SeekDoc: Seeking eligible doctors from electronic health record.
Math Biosci Eng
; 18(5): 5347-5363, 2021 06 16.
Article
in En
| MEDLINE
| ID: mdl-34517491
ABSTRACT
With the development of online medical service platform, patients can find more medical information resources and obtain better medical treatment. However, it is difficult for patients to discover the most suitable doctors from the complex information resources. Therefore, the analysis and mining of Electronic Health Record(EHR) is very important for patients' timely and accurate treatment. Discovering the most suitable doctor is actually predicting the exact performance of the doctor for a specific disease. We believe that "a curative/bad treatment is likely to be caused by a good/bad doctor, and a good/bad doctor has a higher/lower evaluation by the patient(s)". In this paper, we propose a novel approach named SeekDoc, which is to seek the most effective doctor for a specific disease. Specifically, we build a doctor-disease heterogeneous information network and collect patients reviews and rating records for doctors. Then, we embed the comprehensive comment data for doctors and the constructed heterogeneous information network. Next, we use the autoencoder mechanism to learn the embedded features, which is an effective learning algorithm for constructing the latent feature representation in an unsupervised manner. After this learning, the latent features are input into the extreme gradient boosting (XGBoost) algorithm to improve their detection capabilities. Finally, extensive experiments show that our method can effectively and efficiently predict the doctor's experience score for specific diseases and has good performance compared with other algorithms.
Key words
Full text:
1
Collection:
01-internacional
Database:
MEDLINE
Main subject:
Physicians
/
Electronic Health Records
Type of study:
Prognostic_studies
Limits:
Humans
Language:
En
Journal:
Math Biosci Eng
Year:
2021
Document type:
Article
Affiliation country:
China