A comparative evaluation of ChatGPT 3.5 and ChatGPT 4 in responses to selected genetics questions.

OBJECTIVES: To evaluate the efficacy of ChatGPT 4 (GPT-4) in delivering genetic information about BRCA1, HFE, and MLH1, building on previous findings with ChatGPT 3.5 (GPT-3.5). To focus on assessing the utility, limitations, and ethical implications of using ChatGPT in medical settings. MATERIALS AND METHODS: A structured survey was developed to assess GPT-4's clinical value. An expert panel of genetic counselors and clinical geneticists evaluated GPT-4's responses to these questions. We also performed comparative analysis with GPT-3.5, utilizing descriptive statistics and using Prism 9 for data analysis. RESULTS: The findings indicate improved accuracy in GPT-4 over GPT-3.5 (P < .0001). However, notable errors in accuracy remained. The relevance of responses varied in GPT-4, but was generally favorable, with a mean in the "somewhat agree" range. There was no difference in performance by disease category. The 7-question subset of the Bot Usability Scale (BUS-15) showed no statistically significant difference between the groups but trended lower in the GPT-4 version. DISCUSSION AND CONCLUSION: The study underscores GPT-4's potential role in genetic education, showing notable progress yet facing challenges like outdated information and the necessity of ongoing refinement. Our results, while showing promise, emphasizes the importance of balancing technological innovation with ethical responsibility in healthcare information delivery.

Enabling the clinical application of artificial intelligence in genomics: a perspective of the AMIA Genomics and Translational Bioinformatics Workgroup.

OBJECTIVE: Given the importance AI in genomics and its potential impact on human health, the American Medical Informatics Association-Genomics and Translational Biomedical Informatics (GenTBI) Workgroup developed this assessment of factors that can further enable the clinical application of AI in this space. PROCESS: A list of relevant factors was developed through GenTBI workgroup discussions in multiple in-person and online meetings, along with review of pertinent publications. This list was then summarized and reviewed to achieve consensus among the group members. CONCLUSIONS: Substantial informatics research and development are needed to fully realize the clinical potential of such technologies. The development of larger datasets is crucial to emulating the success AI is achieving in other domains. It is important that AI methods do not exacerbate existing socio-economic, racial, and ethnic disparities. Genomic data standards are critical to effectively scale such technologies across institutions. With so much uncertainty, complexity and novelty in genomics and medicine, and with an evolving regulatory environment, the current focus should be on using these technologies in an interface with clinicians that emphasizes the value each brings to clinical decision-making.

Evaluating ChatGPT as an Agent for Providing Genetic Education.

Genetic disorders are complex and can greatly impact an individual's health and well-being. In this study, we assess the ability of ChatGPT, a language model developed by OpenAI, to answer questions related to three specific genetic disorders: BRCA1, MLH1, and HFE. ChatGPT has shown it can supply articulate answers to a wide spectrum of questions. However, its ability to answer questions related to genetic disorders has yet to be evaluated. The aim of this study is to perform both quantitative and qualitative assessments of ChatGPT's performance in this area. The ability of ChatGPT to provide accurate and useful information to patients was assessed by genetic experts. Here we show that ChatGPT answered 64.7% of the 68 genetic questions asked and was able to respond coherently to complex questions related to the three genes/conditions. Our results reveal that ChatGPT can provide valuable information to individuals seeking information about genetic disorders, however, it still has some limitations and inaccuracies, particularly in understanding human inheritance patterns. The results of this study have implications for both genomics and medicine and can inform future developments in this area. AI platforms, like ChatGPT, have significant potential in the field of genomics. As these technologies become integrated into consumer-facing products, appropriate oversight is required to ensure accurate and safe delivery of medical information. With such oversight and training specifically for genetic information, these platforms could have the potential to augment some clinical interactions.

The ACTIVATE Digital Health Pilot Program for Diabetes and Hypertension in an Underserved and Rural Community.

BACKGROUND: Community health centers and patients in rural and agricultural communities struggle to address diabetes and hypertension in the face of health disparities and technology barriers. The stark reality of these digital health disparities were highlighted during the coronavirus disease 2019 pandemic. OBJECTIVES: The objective of the ACTIVATE (Accountability, Coordination, and Telehealth in the Valley to Achieve Transformation and Equity) project was to codesign a platform for remote patient monitoring and program for chronic illness management that would address these disparities and offer a solution that fit the needs and context of the community. METHODS: ACTIVATE was a digital health intervention implemented in three phases: community codesign, feasibility assessment, and a pilot phase. Pre- and postintervention outcomes included regularly collected hemoglobin A1c (A1c) for participants with diabetes and blood pressure for those with hypertension. RESULTS: Participants were adult patients with uncontrolled diabetes and/or hypertension (n = 50). Most were White and Hispanic or Latino (84%) with Spanish as a primary language (69%), and the mean age was 55. There was substantial adoption and use of the technology: over 10,000 glucose and blood pressure measures were transmitted using connected remote monitoring devices over a 6-month period. Participants with diabetes achieved a mean reduction in A1c of 3.28 percentage points (standard deviation [SD]: 2.81) at 3 months and 4.19 percentage points (SD: 2.69) at 6 months. The vast majority of patients achieved an A1c in the target range for control (7.0-8.0%). Participants with hypertension achieved reductions in systolic blood pressure of 14.81 mm Hg (SD: 21.40) at 3 months and 13.55 mm Hg (SD: 23.31) at 6 months, with smaller reductions in diastolic blood pressure. The majority of participants also reached target blood pressure (less than 130/80). CONCLUSION: The ACTIVATE pilot demonstrated that a codesigned solution for remote patient monitoring and chronic illness management delivered by community health centers can overcome digital divide barriers and show positive health outcomes for rural and agricultural residents.

Predictions, Pivots, and a Pandemic: a Review of 2020's Top Translational Bioinformatics Publications.

OBJECTIVES: Provide an overview of the emerging themes and notable papers which were published in 2020 in the field of Bioinformatics and Translational Informatics (BTI) for the International Medical Informatics Association Yearbook. METHODS: A team of 16 individuals scanned the literature from the past year. Using a scoring rubric, papers were evaluated on their novelty, importance, and objective quality. 1,224 Medical Subject Headings (MeSH) terms extracted from these papers were used to identify themes and research focuses. The authors then used the scoring results to select notable papers and trends presented in this manuscript. RESULTS: The search phase identified 263 potential papers and central themes of coronavirus disease 2019 (COVID-19), machine learning, and bioinformatics were examined in greater detail. CONCLUSIONS: When addressing a once in a centruy pandemic, scientists worldwide answered the call, with informaticians playing a critical role. Productivity and innovations reached new heights in both TBI and science, but significant research gaps remain.

Legal Challenges in Precision Medicine: What Duties Arising From Genetic and Genomic Testing Does a Physician Owe to Patients?

Precision medicine is increasingly incorporated into clinical practice via three primary data conduits: environmental, lifestyle, and genetic data. In this manuscript we take a closer look at the genetic tier of precision medicine. The volume and variety of data provides a more robust picture of health for individual patients and patient populations. However, this increased data may also have an adverse effect by muddling our understanding without the proper pedagogical tools. Patient genomic data can be challenging to work with. Physicians may encounter genetic results which are not fully understood. Genetic tests may also lead to the quandary of linking patients with diseases or disorders where there are no known treatments. Thus, physicians face a unique challenge of establishing the proper scope of their duty to patients when dealing with genomic data. Some of those scope of practice boundaries have been established as a result of litigation, while others remain an open question. In this paper, we map out some of the legal challenges facing the genomic component of precision medicine, both established and some questions requiring additional guidance. If physicians begin to perceive genomic data as falling short in overall benefit to their patients, it may detrimentally impact precision medicine as a whole. Helping to develop guidance for physicians working with patient genomic data can help avoid this fate of faltering confidence.

Current Approaches and Trends in Graduate Public Health Informatics Education in the United States: Four Case Studies from the Field.

Background:Public Health Informatics (PHI) has taken on new importance in recent years as health and well-being face a number of challenges, including environmental disasters, emerging infectious diseases, such as Zika, Ebola and SARS-CoV-2, the growing impact of the Influenza virus, the opioid epidemic, and social determinants of health. Understanding the relationship between climate change and the health of populations adds further complexity to global health issues. Objectives: To describe four examples of curricula that exist in U.S. based graduate-level public and population health informatics training programs. Methods: Biomedical informatics educators are challenged to provide learners with relevant, interesting, and meaningful educational experiences in working with and learning from the many data sources that comprise the domain of PHI. Programs at four institutions were reviewed to examine common teaching practices that stimulate learners to explore the field of public health informatics. Results: Four case studies represent a range of pedagogical approaches to meeting the requirements of three established accreditation/certification agencies relevant to PHI education. Despite their differences, each program achieved the established learning objectives along with a substantive record of student learning achievements. Conclusion: The overarching goal of empowering learners to serve an active and dynamic role in enhancing preventive measures, informing policy, improving personal health behaviors, and clarifying issues such as quality, cost of care, and the social determinants of health, are essential components of PHI education and training, and must receive additional consideration now and in the future by educators, policy makers, administrators, and government officials.

Are providers prepared for genomic medicine: interpretation of Direct-to-Consumer genetic testing (DTC-GT) results and genetic self-efficacy by medical professionals.

BACKGROUND: Precision medicine is set to deliver a rich new data set of genomic information. However, the number of certified specialists in the United States is small, with only 4244 genetic counselors and 1302 clinical geneticists. We conducted a national survey of 264 medical professionals to evaluate how they interpret genetic test results, determine their confidence and self-efficacy of interpreting genetic test results with patients, and capture their opinions and experiences with direct-to-consumer genetic tests (DTC-GT). METHODS: Participants were grouped into two categories, genetic specialists (genetic counselors and clinical geneticists) and medical providers (primary care, internists, physicians assistants, advanced nurse practitioners, etc.). The survey (full instrument can be found in the Additional file 1) presented three genetic test report scenarios for interpretation: a genetic risk for diabetes, genomic sequencing for symptoms report implicating a potential HMN7B: distal hereditary motor neuropathy VIIB diagnosis, and a statin-induced myopathy risk. Participants were also asked about their opinions on DTC-GT results and rank their own perceived level of preparedness to review genetic test results with patients. RESULTS: The rates of correctly interpreting results were relatively high (74.4% for the providers compared to the specialist's 83.4%) and age, prior genetic test consultation experience, and level of trust assigned to the reports were associated with higher correct interpretation rates. The self-selected efficacy and the level of preparedness to consult on a patient's genetic results were higher for the specialists than the provider group. CONCLUSION: Specialists remain the best group to assist patients with DTC-GT, however, primary care providers may still provide accurate interpretation of test results when specialists are unavailable.

A Decade of Translational Bioinformatics: A Retrospective Analysis of "Year-in-Review" Presentations.

For the past 11 years, the year-in-review (YIR) keynote presentation at the AMIA Informatics summit has been a perennial highlight. We hypothesized that the presented material from these keynotes could be used to assess both the recent trajectory of topics in informatics-especially translational bioinformatics (TBI)-as well as the scientific merit of the crowd-sourced process used to nominate, review, and select the papers presented at the YIR. We compare YIR articles to a background set of non-YIR articles from informatics journals using structured metadata and qualitative thematic analysis, paying specific attention to trends and popularity over time. These trends were inspected both internally (comparing the YIR sessions to each other) and externally (comparing them to the overall content of scientific literature for the same time period). In doing so, we identified some unexpected patterns that suggest important opportunities for TBI research in the future.

Improving the Odds of Success for Precision Medicine Using the Social Ecological Model.

The concept of precision medicine aims to provide additional context to patient data for healthcare providers A decade after the HITECH act of 2009, the state of EHRs can be considered a mixed bag. Increased levels of physician burnout have been attributed to the impact EHRs have had on traditional patient and provider interactions. In order for precision medicine to be allowed to establish a foothold, it must demonstrate the ability to improve clinical outcomes. One path to achieving this is by improving health behavior, which is a difficult task. In this paper, the case is presented for using the social ecological model to help shift health behaviors with precision medicine.

Developing a concussion assessment mHealth app for certified Athletic Trainers.

Annually, 1.6-3.8 million concussions occur from sports in the United States, which account for 5-9% of all sports injuries. The dangers of concussions include prolonged post-concussive symptoms, increased risk of subsequent concussions, seizures, mental health issues, and in cases of second-impact syndrome (SIS), possible death. Certified Athletic Trainers (ATC) continue to serve an important role in providing assessment and treatments for athletes with sports-related injuries. They provide a critical safety net due to limited knowledge and misconceptions of concussion held by some youth sports coaches and athletes. However, availability of services from ATCs in rural areas is a challenge. In order to help extend coverage to more rural student athletes, we propose designing a telemedicine app following the mHealth development roadmap from the Center for eHealth Research (CeHRes). In this paper we will document contextual inquiry, user requirements capture, design phases, and app evaluation from the targeted user base.

Comprehension and Data-Sharing Behavior of Direct-To-Consumer Genetic Test Customers.

AIM: The aim of this study was to evaluate current direct-to-consumer (DTC) genetic customers' ability to interpret and comprehend test results and to determine if honest brokers are needed. METHOD: One hundred and twenty-two customers of the DTC genetic testing company 23andMe were polled in an online survey. The subjects were asked about their personal test results and to interpret the results of two mock test cases (type 2 diabetes and multiple sclerosis), where results were translated into disease probability for an individual compared to the public. RESULTS: When asked to evaluate the risk, 72.1% correctly assessed the first case and 77% were correct on the second case. Only 23.8% of those surveyed were able to interpret both cases correctly. x03C7;2 and logistic regression were used to interpret the results. Participants who took the time to read the DTC test-provided supplemental material were 3.93 times (p = 0.040) more likely to correctly interpret the test results than those who did not. The odds for correctly interpreting the test cases were 3.289 times (p = 0.011) higher for those who made more than USD 50,000 than those who made less. Survey results were compared to the Health Information National Trends Survey (HINTS) phase 4 cycle 3 data to evaluate national trends. CONCLUSIONS: Most of the subjects were able to correctly interpret the test cases, yet a majority did not share their results with a health-care professional. As the market for DTC genetic testing grows, test comprehension will become more critical. Involving more health professionals in this process may be necessary to ensure proper interpretations.