Applying Deep Learning Model to Predict Diagnosis Code of Medical Records

Abstract

The International Classification of Diseases (ICD) code is a diagnostic classification standard that is frequently used as a referencing system in healthcare and insurance. However, it takes time and effort to find and use the right diagnosis code based on a patient’s medical records. In response, deep learning (DL) methods have been developed to assist physicians in the ICD coding process. Our findings propose a deep learning model that utilized clinical notes from medical records to predict ICD-10 codes. Our research used text-based medical data from the outpatient department (OPD) of a university hospital from January to December 2016. The dataset used clinical notes from five departments, and a total of 21,953 medical records were collected. Clinical notes consisted of a subjective component, objective component, assessment, plan (SOAP) notes, diagnosis code, and a drug list. The dataset was divided into two groups: 90% for training and 10% for test cases. We applied natural language processing (NLP) technique (word embedding, Word2Vector) to process the data. A deep learning-based convolutional neural network (CNN) model was created based on the information presented above. Three metrics (precision, recall, and F-score) were used to calculate the achievement of the deep learning CNN model. Clinically acceptable results were achieved through the deep learning model for five departments (precision: 0.53–0.96; recall: 0.85–0.99; and F-score: 0.65–0.98). With a precision of 0.95, a recall of 0.99, and an F-score of 0.98, the deep learning model performed the best in the department of cardiology. Our proposed CNN model significantly improved the prediction performance for an automated ICD-10 code prediction system based on prior clinical information. This CNN model could reduce the laborious task of manual coding and could assist physicians in making a better diagnosis.

Empowering Health Care Providers

“…It is not surprising that most of our static, lower-producing providers opted to change habits and templates after our system's announcement that it was being acquired and the heightened scrutiny and pressure that followed. Fortunately, AI coding is in development 20 , 21 which could lessen the need for providers to have expertise in billing and coding. Future applications of this method will be used for executive-level departmental planning.…”

A systematic evaluation of the performance of GPT‐4 and PaLM2 to diagnose comorbidities in MIMIC‐IV patients

“…We further ask the reader to bear in mind that our study is inherently different from the simultaneous ongoing effort of ICD code extraction from clinical notes, such as the one described in [ 17 ]. This is because those clinical notes provide a complete picture of the patient after the doctor made note of the diagnosis and prepared the subjective objective assessment plan.…”

Literatur Review Management Analysis of Medical Record Management System in Puskesmas

“…Pada Kegiatan pelaksanaanpengkodean belum terlaksana dengan baik karena yang melakukan pengkodean adalah pemegang program masing-masing poliklinik yaitu dokter dengan cara menginputkan diagnosa pasien ke komputer denganberpedoman kepada ICD-10, akan tetapi kegiatan penginputan kode hanya untuk pasien BPJS saja, dan untuk pelaksanaan pengkodean di DRM pasien jarang dilakukan baik pasien BPJS maupun pasien umum. Pada hasil penelitian (Masud et al, 2023)terdapat Surat Keputusan (SK) dan Standar Operational Prosedur (SOP) mengenai pembakuan kode klasifikasi diagnosis. Pembakuan kode klasifikasi diagnosis menggunakan ICD-10 sebagai pedoman pemberian kode penyakit (Beam et al, 2021); (Golpira et al, 2021); (Pfaff et al, 2023); (Sammani et al, 2021); (Rico et al, 2021); (Song et al, 2023).…”