Background: A scientific, personalized, and quantitative exercise prescription that has the potential to be an important therapeutic agent for all ages in the prevention of chronic disease is highly recommended. However, it is often poorly implemented, as clinicians lack the necessary knowledge and skills while participants have low adherence due to design defects (eg, prescriptions fail to take individual willingness, the appeal of exercise, and complex physical conditions into account). Intelligent personalized prescription is thus worth exploring. Objective: The aim of this study was to investigate whether a year-long cloud platform–based and intelligent personalized exercise prescription intervention could improve Chinese middle-aged and older adult community dwellers’ health outcomes. Methods: A total of 177 participants (aged 52-85 years; mean 67.93, SD 7.05) were recruited from 2 Chinese community health service centers in Anhui Province, China. The exercise intervention was delivered over 12 months with a single-group pretest–posttest design. After being assessed in terms of physical activity, health-related lifestyle, history of chronic diseases and drug use, family history of disease and cardiovascular function, body composition, bone mineral density, and physical fitness through an eHealth promotion system, participants with relative contraindications for exercise were personally prescribed the health care exercise mode by an intelligent system, while those without relative contraindication and who had a regular exercise habit were prescribed the scientific fitness mode. Paired t tests were used for the analysis. Results: A total of 97 participants were classified into the health care mode, and the remaining 80 participants were assigned to the scientific fitness mode. Significant changes in heart rate (mean difference [MD] 2.97; 95% CI 1.1-4.84; P=.002), subendocardial viability ratio (MD –0.13; CI: –1.19 to –0.63; P<.001), weight (MD 0.99; CI 0.29-1.69; P=.006), BMI (MD 0.38; CI 0.11-0.64; P=.006), body fat rate (MD 0.88; CI 0.24-1.51; P=.007), fat mass (MD 0.92; CI 0.33-1.53; P=.003), and brachial-ankle pulse wave velocity (MD: –0.72; CI –1.17 to –0.27; P=.002) were observed among participants with the health care mode exercise prescriptions at the 12-month postintervention versus the baseline assessment, while no changes in systolic blood pressure, diastolic blood pressure, muscle mass, bone mineral density, t value, z value, balance, or ability were discerned. The results showed a functional decline in the physical fitness of both groups, including in handgrip strength (healthcare mode: MD 4.41; scientific fitness mode: MD 3.11), vital capacity (healthcare mode: MD 261.99; scientific fitness mode: MD 250.78), and agility (healthcare mode MD=–0.35; scientific fitness mode: MD=–0.39) with all P values <.001, except handgrip strength in the scientific fitness mode (P=.002). There were no significant differences in other parameters among participants with scientific fitness mode exercise prescriptions. Conclusions: The observations suggest that our exercise prescription intervention program might promote certain health outcomes in Chinese middle-aged and older adult community dwellers, yet we are unable to recommend such a program given the existing limitations. Future randomized controlled trials with diverse samples are warranted to confirm our findings.

Named Entity Recognition (NER) is the fundamental task for Natural Language Processing (NLP) and the initial step in building a Knowledge Graph (KG). Recently, BERT (Bidirectional Encoder Representations from Transformers), which is a pre-training model, has achieved state-of-the-art (SOTA) results in various NLP tasks, including the NER. However, Chinese NER is still a more challenging task for BERT because there are no physical separations between Chinese words, and BERT can only obtain the representations of Chinese characters. Nevertheless, the Chinese NER cannot be well handled with character-level representations, because the meaning of a Chinese word is quite different from that of the characters, which make up the word. ERNIE (Enhanced Representation through kNowledge IntEgration), which is an improved pre-training model of BERT, is more suitable for Chinese NER because it is designed to learn language representations enhanced by the knowledge masking strategy. However, the potential of ERNIE has not been fully explored. ERNIE only utilizes the token-level features and ignores the sentence-level feature when performing the NER task. In this paper, we propose the ERNIE-Joint, which is a joint model based on ERNIE. The ERNIE-Joint can utilize both the sentence-level and token-level features by joint training the NER and text classification tasks. In order to use the raw NER datasets for joint training and avoid additional annotations, we perform the text classification task according to the number of entities in the sentences. The experiments are conducted on two datasets: MSRA-NER and Weibo. These datasets contain Chinese news data and Chinese social media data, respectively. The results demonstrate that the ERNIE-Joint not only outperforms BERT and ERNIE but also achieves the SOTA results on both datasets.

Medical text classification, as a fundamental medical natural language processing task, aims to identify the categories to which a short medical text belongs. Current research has focused on performing the medical text classification task using a pre-training language model through fine-tuning. However, this paradigm introduces additional parameters when training extra classifiers. Recent studies have shown that the “prompt-tuning” paradigm induces better performance in many natural language processing tasks because it bridges the gap between pre-training goals and downstream tasks. The main idea of prompt-tuning is to transform binary or multi-classification tasks into mask prediction tasks by fully exploiting the features learned by pre-training language models. This study explores, for the first time, how to classify medical texts using a discriminative pre-training language model called ERNIE-Health through prompt-tuning. Specifically, we attempt to perform prompt-tuning based on the multi-token selection task, which is a pre-training task of ERNIE-Health. The raw text is wrapped into a new sequence with a template in which the category label is replaced by a [UNK] token. The model is then trained to calculate the probability distribution of the candidate categories. Our method is tested on the KUAKE-Question Intention Classification and CHiP-Clinical Trial Criterion datasets and obtains the accuracy values of 0.866 and 0.861. In addition, the loss values of our model decrease faster throughout the training period compared to the fine-tuning. The experimental results provide valuable insights to the community and suggest that prompt-tuning can be a promising approach to improve the performance of pre-training models in domain-specific tasks.

Early and accurate diagnoses of sepsis patients are essential to reduce the mortality. However, the sepsis is still diagnosed in a traditional way in China despite the increasing number of related studies, which may to some extent lead to delays in the treatment. The study included 2,385 patients, including 364 with sepsis, collected from the First Affiliated Hospital of Anhui Medical University and partner hospitals from April to July 2022. External validation was conducted using the MIMIC-III database (over 60,000 patients from 2001 to 2012) and the eICU Collaborative Research Database (139,000 patients from 2014 to 2015). Multiple algorithm models, along with the SHapley Additive exPlanations (SHAP) analysis, are applied to explore the main risk factors for the accurate prediction of the sepsis. Multiple Imputations for filling missing data and the Synthetic Minority Oversampling (SMOTE) balancing method for balancing data are used for the data processing. Eighteen diagnostic features are used in the predictive model for early sepsis. The Random Forest model has the best performance among all the models, with an Area Under the Curve (AUC) of 87% and an F1-score (F1) of 77%. Moreover, the interpretation from the SHAP analysis is generally consistent with the current clinical situation. The study revealed the relationship between these 18 clinical features and diagnostic outcomes. The results indicate that patients with laboratory values of Systolic Blood Pressure, Albumin, and Heart Rate exceeding certain thresholds are at a high likelihood of developing sepsis.

The medical literature contains valuable knowledge, such as the clinical symptoms, diagnosis, and treatments of a particular disease. Named Entity Recognition (NER) is the initial step in extracting this knowledge from unstructured text and presenting it as a Knowledge Graph (KG). However, the previous approaches of NER have often suffered from small-scale human-labelled training data. Furthermore, extracting knowledge from Chinese medical literature is a more complex task because there is no segmentation between Chinese characters. Recently, the pretraining models, which obtain representations with the prior semantic knowledge on large-scale unlabelled corpora, have achieved state-of-the-art results for a wide variety of Natural Language Processing (NLP) tasks. However, the capabilities of pretraining models have not been fully exploited, and applications of other pretraining models except BERT in specific domains, such as NER in Chinese medical literature, are also of interest. In this paper, we enhance the performance of NER in Chinese medical literature using pretraining models. First, we propose a method of data augmentation by replacing the words in the training set with synonyms through the Mask Language Model (MLM), which is a pretraining task. Then, we consider NER as the downstream task of the pretraining model and transfer the prior semantic knowledge obtained during pretraining to it. Finally, we conduct experiments to compare the performances of six pretraining models (BERT, BERT-WWM, BERT-WWM-EXT, ERNIE, ERNIE-tiny, and RoBERTa) in recognizing named entities from Chinese medical literature. The effects of feature extraction and fine-tuning, as well as different downstream model structures, are also explored. Experimental results demonstrate that the method of data augmentation we proposed can obtain meaningful improvements in the performance of recognition. Besides, RoBERTa-CRF achieves the highest F1-score compared with the previous methods and other pretraining models.

Medical text classification aims to identify the category to which a short medical text belongs. Recent research indicates that the “prompt-based learning” paradigm, especially the soft prompt, can improve the performance in text classification tasks by bridging the gap between pre-training objectives and downstream tasks. However, current research on soft prompt learning neglects the relation between the pseudo tokens and raw sentences when generating embeddings for the template. This study investigates, for the first time, how to simulate human cognitive processes in medical text classification tasks using soft prompt learning based on attention mechanisms. The proposed approach pays more attention to the parts of the raw sentence that are more relevant to the category label when generating embeddings for the pseudo tokens, resembling the reasoning process humans go through during text classification. Experiments conducted on two datasets, KUAKE-QIC and CHIP-CTC, indicate that the F1-macro scores of the proposed approach are 0.8064 and 0.8434, which outperform the benchmark and previous prompt learning approaches. In addition, the corresponding experiments also demonstrate the generalization ability and few-shot learning capability of the proposed method.