We present an approach to classify medical text at a sentence level automatically.Given the inherent complexity of medical text classification,we employ adapters based on pre-trained language models to extract informa...We present an approach to classify medical text at a sentence level automatically.Given the inherent complexity of medical text classification,we employ adapters based on pre-trained language models to extract information from medical text,facilitating more accurate classification while minimizing the number of trainable parameters.Extensive experiments conducted on various datasets demonstrate the effectiveness of our approach.展开更多
Dropout from medical attendance is a well-recognized issue among patients with human immunodeficiency virus (HIV) infection. We interviewed 23 HIV-positive patients and used text mining methods to analyse the risk fac...Dropout from medical attendance is a well-recognized issue among patients with human immunodeficiency virus (HIV) infection. We interviewed 23 HIV-positive patients and used text mining methods to analyse the risk factors for dropout. Fifteen patients continued medical attendance and eight patients dropped out of medical attendance. Categories were extracted from the interview data of the patients who continued medical attendance (i.e., the continuity group) and the patients who dropped out of medical care (i.e., the discontinuity group). Categories of the continuity group included needing to take a day off for medical attendance, scheduling each appointment, writing down medical appointments, being grateful for the medical care, and 12 additional categories. Categories of discontinuity group included forgetting the dates of medical appointments, not needing to get a day off for medical attendance, allowing aid for medical care to expire, and 10 additional categories. The discontinuity group had poorer schedule management than the continuity group, which caused them to forget their next medical appointments and delay the renewal of aid for medical care. Thus, medical staff may be able to prevent dropouts by ensuring that patients record the dates of their medical appointments.展开更多
文摘We present an approach to classify medical text at a sentence level automatically.Given the inherent complexity of medical text classification,we employ adapters based on pre-trained language models to extract information from medical text,facilitating more accurate classification while minimizing the number of trainable parameters.Extensive experiments conducted on various datasets demonstrate the effectiveness of our approach.
文摘Dropout from medical attendance is a well-recognized issue among patients with human immunodeficiency virus (HIV) infection. We interviewed 23 HIV-positive patients and used text mining methods to analyse the risk factors for dropout. Fifteen patients continued medical attendance and eight patients dropped out of medical attendance. Categories were extracted from the interview data of the patients who continued medical attendance (i.e., the continuity group) and the patients who dropped out of medical care (i.e., the discontinuity group). Categories of the continuity group included needing to take a day off for medical attendance, scheduling each appointment, writing down medical appointments, being grateful for the medical care, and 12 additional categories. Categories of discontinuity group included forgetting the dates of medical appointments, not needing to get a day off for medical attendance, allowing aid for medical care to expire, and 10 additional categories. The discontinuity group had poorer schedule management than the continuity group, which caused them to forget their next medical appointments and delay the renewal of aid for medical care. Thus, medical staff may be able to prevent dropouts by ensuring that patients record the dates of their medical appointments.
