Background: Lung cancer screening and intervention might be important to help detect lung cancer early and reduce the mortality, but little was known about lung cancer intervention strategy associated with intervention effect for preventing lung cancer. We employed Deep Q-Networks (DQN) to respond to this gap. The aim was to quantitatively predict lung cancer optimal intervention strategy and assess intervention effect in aged 65 years and older (the elderly). Methods: We screened lung cancer high risk with web-based survey data and conducted simulative intervention. DQN models were developed to predict optimal intervention strategies to prevent lung cancer in elderly men and elderly women separately. We assessed the intervention effects to evaluate the optimal intervention strategy. Results: Proposed DQN models quantitatively predicted and assessed lung cancer intervention. DQN models performed well in five stratified groups (elderly men, elderly women, men, women and the whole population). Stopping smoking and extending quitting smoking time were optimal intervention strategies in elderly men. Extending quitting time and reducing smoked cigarettes number were optimal intervention strategies in elderly women. In elderly men and women, the maximal reductions of lung cancer incidence were 31.81% and 24.62% separately. Lung cancer incidence trend was deduced from the year of 1984 to 2050, which predicted that the difference of lung cancer incidence between elderly men and women might be significantly decreased after thirty years quitting time. Conclusions: We quantitatively predicted optimal intervention strategy and assessed lung cancer intervention effect in the elderly through DQN models. Those might improve intervention effects and reasonably prevent lung cancer.

Background: Named entity recognition (NER) models are essential for extracting structured information from unstructured medical texts by identifying entities such as diseases, treatments, and conditions, enhancing clinical decision-making and research. Innovations in machine learning, particularly those involving Bidirectional Encoder Representations From Transformers (BERT)–based deep learning and large language models, have significantly advanced NER capabilities. However, their performance varies across medical datasets due to the complexity and diversity of medical terminology. Previous studies have often focused on overall performance, neglecting specific challenges in medical contexts and the impact of macrofactors like lexical composition on prediction accuracy. These gaps hinder the development of optimized NER models for medical applications. Objective: This study aims to meticulously evaluate the performance of various NER models in the context of medical text analysis, focusing on how complex medical terminology affects entity recognition accuracy. Additionally, we explored the influence of macrofactors on model performance, seeking to provide insights for refining NER models and enhancing their reliability for medical applications. Methods: This study comprehensively evaluated 7 NER models—hidden Markov models, conditional random fields, BERT for Biomedical Text Mining, Big Transformer Models for Efficient Long-Sequence Attention, Decoding-enhanced BERT with Disentangled Attention, Robustly Optimized BERT Pretraining Approach, and Gemma—across 3 medical datasets: Revised Joint Workshop on Natural Language Processing in Biomedicine and its Applications (JNLPBA), BioCreative V CDR, and Anatomical Entity Mention (AnatEM). The evaluation focused on prediction accuracy, resource use (eg, central processing unit and graphics processing unit use), and the impact of fine-tuning hyperparameters. The macrofactors affecting model performance were also screened using the multilevel factor elimination algorithm. Results: The fine-tuned BERT for Biomedical Text Mining, with balanced resource use, generally achieved the highest prediction accuracy across the Revised JNLPBA and AnatEM datasets, with microaverage (AVG_MICRO) scores of 0.932 and 0.8494, respectively, highlighting its superior proficiency in identifying medical entities. Gemma, fine-tuned using the low-rank adaptation technique, achieved the highest accuracy on the BioCreative V CDR dataset with an AVG_MICRO score of 0.9962 but exhibited variability across the other datasets (AVG_MICRO scores of 0.9088 on the Revised JNLPBA and 0.8029 on AnatEM), indicating a need for further optimization. In addition, our analysis revealed that 2 macrofactors, entity phrase length and the number of entity words in each entity phrase, significantly influenced model performance. Conclusions: This study highlights the essential role of NER models in medical informatics, emphasizing the imperative for model optimization via precise data targeting and fine-tuning. The insights from this study will notably improve clinical decision-making and facilitate the creation of more sophisticated and effective medical NER models.

Artificial intelligence (AI) has driven innovative transformation in healthcare service patterns, despite a lack of understanding of its performance in clinical practice. We conducted a cross-sectional analysis of AI-related trials in healthcare based on ClinicalTrials.gov, intending to investigate the trial characteristics and AI’s development status. Additionally, the Neo4j graph database and visualization technology were employed to construct an AI technology application graph, achieving a visual representation and analysis of research hotspots in healthcare AI. A total of 1725 eligible trials that were registered in ClinicalTrials.gov up to 31 March 2022 were included in this study. The number of trial registrations has dramatically grown each year since 2016. However, the AI-related trials had some design drawbacks and problems with poor-quality result reporting. The proportion of trials with prospective and randomized designs was insufficient, and most studies did not report results upon completion. Currently, most healthcare AI application studies are based on data-driven learning algorithms, covering various disease areas and healthcare scenarios. As few studies have publicly reported results on ClinicalTrials.gov, there is not enough evidence to support an assessment of AI’s actual performance. The widespread implementation of AI technology in healthcare still faces many challenges and requires more high-quality prospective clinical validation.

Background: With the increasing incidences and mortality of digestive system tumor diseases in China, ways to use clinical experience data in Chinese electronic medical records (CEMRs) to determine potentially effective relationships between diagnosis and treatment have become a priority. As an important part of artificial intelligence, a knowledge graph is a powerful tool for information processing and knowledge organization that provides an ideal means to solve this problem. Objective: This study aimed to construct a semantic-driven digestive system tumor knowledge graph (DSTKG) to represent the knowledge in CEMRs with fine granularity and semantics. Methods: This paper focuses on the knowledge graph schema and semantic relationships that were the main challenges for constructing a Chinese tumor knowledge graph. The DSTKG was developed through a multistep procedure. As an initial step, a complete DSTKG construction framework based on CEMRs was proposed. Then, this research built a knowledge graph schema containing 7 classes and 16 kinds of semantic relationships and accomplished the DSTKG by knowledge extraction, named entity linking, and drawing the knowledge graph. Finally, the quality of the DSTKG was evaluated from 3 aspects: data layer, schema layer, and application layer. Results: Experts agreed that the DSTKG was good overall (mean score 4.20). Especially for the aspects of “rationality of schema structure,” “scalability,” and “readability of results,” the DSTKG performed well, with scores of 4.72, 4.67, and 4.69, respectively, which were much higher than the average. However, the small amount of data in the DSTKG negatively affected its “practicability” score. Compared with other Chinese tumor knowledge graphs, the DSTKG can represent more granular entities, properties, and semantic relationships. In addition, the DSTKG was flexible, allowing personalized customization to meet the designer's focus on specific interests in the digestive system tumor. Conclusions: We constructed a granular semantic DSTKG. It could provide guidance for the construction of a tumor knowledge graph and provide a preliminary step for the intelligent application of knowledge graphs based on CEMRs. Additional data sources and stronger research on assertion classification are needed to gain insight into the DSTKG’s potential.

Background: Although many studies have analyzed the mental health problems (MHP) of Chinese adolescents, the associations of Chinese high school students’ MHP with personal and family circumstances, parents’ educational level, physical activity, and school adaptation are rarely discussed. Methods: The participants were 9398 students who were randomly recruited from 30 high schools in Shandong, China. Self-reported questionnaires were used to collect data. Multivariate logistic regression models were used to investigate associations between MHP and related factors. Results: The positive rate of MHP among high school students was 27.0%. Female, intimate friends of the opposite sex, poor family economic status, father’s educational level of primary school or below, low social competence, and high antisocial behavior were significantly associated with higher odds of having MHP (p < 0.05). Students’ self-reported odds of having obsessive–compulsive disorder, interpersonal sensitivity, and depression were inversely related to their mother’s educational level. Compared with students who did not exercise, students who engaged in more than 30 min of physical activity 5–6 times per week had 60% lower self-reported odds of depression. Conclusions: We recommend strengthening the prevention, early detection, and treatment of MHP in high school students, especially those whose parents have low educational attainment, inactivity, and high disruptive behaviors.

Identifying high risk factors and predicting lung cancer incidence risk are essential to prevention and intervention of lung cancer for the elderly. We aim to develop lung cancer incidence risk prediction model in the elderly to facilitate early intervention and prevention of lung cancer. We stratified the population into six subgroups according to age and gender. For each subgroup, random forest, extreme gradient boosting, deep neural networks, support vector machine, multiple logistic regression and deep Q network (DQN) models were developed and validated. Models were trained and tested using samples from 2000 to 2015 and independent external validated through those from 2016 to 2019. The suitable model for lung cancer risk prediction and high risk factors identification was chosen based on internal validation and independent external validation. The DQN model achieved the optimal prediction performance in stratified subgroups, with AUROC ranging from 0.937 to 0.953, recall ranging from 0.932 to 0.943, F2-score ranging from 0.929 to 0.946, precision ranging from 0.926 to 0.952, F1-score ranging from 0.933 to 0.963 and RMSE ranging from 0.21 to 0.27. SHAP values were supplied for model interpretability. High risk factors of lung cancer incidence were identified in the elderly. Men ≥ 65 carrying C > A/G > T mutation had the highest lung cancer incidence decrease of 39.5% after five years quitting in stratified elderly groups, which were 1.83 times more than women ≥ 65 not carrying C > A/G > T mutation. The DQN model may be suitable for identifying high risk factors and predicting lung cancer risk with high performance. The proposed intervention and diagnosis pathways could be used for early screening and intervention before the occurrence of lung cancer, which could help oncologists develop targeted intervention strategies for the stratified elderly to reduce lung cancer incidence and improve therapeutic effect. Proposed method could also be used in predicting the risk of other chronic diseases to help conduct intervention and reduce incidence.