JMIR Formative Research最新文献

This formative research explored health science researchers' perspectives on the development of an artificial intelligence-based virtual study assistant and identified 8 potential features and their priorities.

Background: Case formulation (CF) is a core skill for therapists; however, creating high-quality CF requires considerable time.

Objective: This study demonstrates that providing a knowledge graph based on the meta-analytic literature can enhance CF quality.

Methods: Five groups were established, including four large language model (LLM) groups and one human expert group, each generating 25 CFs based on 25 vignettes. The Control group with Claude Sonnet 3.7 produced 25 CFs. The Personalization group served as the control group with additional personalization prompts. The Knowledge Graph group employed an LLM that generated 25 CFs, which was provided with a meta-analysis Knowledge Graph. Further incorporation of additional personalization prompts then comprised the Knowledge Graph with Personalization group. Finally, the Expert Group consisted of 25 CFs generated by a human expert. These 125 CFs in total were evaluated for general quality (i.e., correctness, completeness, feasibility, and consistency) using a 7-point scale and 18 essential elements with binary scores (0 or 1) by another human expert. The CFs were also qualitatively analyzed.

Results: The Knowledge Graph and Knowledge Graph with Personalization groups scored significantly higher than the control group in terms of correctness, completeness, and feasibility. The Expert group scored significantly higher on consistency than the machine-generated groups. Additionally, there was no significant difference in the feasibility scores between the Knowledge Graph, Knowledge Graph with Personalization, and expert groups. The qualitative evaluation suggested that human CFs narrow the text to content that is easy for the client to read, whereas machine CFs are more likely to include expressions that are unnatural to the client.

Conclusions: These results indicate that providing knowledge graphs to novice therapists increases the correctness, completeness, and feasibility of CF. Providing experienced therapists with knowledge graphs is suggested to improve the quality of their CF and mental health services.

Clinicaltrial: None.

Background: The Swedish National Board of Health and Welfare recently updated the national guidelines for at-risk consumption of alcohol. Nearly 30% of the Swedish population now falls under the at-risk category and should be provided with support.

Objective: This project aims to identify and evaluate efficient, scalable tools to support individuals with risk-prone alcohol consumption. The project seeks to explore innovative, accessible technologies that could be implemented in large-scale public health interventions.

Methods: A pilot-scale clinical study was conducted to assess the feasibility of using emerging technologies for this purpose. Eight healthy volunteers participated in controlled alcohol consumption while being monitored through 2 methods: an eye-scanning tool integrated into a standard mobile phone and saliva sampling for biomarkers such as serotonin and orexin.

Results: Eye-scanning parameters began to shift in some participants at approximately 0.4 to 0.5 per mille blood alcohol concentration, particularly in the form of impaired eye convergence. Furthermore, at around 0.5 per mille, participants encountered practical difficulties in managing the eye-scanning app. Salivary biomarkers did not show any clear correlation with alcohol intake, presumably due to the low number of participants. Beyond biological findings, the study also generated important procedural insights for designing a large-scale clinical study.

Conclusions: Eye scanning showed potential as a noninvasive and accessible method for detecting and monitoring moderate alcohol consumption effects, while serotonin and orexin biomarkers were not informative in this context. On the basis of these findings and procedural learnings, eye-scanning tools warrant further investigation in larger clinical studies aimed at developing scalable support for risk-prone alcohol consumption.

Unlabelled: This study uses the 2011-2017 National Health Interview Survey (NHIS) data to demonstrate that sociodemographic factors are associated with transportation delays among individuals with knee osteoarthritis.

Background: In contrast to all previous generations, life today is lived both in-person and online. This creates both opportunities and risks to mental health and well-being. Social interaction is no longer geographically constrained, yet the anonymity and impersonality of social media create new problems. To quote Mike Tyson (July 2020), "Social media have made y'all way too comfortable with disrespecting people and not getting punched in the face for it."

Objective: This study set out to propose and test a hypothesized model to identify both direct and indirect predictors of life satisfaction. Independent or predictor variables included social media use, loneliness, and online and traditional social support.

Methods: From March 2024 to October 2024, a total of 112 adults in the United States were recruited online and proceeded to complete study questionnaires. Participants were aged 42.62 (SD 12.74) years on average, had completed an average of 15.46 (SD 3.25) years of education, and reported an average household income of US $67,005 (SD US $41,560) per year.

Results: Using path analysis, we found that social media use and online social support emerged as significant, indirect predictors of life satisfaction via loneliness and traditional in-person social support (P<.01). In total, 39% of variance in life satisfaction was explained by this path model (R²=0.39; P<.01).

Conclusions: Contrary to hypothesis, these findings support the rich get richer hypothesis regarding online social support, not the social compensation theory, that is, online social support appears to function as an adjunct to in-person support, not as a substitute. The results of this study need to be replicated with more diverse, larger samples, with responses collected over multiple time points.

Background: It is considered advantageous to adopt an interdisciplinary approach when creating serious games in the sphere of health practice. However, different fields have reported that interdisciplinary work is challenging. Yet, the literature is scarce regarding how participants within health research have experienced collaborative research. In 2019 and 2020, total 3 teams collaborated to produce a serious game for children undergoing radiotherapy.

Objective: The aim of this study was to describe the experiences of collaborating within and between teams, during their participation in the development of a serious game about radiotherapy for children.

Methods: A qualitative design was used for gathering data through in depth interviews and a reflective thematic analysis was made. The collaboration included 15 people, 14 of them were asked to participate and 13 accepted. The teams included a game design team, a research team, and an expert team. The latter consisted of a play therapist, a pediatric nurse, and radiation oncology nurses.

Results: In total, 1 main theme and 4 subthemes were formulated. The main theme was a learning experience during the participatory process. The subthemes were: (1) new insights were established due to the collaboration, (2) discovering the mechanisms behind the design elements provided understanding of the game's complexity, (3) collaboration within teams and between teams needs time and takes time, and (4) confidence that the project was going to make a difference created engagement.

Conclusions: In conclusion, knowledge expansion arose on several levels during the time the participants were part of the project. Having time and building trust in team constellations are significant factors in achieving a productive, favorable and beneficial experience for participants. Furthermore, confidence in the usefulness of the end product could be a contributory factor for participants continuing to work and the understanding of the complexity of the evolving process. Based on the findings of the team members' individual experiences, we recommend other medical research teams to consider the following implications for practice before starting interdisciplinary design research: (1) establish who can bridge the fields and act to establish mutual understanding; (2) make time for frequent meetings to update on progress; and (3) be responsive, because when everybody feels connected to what needs to be done and feel safe it gets easier to work together.

Background: Chronic back pain is a severe health condition with underlying biopsychosocial factors that make diagnosis difficult, and pain chronicity has been shown to be an important variable for studying patient outcomes. Due to the absence of standardized criteria, pain chronicity needs to be manually annotated by clinicians in electronic health records (EHRs), which is not only time consuming but also has the potential to introduce variability in analysis and interpretation among practitioners.

Objective: Pain chronicity is not typically recorded in EHRs and currently needs to be manually annotated by experts. Using a dataset from an interdisciplinary spine clinic consisting of 386 patients manually annotated for pain chronicity by clinical experts, this study has two objectives: (1) to examine the relationship between expert-annotated chronicity and social determinant variables present in EHRs and (2) to evaluate the feasibility of extracting pain chronicity from the EHR without expert annotation.

Methods: We used a supervised machine learning model, specifically univariate regression, to examine associations between clinician-annotated pain chronicity values and the structured variables present in EHRs. Next, we trained a random forest model to predict pain chronicity by using both structured and unstructured data extracted by clinical Text Analysis and Knowledge Extraction System, a natural language processing (NLP) tool. The features extracted included clinical keywords; duration of pain reported; and the International Classification of Diseases, Tenth Revision codes. The model was assessed using the Pearson correlation coefficient and mean absolute error (MAE).

Results: The study analyzed 386 patients (mean age 60.2 years, SD 16.1 years and median age 62.0 years, IQR 48.8-72.0 years) from the San Francisco Bay Area, with 62.7% (n=242) identifying as women. Our univariate regression analysis identified structured EHR variables associated with pain chronicity, which include pain severity before the last visit (P=.006), number of imaging orders (P=.006), number of visits to the neurology department (P=.01), and Medi-Cal insurance coverage (P=.03). Our random forest model using structured data showed a strong correlation of 0.887 (P<.001) with an MAE of 18.45 between predicted and observed chronicity, whereas our model that used the NLP tool to extract information from unstructured clinical notes and structured data showed a slightly higher correlation of 0.968 (P<.001) with an MAE of 10.87 between predicted and observed chronicity.

Conclusions: Our study indicates that pain chronicity from EHR data could be used to study more topics on larger datasets in the future without the need for manual annotation and that using NLP tools to automate prediction is feasible.