicting systems need clinical information collected by the medical staff from the patients in hospitals. In this paper, we propose a deep learning algorithm to classify disease types and identify diagnostic codes by using only the subjective component of progress notes in medical records. In this study, we have a dataset, consisting of about one hundred and sixty-eight thousand medical records, from a medical center, collected during 2003 and 2017. First, we apply standard text processing procedures to parse the sentences and word embedding techniques for vector representations. Next, we build a convolution neural network model on the medical records to predict the ICD-9 code by using a subjective component of the progress note. The prediction performance is evaluated by ten-fold cross-validation and yields an accuracy of 0.409, recall of 0.409 and precision of 0.436. If we only consider the “chapter match” of ICD-9 code, our model achieves an accuracy of 0.580, recall of 0.580, and precision of 0.582. Since our diagnostic code prediction model is solely based on subjective components (mainly, patients’ self-report descriptions), the proposed approach could serve as a remote and self-diagnosis assistance tool, prior to seeking medical advice or going to the hospital. In addition, our work may be used as a primary evaluation tool for discomfort in the rural area where medical resources are restricted.

Forecasting the Tuberculosis Incidence Using a Novel Ensemble Empirical Mode Decomposition-Based Data-Driven Hybrid Model in Tibet, China

“…Infection and Drug Resistance 2021:14 1950 temperature, 28 and ICD-9 codes of medical records, 51 and these studies suggested that the LSTM and CNN also showed high accuracy for forecasting the target series. Therefore, further work is supposed to compare the forecasting ability between our proposed combined method and the above deep mining methods.…”

Predicting ICD-9 Codes Using Self-Report of Patients

“…In our previous study [13], we employed a CNN based network to predict ICD-9 code, which scores the recall of 58% in chapter level. In this work, we applied the LSTM and GRU network to predict ICD codes.…”

“…Many countries consider ICD as the tool to follow up death and statistics of death. The ICD system has more than one version, which depends on the situation in different countries and their clinical conditions [13]. Various countries have adopted the ICD-10, including the United States.…”

“…The POMR (Problem-Oriented Medical Record) is a recording approach of medical data; It consist of four parts, which include database, problem list, initial plan, and progress note. The POMR follows the format of SOAP, which consists of subjective component, objective component, assessment, and plan [13,15]. In the SOAP format, the subjective component is said to be a training data, which includes feelings, opinions, and complaints of patients.…”

MR-KPA: medication recommendation by combining knowledge-enhanced pre-training with a deep adversarial network

“…for a single admission. More and more attention has been paid to EMR-based auxiliary diagnosis and treatment, such as clinical knowledge question answering [1,2], health risk warning [3][4][5][6], auxiliary diagnostic [7,8] and electronic prescription recommendation [9,10]. Medication recommendation is an important research direction in EMRbased applications.…”