Annotated dataset creation through large language models for non-english medical NLP.

Obtaining text datasets with semantic annotations is an effortful process, yet crucial for supervised training in natural language processing (NLP). In general, developing and applying new NLP pipelines in domain-specific contexts for tasks often requires custom-designed datasets to address NLP tasks in a supervised machine learning fashion. When operating in non-English languages for medical data processing, this exposes several minor and major, interconnected problems such as the lack of task-matching datasets as well as task-specific pre-trained models. In our work, we suggest to leverage pre-trained large language models for training data acquisition in order to retrieve sufficiently large datasets for training smaller and more efficient models for use-case-specific tasks. To demonstrate the effectiveness of your approach, we create a custom dataset that we use to train a medical NER model for German texts, GPTNERMED, yet our method remains language-independent in principle. Our obtained dataset as well as our pre-trained models are publicly available at https://github.com/frankkramer-lab/GPTNERMED.

Retrospective Study on 53 Cases of Anaphylactic Shock Induced by Paclitaxel / 中国药房

OBJECTIVE:To provide reference for safe drug use of paclitaxel in clinic. METHODS:The literatures about anaphylactic shock induced by paclitaxel were retrieved from China Hospital Knowledge Database during 2006-2016. After screening literatures which met inclusion criteria,the literatures were analyzed statistically in respects of the distribution of patient's gender and age,primary disease,distribution of occurrence time of anaphylactic shock,prophylactic drug use,route of administration and dosage,combined with chemotherapy drugs,prodromal clinical manifestations,first-aid measures and prognosis,etc. RESULTS:A total of 53 cases of anaphylactic shock induced by paclitaxel were included,among which there were 16 male and 37 female,aged 17-72 years;female patients over 40 year-old took up the highest proportion(30 cases,56.60%). The major primary diseases were lung cancer(15 cases,28.30%),breast cancer(12 cases,22.64%)and ovarian cancer(11 cases,20.75%). Anaphylactic shock mainly occurred within 5 min after intravenous dripping(34 cases,64.15%). 45 cases (84.90%)received antiallergic prophylactic program before using paclitaxel;53 patients were given intravenous dripping with single dose of 30-300 mg. Among 53 patients,25 patients were given paclitaxel alone,and other patients were given paclitaxel combined with chemotherapy drugs. The prodromal clinical symptoms of anaphylactic shock mainly involved cardiovascular system (123 case time,36.07%),skin and mucous membrane system(73 case time,21.41%)and respiratory system(67 case time, 19.64%). 2 patients(3.77%)died after rescue treatment. CONCLUSIONS:More attention must be paid to the occurrence of anaphylactic shock induced by paclitaxel.