Semantic categorization of Chinese eligibility criteria in clinical trials using machine learning methods

Zong, Hui; Yang, Jiancheng; Zhang, Zeyu; Li, Zuofeng; Zhang, Xiaoyan

doi:10.1186/s12911-021-01487-w

Cited by 18 publications

(7 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…ERNIE with the splitting ratio of 8: Transformer is built entirely on a self-attentive mechanism, which not only allows parallel operations but also captures long-range feature dependencies [20]. In the classi cation task of Chinese eligibility criteria sentences, ERNIE narrowly beat BERT's results in both micro and macro F 1 score [21], and it exhibited higher accuracy under the same conditions which was consistent with the results of this study. The results of the nal hidden layer computation we can perform downstream tasks by changing the pretrained model parameters which is also called ne-tuning.…”

Section: Discussionsupporting

confidence: 83%

A Comparative Study of Natural Language Processing Algorithms Based on Cities Changing Diabetes’ Vulnerability Data

Wang

Song

Qiao

et al. 2021

Preprint

View full text Add to dashboard Cite

Background: Diabetes has become a global public health priority resulting in significant workforce losses and health care expenditures. Therefore, research on diabetes vulnerability has become imperative. Current methods for studying disease vulnerability mainly use qualitative research methods represented by Thematic Analysis (TCA), which has the disadvantage of being staff-intensive for long periods of time. Natural Language Processing (NLP) could achieve efficient results in information mining tasks, but we didn't find many studies talking about NLP in non-infectious chronic diseases.Methods: In this study, hyperparameters were adjusted to obtain more cost-effective model applicable to The Cities Changing Diabetes’ vulnerability data by comparing Bidirectional Encoder Representation from Transformers (BERT) and Enhanced Language Representation with Informative Entities (ERNIE) in terms of test accuracy, completion time and evaluation metrics on classification.Results: The results showed that BERT took less time for the same hyperparameter cases, and the test accuracy of ERNIE was slightly better than that of BERT. We further adjusted the Batch size of ERNIE as we found that ERNIE with the splitting ratio of 8:1:1 and Batch size of 64 had the better efficiency with the test accuracy was 97.67%, the completion time was 12min36s and Macro-F1 score was 0.9734.Conclusions: In this study, BERT overwhelmed ERNIE in terms of completion speed with the same hyperparameters. ERNIE showed higher accuracy, especially the ideal performance at the split ratio of 8:1:1 after enhancing the Batch size. From the point of view, we pursue a model with high accuracy and fast processing speed, which means that we can obtain the highest accuracy in the shortest time. It could be selected according to the actual situation in the application process.

show abstract

Section: Discussionsupporting

confidence: 83%

A Comparative Study of Natural Language Processing Algorithms Based on Cities Changing Diabetes’ Vulnerability Data

Wang

Song

Qiao

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…The ERNIE model is more capable of capturing and grasping semantic information. It had shown superior performance over BERT in previous Chinese corpus learning studies [ 25 , 29 ].…”

Section: Methodsmentioning

confidence: 99%

“…These ERNIEs have few differences and they all perform well in the tasks with specific Chinese-language medical environments. In the classification task of Chinese eligibility criteria sentences, ERNIE outperformed baseline machine learning algorithms and deep learning algorithms [ 25 ].…”

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

A Comparative Study of Natural Language Processing Algorithms Based on Cities Changing Diabetes Vulnerability Data

et al. 2022

View full text Add to dashboard Cite

(1) Background: Poor adherence to management behaviors in Chinese Type 2 diabetes mellitus (T2DM) patients leads to an uncontrolled prognosis of diabetes, which results in significant economic costs for China. It is imperative to quickly locate vulnerability factors in the management behavior of patients with T2DM. (2) Methods: In this study, a thematic analysis of the collected interview materials was conducted to construct the themes of T2DM management vulnerability. We explored the applicability of the pre-trained models based on the evaluation metrics in text classification. (3) Results: We constructed 12 themes of vulnerability related to the health and well-being of people with T2DM in Tianjin. We considered that Bidirectional Encoder Representation from Transformers (BERT) performed better in this Natural Language Processing (NLP) task with a shorter completion time. With the splitting ratio of 6:3:1 and batch size of 64 for BERT, the test accuracy was 97.71%, the completion time was 10 min 24 s, and the macro-F1 score was 0.9752. (4) Conclusions: Our results proved the applicability of NLP techniques in this specific Chinese-language medical environment. We filled the knowledge gap in the application of NLP technologies in diabetes management. Our study provided strong support for using NLP techniques to rapidly locate vulnerability factors in T2DM management.

show abstract

“…The second one is an application category classification dataset (IFLYTEK) maintained by CLUE . The third one is a clinical trial criterion categorization dataset (CTC) (Zong et al, 2021). The fourth one is an entity typing dataset (MSRA) originally released as a named entity recognition dataset (Levow, 2006).…”

Section: Setupmentioning

confidence: 99%

Making Pre-trained Language Models Good Long-tailed Learners

Zhang¹,

Liu²,

Wang³

et al. 2022

Preprint

View full text Add to dashboard Cite

Prompt-tuning has shown appealing performance in few-shot classification by virtue of its capability in effectively exploiting pretrained knowledge. This motivates us to check the hypothesis that prompt-tuning is also a promising choice for long-tailed classification, since the tail classes are intuitively fewshot ones. To achieve this aim, we conduct empirical studies to examine the hypothesis. The results demonstrate that prompt-tuning exactly makes pre-trained language models at least good long-tailed learners. For intuitions on why prompt-tuning can achieve good performance in long-tailed classification, we carry out an in-depth analysis by progressively bridging the gap between prompt-tuning and commonly used fine-tuning. The summary is that the classifier structure and parameterization form the key to making good long-tailed learners, in comparison with the less important input structure. Finally, we verify the applicability of our finding to few-shot classification.parameter-efficient prompt tuning (Lester et al., 2021). However, we insist on the use of it to accord with CLS-tuning.

show abstract

Semantic categorization of Chinese eligibility criteria in clinical trials using machine learning methods

Cited by 18 publications

References 31 publications

A Comparative Study of Natural Language Processing Algorithms Based on Cities Changing Diabetes’ Vulnerability Data

A Comparative Study of Natural Language Processing Algorithms Based on Cities Changing Diabetes’ Vulnerability Data

A Comparative Study of Natural Language Processing Algorithms Based on Cities Changing Diabetes Vulnerability Data

Making Pre-trained Language Models Good Long-tailed Learners

Contact Info

Product

Resources

About