Artificial intelligence can help physicians improve the accuracy of breast cancer diagnosis. However, the effectiveness of AI applications is limited by doctors’ adoption of the results recommended by the personalized medical decision support system. Our primary purpose is to study the impact of external case characteristics (ECC) on the effectiveness of the personalized medical decision support system for breast cancer assisted diagnosis (PMDSS-BCAD) in making accurate recommendations. Therefore, we designed a novel comprehensive framework for case-based reasoning (CBR) that takes the impact of external features of cases into account, made use of the naive Bayes and k-nearest neighbor (KNN) algorithms (CBR-ECC), and developed a PMDSS-BCAD system by using the CBR-ECC model and external features as system components. Under the new case-based reasoning framework, the accuracy of the combined model of naive Bayes and KNN with an optimal K value of 2 is 99.40%. Moreover, in a real hospital scenario, users rated the PMDSS-BCAD system, which takes into account the external characteristics of the case, better than the original personalized system. These results suggest that PMDSS-BCD can not only provide doctors with more personalized and accurate results for auxiliary diagnosis, but also improve doctors’ trust in the results, so as to encourage doctors to adopt the results recommended by the personalized system.

Increasingly, machine learning methods have been applied to aid in diagnosis with good results. However, some complex models can confuse physicians because they are difficult to understand, while data differences across diagnostic tasks and institutions can cause model performance fluctuations. To address this challenge, we combined the Deep Ensemble Model (DEM) and tree-structured Parzen Estimator (TPE) and proposed an adaptive deep ensemble learning method (TPE-DEM) for dynamic evolving diagnostic task scenarios. Different from previous research that focuses on achieving better performance with a fixed structure model, our proposed model uses TPE to efficiently aggregate simple models more easily understood by physicians and require less training data. In addition, our proposed model can choose the optimal number of layers for the model and the type and number of basic learners to achieve the best performance in different diagnostic task scenarios based on the data distribution and characteristics of the current diagnostic task. We tested our model on one dataset constructed with a partner hospital and five UCI public datasets with different characteristics and volumes based on various diagnostic tasks. Our performance evaluation results show that our proposed model outperforms other baseline models on different datasets. Our study provides a novel approach for simple and understandable machine learning models in tasks with variable datasets and feature sets, and the findings have important implications for the application of machine learning models in computer-aided diagnosis.

Background: In online mental health communities, the interactions among members can significantly reduce their psychological distress and enhance their mental well-being. The overall quality of support from others varies due to differences in people’s capacities to help others. This results in some support seekers’ needs being met, while others remain unresolved. Objective: This study aimed to examine which characteristics of the comments posted to provide support can make support seekers feel better (ie, result in cognitive change). Methods: We used signaling theory to model the factors affecting cognitive change and used consulting strategies from the offline, face-to-face psychological counseling process to construct 6 characteristics: intimacy, emotional polarity, the use of first-person words, the use of future-tense words, specificity, and language style. Through text mining and natural language processing (NLP) technology, we identified linguistic features in online text and conducted an empirical analysis using 12,868 online mental health support reply data items from Zhihu to verify the effectiveness of those features. Results: The findings showed that support comments are more likely to alter support seekers’ cognitive processes if those comments have lower intimacy (βintimacy=–1.706, P<.001), higher positive emotional polarity (βemotional_polarity=.890, P<.001), lower specificity (βspecificity=–.018, P<.001), more first-person words (βfirst-person=.120, P<.001), more future- and present-tense words (βfuture-words=.301, P<.001), and fewer function words (βlinguistic_style=–.838, P<.001). The result is consistent with psychotherapists’ psychotherapeutic strategy in offline counseling scenarios. Conclusions: Our research contributes to both theory and practice by proposing a model to reveal the factors that make support seekers feel better. The findings have significance for support providers. Additionally, our study offers pointers for managing and designing online communities for mental health.

In order to explore the knowledge base, research hotspot, development status, and future research direction of healthcare research based on information theory and complex science, a total of 3031 literature data samples from the core collection of Web of Science from 2003 to 2019 were selected for bibliometric analysis. HistCite, CiteSpace, Excel, and other analytical tools were used to deeply analyze and visualize the temporal distribution, spatial distribution, knowledge evolution, literature co-citation, and research hotspots of this field. This paper reveals the current development of healthcare research field based on information theory and science of complexity, analyzes and discusses the research hotspots and future development that trends in this field, and provides important knowledge support for researchers in this field for further relevant research.

BACKGROUND In online mental health communities, the interactions among members can significantly reduce their psychological distress and enhance their mental well-being. The overall quality of support from others varies due to differences in people’s capacities to help others. This results in some support seekers’ needs being met, while others remain unresolved. OBJECTIVE This study aimed to examine which characteristics of the comments posted to provide support can make support seekers feel better (ie, result in cognitive change). METHODS We used signaling theory to model the factors affecting cognitive change and used consulting strategies from the offline, face-to-face psychological counseling process to construct 6 characteristics: intimacy, emotional polarity, the use of first-person words, the use of future-tense words, specificity, and language style. Through text mining and natural language processing (NLP) technology, we identified linguistic features in online text and conducted an empirical analysis using 12,868 online mental health support reply data items from Zhihu to verify the effectiveness of those features. RESULTS The findings showed that support comments are more likely to alter support seekers’ cognitive processes if those comments have lower intimacy (βintimacy=–1.706, P<.001), higher positive emotional polarity (βemotional_polarity=.890, P<.001), lower specificity (βspecificity=–.018, P<.001), more first-person words (βfirst-person=.120, P<.001), more future- and present-tense words (βfuture-words=.301, P<.001), and fewer function words (βlinguistic_style=–.838, P<.001). The result is consistent with psychotherapists’ psychotherapeutic strategy in offline counseling scenarios. CONCLUSIONS Our research contributes to both theory and practice by proposing a model to reveal the factors that make support seekers feel better. The findings have significance for support providers. Additionally, our study offers pointers for managing and designing online communities for mental health.