Privacy Protection in Online Health Communities: Natural Experimental Empirical Study

A Systematic Review of Online Medical Consultation Research

Online medical consultation is a form of medical service that facilitates interactions between patients and doctors online, offering significant utility and value. This review aims to retrieve, screen, and analyze articles related to online medical consultations, formulating a theoretical framework and proposing future research directions. According to PRISMA guidelines, a systematic search was conducted in Web of Science, EBSCO, ScienceDirect, PubMed, and Scopus, retrieving a total of 4072 English records on 16 December 2023. After rigorous screening, 75 articles were included in this review. Among these, 8 articles focused on patients utilizing online medical consultation platforms, 5 on doctors participating in online medical platforms, 18 on patients' choice of doctors, 12 on doctors providing services, 7 on online reviews of patients, 14 on service quality for patients, 8 on rewards to doctors, and 11 on the spillover effect between online and offline services. These themes comprise the theoretical framework of the starting point, process, and outcomes of the online medical consultation system, providing a comprehensive understanding of the field and a foundation for future research.

Setting goal difficulty in monetary incentives to physicians: evidence from an online health knowledge-sharing platform

Purpose

Prior studies on the impact of incentives on physicians’ online participation mainly focused on different incentives while ignoring the difficulty of setting monetary incentives efficiently. Based on goal-setting theory, the current research examines the relationship between incentives with goals of varying difficulty and professional health knowledge sharing (PHKS) in online health knowledge-sharing platforms (OHKSPs).

Design/methodology/approach

Four field experiments with different monetary incentives were conducted by one of China’s largest OHKSPs, with whom the researchers cooperated in data collection. Monthly panel data on 10,584 physicians were collected from September 2018 to December 2019. There were 9,376 physicians in the treatment group and 1,208 in the control group. The authors used a difference-in-difference (DID) model to explore the research question based on the same control group and the Chow test with seemingly unrelated estimation (sureg) to compare regression coefficients between four groups. Several robustness checks were performed to validate the main results, including a relative time model, multiple falsification tests and a DID estimation using the propensity score matching method.

Findings

The results show that the monetary incentive significantly positively affected the volume of physicians’ PHKS directly with negative spillover to the duration of physicians’ PHKS. Moreover, the positive effect of incentives with higher difficulty on the volume of physicians’ PHKS was significantly smaller than that of incentives with low difficulty. Finally, professional title had a positive moderating effect on the volume of goal difficulty setting and did not significantly moderate the effect on the duration of physicians’ PHKS.

Research limitations/implications

Some limitations of this study are: firstly, because the field experiments were enterprise benefit oriented, the treatment and control groups were not balanced. Secondly, the experiments for different incentive measures were relatively similar, making it challenging to validate a causal effect. Finally, more consideration should be given to the strategy for setting hierarchical incentives in future research.

Originality/value

The research indicates that monetary incentives have a bilateral effect on PHKS, i.e. a positive direct effect on the volume of physicians’ contributions and a negative spillover effect on the duration of physicians’ PHKS. The professional titles of physicians also moderate such bilateral switches of PHKS. Furthermore, when a physician’s energy is limited, the goal difficulty setting of the incentive mechanism tends to be low. The more difficult the incentives are, the more inefficient the effects on physicians’ PHKS will be.

The Effect of Offline Medical Resource Distribution on Online Physician-Patient Interaction: Empirical Study With Online and Offline Data

BACKGROUND

The relationship between online health communities (OHCs) and offline medical care is unclear because both provide physician-patient interaction services and channels. Taking advantage of information and communication technology, patients have been using OHCs widely. However, some physical medical resources (such as hospital beds and medical devices) cannot be replicated by information and communication technologies. Therefore, it is worth studying how offline medical resources affect physician-patient interactions in OHCs and how OHCs help to solve resource scarcity and the uneven distribution of traditional medical treatment.

OBJECTIVE

This study aimed to support the notion that physician-patient consultations in OHCs are influenced by the objective distribution of offline health care capital (accessibility and availability) and to provide suggestions for the allocation of medical resources in practice through the judicious use of offline and online channels.

METHODS

The empirical data in this study were collected from both online and offline channels. The offline data include 9 years (2006-2014) of medical resource statistics of 31 provincial administrative regions in mainland China. Moreover, data regarding the geolocation-based physician-patient interaction network in the OHC were also collected. The online data come from one of China's largest OHCs. We obtained 92,492 telephone consultation records of 6006 physicians using an automatic web crawler program. Social network analysis was used to visualize the descriptive statistics of the offline geolocation-based physician-patient interaction network in the OHC. A regression model with a squared variable was applied to analyze online and offline empirical data to further test our hypothesis. Two types of robustness tests were used to increase the reliability of the test results of the initial model.

RESULTS

The results of our social network analysis show that there is a uniform geographic distribution of patients who use OHCs, whereas the physician relies more on geographic advantage (eg, a higher medical resource capability). Moreover, the empirical results of the regression model support the notion that physician-patient telephone consultations are positively influenced by physicians' online contributions (β_contribution=.210; P<.001) and capital availability (β_bed=.935; P=.07), and, interestingly, spatial accessibility has an inverted U-shaped effect (β_distance=.199; P<.001 and β_distance²=-.00449; P=.008). The results indicate that the use of OHCs, although constrained by offline medical resources, provides a channel for offline resources to flow from areas with high availability to those with low availability.

CONCLUSIONS

This study explores the relationship between online and offline channels by investigating online physician-patient interactions and offline medical resources. In particular, this study analyzes the impact of offline channels on online channels and verifies the possibility of OHC capital use shifting from a high-availability area to a low-availability area. In addition, it provides a theoretical and practical basis for understanding the interaction of online and offline channels of medical care.

Sharing intention of electronic health records in online health communities: Patients' behavioral decisions in the context of privacy protection measures

Online health communities (OHCs) have become more important to people's daily lives on the foundation of the voluntary sharing of electronic health records (EHRs). However, no in-depth investigation has been conducted concerning the influence of the perceptions of privacy protection among patients on their willingness to share EHRs. To fill the knowledge gap, by combining and modifying the theory of planned behavior (TPB) and the health belief model in the context of the privacy protection models implemented by OHCs, an empirical research method using a questionnaire approach is conducted to validate the hypotheses. The results indicate that the more positive a patient's attitude toward medical information sharing behavior is, the higher that patient's level of perceived behavioral control; in addition, the greater the social rewards obtained from this process, the more willing the patient is to share his or her EHRs after privacy protection measures are implemented by OHCs. Meanwhile, the effects of past positive experiences and disease severity have also been tested. The findings of this study can be used to promote patients' full participation in OHCs from a privacy perspective and offer theoretical and practical suggestions to promote the development of OHCs.

Multi-Label Classification in Patient-Doctor Dialogues With the RoBERTa-WWM-ext + CNN (Robustly Optimized Bidirectional Encoder Representations From Transformers Pretraining Approach With Whole Word Masking Extended Combining a Convolutional Neural Network) Model: Named Entity Study

Background

With the prevalence of online consultation, many patient-doctor dialogues have accumulated, which, in an authentic language environment, are of significant value to the research and development of intelligent question answering and automated triage in recent natural language processing studies.

Objective

The purpose of this study was to design a front-end task module for the network inquiry of intelligent medical services. Through the study of automatic labeling of real doctor-patient dialogue text on the internet, a method of identifying the negative and positive entities of dialogues with higher accuracy has been explored.

Methods

The data set used for this study was from the Spring Rain Doctor internet online consultation, which was downloaded from the official data set of Alibaba Tianchi Lab. We proposed a composite abutting joint model, which was able to automatically classify the types of clinical finding entities into the following 4 attributes: positive, negative, other, and empty. We adapted a downstream architecture in Chinese Robustly Optimized Bidirectional Encoder Representations from Transformers Pretraining Approach (RoBERTa) with whole word masking (WWM) extended (RoBERTa-WWM-ext) combining a text convolutional neural network (CNN). We used RoBERTa-WWM-ext to express sentence semantics as a text vector and then extracted the local features of the sentence through the CNN, which was our new fusion model. To verify its knowledge learning ability, we chose Enhanced Representation through Knowledge Integration (ERNIE), original Bidirectional Encoder Representations from Transformers (BERT), and Chinese BERT with WWM to perform the same task, and then compared the results. Precision, recall, and macro-F1 were used to evaluate the performance of the methods.

Results

We found that the ERNIE model, which was trained with a large Chinese corpus, had a total score (macro-F1) of 65.78290014, while BERT and BERT-WWM had scores of 53.18247117 and 69.2795315, respectively. Our composite abutting joint model (RoBERTa-WWM-ext + CNN) had a macro-F1 value of 70.55936311, showing that our model outperformed the other models in the task.

Conclusions

The accuracy of the original model can be greatly improved by giving priority to WWM and replacing the word-based mask with unit to classify and label medical entities. Better results can be obtained by effectively optimizing the downstream tasks of the model and the integration of multiple models later on. The study findings contribute to the translation of online consultation information into machine-readable information.