Screening/diagnosis of pediatric endocrine disorders through the artificial intelligence model in different language settings

This study is aimed at examining the impact of ChatGPT on pediatric endocrine and metabolic conditions, particularly in the areas of screening and diagnosis, in both Chinese and English modes. A 40-question questionnaire covering the four most common pediatric endocrine and metabolic conditions was posed to ChatGPT in both Chinese and English three times each. Six pediatric endocrinologists evaluated the responses. ChatGPT performed better when responding to questions in English, with an unreliable rate of 7.5% compared to 27.5% for Chinese questions, indicating a more consistent response pattern in English. Among the reliable questions, the answers were more comprehensive and satisfactory in the English mode. We also found disparities in ChatGPT's performance when interacting with different target groups and diseases, with improved performance for questions posed by clinicians in English and better performance for questions related to diabetes and overweight/obesity in Chinese for both clinicians and patients. Language comprehension, providing incomprehensive answers, and errors in key data were the main contributors to the low scores, according to reviewer feedback.

CONCLUSION

Despite these limitations, as ChatGPT continues to evolve and expand its network, it has significant potential as a practical and effective tool for clinical diagnosis and treatment.

WHAT IS KNOWN

• The deep learning-based large-language model ChatGPT holds great promise for improving clinical practice for both physicians and patients and has the potential to increase the speed and accuracy of disease screening and diagnosis, as well as enhance the overall efficiency of the medical process. However, the reliability and appropriateness of AI model responses in specific field remains unclear. • This study focused on the reliability and appropriateness of AI model responses to straightforward and fundamental questions related to the four most prevalent pediatric endocrine and metabolic disorders, for both healthcare providers and patients, in different language scenarios.

WHAT IS NEW

• The AI model performed better when responding to questions in English, with more consistent, as well as more comprehensive and satisfactory responses. In addition, we also found disparities in ChatGPT's performance when interacting with different target groups and different diseases. • Despite these limitations, as ChatGPT continues to evolve and expand its network, it has significant potential as a practical and effective tool for clinical diagnosis and treatment.

Pregnant women's attitudes and decision-making regarding prenatal Down syndrome screening and diagnosis: scale development and validation

Background

Down syndrome is a common chromosomal abnormality and prenatal screening can inform parents of the risk of their baby having Down syndrome. Little research has examined how decisions regarding both Down syndrome screening as well as diagnosis are made among women who are currently pregnant and how their decisions are influenced by their social contexts, specifically family and social media, using mixed methods. The study was to test the validity and reliability of a scale that measures pregnant women’s attitudes and decision-making concerning prenatal Down syndrome screening and diagnosis in urban areas of Taiwan.

Methods

We developed an item pool based on a literature review and in-depth interviews with 30 pregnant women recruited at two district hospitals in urban areas. The item pool was reviewed by a panel of experts and then administered to 300 women who had been pregnant for less than 24 weeks and had not received the Down syndrome screening tests. We used item analysis and exploratory factor analysis to validate the scale and test its reliability.

Results

The initial item pool had 54 items. After the expert review, three items were deleted. After the item analysis, 16 additional items were deleted. Exploratory factor analysis of the remaining items revealed four factors labeled – “Attitudes towards Down syndrome and Screening Tests,” “Important others’ Attitudes towards Down Syndrome,” “Influence of Important Others on Decision-Making,” and “Influence of Social Media on Decision-Making” – and 16 of the remaining items had satisfactory loadings on those factors, explaining 72.0% of the total variance. The Cronbach’s α values of the dimensions ranged between 0.75 and 0.90, demonstrating satisfactory internal reliability.

Conclusions

The scale has satisfactory validity and reliability, and can be used to understand pregnant women’s attitudes and decision-making regarding Down syndrome screening and diagnosis, and to help design tailored consultations for pregnant women in clinical settings.

Rural stakeholder perceptions about cognitive screening

Objectives: The study aims were to explore stakeholder perceptions about cognitive screening in a rural, ethnically diverse, underserved setting, and to examine whether perceptions varied by years lived in a rural area, career, health literacy, willingness to be screened, ethnicity, education, or age. Methods: Twenty-one rural, ethnically diverse stakeholders completed an open-ended interview of five questions and a measure regarding perceptions about cognitive screening (PRISM-PC, Boustani, et al., 2008 ). Open coding using the in vivo process (Saldaña, 2015 ) to "derive codes from the actual participant language" (p. 77) was used to analyze the qualitative data. We used Pearson correlation to examine relationships between the PRISM-PC and sociodemographics including age, years of education, health literacy, years lived in rural areas, and willingness to participate in cognitive screening. Results: Eight codes and two themes were identified from the in vivo analysis. The eight codes were "a sentence being pronounced over the lives", "keep everybody at home", "Education is big", the trust issues is everything here", "identify support systems", "access to care", and "there is a cost to do that". The two themes were "Trust is the essential component of connecting with Community", and (2) "The Community recognizes the importance of knowledge in improving care. PRISM-PC results added new information in that persons were concerned about the emotional and financial burden on their families. Overall, regardless of age, careers, care involvement, health literacy, or education, 81% of stakeholders indicated they would seek annual cognitive screening. Discussion: It is important for rural health professionals to consider that contrary to previous stigma concerns, stakeholders may support earlier dementia detection.

Delirium clinical motor subtypes: a narrative review of the literature and insights from neurobiology

INTRODUCTION

Clinical motor subtypes have been long recognised in delirium and, despite a growing body of research, a lack of clarity exists regarding the importance of these motor subtypes. The aims of this review are to (1) examine how the concept of motor subtypes has evolved, (2) explore their relationship to the clinical context, (3) discuss the relationship between the phenomenology of delirium and motor activity, (4) discuss the application of neurobiology to the theory of delirium motor subtypes, and (5) identify methodological issues and provide solutions for further studies.

METHODS

The following databases were searched: PubMed, PsychInfo, EBSCO, Medline, BioMed central and Science Direct. Inclusion criteria specified peer-reviewed research assessing delirium motor subtypes published between 1990 and 2016.

RESULTS

Sixty-one studies met the inclusion criteria. The majority of studies (n = 50) were found to use validated psychometric tools, while the remainder (n = 11) used clinical criteria. The majority of studies (n = 45) were conducted in the medical setting, while the remainder were in the ICU/post-operative setting (n = 17).

CONCLUSION

Although host sensitivities (e.g. frailty) and exogenous factors (e.g. medication exposure) may determine the type of motor disturbance, it remains unclear to what extent motor subtypes are influenced by other features of delirium. The use of more specialised tools (e.g. delirium motor subtyping scale), may enable researchers to develop an approach to delirium that has a greater nosological consistency. Future studies investigating delirium motor subtypes may benefit from enhanced theoretical considerations of the dysfunctional neural substrate of the delirious state.

Assessment of gastroesophageal reflux disease by serodiagnosis of Helicobacter pylori-related chronic gastritis stage

AIM: To evaluate the association of Helicobacter pylori (H.pylori)-related chronic gastritis stage with upper gastrointestinal symptoms and gastroesophageal reflux disease (GERD).

METHODS: Subjects underwent upper gastrointestinal endoscopy, a questionnaire using a frequency scale for symptoms of GERD (FSSG), and measurements of serum H.pylori-antibody and pepsinogen (PG) levels. They were classified into the following 4 groups in terms of H.pylori-related chronic gastritis stage: Group A (n = 219), H.pylori(-)PG(-); Group B (n = 310), H.pylori(+)PG(-); Group C (n = 279), H.pylori(+)PG(+); and Group D (n = 17), H.pylori(-)PG(+).

RESULTS: Reflux esophagitis occurred in 30.6% of Group A, 14.5% of Group B, 6.8% of Group C, and 0% of Group D (P < 0.001). Scores for acid reflux symptoms decreased significantly with chronic gastritis stage (from Group A to D) (P < 0.05), while scores for dysmotility symptoms did not differ significantly. The prevalence of non-erosive reflux disease (NERD) did not differ among groups. However, in subjects with GERD, the prevalence of NERD tended to increase with chronic gastritis stage (P = 0.081).

CONCLUSION: Acid reflux symptoms and the prevalence of reflux esophagitis can be assessed by measuring both serum H.pylori-antibody and PG levels.