Patient Education Tool Research Articles

ChatGPT as a patient education tool in colorectal cancer-An in-depth assessment of efficacy, quality and readability.

Artificial intelligence (AI) chatbots such as Chat Generative Pretrained Transformer-4 (ChatGPT-4) have made significant strides in generating human-like responses. Trained on an extensive corpus of medical literature, ChatGPT-4 has the potential to augment patient education materials. These chatbots may be beneficial to populations considering a diagnosis of colorectal cancer (CRC). However, the accuracy and quality of patient education materials are crucial for informed decision-making. Given workforce demands impacting holistic care, AI chatbots can bridge gaps in CRC information, reaching wider demographics and crossing language barriers. However, rigorous evaluation is essential to ensure accuracy, quality and readability. Therefore, this study aims to evaluate the efficacy, quality and readability of answers generated by ChatGPT-4 on CRC, utilizing patient-style question prompts. To evaluate ChatGPT-4, eight CRC-related questions were derived using peer-reviewed literature and Google Trends. Eight colorectal surgeons evaluated AI responses for accuracy, safety, appropriateness, actionability and effectiveness. Quality was assessed using validated tools: the Patient Education Materials Assessment Tool (PEMAT-AI), modified DISCERN (DISCERN-AI) and Global Quality Score (GQS). A number of readability assessments were measured including Flesch Reading Ease (FRE) and the Gunning Fog Index (GFI). The responses were generally accurate (median 4.00), safe (4.25), appropriate (4.00), actionable (4.00) and effective (4.00). Quality assessments rated PEMAT-AI as 'very good' (71.43), DISCERN-AI as 'fair' (12.00) and GQS as 'high' (4.00). Readability scores indicated difficulty (FRE 47.00, GFI 12.40), suggesting a higher educational level was required. This study concludes that ChatGPT-4 is capable of providing safe but nonspecific medical information, suggesting its potential as a patient education aid. However, enhancements in readability through contextual prompting and fine-tuning techniques are required before considering implementation into clinical practice.

Online Screening and Virtual Patient Education for Hereditary Cancer Risk Assessment and Testing.

To use online screening and virtual patient education tools to improve the provision of hereditary cancer risk assessment. We conducted a prospective, single-arm study in which clinicians at five U.S. community obstetrics and gynecology practices underwent an 8-week observation followed by 3-4 weeks of training on online patient screening and virtual patient education (prerecorded video with or without a genetic counselor phone call) for genetic testing-eligible patients. After a 4-week practice period, hereditary cancer risk assessment and patient education metrics were collected at 8 weeks and compared with preintervention metrics using univariate conditional logistic regression models stratified by site. The primary outcome was the change in genetic testing completion rate. Clinicians and patients were invited to complete a satisfaction survey. A total of 5,795 and 5,135 patients were seen before and after the intervention, respectively. The proportion of screened patients meeting testing guidelines increased from 21.6% before the intervention to 28.2% after the intervention (odds ratio [OR] 1.36, 95% CI, 1.26-1.47, P<.001). Guideline-eligible patients were significantly more likely to be offered genetic testing (59.1% vs 89.1%, OR 2.06, 95% CI, 1.87-2.27, P<.001), to submit a sample (32.9% vs 45.0%, OR 1.49, 95% CI, 1.27-1.74, P<.001), and to complete testing (16.0% vs 34.2%, OR 2.38, 95% CI, 2.00-2.83, P<.001). Most clinicians agreed or strongly agreed that the screening tool improved the identification of patients meeting hereditary cancer risk assessment guidelines (92.1%), saved time (64.9%), and was easy to incorporate (68.4%) and that patient education improved their ability to deliver hereditary cancer risk assessment standard of care (84.2%). Most patients agreed or strongly agreed that virtual education helped them understand the purpose (91.7%) and implications (92.6%) of genetic testing. A guideline-based online patient screening tool and virtual patient education were well received. The online tool enabled identification of significantly more guideline-eligible candidates for hereditary cancer risk assessment, and education improved patients' genetic literacy. Together, these tools ultimately improved the genetic testing completion rate.

Patient education tools for chronic pain medications, AI versus traditional PILs – Clarifications

Patient education tools for chronic pain medications, AI versus traditional PILs – Clarifications

Patient education tools for chronic pain medications: Artificial intelligence chatbot versus traditional patient information leaflets

Patient education tools for chronic pain medications: Artificial intelligence chatbot versus traditional patient information leaflets

A multimetric health literacy analysis of phalloplasty techniques: Comparing artificial intelligence and online resources

BackgroundThis study aims to compare the informational quality of online and artificial intelligence (AI) - sources on different phalloplasty donor sites to assess reliability and accessibility. MethodsA deidentified Google search was conducted using search phrases for forearm, thigh, back, and abdomen phalloplasty. The first ten websites for each donor site were included. The same search phrases were entered into three AI platforms: ChatGPT-4o mini, Google Gemini, and MetaAI. The Simple Measure of Gobbledygook (SMOG), Patient Education and Materials Assessment Tool (PEMAT), and the DISCERN tool to evaluate readability, understandability and actionability, and quality, respectively. ResultsWebsite readability was higher than AI platforms, though not statistically significant (p=0.10). All means exceeded the eighth-grade reading level, with AI outperforming websites in understandability and actionability (p<0.0001 and p=0.006). While websites were deemed understandable, they lacked actionable content. AI scores averaged 51.9, categorized as “good quality,” whereas websites averaged 46.9, classified as “fair quality” (p=0.001). No significant differences across donor sites were found (p=0.82). ConclusionsImproving the quality of online health resources for phalloplasty donor sites is essential in enabling patients to make informed surgical decisions. The emergence of AI as an educational tool enhances the understandability and quality of online phalloplasty materials, but its overall value warrants further evaluation.

The evaluation of different information methods on behaviour and anxiety levels of children aged 6 to 9years: a randomised controlled trial.

To evaluate the alteration of pre-post informing anxiety levels and behavioural scores of the children in the groups between those who were shown the multimedia-application and verbally explained. In this randomized controlled study, healthy children, who applied to a paediatric-dental-clinic who never had a dental visit or dental procedure rather than oral examination were included. In the waiting room evaluation of children with a behaviour-control-list and Frankl's-Behaviour-Rating-Scale were performed, Venham-Picture-Test (VPT) was shown to the children. Then, the random information method (with a multimedia-application or verbally) was used for giving information. Finally, the child was observed whilst sitting in the dental chair and meeting with dentist, the behaviour-control-list was filled out again, and child's behaviour were re-scored. A total of 56 children [mean (± sd) age of 7.3 (± 1.1)] participated. There was no statistically significant difference between the median values of the change in Frankl and VPT-scores after the information (p = 0.261 and p = 0.651, respectively). The percentage change of pre-post informing in definitively negative children according to Frankl's score was higher in the multimedia application group (25%). Besides, the percentage change in children scored with score 5-6 according to VPT was also higher in multimedia-application group (25%-28.6%, respectively, for scores 5-6). Although the score changes after the information procedure were more pronounced in the multimedia-application group for both VPT and Frankl-scores, the difference was not statistically significant. Multimedia applications seem to offer a promising modern tool for patient education before dental examination in 6- to 9-year-old children.

How accurately can ChatGPT 3.5 answer frequently asked questions by patients on glenohumeral osteoarthritis?

Abstract Background Conversational artificial intelligence (AI) systems like ChatGPT have emerged as valuable assets in providing accessible information across various domains, including the healthcare system. The use of ChatGPT may contribute to better patient education and better general healthcare knowledge. However, there is a paucity of data on the reliability of responses generated by ChatGPT in the context of specific medical diagnoses. Methods We identified 12 frequently asked questions by patients about glenohumeral osteoarthritis. These questions were formulated in both English and German, using common and medical terms for the condition, thus creating four groups for evaluation. The questions were then presented to ChatGPT 3.5. The generated responses were evaluated for accuracy by four independent orthopedic and trauma surgery consultants using a Likert scale (0 = fully inaccurate to 4 = fully accurate). Results Although there were two questions in two groups, all questions across all versions were answered with good accuracy by ChatGPT 3.5. The highest score on the Likert scale was 3.9 for the group where questions were posed in English using the medical term “glenohumeral osteoarthritis.” The lowest score of 3.2 was for the group where questions were posed in English using the common term “shoulder arthrosis.” On average, questions in English received a score of 3.5 on the Likert scale, slightly higher than those in German, which received a score of 3.4. Conclusion ChatGPT 3.5 can already provide accurate responses to patients’ frequently asked questions on glenohumeral osteoarthritis. ChatGPT can therefore be a valuable tool for patient communication and education in the field of orthopedics. Further studies, however, have to be performed in order to fully understand the mechanisms and impact of ChatGPT in the field.

Sharing Genomic Tumor Sequencing Results With Patients: Experiences of Advanced Practice Oncology Providers

Background: Patients with cancer routinely undergo genomic tumor sequencing, a component of molecular profiling (MP), to better characterize their cancer and identify potential targetable alterations. Targeted treatments potentially confer higher response rates and better efficacy. With increasing complexity, patients may require detailed explanations of MP results. Patient understanding of MP results increases the likelihood that eligible patients receive targeted treatment. Advanced practice providers (APPs), defined as nurse practitioners, physician assistants, and pharmacists, frequently review and discuss MP results with patients. Purpose: The aim of this study is to understand APP experiences discussing MP results with adult cancer patients. Methods: A qualitative study was conducted through virtual semi-structured interviews with APPs recruited via study invitation shared through the Advanced Practitioner Society for Hematology and Oncology (APSHO). Eligibility criteria included APPs with &gt; 1 year of oncology experience and involvement in discussing MP results. Data were analyzed utilizing a constant comparative analysis and coded in three stages: open, axial, and selective. Results: Thirteen participants were enrolled from across the United States. Participants discussed learning to understand and explain MP findings primarily through on-the-job experiences. Barriers to patient education were also described. Initially coded participant statements (open codes) produced six themes (axial codes). Conclusions: With MP now standard practice in oncology, APPs frequently discuss these results with patients. This study highlights that additional and continuing education related to MP is needed in communicating complex results. Patient educational tools, specific to patients’ MP findings and tailored to their preferences and literacy levels, are critically needed.

Integrating Domain-Specific Resources: Advancing AI for Foot and Ankle Surgery

Large language models like ChatGPT offer significant potential for applications in medicine, including patient education and clinical support. This study evaluates the performance of ChatGPT-4, ChatGPT-4 augmented with retrieval-augmented generation, and Gemini AI in responding to clinical vignette questions about Hallux Rigidus, a condition requiring specialized knowledge in foot and ankle surgery. The ChatGPT-4 + RAG model, enhanced with the 2024 ACFAS clinical consensus statements, demonstrated the highest agreement with surveyor majority responses (83.26%) compared to ChatGPT-4 (59.54%) and Gemini AI (53.02%). All models provided clinically appropriate responses to most questions, with the ChatGPT-4 + RAG model excelling in accuracy, despite the rationale for answers being deemed most difficult to read. These findings highlight the limitations of generic AI models, which may propagate misinformation if used by patients seeking health information. By incorporating domain-specific resources, the RAG-augmented model showed enhanced reliability and contextual accuracy, suggesting their potential as tools for both clinical decision-making and patient education. This study emphasizes the importance of integrating verified medical resources to advance AI in healthcare, addressing critical gaps in existing capabilities while minimizing risks of misinformation.

Dental photography using DSLR cameras vs smartphones

Background: Smartphone photography has increased in quality with the advancement of technology. Dental photography using a digital single-lens reflex (DSLR) camera has been a critical tool for patient education, treatment planning, self-evaluation, and research in the orthodontic profession. This study aims to determine if there is a significant difference in quality between facial and intraoral photographs taken with DSLR cameras and smartphones.Method: Dental students and practicing orthodontists took an 18-question survey to compare facial and intraoral photographs taken with a DSLR camera and a smartphone. Participants evaluated the photographs based on color, sharpness, depth of field, and overall quality. Chi-square analyses and Fisher's exact tests were used to evaluate potential differences across image sources and respondent types.Results: Three hundred twenty-nine participants completed this survey with an overall response rate of 74.9%. Facial photographs taken with a DSLR had significantly superior overall quality, sharpness, and depth of field compared to smartphone facial photographs (P<0.05). Intraoral photographs taken with a smartphone had significantly superior overall quality, color, sharpness, and depth of field compared to DSLR photographs (P< 0.01).Conclusions: This study suggests that intraoral photographs taken with a smartphone could provide a superior image quality compared to those taken by a DSLR camera, but not for facial photographs. As smartphone cameras continue to evolve, they have the potential to provide superior photographic quality for intraoral photographs compared to DSLR cameras.

Tools for effective patient education to manage outcome expectations in paediatric facial reanimation: a systematic review

Aim: Informed consent for paediatric facial reanimation requires effective patient/parent education and involvement in a shared decision-making (SDM) process to help set their expectations and understanding from the outset. No article in the current literature has systematically reviewed the available tools for facilitating effective patient/parent education and the validity of informed consent in the context of paediatric facial reanimation. Methods: A systematic literature review was undertaken, following the Preferred Reporting Items of Systematic Reviews and Meta-analyses (PRISMA) 2020 guidelines. MEDLINE via PubMed, Embase and Cochrane Library were searched and the results screened and reviewed in accordance with pre-defined inclusion and exclusion criteria. Results: The initial search yielded 478 articles, of which only 4 fulfilled the study’s inclusion criteria. One cohort study evaluated qualitative feedback from patients and their relatives participating in a family education and support day for paediatric facial palsy, while another article from the same group reviewed the readability of online education resources. The remaining two articles represented educational reviews focusing on treatment and patient education based on expert opinion without providing original outcome data. Conclusion: There is a paucity of evidence regarding patient/parent education to support the informed consent process for children undergoing paediatric facial reanimation. There remains a need for further resources and platforms to be developed that may support children and their parents in engaging in a SDM process, setting appropriate expectations, and providing valid informed consent for their surgery.

Qualitatively Assessing ChatGPT Responses to Frequently Asked Questions Regarding Sexually Transmitted Diseases.

ChatGPT, a large language model artificial intelligence platform that uses natural language processing, has seen its implementation across a number of sectors, notably in healthcare. However, there remains limited understanding regarding the efficacy of ChatGPT in addressing commonly asked questions on public health subjects. This study aimed to investigate whether ChatGPT could appropriately answer frequently asked questions related to sexually transmitted diseases (STDs). Ten frequently asked questions on STDs were gathered from 25 different government agency websites. The questions were inputted into ChatGPT and subsequent responses were analyzed for accuracy, clarity, and appropriateness using an evidence-based approach on a 4-point grading scale. Of the responses provided by ChatGPT, four were determined to be excellent requiring no clarification and six requiring minimal clarification. No responses were graded as unsatisfactory. Additionally, the responses appropriately emphasized consulting a healthcare specialist. While the majority of responses required minimal clarification, ChatGPT has the potential to be an effective supplementary tool for patient education. Additional research is necessary to explore possible public health strategies that incorporate artificial intelligence to address concerns related to STDs.

Tiktok as a Source of Education and Misinformation in Lichen Sclerosus.

The purpose of this study is to evaluate the content, delivery, and quality of medical information for vulvar lichen sclerosus on the social media platform TikTok. This is a descriptive, cross-sectional study. Using the third-party data scraping tool Apify, TikTok videos tagged with #lichensclerosus or "lichen sclerosus" were identified and sorted by view count. A sample of 100 videos was reviewed by 2 independent reviewers, excluding those not discussing lichen sclerosus. Videos were assessed using a coding document, the Patient Educational Materials Assessment Tool, and the DISCERN instrument. Interrater reliability was measured, and statistical analyses included Fleiss' kappa, intraclass correlation coefficient, t tests, and Wilcoxon rank sum test with Holm-Bonferroni correction. Content creators included patients (46%), health care professionals (30%), and others. Topics focused on clinical disease (52%) and treatment (48%). Evidence-based medicine was discussed in 71.7% of treatment-related videos, while 51.7% included nonevidence-based approaches, with a neutral or positive sentiment. Videos discussing topical steroids often had negative sentiments. Quality assessment revealed 61% of videos were understandable, 27% actionable, and 46% contained misinformation. Videos by health care professionals had less misinformation and higher quality scores compared to patient-generated content. Commercially biased videos were more understandable but contained more misinformation. TikTok serves as a significant platform for sharing information on lichen sclerosus, but nearly half of the content contains misinformation. Health care professionals need to engage in social media to provide accurate information and counteract misinformation. Enhanced collaboration with patient advocates and careful resource sharing can improve the quality and reliability of medical information available online.

Technology Update in Management of Multi-Ligament Knee Injuries.

Multi-ligament knee injuries present in various combinations of structures around the knee joint, with or without involvement of neurovascular structures, posing significant challenges to the treating physician and therapists. Accurate diagnosis with appropriate surgical intervention and comprehensive rehabilitation to restore function and stability is, therefore, paramount. This article looks at the recent advancements in technology that are aiding in the management of these injuries. An extensive search of literature was done in PubMed, SCOPUS, and Google Scholar on this topic and the necessary information was derived from the relevant articles for this review. The progress made in the field of diagnosis, surgical management, rehabilitation and patient education tools were explored. A wide variety of diagnostic tools exists that are providing a more accurate evaluation of multi-ligament knee injuries both pre-operatively and post operatively. Advances in technology and techniques have aided in transforming their surgical management to a more minimally invasive approach. Patient-specific instrumentation, computer navigation and robotic-assisted surgery are in various stages of development offering enhanced precision and accuracy during ligament reconstruction procedures along with developments in digital technology and artificial intelligence. Advancements in technology have transformed the management of multi-ligament knee injuries, offering new tools and techniques that enhance diagnostic accuracy, surgical precision, and rehabilitation effectiveness. Artificial intelligence and its utility have widened the horizons, while at the same time bringing in the need for regulations necessary to monitor and develop these technologies.

Accuracy of natural language processors for patients seeking inguinal hernia information.

NLPs such as ChatGPT are novel sources of online healthcare information that are readily accessible and integrated into internet search tools. The accuracy of NLP-generated responses to health information questions is unknown. We queried four NLPs (ChatGPT 3.5 and 4, Bard, and Claude 2.0) for responses to simulated patient questions about inguinal hernias and their management. Responses were graded on a Likert scale (1 poor to 5 excellent) for relevance, completeness, and accuracy. Responses were compiled and scored collectively for readability using the Flesch-Kincaid score and for educational quality using the DISCERN instrument, a validated tool for evaluating patient information materials. Responses were also compared to two gold-standard educational materials provided by SAGES and the ACS. Evaluations were performed by six hernia surgeons. The average NLP response scores for relevance, completeness, and accuracy were 4.76 (95% CI 4.70-4.80), 4.11 (95% CI 4.02-4.20), and 4.14 (95% CI 4.03-4.24), respectively. ChatGPT4 received higher accuracy scores (mean 4.43 [95% CI 4.37-4.50]) than Bard (mean 4.06 [95% CI 3.88-4.26]) and Claude 2.0 (mean 3.85 [95% CI 3.63-4.08]). The ACS document received the best scores for reading ease (55.2) and grade level (9.2); however, none of the documents achieved the readibility thresholds recommended by the American Medical Association. The ACS document also received the highest DISCERN score of 63.5 (57.0-70.1), and this was significantly higher compared to ChatGPT 4 (50.8 [95% CI 46.2-55.4]) and Claude 2.0 (48 [95% CI 41.6-54.4]). The evaluated NLPs provided relevant responses of reasonable accuracy to questions about inguinal hernia. Compiled NLP responses received relatively low readability and DISCERN scores, although results may improve as NLPs evolve or with adjustments in question wording. As surgical patients expand their use of NLPs for healthcare information, surgeons should be aware of the benefits and limitations of NLPs as patient education tools.

Discrepancies in ChatGPT's Hip Fracture Recommendations in Older Adults for 2021 AAOS Evidence-Based Guidelines.

Background: This study aimed to assess the reproducibility and reliability of Chat-Based GPT (ChatGPT)'s responses to 19 statements regarding the management of hip fractures in older adults as adopted by the American Academy of Orthopaedic Surgeons' (AAOS) evidence-based clinical practice guidelines. Methods: Nineteen statements were obtained from the 2021 AAOS evidence-based clinical practice guidelines. After generating questions based on these 19 statements, we set a prompt for both the GPT-4o and GPT-4 models. We repeated this process three times at 24 h intervals for both models, producing outputs A, B, and C. ChatGPT's performance, the intra-ChatGPT reliability, and the accuracy rates were assessed to evaluate the reproducibility and reliability of the hip fracture-related guidelines. Regarding the strengths of the recommendation compared with the 2021 AAOS guidelines, we observed accuracy of 0.684, 0.579, and 0.632 for outputs A, B, and C, respectively. Results: The precision was 0.740, 0.737, and 0.718 in outputs A, B, and C, respectively. For the reliability of the strengths of the recommendation, the Fleiss kappa was 0.409, indicating a moderate level of agreement. No statistical differences in the strengths of the recommendation were observed in outputs A, B, and C between the GPT-4o and GPT-4 versions. Conclusion: ChatGPT may be useful in providing guidelines for hip fractures but performs poorly in terms of accuracy and precision. However, hallucinations remain an unresolved limitation associated with using ChatGPT to search for hip fracture guidelines. The effective utilization of ChatGPT as a patient education tool for the management of hip fractures should be addressed in the future.

Assessing the Clinical Appropriateness and Practical Utility of ChatGPT as an Educational Resource for Patients Considering Minimally Invasive Spine Surgery.

Introduction Minimally invasive spine surgery (MISS) has evolved over the last three decades as a less invasive alternative to traditional spine surgery, offering benefits such as smaller incisions, faster recovery, and lower complication rates. With patients frequently seeking information about MISS online, the comprehensibility and accuracy of this information are crucial. Recent studies have shown that much of the online material regarding spine surgery exceeds the recommended readability levels, making it difficult for patients to understand. This study explores the clinical appropriateness and readability of responses generated by Chat Generative Pre-Trained Transformer (ChatGPT) to frequently asked questions (FAQs) about MISS. Methods A set of 15 FAQs was formulated based on clinical expertise and existing literature on MISS. Each question was independently inputted into ChatGPT five times, and the generated responses were evaluated by three neurosurgery attendings for clinical appropriateness. Appropriateness was judged based on accuracy, readability, and patient accessibility. Readability was assessed using seven standardized readability tests, including the Flesch-Kincaid Grade Level and Flesch Reading Ease (FRE) scores. Statistical analysis was performed to compare readability scores across preoperative, postoperative, and intraoperative/technical question categories. Results The mean readability scores for preoperative, postoperative, and intraoperative/technical questions were 15±2.8, 16±3, and 15.7±3.2, respectively, significantly exceeding the recommended sixth- to eighth-grade reading level for patient education (p=0.017). Differences in readability across individual questions were also statistically significant (p<0.001). All responses required a reading level above 11th grade, with a majority indicating college-level comprehension. Although preoperative and postoperative questions generally elicited clinically appropriate responses, 50% of intraoperative/technical questions yielded either "inappropriate" or "unreliable" responses, particularly for inquiries about radiation exposure and the use of lasers in MISS. Conclusions While ChatGPT is proficient in providing clinically appropriate responses to certain FAQs about MISS, it frequently produces responses that exceed the recommended readability level for patient education. This limitation suggests that its utility may be confined to highly educated patients, potentially exacerbating existing disparities in patient comprehension. Future AI-based patient education tools must prioritize clear and accessible communication, with oversight from medical professionals to ensure accuracy and appropriateness. Further research comparing ChatGPT's performance with other AI models could enhance its application in patient education across medical specialties.

A Pilot Survey of Patient Perspectives on an Artificial Intelligence-Generated Presenter in a Patient Information Video about Face-Down Positioning after Vitreoretinal Surgery

Introduction: Video education is a commonly used patient education tool. However, the impact of integrating artificial intelligence (AI) into video education remains unexplored. This study aimed to examine the acceptability of an AI-generated presenter in a patient information video about face-down positioning after vitreoretinal surgery. Method: We prospectively enrolled participants who were planned for vitreoretinal surgery in which postoperative face-down positioning was recommended at the Royal Adelaide Hospital between December 2022 and September 2023. Participants were preoperatively provided with an educational video presented by an AI-generated presenter, incorporated into a surveyredcap. A pre- and post-video questionnaire was administered electronically. Results: There were 15 participants included in the study. In the pre-video questionnaire, most participants rated their awareness of special equipment for positioning as “not aware” (33%) and “slightly aware” (33%). The median pre-video six-item Spielberger State-Trait Anxiety Inventory Score was 12 (interquartile range 12–15). In the post-video questionnaire, most participants rated the video’s quality as “excellent” (73%) and would recommend it to others (73%). The majority of participants strongly agreed that they understood the AI presenter (60%), felt at ease with the presenter (60%), and trusted the presenter (60%). Four participants (22%) disagreed with the statement: “I was aware the presenter was computer generated.” Conclusions: Video-based education may provide information that patients find useful, particularly for physical maneuvers such as face-down positioning. The use of an AI-generated presenter was well-received by the majority of patients. Further research regarding the use of AI to develop educational video content is warranted.

Assessing the performance of AI chatbots in answering patients’ common questions about low back pain

ObjectivesThe aim of this study was to assess the accuracy and readability of the answers generated by large language model (LLM)-chatbots to common patient questions about low back pain (LBP).MethodsThis...

Online Patient Education in Obstructive Sleep Apnea: ChatGPT versus Google Search.

The widespread implementation of artificial intelligence technologies provides an appealing alternative to traditional search engines for online patient healthcare education. This study assessed ChatGPT-3.5's capabilities as a source of obstructive sleep apnea (OSA) information, using Google Search as a comparison. Ten frequently searched questions related to OSA were entered into Google Search and ChatGPT-3.5. The responses were assessed by two independent researchers using the Global Quality Score (GQS), Patient Education Materials Assessment Tool (PEMAT), DISCERN instrument, CLEAR tool, and readability scores (Flesch Reading Ease and Flesch-Kincaid Grade Level). ChatGPT-3.5 significantly outperformed Google Search in terms of GQS (5.00 vs. 2.50, p < 0.0001), DISCERN reliability (35.00 vs. 29.50, p = 0.001), and quality (11.50 vs. 7.00, p = 0.02). The CLEAR tool scores indicated that ChatGPT-3.5 provided excellent content (25.00 vs. 15.50, p < 0.001). PEMAT scores showed higher understandability (60-91% vs. 44-80%) and actionability for ChatGPT-3.5 (0-40% vs. 0%). Readability analysis revealed that Google Search responses were easier to read (FRE: 56.05 vs. 22.00; FKGL: 9.00 vs. 14.00, p < 0.0001). ChatGPT-3.5 delivers higher quality and more comprehensive OSA information compared to Google Search, although its responses are less readable. This suggests that while ChatGPT-3.5 can be a valuable tool for patient education, efforts to improve readability are necessary to ensure accessibility and utility for all patients. Healthcare providers should be aware of the strengths and weaknesses of various healthcare information resources and emphasize the importance of critically evaluating online health information, advising patients on its reliability and relevance.