Online Physician Research Articles

Long-Term Impact of an Online Physician Group-Coaching Program to Improve Burnout and Self-Compassion in Trainees

SUMMARY Goal To evaluate long-term outcomes of Better Together Physician Coaching, a digital life-coaching program to improve resident well-being. Methods We performed a secondary analysis of survey data from the pilot program implementation between January 2021 and June 2022. An intention-to-treat analysis was completed for baseline versus post-6 months and baseline versus post-12 months for all outcome measures. Principal Findings Of 101 participants, 95 completed a baseline survey (94%), 66 completed a 6-month survey (65%) and 36 completed a 12-month survey (35%). There were no significant differences in burnout scale scores between baseline to 6 or 12 months. Self-compassion scores (i.e., means) improved after 6 months, from 33.2 to 38.2 (p < .001) and remained improved after 12 months at 36.7 (p = .020). Impostor syndrome score means decreased after 6 months, from 5.41 to 4.38 (p = .005) but were not sustained after 12 months (4.66, p = .081). Moral injury score means decreased from baseline to 6 months from 41.2 to 37.0 (p = .018), but reductions were not sustained at 12 months (38.1, p = .166). Practical Applications This study showed significant, sustained improvement in self-compassion for coaching program participants.

The utility of ChatGPT in gender-affirming mastectomy education

IntroductionThe integration of AI such as ChatGPT in medicine has been showing promise in enhancing patient education. Gender-affirming mastectomy (GAM) is a surgical procedure designed to help individuals transition to their self-identified gender, playing a crucial role in mitigating psychological distress for many transmasculine and non-binary (TNB) patients. With increased demand and attention towards GAM, plastic and reconstructive surgeons may rely on AI-driven chatbots as an accessible, accurate, and patient-driven model for relevant details on this procedure. Specific Aim(s)This study aimed to assess the quality and readability of information provided by ChatGPT in response to frequently asked questions (FAQs) related to GAM. MethodsInspired by online forums and physician websites, 10 frequently asked questions (FAQs) about pre- and postoperative topics were submitted to ChatGPT and assessed using validated readability score measures and expert interpretation. ResultsThe average readability score was 16.0 ± 1, indicating a college or graduate reading level. Mean accuracy, comprehensiveness, and danger scores were 8.8 ± 0.5, 7.8 ± 0.7, and 2.2 ± 0.4, respectively. Although physicians appreciated ChatGPT's tone, patient autonomy, and advice to seek professional medical and mental help, they also cited instance of generic information, misinformation, support of debated techniques, and pathologization of gender dysphoria. ConclusionEven with its promise in providing accurate and comprehensive information on GAM, ChatGPT’s current limitations suggest caution as a supplementary tool to physician consultation.

Delphi Panel Consensus Statement Generation: COVID-19 Vaccination Recommendations for Immunocompromised Populations in the European Union.

The coronavirus disease 2019 (COVID-19) pandemic has caused unprecedented pressure on healthcare systems globally. The lack of quality guidelines on the management of COVID-19 in rheumatologic disease, renal disease, hematological malignancy, and solid organ transplant recipients has resulted in a wide variation in clinical practice. Using a Delphi process, a panel of 16 key opinion leaders developed clinical practice statements regarding vaccine recommendations in areas where standards are absent or limited. Agreement among practicing physicians with consensus statements was also assessed via an online physician survey. The strength of the consensus was determined by the following rating system: a strong rating was defined as all four key opinion leaders (KOLs) rating the statement ≥ 8, a moderate rating was defined as three out of four KOLs rating the statement ≥ 8, and no consensus was defined as less than three out of four KOLs provided a rating of ≤ 8. Specialists voted on agreement with each consensus statement for their disease area using the same ten-point scoring system. Key opinion leaders in rheumatology, nephrology, and hematology achieved consensuses for all nine statements pertaining to the primary and booster series with transplant physicians reaching consensus on eight of nine statements. Experts agreed that COVID-19 vaccines are safe, effective, and well tolerated by patients with rheumatological conditions, renal disease, hematologic malignancy, and recipients of solid organ transplants. The Delphi process yielded strong to moderate suggestions for the use of COVID-19 messenger ribonucleic acid (mRNA) vaccines and the necessity of the COVID-19 booster for the immunocompromised population. The expert panel had mixed feelings concerning the measurement of antibody titers, higher-dose mRNA vaccines, and the development of disease-specific COVID-19 guidance. These results confirmed the necessity of COVID-19 vaccines and boosters in immunocompromised patients with rheumatologic disease, renal disease, hematological malignancy, and solid organ transplant recipients. Statements where consensus was not achieved were due to absent or limited evidence.

Usefulness and accessibility of information on the treatment of children with congenital clubfoot: results of a survey of parents

BACKGROUND: Treatment of congenital clubfoot remains controversial from both specialists and parents regarding the details of its practical application, individual effectiveness, and follow-up, rehabilitation treatment, prevention, and treatment of relapses. The assessment of parental attitudes using an online survey optimizes doctor–patient interaction. Information available to parents regarding the diagnosis and treatment of children with congenital clubfoot is lacking. AIM: This study aimed to assess the usefulness and accessibility of information for parents about the treatment of children with congenital clubfoot. MATERIALS AND METHODS: To assess the usefulness and accessibility of information about the treatment of congenital clubfoot, a survey of the patients’ parents was conducted using an electronic fillable form proposed for anonymous completion in a thematic group dedicated to the treatment of congenital clubfoot on the social network “VKontakte”; the study included 5500 participants at the time of the survey (2 weeks), with 328 responses received. RESULTS: Most parents noted a lack of information regarding clubfoot treatment before it actually began. The preferred source of information was Internet resources (i.e., websites of medical institutions and social networks). Achilles tenotomy and wearing braces raised the most questions, requiring additional information from both doctors and alternative sources. The possibility of errors and complications in wearing braces caused the greatest concern among parents, as well as possible relapses and the correctness of prescriptions during the rehabilitation treatment. Online parent communities and physician blogs are considered significant information sources. Most parents prefer to expand information about congenital clubfoot on the Internet, including social networks and popular resources. CONCLUSIONS: Analysis of the results of an anonymous survey of parents of children with congenital clubfoot showed a significant demand for high-quality, accessible information regarding the diagnosis, treatment, and rehabilitation of children with congenital clubfoot. Significant interest in the information provided by social media and other Internet resources determines the need for competent representatives of the professional community to participate in this process.

Pathways Linking Online Physician–Patient Communication to Health Outcomes

ABSTRACT Online platforms have proliferated in response to the increasing demand for online medical services. However, the underlying mechanisms through which online physician‒patient communication are associated with better health outcomes are under-researched. We employed mixed focus groups and in-depth interviews to investigate the impact of online physician‒patient communication on health outcomes, including psychological and physical quality of life, as well as perceived diagnosticity. A modified pathway framework was subsequently generated to illustrate the relationship between online communication and health outcomes based on the clinician‒patient communication pathway model. Overall, we redefined the concept of perceived diagnosticity in online healthcare and identified an indirect pathway through which psychological quality of life affects physical quality of life mediated by perceived diagnosticity.

Visualizing Hospital Management Data in R Shiny-A Case Study.

There is a demand to make hospital management information beyond basic key performance indicators (KPIs) accessible for clinicians. We developed an interactive application (IAPP) in R Shiny to visualize such information. We provided the IAPP source code online. As a use case, we recorded basic KPIs (numbers of patients (NPs), reimbursed valuation ratios (RVRs), mean length of stay (LOS)), main diagnoses (MDGNs), main procedures (MPRCs), and catchment area (CA) by district from April 2022 to March 2024 at the index department in central Germany, where a neurotrauma and spinal surgery service was resumed on 1 April 2022. Case mix indexes (CMIs) were calculated. We retrieved information about online-reported patient satisfaction (ORPS) from an online physician rating platform between January 2022 and March 2024. Information on longitudes and latitudes of the index department and neighbouring hospitals was collected. We calculated car travelling isochrones (CTIs) of the hospitals as a proxy variable for accessibility. Chi-square and Fisher's exact served as statistical tests. During the observation period, the monthly NPs increased from 26 to 43, the RVR showed a 3.96-fold increase, the CMI showed a 2.41-fold increase, and the LOS reached a steady state in the 2nd year after service resumption. CA (p = 0.03), MDGNs, and MPRCs diversified. ORPS trended towards better overall evaluation after service resumption (p = 0.09). CTI mapping identified a unique market position of the index department. The IAPP makes extended hospital management data accessible to clinicians, can inform other stakeholders in healthcare, and can be tailored to local conditions.

Fecal urgency and incontinence in inflammatory bowel disease perceived by physician and patient: Results from the Swiss fecal urgency survey.

Although increasingly appreciated, little is known about the prevalence of fecal urgency, fecal incontinence and differences between patients' and physicians' perception in inflammatory bowel disease (IBD). We performed an online patient and physician survey to evaluate the assessment, prevalence and impact of fecal urgency and incontinence in IBD. A total of 593 patients (44.0% ulcerative colitis (UC), 53.5% Crohn's disease (CD), 2.2% indeterminate colitis, 2 not specified) completed the survey (65.8% females, mean age 47.1years). Fecal urgency was often reported (UC: 98.5%, CD: 96.2%) and was prevalent even during remission (UC: 65.9%, CD: 68.5%). Fecal urgency considerably impacted daily activities (visual analog scale [VAS] 5, IQR 3-8). Yet, 22.8% of patients have never discussed fecal urgency with their physicians. Fecal incontinence was experienced by 44.7% of patients and 7.9% on a weekly basis. Diapers/pads were required at least once a month in 20.4% of patients. However, 29.7% of patients never talked with their physician about fecal incontinence. UC was an independent predictor for the presence of moderate-severe fecal urgency (OR 1.65, 95% CI 1.13-2.41) and fecal incontinence (OR 1.77, 95% CI 1.22-2.59). All physicians claimed to regularly inquire about fecal urgency and incontinence. However, the impact of these symptoms on daily activities was overestimated compared with the patient feedback (median VAS 8 vs. 5, p=0.0113, and 9 vs. 5, p=0.0187). Fecal urgency and incontinence are burdensome symptoms in IBD, with a similar prevalence in UC and CD. A mismatch was found between the physician and patient perception. These symptoms should be addressed during outpatient visits.

A Bayesian deep recommender system for uncertainty-aware online physician recommendation

Online physician recommender systems alleviate information overload by automatically recommending the best-fit physicians to patients. In contrast to general recommendations, physicians with greater uncertainty (i.e., greater variance in patients’ feedback) may not be preferred as this could affect patients’ treatment. However, most existing recommender systems don't consider uncertainty, reducing systems’ reliability and patients’ readiness to trust. To address this concern, this study leverages Bayesian theory and develops an uncertainty-aware online physician recommender system, including a Bayesian deep collaborative filtering (BDCF) model and a novel uncertainty-aware ranking algorithm. Experiments on real-world data demonstrate the superiority of BDCF and the ranking algorithm.

AI-Assisted Sentiment Analysis of ACFAS Fellowship-Trained Foot and Ankle Surgeon Online Reviews

Online physician ratings and reviews prove useful among patients when selecting a provider. Analyzing such reviews across medical and surgical specialties to determine their emotional tone through sentiment analysis yielded varying levels of positivity, negativity, and neutrality. To provide insight into what patients are saying, this study similarly analyzes the sentiment of physician ratings and reviews among foot and ankle surgeons. Healthgrades ratings and reviews, entered as of February 2024, were collected among the American College of Foot and Ankle Surgeons (ACFAS) fellows along with each surgeon's demographic information. ChatGPT was used to perform a sentiment analysis to describe the positivity, negativity, and neutrality of online physician reviews. Ratings and review sentiment were described among the sample and between sexes. Among 268 fellows, men received higher average rating scores than women (p = 0.02), From the 2,339 reviews, women received a greater proportion of negative reviews compared to men (p<0.001). The overall sentiment scores among men were higher than women (p < 0.001). There existed a very weak inverse relationship between ratings and years in practice (R = -0.16; p = 0.01). Fellowship-trained foot and ankle surgeons received predominantly positive reviews. When comparing sexes, males received higher ratings with higher sentiment scores. As patients place high credence in online reviews when selecting their provider, surgeons should remain mindful of and monitor or manage their online reputation. Level of EvidenceIV

Social media use and patient ratings in shoulder and elbow surgeons: how many “likes” for five stars?

IntroductionSocial media plays an important role in healthcare and physician selection by facilitating direct communication with patients and impacting physician ratings. A concern however is the increased online scrutiny and negative impact on patient satisfaction with these connections. This study aimed to investigate whether social media activity by fellowship-trained shoulder and elbow surgeons impacts patient’s perceptions and ratings on physician rating websites (PRWs). Materials and MethodsThe American Shoulder and Elbow Surgeons (ASES) physician directory was used to identify currently practicing shoulder and elbow surgeons in the US. Physician ratings were collected from Healthgrades, Google reviews, and Vitals. The surgeons were divided into two groups: social media users (SMU) and non-social media users (NSMU). The association of social media use with online physician ratings was evaluated using simple and multilinear regressions. ResultsA total of 385 ASES surgeons were included and 21.3% were SMU. SMU were younger (mean age, 48 years) compared to NSMU (mean age, 51 years) (p = 0.01), all other demographics were comparable including sex (p = 0.797), medical degree (MD or DO) (p = 0.114), and geographic location within the US (p = 0.49). SMU had significantly higher ratings on Healthgrades (p<0.001) and Vitals (p<0.001). However, social media use did not impact the total number of ratings on PRWs. Additionally, surgeons who utilized Facebook had higher physician ratings and number of website reviews on Healthgrades (p = 0.028 and p=0.014, respectively). In addition, surgeons who used Twitter had higher ratings on Healthgrades (p<0.001) and Vitals (p=0.001). Surgeons with a greater average number of likes per post on Twitter had significantly higher average ratings across all three sites (p=0.004). Surgeons with a greater number of Twitter followers and greater average number of likes per post had significantly higher average ratings on Healthgrades (p=0.052 and p=0.005, respectively) while surgeons with a greater average number of likes per post had significantly higher average ratings on Vitals (p=0.006). Finally, surgeons with a greater average posting frequency on Instagram had significantly higher average ratings across all websites (p=0.029). ConclusionShoulder and elbow surgeons who use Twitter and Facebook had significantly higher online ratings. However, the increased use of these platforms in terms of post content, post frequency, comments, and number of followers was not as influential on PRWs. This suggests that social media is an important marketing and outreach method for orthopedic surgeons to improve their ratings and patient reviews.

Accuracy and consistency of online large language model-based artificial intelligence chat platforms in answering patients' questions about heart failure

BackgroundHeart failure (HF) is a prevalent condition associated with significant morbidity. Patients may have questions that they feel embarrassed to ask or will face delays awaiting responses from their healthcare providers which may impact their health behavior. We aimed to investigate the potential of large language model (LLM) based artificial intelligence (AI) chat platforms in complementing the delivery of patient-centered care. MethodsUsing online patient forums and physician experience, we created 30 questions related to diagnosis, management and prognosis of HF. The questions were posed to two LLM-based AI chat platforms (OpenAI's ChatGPT-3.5 and Google's Bard). Each set of answers was evaluated by two HF experts, independently and blinded to each other, for accuracy (adequacy of content) and consistency of content. ResultsChatGPT provided mostly appropriate answers (27/30, 90%) and showed a high degree of consistency (93%). Bard provided a similar content in its answers and thus was evaluated only for adequacy (23/30, 77%). The two HF experts' grades were concordant in 83% and 67% of the questions for ChatGPT and Bard, respectively. ConclusionLLM-based AI chat platforms demonstrate potential in improving HF education and empowering patients, however, these platforms currently suffer from issues related to factual errors and difficulty with more contemporary recommendations. This inaccurate information may pose serious and life-threatening implications for patients that should be considered and addressed in future research.

Does the Gender of Doctors Change a Patient’s Perception?

ABSTRACT In the past, researchers have used various data sources like social media, admission applications, or letters of recommendation to identify gender-based differences in linguistic data. One such avenue in healthcare is the online physician reviews website. Such websites, for example, RateMyDoctors.com, ZocDoc, or even Yelp.com have become a go-to place for patients when choosing their physicians. In the current research, we used two different natural language processing (NLP) approaches: semi-supervised and unsupervised topic modeling to analyze the text of the reviews to identify gender-based linguistic differences from patients’ perspectives. We found that female physicians receive more reviews on their personable skills and warmth, aligning with the Stereotype Content Model. We also found other popular topics discussing bedside manners and overall patient experiences, where the reviews suggested that patients were happier with their experience with female physicians and perceived them to have more positive traits than their male counterparts. Although our study did not reflect significant linguistic differences; it highlights the importance for patients and doctors to be more aware of potential gender stereotypes and perceptions.

Do social media use and patient satisfaction scores correlate with online award recognition among hip and knee arthroplasty specialists?

IntroductionThe physician–patient interaction now begins before patients arrive in the office. Online ratings, social media profiles, and online award status are all components of physician online reputation which contributes to the patient's initial impressions. Therefore, it is important to understand the interplay of these factors and determine if there is a consistent trend indicating the value of this information. MethodsWe Identified all (N ​= ​160) registered American Association of Hip and Knee Surgeons (AAHKS) in New England using the https://findadoctor.aahks.net/tool for Massachusetts (MA), Connecticut (CT), Rhode Island (RI), Vermont (VT), New Hampshire (NH), and Maine (ME) on 6/26/2023. We collected surgeon age, fellowship graduation year, and practice type (i.e. Academic or Private). The average 5-star rating and number of ratings were collected from four websites. Any professional-use Facebook, Instagram, Twitter, LinkedIn, YouTube Channel, Personal Websites, or Institutional Websites were identified and a modified SMI Score was calculated. Finally, Castle Connolly Top Doctor, Local Magazine (e.g. Boston Magazine) Top Doctor, or the presence of having any award was noted for each surgeon. ResultsWe identified several significant trends indicating that online awards were associated with higher online ratings. Social media presence, as determined by SMI Score, was also correlated with higher ratings overall and a higher likelihood of having an online award. ConclusionGiven the observed trends and reported importance patients place on ratings and awards, surgeons may consider increasing online engagement via social media and encouraging patients to share their experience via online ratings.

Identifying patients in need of psychological treatment with language representation models

AbstractEarly diagnosis of psychological disorders is very important for patients to regain their health. Research shows that many patients do not realize that they have a psychological disorder or apply to different departments for treatment. The detection of hidden psychological disorders in patients will both increase the quality of life of patients and reduce the traffic of patients who apply to the wrong department. This study aimed to determine whether patients who consult a physician for any reason need psychological treatment. For this purpose, the relationships, and similarities between the sentences of previous psychiatric patients and the sentences of newly arrived patients were analyzed. Domain-based trained ELECTRA language model was used to detect sentence similarities semantically. In the study, the dialogues of patients with physicians in 92 different specialties were analyzed using the MedDialog dataset, which consists of online physician applications, and the DAIC-WOZ dataset. As a result of the experiments, 90.49% success was achieved for the MedDialog dataset and 89.36% for the DAIC-WOZ dataset. With the proposed model, patients in need of psychological treatment were identified and the medical departments where psychological problems were revealed the most were determined. These divisions are Neurology, Sexology, Cardiology, and Plastic Surgery, respectively. With the findings obtained, complications caused by psychological problems and types of diseases that are precursors to psychological disorders were determined. To the best of our knowledge, this article is the first study that aims to analyze all psychological illness instead of focusing on any of the psychological problems (depression, OCD, schizophrenia, etc.) and validated by electronic health records.

How do patients' perceptions and doctors' images impact patient decisions? Deconstructing online physician selection using multimodal data

In the post-pandemic era, medical resources are uneven, and access to healthcare is complicated. Online medical platforms have become a solution to bridge the information gap and reduce hospital pressure. This study uses the stereotype content model and signaling theory to explore the impact of patient perception of patient decision making (PDM) on online medical service platforms. Also, it tests the moderating effect of physician image. We collected information on 12,890 physicians and 746,981 patient reviews from online medical platforms in China. Unsupervised machine learning was used to construct a topic model to extract patients' perceptions of physicians' competence and warmth. Meanwhile, the facial features of physicians, such as age, smile, and glasses, are recognized by convolutional neural networks. Finally, the influence of PDM concern on decision-making and the moderating effect of physician image were analyzed by multiple linear regression. The results of the study showed that (1) patients' perceptions of physicians' competence and warmth had a positive effect on decision-making; (2) physicians' age and wearing glasses enhanced the positive effect of perception on decision-making; and (3) however, physicians' smiles weakened the positive effect of perception on decision-making. This study provides new insights into patients' online physician selection, guides the construction and promotion of medical service platforms, and provides an effective avenue of exploration to alleviate the problem of uneven distribution of offline medical resources.

Effect of Negative Online Reviews and Physician Responses on Health Consumers' Choice: Experimental Study.

The COVID-19 pandemic has highlighted the importance of online medical services. Although some researchers have investigated how numerical ratings affect consumer choice, limited studies have focused on the effect of negative reviews that most concern physicians. This study aimed to investigate how negative review features, including proportion (low/high), claim type (evaluative/factual), and physician response (absence/presence), influence consumers' physician evaluation process under conditions in which a physician's overall rating is high. Using a 2×2×2 between-subject decision-controlled experiment, this study examined participants' judgment on physicians with different textual reviews. Collected data were analyzed using the t test and partial least squares-structural equation modeling. Negative reviews decreased consumers' physician selection intention. The negative review proportion (β=-0.371, P<.001) and claim type (β=-0.343, P<.001) had a greater effect on consumers' physician selection intention compared to the physician response (β=0.194, P<.001). A high negative review proportion, factual negative reviews, and the absence of a physician response significantly reduced consumers' physician selection intention compared to their counterparts. Consumers' locus attributions on the negative reviews affected their evaluation process. Physician attribution mediated the effects of review proportion (β=-0.150, P<.001), review claim type (β=-0.068, P=.01), and physician response (β=0.167, P<.001) on consumer choice. Reviewer attribution also mediated the effects of review proportion (β=-0.071, P<.001), review claim type (β=-0.025, P=.01), and physician response (β=0.096, P<.001) on consumer choice. The moderating effects of the physician response on the relationship between review proportion and physician attribution (β=-0.185, P<.001), review proportion and reviewer attribution (β=-0.110, P<.001), claim type and physician attribution (β=-0.123, P=.003), and claim type and reviewer attribution (β=-0.074, P=.04) were all significant. Negative review features and the physician response significantly influence consumer choice through the causal attribution to physicians and reviewers. Physician attribution has a greater effect on consumers' physician selection intention than reviewer attribution does. The presence of a physician response decreases the influence of negative reviews through direct and moderating effects. We propose some practical implications for physicians, health care providers, and online medical service platforms.

Exploring the Effects of Online Physician Voice Pitch Range and Filled Pauses on Patient Satisfaction in Mobile Health Communication

ABSTRACT The convenience of mobile devices has driven the widespread use of voice technology in mobile health communication, significantly improving the timeliness of online service. However, the issue of listening to therapeutic content, which requires great cognitive effort and may exceed the patient’s information processing capacity (i.e., information overload), is of concern. Based on information processing theory, this study reports how online physicians’ voice characteristics (pitch range and filled pauses) affect patient satisfaction. We obtained 10,585 mobile voice consultation records of 1,416 doctors from China’s largest mHealth platform and analyzed them using audio mining and empirical methods. Results showed that pitch range (β = 0.0539, p < .01) and filled pauses (β = 0.0365, p < .01) in doctors’ voice positively influenced online patient satisfaction. However, the effect of filled pauses becomes weaker for patients with higher health literacy and higher disease risk. This suggests that there is heterogeneity in the way different patients process audio information. This study provides important insights for guiding online physician behaviors, enhancing patient satisfaction, and improving mobile health platform management.

Exploring user interaction patterns in an online physician interactive community based on exponential random graph models

The online physician interactive community (OPIC) is a platform designed for medical workers to discuss medical issues. Physician users can create content in OPIC by posting and replying to posts to discuss the solutions of medical problems with other users. The OPIC plays an important role in bringing together physicians from different medical specialties and disseminating medical experience. However, most OPIC users are not very active in replying to posts, which makes it difficult to fulfill users’ needs for medical information exchange and the development of OPIC is difficult. Current research has given little attention to the communication of physician users in the OPIC. It is necessary to examine how reposting links are established between users in OPIC. This study builds a user interaction network based on the perspective of social network analysis using user repost data from a well-known OPIC in China. Then, an exponential random graph model (ERGM) was applied to quantitatively analyze this user interaction network. Some reposting patterns among OPIC users were discovered. There is significant reciprocity in OPIC of reposting interactions between users. Users with homogeneous characteristics in terms of professional status, community honor status, and geographic location were more likely to interact with each other. In addition, users who added a profile, had a higher level of social effort, and generated more neutral content were more likely to receive responses from others. This study reveals the interaction patterns between physician users in OPIC, which enriches the related research within the OPIC domain and helps to improve communication between users in OPIC.

An Assessment of the COVID-19 Pandemic’s Impact on US Physicians’ Acceptance of Telemedicine: An Exploratory Study

Prior to the COVID-19, various issues in ethics, laws, regulations and security risks limited physicians in their ability to deliver medical care via telemedicine. However, in 2020, telemedicine quickly became mainstream when the US government issued a waiver granting the use of telemedicine to reduce COVID-19 transmission. This study examined the US physicians’ acceptance of telemedicine after its sudden wide-scale implementation. The authors developed a survey based on the Unified Theory of Acceptance and Use of Technology to assess the US physicians’ intentions and attitudes toward the use of telemedicine in the delivery of medical care. This survey was distributed between March and June in 2021 across several voluntary online physician groups. The survey was validated using factor analysis. The 110 participants who completed this study were all active physicians practising telemedicine in the USA. The majority of the participants were female (93%), between 34 and 59 years of age (93%), had at least 10 years of medical experience (84%) and practised in a city (92%). The behavioural intention to use telemedicine was influenced by performance expectancy ( β = 0.34, p&lt;.001), social influence ( β = 0.34, p&lt;.001), facilitating conditions ( β = 0.14, p&lt;.05) and attitude towards telemedicine use ( β = 0.36, p&lt;.001). Attitude towards telemedicine use was influenced by performance expectancy ( β = 0.60, p&lt;.001), effort expectancy ( β = 0.16, p&lt;.05) and social influence ( β = 0.16, p&lt;.05). In addition, telemedicine experience moderated the influence of performance expectancy on behavioural intention negatively ( β =−0.39, p&lt;.001) and moderated the influence of facilitating conditions on behavioural intention positively( β = 0.27, p&lt;.001). This study found that the physicians’ performance expectancy of and attitude towards telemedicine use were significant predictors of physicians’ acceptance. Social influence from colleagues and administrators also played an essential role in impacting physicians’ acceptance of telemedicine. Physicians’ effort expectancy merely affected their attitude towards telemedicine use. Facilitating conditions—such as the inability to perform physical exams, labs, etc.—only influenced the physicians’ intention to use telemedicine. Finally, the survey data suggested that as physicians gained telemedicine experience, their performance expectancy predicted lower behavioural intention than counterparts with less experience.

How to detect fake online physician reviews: A deep learning approach.

The COVID-19 pandemic has spurred an increased interest in online healthcare and a surge in usage of online healthcare platforms, leading to a proliferation of user-generated online physician reviews. Yet, distinguishing between genuine and fake reviews poses a significant challenge. This study aims to address the challenges delineated above by developing a reliable and effective fake review detection model leveraging deep learning approaches based on a fake review dataset tailored to the context of Chinese online medical platforms. Inspired by prior research, this paper adopts a crowdsourcing approach to assemble the fake review dataset for Chinese online medical platforms. To develop the fake review detection models, classical machine learning models, along with deep learning models such as Convolutional Neural Network and Bidirectional Encoder Representations from Transformers, were applied. Our experimental deep learning model exhibited superior performance in identifying fake reviews on online medical platforms, achieving a precision of 98.36% and an F2-Score of 97.97%. Compared to the traditional machine learning models (i.e., logistic regression, support vector machine, random forest, ridge regression), this represents an 8.16% enhancement in precision and a 7.7% increase in F2-Score. Overall, this study provides a valuable contribution toward the development of an effective fake physician review detection model for online medical platforms.