Predicting Multiple ICD-10 Codes from Brazilian-Portuguese Clinical Notes

  title={Predicting Multiple ICD-10 Codes from Brazilian-Portuguese Clinical Notes},
  author={Arthur D. Reys and Danilo Silva and Daniel de Souza Severo and Saulo Pedro and Marcia M. de Souza e S'a and Guilherme A. C. Salgado},
ICD coding from electronic clinical records is a manual, time-consuming and expensive process. Code assignment is, however, an important task for billing purposes and database organization. While many works have studied the problem of automated ICD coding from free text using machine learning techniques, most use records in the English language, especially from the MIMIC-III public dataset. This work presents results for a dataset with Brazilian Portuguese clinical notes. We develop and… Expand

Figures and Tables from this paper

Clinical Outcome Prediction from Admission Notes using Self-Supervised Knowledge Integration
This work simulates patients at admission time, when decision support can be especially valuable, and proposes *clinical outcome pre-training* to integrate knowledge about patient outcomes from multiple public sources and presents a simple method to incorporate ICD code hierarchy into the models. Expand
Read, Attend, and Code: Pushing the Limits of Medical Codes Prediction from Clinical Notes by Machines
A meaningful step toward fully autonomous medical coding (AMC) in machines reaching parity with human coders’ performance in medical code prediction is marked, as RAC establishes a new state of the art (SOTA), considerably outperforming the current best Macro-F1 by 18.7%, and reaches past the human-level coding baseline. Expand


ICD Coding from Clinical Text Using Multi-Filter Residual Convolutional Neural Network
A Multi-Filter Residual Convolutional Neural Network (MultiResCNN) for ICD coding that utilizes a multi-filter convolutional layer to capture various text patterns with different lengths and a residual convolutionAL layer to enlarge the receptive field. Expand
An Empirical Evaluation of Deep Learning for ICD-9 Code Assignment using MIMIC-III Clinical Notes
Traditional machine learning algorithms, as well as state-of-the-art deep learning methods such as Recurrent Neural Networks and Convolution Neural Networks, were applied to the Medical Information Mart for Intensive Care dataset and showed that the deep learning-based methods outperformed other conventional machine learning methods. Expand
Multimodal Machine Learning for Automated ICD Coding
Two separate machine learning models that can handle data from different modalities, including unstructured text, semi-structuring text and structured tabular data are developed and an ensemble method to integrate all modality-specific models to generate ICD-10 codes is employed. Expand
Deep neural models for ICD-10 coding of death certificates and autopsy reports in free-text
We address the assignment of ICD-10 codes for causes of death by analyzing free-text descriptions in death certificates, together with the associated autopsy reports and clinical bulletins, from theExpand
A Neural Architecture for Automated ICD Coding
A neural architecture for automated coding that takes the diagnosis descriptions of a patient as inputs and selects the most relevant ICD codes, and demonstrates the effectiveness of the proposed methods on a clinical datasets with 59K patient visits. Expand
Tagging Patient Notes With ICD-9 Codes
There is substantial growth in the amount of medical/data being generated in hospitals. With over 96% adoption rate[1], Electronic Medical/Health Records are used to store most of this medical data.Expand
Automated ICD-9 Coding via A Deep Learning Approach
A deep learning framework called DeepLabeler is presented to automatically assign ICD-9 codes and it is found that the convolutional neural network is the most effective component in the network and the ‘Document to Vector’ technique is also necessary for enhancing classification performance since it extracts well-recognized global features. Expand
Explainable Prediction of Medical Codes from Clinical Text
An attentional convolutional network that predicts medical codes from clinical text using a convolutionAL neural network and uses an attention mechanism to select the most relevant segments for each of the thousands of possible codes is presented. Expand
Convolutional Neural Networks for Medical Diagnosis from Admission Notes
An automatic diagnostic system which only uses textual admission information from Electronic Health Records and assist clinicians with a timely and statistically proved decision tool is developed, demonstrating capability of representing complex medical meaningful features from unstructured clinical notes and prediction power for commonly misdiagnosed frequent diseases. Expand
Using Structured EHR Data and SVM to Support ICD-9-CM Coding
A methodology entailing an adaptive data processing method based on structured electronic health record data, whereby raw clinical data is mapped into a feature set, and based on which supervised learning algorithms are trained. Expand