Chai Yang;Xiaoxuan Hu;Qingli Zhu;Qiang Tu;Hongyang Geng;Jing Xu;Zhenfeng Liu;Yanjun Wang;Jing Wang
{"title":"Individual Medical Costs Prediction Methods Based on Clinical Notes and DRGs","authors":"Chai Yang;Xiaoxuan Hu;Qingli Zhu;Qiang Tu;Hongyang Geng;Jing Xu;Zhenfeng Liu;Yanjun Wang;Jing Wang","doi":"10.1109/JRFID.2024.3392682","DOIUrl":null,"url":null,"abstract":"Individual medical costs prediction refers to the process of estimating the expenses associated with a patient’s medical care. Effective medical costs prediction helps in budgeting, resource allocation, and financial planning in healthcare settings, making it a crucial tool for both healthcare providers and patients. This study introduces an advanced method for predicting medical consumables costs, leveraging clinical notes and diagnosis related groups (DRGs). The approach employs Bidirectional Encoder Representations from Transformers (BERT) for text vectorization to enhance disease diagnosis and surgical procedure prediction within DRGs using Light Gradient Boosting Machine (LightGBM), and Random Forest Regression for accurate medical costs prediction. It achieves over 91% accuracy in predicting disease diagnosis and surgical procedures, and a Mean Absolute Error (MAE) of 2281.20 and an R-squared value of 0.8557. These metrics indicate a high level of accuracy and reliability, showcasing the model’s efficacy in predicting medical costs in a healthcare setting. This method improves hospital resource management and costs estimation by integrating semantic information with machine learning algorithms.","PeriodicalId":73291,"journal":{"name":"IEEE journal of radio frequency identification","volume":"8 ","pages":"412-418"},"PeriodicalIF":2.3000,"publicationDate":"2024-04-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"IEEE journal of radio frequency identification","FirstCategoryId":"1085","ListUrlMain":"https://ieeexplore.ieee.org/document/10507203/","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"ENGINEERING, ELECTRICAL & ELECTRONIC","Score":null,"Total":0}
引用次数: 0
Abstract
Individual medical costs prediction refers to the process of estimating the expenses associated with a patient’s medical care. Effective medical costs prediction helps in budgeting, resource allocation, and financial planning in healthcare settings, making it a crucial tool for both healthcare providers and patients. This study introduces an advanced method for predicting medical consumables costs, leveraging clinical notes and diagnosis related groups (DRGs). The approach employs Bidirectional Encoder Representations from Transformers (BERT) for text vectorization to enhance disease diagnosis and surgical procedure prediction within DRGs using Light Gradient Boosting Machine (LightGBM), and Random Forest Regression for accurate medical costs prediction. It achieves over 91% accuracy in predicting disease diagnosis and surgical procedures, and a Mean Absolute Error (MAE) of 2281.20 and an R-squared value of 0.8557. These metrics indicate a high level of accuracy and reliability, showcasing the model’s efficacy in predicting medical costs in a healthcare setting. This method improves hospital resource management and costs estimation by integrating semantic information with machine learning algorithms.