Using Natural Language Processing Techniques to Provide Personalized Educational Materials for Chronic Disease Patients in China: Development and Assessment of a Knowledge-Based Health Recommender System

Artificial intelligence technology in ophthalmology public health: current applications and future directions

Global eye health has become a critical public health challenge, with the prevalence of blindness and visual impairment expected to rise significantly in the coming decades. Traditional ophthalmic public health systems face numerous obstacles, including the uneven distribution of medical resources, insufficient training for primary healthcare workers, and limited public awareness of eye health. Addressing these challenges requires urgent, innovative solutions. Artificial intelligence (AI) has demonstrated substantial potential in enhancing ophthalmic public health across various domains. AI offers significant improvements in ophthalmic data management, disease screening and monitoring, risk prediction and early warning systems, medical resource allocation, and health education and patient management. These advancements substantially improve the quality and efficiency of healthcare, particularly in preventing and treating prevalent eye conditions such as cataracts, diabetic retinopathy, glaucoma, and myopia. Additionally, telemedicine and mobile applications have expanded access to healthcare services and enhanced the capabilities of primary healthcare providers. However, there are challenges in integrating AI into ophthalmic public health. Key issues include interoperability with electronic health records (EHR), data security and privacy, data quality and bias, algorithm transparency, and ethical and regulatory frameworks. Heterogeneous data formats and the lack of standardized metadata hinder seamless integration, while privacy risks necessitate advanced techniques such as anonymization. Data biases, stemming from racial or geographic disparities, and the "black box" nature of AI models, limit reliability and clinical trust. Ethical issues, such as ensuring accountability for AI-driven decisions and balancing innovation with patient safety, further complicate implementation. The future of ophthalmic public health lies in overcoming these barriers to fully harness the potential of AI, ensuring that advancements in technology translate into tangible benefits for patients worldwide.

AI Applications for Chronic Condition Self-Management: Scoping Review

BACKGROUND

Artificial intelligence (AI) has potential in promoting and supporting self-management in patients with chronic conditions. However, the development and application of current AI technologies to meet patients' needs and improve their performance in chronic condition self-management tasks remain poorly understood. It is crucial to gather comprehensive information to guide the development and selection of effective AI solutions tailored for self-management in patients with chronic conditions.

OBJECTIVE

This scoping review aimed to provide a comprehensive overview of AI applications for chronic condition self-management based on 3 essential self-management tasks, medical, behavioral, and emotional self-management, and to identify the current developmental stages and knowledge gaps of AI applications for chronic condition self-management.

METHODS

A literature review was conducted for studies published in English between January 2011 and October 2024. In total, 4 databases, including PubMed, Web of Science, CINAHL, and PsycINFO, were searched using combined terms related to self-management and AI. The inclusion criteria included studies focused on the adult population with any type of chronic condition and AI technologies supporting self-management. This review was conducted following the PRISMA-ScR (Preferred Reporting Items for Systematic Reviews and Meta-Analyses Extension for Scoping Reviews) guidelines.

RESULTS

Of the 1873 articles retrieved from the search, 66 (3.5%) were eligible and included in this review. The most studied chronic condition was diabetes (20/66, 30%). Regarding self-management tasks, most studies aimed to support medical (45/66, 68%) or behavioral self-management (27/66, 41%), and fewer studies focused on emotional self-management (14/66, 21%). Conversational AI (21/66, 32%) and multiple machine learning algorithms (16/66, 24%) were the most used AI technologies. However, most AI technologies remained in the algorithm development (25/66, 38%) or early feasibility testing stages (25/66, 38%).

CONCLUSIONS

A variety of AI technologies have been developed and applied in chronic condition self-management, primarily for medication, symptoms, and lifestyle self-management. Fewer AI technologies were developed for emotional self-management tasks, and most AIs remained in the early developmental stages. More research is needed to generate evidence for integrating AI into chronic condition self-management to obtain optimal health outcomes.

Implementation of a coach-supported mHealth intervention for dementia prevention in China: a qualitative study among Chinese participants and coaches in the PRODEMOS trial

Background

Modifiable risk factors have been linked to 45% of dementia cases. Mobile health (mHealth) interventions targeting lifestyle-related risk factors with remote coaching have the potential to reach underserved high-risk populations globally. To date, little is known about the implementation of such interventions in China.

Methods

Fifty semi-structured interviews were conducted with 14 participants and 11 health coaches involved in the PRODEMOS trial. This trial investigated whether a coach-supported mHealth application intervention can reduce dementia risk in people aged 55-75 years with multiple risk factors. Interviews were conducted three months and 12-18 months into the intervention, focusing on implementation outcomes among Chinese participants using thematic analysis.

Results

Participants found the PRODEMOS app easy to use and remote coaching convenient, although coach responses were sometimes perceived as slow due to not logging into the mHealth platform simultaneously, thus delaying text chat communication. The intervention's appropriateness was shaped by its effectiveness in enhancing health awareness and meeting participants' needs. Feasibility depended on integration into daily routines, participant progress, partner support, coach attention, smartphone literacy, and time availability. Challenges for the coaches included remote motivational interviewing and sustained participant-coach engagement, influenced by participant-coach relationships, social environment, and the COVID-19 pandemic. Participants generally adhered to goals, but fidelity varied. Integration into primary care was endorsed.

Conclusions

This first qualitative study of the Chinese arm of the PRODEMOS intervention demonstrates that it is an acceptable and implementable approach for promoting lifestyle changes in individuals at increased risk of dementia. While coaching is crucial for sustained engagement, it presents challenges when delivered remotely. Despite significant variability in participants' adherence, positive feedback underscores its potential for integration into primary care and large-scale implementation, provided issues with coaching and engagement are addressed. These findings offer valuable insights for practitioners and policymakers seeking to incorporate mHealth solutions into public health strategies for dementia prevention.

Registration

PRODEMOS: ISRCTN15986016.

The application of artificial intelligence in health communication development: A scoping review

This scoping review explores the integration of Artificial Intelligence (AI) with communication, behavioral, and social theories to enhance health behavior interventions. A systematic search of articles published through February 2024, following PRISMA guidelines, identified 28 relevant studies from 13,723 screened. These studies, conducted across various countries, addressed health issues such as smoking cessation, musculoskeletal injuries, diabetes, chronic diseases and mental health using AI-driven tools like chatbots and apps. Despite AI's potential, a gap exists in aligning technical advancements with theoretical frameworks. The proposed AI Impact Communications Model (AI-ICM) aims to bridge this gap, offering a road map for future research and practice.

Natural Language Processing for Radiation Oncology: Personalizing Treatment Pathways

Natural language processing (NLP), a technology that translates human language into machine-readable data, is revolutionizing numerous sectors, including cancer care. This review outlines the evolution of NLP and its potential for crafting personalized treatment pathways for cancer patients. Leveraging NLP's ability to transform unstructured medical data into structured learnable formats, researchers can tap into the potential of big data for clinical and research applications. Significant advancements in NLP have spurred interest in developing tools that automate information extraction from clinical text, potentially transforming medical research and clinical practices in radiation oncology. Applications discussed include symptom and toxicity monitoring, identification of social determinants of health, improving patient-physician communication, patient education, and predictive modeling. However, several challenges impede the full realization of NLP's benefits, such as privacy and security concerns, biases in NLP models, and the interpretability and generalizability of these models. Overcoming these challenges necessitates a collaborative effort between computer scientists and the radiation oncology community. This paper serves as a comprehensive guide to understanding the intricacies of NLP algorithms, their performance assessment, past research contributions, and the future of NLP in radiation oncology research and clinics.

Digital Personal Health Coaching Platform for Promoting Human Papillomavirus Infection Vaccinations and Cancer Prevention: Knowledge Graph-Based Recommendation System

BACKGROUND

Health promotion can empower populations to gain more control over their well-being by using digital interventions that focus on preventing the root causes of diseases. Digital platforms for personalized health coaching can improve health literacy and information-seeking behavior, leading to better health outcomes. Personal health records have been designed to enhance patients' self-management of a disease or condition. Existing personal health records have been mostly designed and deployed as a supplementary service that acts as views into electronic health records.

OBJECTIVE

We aim to overcome some of the limitations of electronic health records. This study aims to design and develop a personal health library (PHL) that generates personalized recommendations for human papillomavirus (HPV) vaccine promotion and cancer prevention.

METHODS

We have designed a proof-of-concept prototype of the Digital Personal Health Librarian, which leverages machine learning; natural language processing; and several innovative technological infrastructures, including the Semantic Web, social linked data, web application programming interfaces, and hypermedia-based discovery, to generate a personal health knowledge graph.

RESULTS

We have designed and implemented a proof-of-the-concept prototype to showcase and demonstrate how the PHL can be used to store an individual's health data, for example, a personal health knowledge graph. This is integrated with web-scale knowledge to support HPV vaccine promotion and prevent HPV-associated cancers among adolescents and their caregivers. We also demonstrated how the Digital Personal Health Librarian uses the PHL to provide evidence-based insights and knowledge-driven explanations that are personalized and inform health decision-making.

CONCLUSIONS

Digital platforms such as the PHL can be instrumental in improving precision health promotion and education strategies that address population-specific needs (ie, health literacy, digital competency, and language barriers) and empower individuals by facilitating knowledge acquisition to make healthy choices.

Telehealth System Based on the Ontology Design of a Diabetes Management Pathway Model in China: Development and Usability Study

BACKGROUND

Diabetes needs to be under control through management and intervention. Management of diabetes through mobile health is a practical approach; however, most diabetes mobile health management systems do not meet expectations, which may be because of the lack of standardized management processes in the systems and the lack of intervention implementation recommendations in the management knowledge base.

OBJECTIVE

In this study, we aimed to construct a diabetes management care pathway suitable for the actual situation in China to express the diabetes management care pathway using ontology and develop a diabetes closed-loop system based on the construction results of the diabetes management pathway and apply it practically.

METHODS

This study proposes a diabetes management care pathway model in which the management process of diabetes is divided into 9 management tasks, and the Diabetes Care Pathway Ontology (DCPO) is constructed to represent the knowledge contained in this pathway model. A telehealth system, which can support the comprehensive management of patients with diabetes while providing active intervention by physicians, was designed and developed based on the DCPO. A retrospective study was performed based on the data records extracted from the system to analyze the usability and treatment effects of the DCPO.

RESULTS

The diabetes management pathway ontology constructed in this study contains 119 newly added classes, 28 object properties, 58 data properties, 81 individuals, 426 axioms, and 192 Semantic Web Rule Language rules. The developed mobile medical system was applied to 272 patients with diabetes. Within 3 months, the average fasting blood glucose of the patients decreased by 1.34 mmol/L (P=.003), and the average 2-hour postprandial blood glucose decreased by 2.63 mmol/L (P=.003); the average systolic and diastolic blood pressures decreased by 11.84 mmHg (P=.02) and 8.8 mmHg (P=.02), respectively. In patients who received physician interventions owing to abnormal attention or low-compliance warnings, the average fasting blood glucose decreased by 2.45 mmol/L (P=.003), and the average 2-hour postprandial blood glucose decreased by 2.89 mmol/L (P=.003) in all patients with diabetes; the average systolic and diastolic blood pressure decreased by 20.06 mmHg (P=.02) and 17.37 mmHg (P=.02), respectively, in patients with both hypertension and diabetes during the 3-month management period.

CONCLUSIONS

This study helps guide the timing and content of interactive interventions between physicians and patients and regulates physicians' medical service behavior. Different management plans are formulated for physicians and patients according to different characteristics to comprehensively manage various cardiovascular risk factors. The application of the DCPO in the diabetes management system can provide effective and adequate management support for patients with diabetes and those with both diabetes and hypertension.

Health Recommender Systems Development, Usage, and Evaluation from 2010 to 2022: A Scoping Review

A health recommender system (HRS) provides a user with personalized medical information based on the user's health profile. This scoping review aims to identify and summarize the HRS development in the most recent decade by focusing on five key aspects: health domain, user, recommended item, recommendation technology, and system evaluation. We searched PubMed, ACM Digital Library, IEEE Xplore, Web of Science, and Scopus databases for English literature published between 2010 and 2022. Our study selection and data extraction followed the Preferred Reporting Items for Systematic Reviews and Meta-Analyses extension for Scoping Reviews. The following are the primary results: sixty-three studies met the eligibility criteria and were included in the data analysis. These studies involved twenty-four health domains, with both patients and the general public as target users and ten major recommended items. The most adopted algorithm of recommendation technologies was the knowledge-based approach. In addition, fifty-nine studies reported system evaluations, in which two types of evaluation methods and three categories of metrics were applied. However, despite existing research progress on HRSs, the health domains, recommended items, and sample size of system evaluation have been limited. In the future, HRS research shall focus on dynamic user modelling, utilizing open-source knowledge bases, and evaluating the efficacy of HRSs using a large sample size. In conclusion, this study summarized the research activities and evidence pertinent to HRSs in the most recent ten years and identified gaps in the existing research landscape. Further work shall address the gaps and continue improving the performance of HRSs to empower users in terms of healthcare decision making and self-management.

Exploring and Characterizing Patient Multibehavior Engagement Trails and Patient Behavior Preference Patterns in Pathway-Based mHealth Hypertension Self-Management: Analysis of Use Data

Background

Hypertension is a long-term medical condition. Mobile health (mHealth) services can help out-of-hospital patients to self-manage. However, not all management is effective, possibly because the behavior mechanism and behavior preferences of patients with various characteristics in hypertension management were unclear.

Objective

The purpose of this study was to (1) explore patient multibehavior engagement trails in the pathway-based hypertension self-management, (2) discover patient behavior preference patterns, and (3) identify the characteristics of patients with different behavior preferences.

Methods

This study included 863 hypertensive patients who generated 295,855 use records in the mHealth app from December 28, 2016, to July 2, 2020. Markov chain was used to infer the patient multibehavior engagement trails, which contained the type, quantity, time spent, sequence, and transition probability value (TP value) of patient behavior. K-means algorithm was used to group patients by the normalized behavior preference features: the number of behavioral states that a patient performed in each trail. The pages in the app represented the behavior states. Chi-square tests, Z-test, analyses of variance, and Bonferroni multiple comparisons were conducted to characterize the patient behavior preference patterns.

Results

Markov chain analysis revealed 3 types of behavior transition (1-way transition, cycle transition, and self-transition) and 4 trails of patient multibehavior engagement. In perform task trail (PT-T), patients preferred to start self-management from the states of task blood pressure (BP), task drug, and task weight (TP value 0.29, 0.18, and 0.20, respectively), and spent more time on the task food state (35.87 s). Some patients entered the states of task BP and task drug (TP value 0.20, 0.25) from the reminder item state. In the result-oriented trail (RO-T), patients spent more energy on the ranking state (19.66 s) compared to the health report state (13.25 s). In the knowledge learning trail (KL-T), there was a high probability of cycle transition (TP value 0.47, 0.31) between the states of knowledge list and knowledge content. In the support acquisition trail (SA-T), there was a high probability of self-transition in the questionnaire (TP value 0.29) state. Cluster analysis discovered 3 patient behavior preference patterns: PT-T cluster, PT-T and KL-T cluster, and PT-T and SA-T cluster. There were statistically significant associations between the behavior preference pattern and gender, education level, and BP.

Conclusions

This study identified the dynamic, longitudinal, and multidimensional characteristics of patient behavior. Patients preferred to focus on BP, medications, and weight conditions and paid attention to BP and medications using reminders. The diet management and questionnaires were complicated and difficult to implement and record. Competitive methods such as ranking were more likely to attract patients to pay attention to their own self-management states. Female patients with lower education level and poorly controlled BP were more likely to be highly involved in hypertension health education.

Play the Pain: A Digital Strategy for Play-Oriented Research and Action

The value of understanding patients' illness experience and social contexts for advancing medicine and clinical care is widely acknowledged. However, methodologies for rigorous and inclusive data gathering and integrative analysis of biomedical, cultural, and social factors are limited. In this paper, we propose a digital strategy for large-scale qualitative health research, using play (as a state of being, a communication mode or context, and a set of imaginative, expressive, and game-like activities) as a research method for recursive learning and action planning. Our proposal builds on Gregory Bateson's cybernetic approach to knowledge production. Using chronic pain as an example, we show how pragmatic, structural and cultural constraints that define the relationship of patients to the healthcare system can give rise to conflicted messaging that impedes inclusive health research. We then review existing literature to illustrate how different types of play including games, chatbots, virtual worlds, and creative art making can contribute to research in chronic pain. Inspired by Frederick Steier's application of Bateson's theory to designing a science museum, we propose DiSPORA (Digital Strategy for Play-Oriented Research and Action), a virtual citizen science laboratory which provides a framework for delivering health information, tools for play-based experimentation, and data collection capacity, but is flexible in allowing participants to choose the mode and the extent of their interaction. Combined with other data management platforms used in epidemiological studies of neuropsychiatric illness, DiSPORA offers a tool for large-scale qualitative research, digital phenotyping, and advancing personalized medicine.

Year 2020 (with COVID): Observation of Scientific Literature on Clinical Natural Language Processing

Objectives: To analyze the content of publications within the medical NLP domain in 2020.

Methods: Automatic and manual preselection of publications to be reviewed, and selection of the best NLP papers of the year. Analysis of the important issues.

Results: Three best papers have been selected in 2020. We also propose an analysis of the content of the NLP publications in 2020, all topics included.

Conclusion: The two main issues addressed in 2020 are related to the investigation of COVID-related questions and to the further adaptation and use of transformer models. Besides, the trends from the past years continue, such as diversification of languages processed and use of information from social networks

Improving information retrieval from electronic health records using dynamic and multi-collaborative filtering

Due to the rapid growth of information available about individual patients, most physicians suffer from information overload and inefficiencies when they review patient information in health information technology systems. In this paper, we present a novel hybrid dynamic and multi-collaborative filtering method to improve information retrieval from electronic health records. This method recommends relevant information from electronic health records to physicians during patient visits. It models information search dynamics using a Markov model. It also leverages the key idea of collaborative filtering, originating from Recommender Systems, for prioritizing information based on various similarities among physicians, patients and information items. We tested this new method using electronic health record data from the Indiana Network for Patient Care, a large, inter-organizational clinical data repository maintained by the Indiana Health Information Exchange. Our experimental results demonstrated that, for top-5 recommendations, our method was able to correctly predict the information in which physicians were interested in 46.7% of all test cases. For top-1 recommendations, the corresponding figure was 24.7%. In addition, the new method was 22.3% better than the conventional Markov model for top-1 recommendations.

Health Recommender Systems: Systematic Review

Background

Health recommender systems (HRSs) offer the potential to motivate and engage users to change their behavior by sharing better choices and actionable knowledge based on observed user behavior.

Objective

We aim to review HRSs targeting nonmedical professionals (laypersons) to better understand the current state of the art and identify both the main trends and the gaps with respect to current implementations.

Methods

We conducted a systematic literature review according to the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) guidelines and synthesized the results. A total of 73 published studies that reported both an implementation and evaluation of an HRS targeted to laypersons were included and analyzed in this review.

Results

Recommended items were classified into four major categories: lifestyle, nutrition, general health care information, and specific health conditions. The majority of HRSs use hybrid recommendation algorithms. Evaluations of HRSs vary greatly; half of the studies only evaluated the algorithm with various metrics, whereas others performed full-scale randomized controlled trials or conducted in-the-wild studies to evaluate the impact of HRSs, thereby showing that the field is slowly maturing. On the basis of our review, we derived five reporting guidelines that can serve as a reference frame for future HRS studies. HRS studies should clarify who the target user is and to whom the recommendations apply, what is recommended and how the recommendations are presented to the user, where the data set can be found, what algorithms were used to calculate the recommendations, and what evaluation protocol was used.

Conclusions

There is significant opportunity for an HRS to inform and guide health actions. Through this review, we promote the discussion of ways to augment HRS research by recommending a reference frame with five design guidelines.

Pathway-Driven Coordinated Telehealth System for Management of Patients With Single or Multiple Chronic Diseases in China: System Development and Retrospective Study

Background

Integrated care enhanced with information technology has emerged as a means to transform health services to meet the long-term care needs of patients with chronic diseases. However, the feasibility of applying integrated care to the emerging “three-manager” mode in China remains to be explored. Moreover, few studies have attempted to integrate multiple types of chronic diseases into a single system.

Objective

The aim of this study was to develop a coordinated telehealth system that addresses the existing challenges of the “three-manager” mode in China while supporting the management of single or multiple chronic diseases.

Methods

The system was designed based on a tailored integrated care model. The model was constructed at the individual scale, mainly focusing on specifying the involved roles and responsibilities through a universal care pathway. A custom ontology was developed to represent the knowledge contained in the model. The system consists of a service engine for data storage and decision support, as well as different forms of clients for care providers and patients. Currently, the system supports management of three single chronic diseases (hypertension, type 2 diabetes mellitus, and chronic obstructive pulmonary disease) and one type of multiple chronic conditions (hypertension with type 2 diabetes mellitus). A retrospective study was performed based on the long-term observational data extracted from the database to evaluate system usability, treatment effect, and quality of care.

Results

The retrospective analysis involved 6964 patients with chronic diseases and 249 care providers who have registered in our system since its deployment in 2015. A total of 519,598 self-monitoring records have been submitted by the patients. The engine could generate different types of records regularly based on the specific care pathway. Results of the comparison tests and causal inference showed that a part of patient outcomes improved after receiving management through the system, especially the systolic blood pressure of patients with hypertension (P<.001 in all comparison tests and an approximately 5 mmHg decrease after intervention via causal inference). A regional case study showed that the work efficiency of care providers differed among individuals.

Conclusions

Our system has potential to provide effective management support for single or multiple chronic conditions simultaneously. The tailored closed-loop care pathway was feasible and effective under the “three-manager” mode in China. One direction for future work is to introduce advanced artificial intelligence techniques to construct a more personalized care pathway.

Using Mobile Health Technology to Deliver a Community-Based Closed-Loop Management System for Chronic Obstructive Pulmonary Disease Patients in Remote Areas of China: Development and Prospective Observational Study

Background

Mobile health (mHealth) technology is an increasingly recognized and effective method for disease management and has the potential to intervene in pulmonary function, exacerbation risk, and psychological status of patients with chronic obstructive pulmonary disease (COPD).

Objective

This study aimed to investigate the feasibility of an mHealth-based COPD management system designed for Chinese remote areas with many potential COPD patients but limited medical resources.

Methods

The system was implemented based on a tailored closed-loop care pathway that breaks the heavy management tasks into detailed pieces to be quantified and executed by computers. Low-cost COPD evaluation and questionnaire-based psychological intervention are the 2 main characteristics of the pathway. A 6-month prospective observational study at the community level was performed to evaluate the effect of the system. Primary outcomes included changes in peak expiratory flow values, quality of life measured using the COPD assessment test scale, and psychological condition. Acute exacerbations, compliance, and adverse events were also measured during the study. Compliance was defined as the ratio of the actual frequency of self-monitoring records to the prescribed number.

Results

A total of 56 patients was enrolled; 39 patients completed the 6-month study. There was no significant difference in the mean peak expiratory flow value before and after the 6-month period (366.1, SD 106.7 versus 313.1, SD 116.6; P=.11). Psychological condition significantly improved after 6 months, especially for depression, as measured using the Patient Health Questionnaire-9 scale (median 6.0, IQR 3.0-9.0 versus median 4.0, IQR 0.0-6.0; P=.001). The COPD assessment test score after 6 months of intervention was also lower than that at the baseline, and the difference was significant (median 4.0, IQR 1.0-6.0 versus median 3.0, IQR 0.0-6.0; P=.003). The median overall compliance was 91.1% (IQR 67%-100%). In terms of acute exacerbation, 110 exacerbations were detected and confirmed by health care providers (per 6 months, median 2.0, IQR 1.0-5.0). Moreover, 72 adverse events occurred during the study, including 1 death, 19 hospitalizations, and 52 clinic visits due to persistent respiratory symptoms.

Conclusions

We designed and validated a feasible mHealth-based method to manage COPD in remote Chinese areas with limited medical resources. The proposed closed-loop care pathway was effective at the community level. Proper education and frequent communication with health care providers may encourage patients’ acceptance and use of smartphones to support COPD self-management. In addition, WeChat might play an important role in improving patient compliance and psychological distress. Further research might explore the effect of such systems on a larger scale and at a higher evidence level.