袁靖
中国医学科学院阜外医院 信息中心
Automated ICD coding via machine learning that focuses on some specific diseases has been a hot topic. As one of the leading causes of death, coronary heart diseases (CHD) have seldom been specifically studied by related research, probably due to lack of data concretely targeting at the diseases. Based on Fuwai-CHD and MIMIC-III-CHD, which are a private dataset from Fuwai Hospital and the CHD-related subset of a public dataset named MIMIC-III respectively, this study aimed at automated CHD coding by a deep learning method, which mainly consists of three modules. The first is a B ERT variant module responsible for encoding clinical text. In the module, we fine-tuned BERT variants with masked language model on clinical text, and proposed a truncation method to tackle the problem that BERT variants generally cannot handle sequences containing more than 512 tokens. The second is a word2vec module for encoding code titles and the third is a label-attention module for integrating the embeddings of clinical text and code titles. In short, we named the method BW_att. We compared BW_att against some widely studied baselines, and found that BW_att performed best in most of the coding missions. Specifically, BW_att reached a Macro-F1 of 96.2% and a Macro-AUC of 98.9% for the top-100 most frequent codes in Fuwai-CHD, which covered 89.2% of the total code occurrences. When predicting the top-50 most frequent codes in MIMIC-III-CHD, BW_att reached a Macro-F1 of 40.5% and a Macro-AUC of 66.1%. Moreover, BW_att was capable of locating informative tokens from clinical text for predicting the target codes. In summary, BW_att can not only suggest CHD codes accurately, but also possess robust interpretability, hence has great potential in facilitating CHD coding in practice.
Heliyon 2023
BACKGROUND:Inappropriate antimicrobial use is common among patients undergoing surgery. It remains unclear whether a multi-faceted computerized antimicrobial stewardship programme is effective and safe in reducing inappropriate antimicrobial use in surgical settings.METHODS:A multi-faceted computerized antimicrobial stewardship intervention system was developed, and an open-label, cluster-randomized, controlled trial was conducted among 18 surgical teams that enrolled 2470 patients for open chest cardiovascular surgery. The surgical teams were divided at random into intervention and control groups at a ratio of 1:1. The primary endpoints were days of therapy (DOT)/1000 patient-days, defined daily dose (DDD)/1000 patient-days and length of therapy (LOT)/1000 patient-days.RESULTS:Mean DOT, DDD and LOT per 1000 patient-days were significantly lower in the intervention group compared with the control group (472.2 vs 539.8, 459.5 vs 553.8, and 438.4 vs 488.7; P<0.05), with reductions of 14.2% [95% confidence interval (CI) 11.8-16.7%], 18.7% (95% CI 15.9-21.4%) and 11.9% (95% CI 9.6-14.1%), respectively. The daily risk of inappropriate antimicrobial use after discharge from the intensive care unit decreased by 23.9% [95% CI 15.5-31.5% (incidence risk ratio 0.76, 95% CI 0.69-0.85)] in the intervention group. There was no significant difference in rates of infection or surgical-related complications between the groups. Median antimicrobial costs were significantly lower in the intervention group {873.4 [interquartile range (IQR) 684.5-1255.4] RMB vs 1178.7 (IQR 869.1-1814.5) RMB; P<0.001} (1 RMB approximately equivalent to 0.16 US$ in 2022).CONCLUSIONS:The multi-faceted computerized antimicrobial stewardship interventions reduced inappropriate antimicrobial use safely.CLINICAL TRIAL REGISTRATION:Clinicaltrials.gov: NCT04328090.
International journal of antimicrobial agents 2023
BACKGROUND:Computer-assisted clinical coding (CAC) based on automated coding algorithms has been expected to improve the International Classification of Disease, tenth version (ICD-10) coding quality and productivity, whereas studies oriented to primary diagnosis auto-coding are limited in the Chinese context.OBJECTIVE:This study aims at developing a machine learning (ML) model for automated primary diagnosis ICD-10 coding.METHODS:A total of 71,709 admissions in Fuwai hospital were included to carry out this study, corresponding to 168 primary diagnosis ICD-10 codes. Based on clinical implications, two feature engineering methods were used to process discharge diagnosis and procedure texts into sequential features and sequential grouping features respectively by which two kinds of models were built and compared. One baseline model using one-hot encoding features was considered. Light Gradient Boosting Machine (LightGBM) was adopted as the classifier, and grid search and cross-validation were used to select the optimal hyperparameters. SHapley Additive exPlanations (SHAP) values were applied to give the interpretability of models.RESULTS:Our best prediction model was developed based on sequential grouping features. It showed good performance in the test phase with accuracy and macro-averaged F1 (Macro-F1) of 95.2% and 88.3% respectively. The comparison of the models demonstrated the effectiveness of the sequential information and the grouping strategy in boosting model performance (P-value < 0.01). Subgroup analysis of the best model on each individual code manifested that 91.1% of the codes achieved the F1 over 70.0%.CONCLUSIONS:Our model has been demonstrated its effectiveness for automated primary diagnosis coding in the Chinese context and its results are interpretable. Hence, it has the potential to assist clinical coders to improve coding efficiency and quality in Chinese inpatient settings.
International journal of medical informatics 2021
BACKGROUND:Secondary hypertension is a kind of hypertension with a definite etiology and may be cured. Patients with suspected secondary hypertension can benefit from timely detection and treatment and, conversely, will have a higher risk of morbidity and mortality than those with primary hypertension.OBJECTIVE:The aim of this study was to develop and validate machine learning (ML) prediction models of common etiologies in patients with suspected secondary hypertension.METHODS:The analyzed data set was retrospectively extracted from electronic medical records of patients discharged from Fuwai Hospital between January 1, 2016, and June 30, 2019. A total of 7532 unique patients were included and divided into 2 data sets by time: 6302 patients in 2016-2018 as the training data set for model building and 1230 patients in 2019 as the validation data set for further evaluation. Extreme Gradient Boosting (XGBoost) was adopted to develop 5 models to predict 4 etiologies of secondary hypertension and occurrence of any of them (named as composite outcome), including renovascular hypertension (RVH), primary aldosteronism (PA), thyroid dysfunction, and aortic stenosis. Both univariate logistic analysis and Gini Impurity were used for feature selection. Grid search and 10-fold cross-validation were used to select the optimal hyperparameters for each model.RESULTS:Validation of the composite outcome prediction model showed good performance with an area under the receiver-operating characteristic curve (AUC) of 0.924 in the validation data set, while the 4 prediction models of RVH, PA, thyroid dysfunction, and aortic stenosis achieved AUC of 0.938, 0.965, 0.959, and 0.946, respectively, in the validation data set. A total of 79 clinical indicators were identified in all and finally used in our prediction models. The result of subgroup analysis on the composite outcome prediction model demonstrated high discrimination with AUCs all higher than 0.890 among all age groups of adults.CONCLUSIONS:The ML prediction models in this study showed good performance in detecting 4 etiologies of patients with suspected secondary hypertension; thus, they may potentially facilitate clinical diagnosis decision making of secondary hypertension in an intelligent way.
JMIR medical informatics 2021