Beyond the Hype-The Actual Role and Risks of AI in Today's Medical Practice: Comparative-Approach Study.

BACKGROUND: The evolution of artificial intelligence (AI) has significantly impacted various sectors, with health care witnessing some of its most groundbreaking contributions. Contemporary models, such as ChatGPT-4 and Microsoft Bing, have showcased capabilities beyond just generating text, aiding in complex tasks like literature searches and refining web-based queries. OBJECTIVE: This study explores a compelling query: can AI author an academic paper independently? Our assessment focuses on four core dimensions: relevance (to ensure that AI's response directly addresses the prompt), accuracy (to ascertain that AI's information is both factually correct and current), clarity (to examine AI's ability to present coherent and logical ideas), and tone and style (to evaluate whether AI can align with the formality expected in academic writings). Additionally, we will consider the ethical implications and practicality of integrating AI into academic writing. METHODS: To assess the capabilities of ChatGPT-4 and Microsoft Bing in the context of academic paper assistance in general practice, we used a systematic approach. ChatGPT-4, an advanced AI language model by Open AI, excels in generating human-like text and adapting responses based on user interactions, though it has a knowledge cut-off in September 2021. Microsoft Bing's AI chatbot facilitates user navigation on the Bing search engine, offering tailored search. RESULTS: In terms of relevance, ChatGPT-4 delved deeply into AI's health care role, citing academic sources and discussing diverse applications and concerns, while Microsoft Bing provided a concise, less detailed overview. In terms of accuracy, ChatGPT-4 correctly cited 72% (23/32) of its peer-reviewed articles but included some nonexistent references. Microsoft Bing's accuracy stood at 46% (6/13), supplemented by relevant non-peer-reviewed articles. In terms of clarity, both models conveyed clear, coherent text. ChatGPT-4 was particularly adept at detailing technical concepts, while Microsoft Bing was more general. In terms of tone, both models maintained an academic tone, but ChatGPT-4 exhibited superior depth and breadth in content delivery. CONCLUSIONS: Comparing ChatGPT-4 and Microsoft Bing for academic assistance revealed strengths and limitations. ChatGPT-4 excels in depth and relevance but falters in citation accuracy. Microsoft Bing is concise but lacks robust detail. Though both models have potential, neither can independently handle comprehensive academic tasks. As AI evolves, combining ChatGPT-4's depth with Microsoft Bing's up-to-date referencing could optimize academic support. Researchers should critically assess AI outputs to maintain academic credibility.

Efficacy of a web-based healthcare innovation to advance the quality of life and care of patients with an implantable cardioverter defibrillator (ACQUIRE-ICD): a randomized controlled trial.

AIMS: Modern clinical management of patients with an implantable cardioverter defibrillator (ICD) largely consists of remote device monitoring, although a subset is at risk of mental health issues post-implantation. We compared a 12-month web-based intervention consisting of goal setting, monitoring of patients' mental health-with a psychological intervention if needed-psychoeducational support from a nurse, and an online patient forum, with usual care on participants' device acceptance 12 months after implantation. METHODS AND RESULTS: This national, multi-site, two-arm, non-blinded, randomized, controlled, superiority trial enrolled 478 first-time ICD recipients from all 6 implantation centres in Denmark. The primary endpoint was patient device acceptance measured by the Florida Patient Acceptance Survey (FPAS; general score range = 0-100, with higher scores indicating higher device acceptance) 12 months after implantation. Secondary endpoints included symptoms of depression and anxiety. The primary endpoint of device acceptance was not different between groups at 12 months [B = -2.67, 95% confidence interval (CI) (-5.62, 0.29), P = 0.08]. Furthermore, the secondary endpoint analyses showed no significant treatment effect on either depressive [B = -0.49, 95% CI (-1.19; 0.21), P = 0.17] or anxiety symptoms [B = -0.39, 95% CI (-0.96; 0.18), P = 0.18]. CONCLUSION: The web-based intervention as supplement to usual care did not improve patient device acceptance nor symptoms of anxiety and depression compared with usual care. This specific web-based intervention thus cannot be recommended as a standardized intervention in ICD patients.

Long-term Weight Loss in a Primary Care-Anchored eHealth Lifestyle Coaching Program: Randomized Controlled Trial.

BACKGROUND: Long-term weight loss in people living with obesity can reduce the risk and progression of noncommunicable diseases. Observational studies suggest that digital coaching can lead to long-term weight loss. OBJECTIVE: We investigated whether an eHealth lifestyle coaching program for people living with obesity with or without type 2 diabetes led to significant, long-term (12-month) weight loss compared to usual care. METHODS: In a randomized controlled trial that took place in 50 municipalities in Denmark, 340 people living with obesity with or without type 2 diabetes were enrolled from April 16, 2018, to April 1, 2019, and randomized via an automated computer algorithm to an intervention (n=200) or a control (n=140) group. Patients were recruited via their general practitioners, the Danish diabetes organization, and social media. The digital coaching intervention consisted of an initial 1-hour face-to-face motivational interview followed by digital coaching using behavioral change techniques enabled by individual live monitoring. The primary outcome was change in body weight from baseline to 12 months. RESULTS: Data were assessed for 200 participants, including 127 from the intervention group and 73 from the control group, who completed 12 months of follow-up. After 12 months, mean body weight and BMI were significantly reduced in both groups but significantly more so in the intervention group than the control group (-4.5 kg, 95% CI -5.6 to -3.4 vs -1.5 kg, 95% CI -2.7 to -0.2, respectively; P<.001; and -1.5 kg/m2, 95% CI -1.9 to -1.2 vs -0.5 kg/m2, 95% CI -0.9 to -0.1, respectively; P<.001). Hemoglobin A1c was significantly reduced in both the intervention (-6.0 mmol/mol, 95% CI -7.7 to -4.3) and control (-4.9 mmol/mol, 95% CI -7.4 to -2.4) groups, without a significant group difference (all P>.46). CONCLUSIONS: Compared to usual care, digital lifestyle coaching can induce significant weight loss for people living with obesity, both with and without type 2 diabetes, after 12 months. TRIAL REGISTRATION: ClinicalTrials.gov NCT03788915; https://clinicaltrials.gov/ct2/show/NCT03788915.

Agreement Between Clinically Measured Weight and Self-reported Weight Among Patients With Type 2 Diabetes Through an mHealth Lifestyle Coaching Program in Denmark: Secondary Analysis of a Randomized Controlled Trial.

BACKGROUND: Digital health interventions are increasingly used to handle and promote positive health behaviors. Clinical measures are often used, and a certain precision is essential for digital health interventions to have an effect. Only few studies have compared clinically measured weights with self-reported weights. No study has examined the validity of self-reported weight from a mobile app used in a tailored weight loss intervention. OBJECTIVE: The aim of this study was to analyze the agreement between clinically measured weight and self-reported weight collected from a mobile health lifestyle coaching program during a 12-month weight loss intervention for obese patients with and without type 2 diabetes. The secondary aim was to investigate the determinants for possible discrepancies between clinically measured and self-reported weights of these patients with different demographic and lifestyle characteristics and achievements of weight loss goals. METHODS: Weight registrations were collected from participants (N=104) in a Danish randomized controlled trial examining the effect of a digital lifestyle intervention on weight loss among obese patients with and without type 2 diabetes. Data were collected at baseline and after 6 and 12 months. Self-reported weight was measured at home and registered in the app. RESULTS: Self-reported body weight was lower than the weight measured in the clinic after 6 months by 1.03 kg (95% CI 1.01-1.05; P<.001) and after 12 months also by 1.03 kg (95% CI 0.99-1.04; P<.001). After 6 months, baseline weight and BMI were associated with a discrepancy of 0.03 kg (95% CI 0.01-0.04; P=.01) and 0.09 kg (95% CI 0.02-0.17; P=.02) per increment of 1 kg and 1 kg/m2, respectively, between clinically measured weight and self-reported weight. Weight change during the first 6 months was also associated with a difference of 0.1 kg (95% CI 0.04-0.01; P<.001) per kilogram of difference in weight between clinically measured weight and self-reported weight. Participants who did not achieve the 5% weight loss goal underestimated their weight by 0.79 kg (95% CI 0.34-1.23) at 6 months. After 12 months, only baseline weight was associated with a discrepancy of 0.03 kg (95% CI 0.01-0.05; P=.02) per increment of kilogram between clinically measured weight and self-reported weight. None of the other factors showed any significant discrepancy after 12 months. CONCLUSIONS: Self-reported weight obtained from mobile health is a valid method for collecting anthropometric measurements. TRIAL REGISTRATION: ClinicalTrials.gov NCT03788915; https://clinicaltrials.gov/ct2/show/NCT03788915.

Electronic Health Lifestyle Coaching Among Diabetes Patients in a Real-Life Municipality Setting: Observational Study.

BACKGROUND: Internet and mobile interventions aiming to promote healthy lifestyle have attracted much attention because of their scalability and accessibility, low costs, privacy and user control, potential for use in real-life settings, as well as opportunities for real-time modifications and interactive advices. A real-life electronic health (eHealth) lifestyle coaching intervention was implemented in 8 Danish municipalities between summer 2016 and summer 2018. OBJECTIVE: The aim of this study was to assess the effects associated with the eHealth intervention among diabetes patients in a real-life municipal setting. The eHealth intervention is based on an initial meeting, establishing a strong empathic relationship, followed by digital lifestyle coaching and collaboration supported by a Web-based community among patients. METHODS: We conducted an observational study examining the effect of an eHealth intervention on self-reported weight change among 103 obese diabetes patients in a real-life municipal setting. The patients in the study participated in the eHealth intervention between 3 and 12 months. A weight change was observed at 6, 9, and 12 months. We used regression methods to estimate the impacts of the intervention on weight change. RESULTS: We found that the eHealth intervention significantly reduced weight among diabetes patients, on average 4.3% of the initial body mass, which corresponds to 4.8 kg over a mean period of 7.3 months. Patients who were in intervention for more than 9 months achieved a weight reduction of 6.3% or 6.8 kg. CONCLUSIONS: This study brings forward evidence of a positive effect of a real-life eHealth lifestyle intervention on diabetes patients' lifestyle in a municipal setting. Future research is needed to show if the effect is sustainable from a long-term perspective.

Determinants of Successful eHealth Coaching for Consumer Lifestyle Changes: Qualitative Interview Study Among Health Care Professionals.

BACKGROUND: Success with lifestyle change, such as weight loss, tobacco cessation, and increased activity level, using electronic health (eHealth) has been demonstrated in numerous studies short term. However, evidence on how to maintain the effect long-term has not been fully explored, even though there is a pressing need for long-term solutions. Recent studies indicate that weight loss can be achieved and maintained over 12 and 20 months in a primary care setting using a collaborative eHealth tool. The effect of collaborative eHealth in promoting lifestyle changes depends on competent and skilled dieticians, nurses, physiotherapists, and occupational therapists acting as eHealth coaches. How such health care professionals perceive delivering asynchronous eHealth coaching and which determinants they find to be essential to achieving successful long-term lifestyle coaching have only been briefly explored and deserve further exploration. OBJECTIVE: The aim of this study is to analyze how health care professionals perceive eHealth coaching and to explore what influences successful long-term lifestyle change for patients undergoing hybrid eHealth coaching using a collaborative eHealth tool. METHODS: A total of 10 health care professionals were recruited by purposive sampling. They were all women aged 36 to 65 years of age with a mean age of 48 years of age. A total of 8/10 (80%) had more than 15 years of experience in their field, and all had more than six months of experience providing eHealth lifestyle coaching using a combination of face-to-face meetings and asynchronous eHealth coaching. They worked in 5 municipalities in the Region of Southern Denmark. We performed individual, qualitative, semistructured, in-depth interviews in their workplace about their experiences with health coaching about lifestyle change, both for their patients and for themselves, and mainly how they perceived using a collaborative eHealth solution as a part of their work. RESULTS: The health care professionals all found establishing and maintaining an empathic relationship essential and that asynchronous eHealth lifestyle coaching challenged this compared to face-to-face coaching. The primary reason was that unlike typical in-person encounters in health care, they did not receive immediate feedback from the patients. We identified four central themes relevant to the health care professionals in their asynchronous eHealth coaching: (1) establishing an empathic relationship, (2) reflection in asynchronous eHealth coaching, (3) identifying realistic goals based on personal barriers, and (4) staying connected in asynchronous coaching. CONCLUSIONS: Establishing and maintaining an empathic relationship is probably the most crucial factor for successful subsequent eHealth coaching. It was of paramount importance to get to know the patient first, and the asynchronous interaction aspect presented challenges because of the delay in response times (both ways). It also presented opportunities for reflection before answering. The health care professionals found they had to provide both relational communication and goal-oriented coaching when using eHealth solutions. Going forward, the quality of the health care professional-patient interaction will need attention if patients are to benefit from collaborative eHealth coaching fully.

General Practitioners' Perspective on eHealth and Lifestyle Change: Qualitative Interview Study.

BACKGROUND: Wearables, fitness apps, and patient home monitoring devices are used increasingly by patients and other individuals with lifestyle challenges. All Danish general practitioners (GPs) use digital health records and electronic health (eHealth) consultations on a daily basis, but how they perceive the increasing demand for lifestyle advice and whether they see eHealth as part of their lifestyle support should be explored further. OBJECTIVE: This study aimed to explore GPs' perspectives on eHealth devices and apps and the use of eHealth in supporting healthy lifestyle behavior for their patients and themselves. METHODS: A total of 10 (5 female and 5 male) GPs were recruited by purposive sampling, aged 38 to 69 years (mean 51 years), of which 4 had an urban uptake of patients and 6 a rural uptake. All of them worked in the region of Southern Denmark where GPs typically work alone or in partnership with 1 to 4 colleagues and all use electronic patient health records for prescription, referral, and asynchronous electronic consultations. We performed qualitative, semistructured, individual in-depth interviews with the GPs in their own office about how they used eHealth and mHealth devices to help patients challenged with lifestyle issues and themselves. We also interviewed how they treated lifestyle-challenged patients in general and how they imagined eHealth could be used in the future. RESULTS: All GPs had smartphones or tablets, and everyone communicated on a daily basis with patients about disease and medicine via their electronic health record and the internet. We identified 3 themes concerning the use of eHealth: (1) how eHealth is used for patients; (2) general practitioners' own experience with improving lifestyle and eHealth support; and (3) relevant coaching techniques for transformation into eHealth. CONCLUSIONS: GPs used eHealth frequently for themselves but only infrequently for their patients. GPs are familiar with behavioral change techniques and are ready to use them in eHealth if they are used to optimize processes and not hinder other treatments. Looking ahead, education of GPs and recognizing patients' ability and preference to use eHealth with regard to a healthy living are needed.

Drivers for successful long-term lifestyle change, the role of e-health: a qualitative interview study.

OBJECTIVES: Assisting patients in lifestyle change using collaborative e-health tools can be an efficient treatment for non-communicable diseases like diabetes, cardiovascular disease and chronic obstructive lung disease that are caused or aggravated by unhealthy living in the form of unhealthy diet, physical inactivity or tobacco smoking. In a prospective pilot study, we tested an online collaborative e-health tool in general practice. The aim of this study was to identify drivers of importance for long-term personal lifestyle changes from a patient perspective when using a collaborative e-health tool, including the support of peers and healthcare professionals. SETTING: General practice clinics in the Region of Southern Denmark. PARTICIPANTS: 10 overweight patients who had previously successfully used a hybrid online collaborative e-health tool with both face-to-face and online consultations to lose weight. RESULTS: The main themes identified were facilitators, barriers and support from family and peers. Establishment of a trustworthy relationship with the healthcare professionals was of paramount importance. It was important for the patients to monitor the measurable outcomes with realistic goals and feedback from a trusted person. Often, significant life events were identified as catalysts for successful long-term lifestyle changes. Dominant barriers to change were perception of insurmountable obstacles, experience of lack of self-efficacy and excess eating of high-calorie food. Finally, experiencing of trustworthy person-to-person forums, need for acknowledgement from referent others and support from family and peers were important drivers for long-term lifestyle change. CONCLUSION: The most important driver in long-term weight loss was a strong relationship with a healthcare professional. Collaborative e-health tools can support the relationship and behavioural changes through monitoring and providing relevant feedback. The support from family and peers also matters, and long-term success depends on the ability to establish strong, positive support on a day-to-day basis.