JMIR Formative Research最新文献

Background: Physicians' perceived compensation satisfaction enhances work enthusiasm, ensures health care system stability, and inspires health care quality. However, few studies have investigated the combined effect of multiple influencing factors on this perception.

Objective: This study investigates the factors influencing Chinese physicians' perceived compensation satisfaction.

Methods: A cross-sectional survey was conducted between April and May 2024 to examine physicians' perceived compensation satisfaction, alongside their sociodemographic characteristics and perceived transparency of compensation schemes. A total of 325 valid responses were obtained, with 163 male and 162 female participants. Qualitative comparative analysis was then employed to identify the factors associated with physicians' perceived compensation satisfaction.

Results: The analysis yielded two models: junior physicians' perceptions and senior physicians' perceptions. For junior physicians, compensation scheme transparency contributed to higher perceived compensation satisfaction, regardless of salary or work hours. For senior physicians, two paths contributed to perceived compensation satisfaction: (1) higher salary and compensation scheme transparency and (2) lower salary and compensation scheme transparency combined with a higher technical rank and fewer work hours.

Conclusions: The determinants of perceived compensation satisfaction showed heterogeneity between junior and senior physicians, which underscores the necessity of formulating tiered, targeted compensation packages to improve their perceived compensation satisfaction.

Background: Despite a 40-year prevalence of HIV, the AIDS epidemic prevails. Effective AIDS treatment requires specialist care and high adherence often hindered by structural issues in care access. Innovative eHealth solutions like treatment-supportive mobile apps can help address these issues. Successful implementation depends on user acceptance. Acceptance can be operationalized as behavioral intention and measured through the Unified Theory of Acceptance and Use of Technology (UTAUT).

Objective: This study examines the acceptance and its influencing factors of treatment-supportive mobile apps among men living with HIV.

Methods: A cross-sectional study was conducted among 172 men living with HIV between September 2021 and April 2024. In addition to the collection of sociodemographic, medical, and eHealth-related data, acceptance and its influencing factors were assessed by applying the UTAUT model. A multiple hierarchical regression analysis was conducted.

Results: High acceptance of treatment-supportive mobile apps in men living with HIV was reported by 45.3% (n=78) of the participants. Significant predictors of acceptance were age (β=-0.27; P<.001); health literacy regarding disease (β=0.11; P<.001); eHealth literacy (β=0.10; P=.001); internet anxiety (β=-0.18; P=.04); and the UTAUT predictors: effort expectancy (β=0.38; P<.001), performance expectancy (β=0.24; P<.001), and social influence (β=0.40; P<.001). The UTAUT model explained 72% of the variance in acceptance.

Conclusions: Since the acceptance of eHealth services is a reliable indicator of the actual usage behavior, the results of this study are a promising basis for the successful implementation of eHealth offerings in the group of men living with HIV.

Unlabelled: This cross-sectional study examined the presence of food stores and availability of fruits and vegetables in food stores with weight among urban public housing residents. While there was no association between average number of fruits or vegetables in food stores and weight, there were positive associations between number of convenience stores and weight and between number of general merchandise stores and weight.

Background: Effective diabetes management requires individualized treatment strategies tailored to patients' clinical characteristics. With recent advances in artificial intelligence, large language models (LLMs) offer new opportunities to enhance clinical decision support, particularly in generating personalized recommendations.

Objective: This study aimed to develop and evaluate an LLM-based outpatient treatment support system for diabetes and examine its potential value in routine clinical decision-making.

Methods: Three compact LLMs (Llama 3.1-8B, Qwen3-8B, and GLM4-9B) were fine-tuned on deidentified outpatient electronic health records using a parameter-efficient low-rank adaptation approach. The optimized models were embedded into a prototype hospital information system via a retrieval-augmented generation framework to generate individualized treatment recommendations, laboratory test suggestions, and medication prompts based on demographic and clinical data.

Results: Among the models evaluated, the fine-tuned GLM4-9B demonstrated the strongest performance, producing clinically reasonable treatment plans and appropriate laboratory test recommendations and medication suggestions. It achieved a mean Bilingual Evaluation Understudy for 4-grams score of 67.93 (SD 2.74) and mean scores of 44.30 (SD 3.91) for Recall-Oriented Understudy for Gisting Evaluation for overlap of unigrams, 27.34 (SD 1.85) for Recall-Oriented Understudy for Gisting Evaluation for overlap of bigrams, and 37.67 (SD 2.88) for Recall-Oriented Understudy for Gisting Evaluation for Longest Common Subsequence.

Conclusions: The fine-tuned GLM4-9B shows strong potential as a clinical decision support tool for personalized diabetes care. It can provide reference recommendations that may improve clinician efficiency and support decision quality. Future work should focus on enhancing medication guidance, expanding data sources, and improving adaptability in cases involving complex comorbidities.

Background: Early detection in primary care could improve pancreatic cancer survival, but diagnosis is often delayed due to the low prevalence of the disease, the nonspecific nature of early symptoms, and the broad range of conditions and volume of consultations managed by general practitioners (GPs). In Australia, improving pancreatic cancer outcomes, including via earlier diagnosis, is a priority being progressed under the National Pancreatic Cancer Roadmap developed by Cancer Australia. Computerized clinical decision support systems (CDSSs) have shown promise in aiding timely cancer diagnosis; however, barriers to adopting CDSS such as mistrust of the recommendations or not being embedded in the clinical workflow remain. Simulation techniques, which offer flexible and cost-effective ways to evaluate digital health interventions, can be used to test CDSS before real-world implementation.

Objective: This study aims to assess the acceptability and feasibility of identifying patients with symptoms associated with pancreatic cancer through a CDSS within a simulated environment.

Methods: We developed a CDSS that interacted with an electronic health record used in general practice to identify patients with symptoms, which may indicate pancreatic cancer (unintended weight loss or new-onset diabetes), in a simulation laboratory for digital interventions. We tested it by inviting GPs (n=11) to use the CDSS, with patient actors simulating specific clinical scenarios. We then interviewed GPs about the interaction to assess the acceptability and feasibility of the CDSS in their clinical practice. We used thematic analysis and 2 relevant frameworks to analyze the data.

Results: GPs found the CDSS easy to use, unobstructive, and effective as a prompt to consider investigations for people with risk factors for pancreatic cancer. However, they expressed concerns about possible overtesting, financial costs, and the potential for anxiety in patients with a very low probability of having cancer.

Conclusions: While GPs found the tool useful and compatible with their workflow, concerns about overtesting, lack of evidence, and cost-effectiveness were identified as barriers. GPs favored a stepwise approach to investigations rather than immediate imaging. Despite the overall acceptability of the tool, additional evidence to underpin clinical recommendations is necessary before implementing a CDSS with these specific recommendations for pancreatic cancer in primary care.

Background: Maternal evaluation during routine antenatal care visits may reduce maternal morbidity and mortality by identifying and addressing issues early on. A health recommender system could help health professionals and pregnant women monitor daily health parameters, provide tailored recommendations, and support timely antenatal care.

Objective: This study aims to qualitatively analyze challenges in the preimplementation of health recommender system for maternal care in Indonesia as perceived by multiple stakeholders, including health care providers, patients, health system managers, government officers, and technology vendors.

Methods: The methodology used a qualitative approach, where qualitative data were obtained from interviews of 37 respondents from multiple stakeholders, consisting of 15 health workers and 15 patients from private and government health care facilities, 4 officers from government health offices, 2 directors of health application vendors, and 1 manager from a private health clinic. These semistructured interview results were analyzed using thematic analysis.

Results: This qualitative study identifies key challenges in implementing a health recommender system for maternal care in Indonesia across the people, process, infrastructure, and policy dimensions. Intercoder reliability for the coding process demonstrated almost perfect agreement (Cohen κ=0.90), supporting the consistency of the coding process. Six major challenges were revealed, mostly regarding skill, accuracy, completeness, timeliness, cost, and standardization. These 6 major challenges were mentioned 96 times, accounting for 64.43% of all codes extracted from the interviews. These findings emphasize the value of user involvement in system design to meet health care professionals' and patients' needs, technical advancements to foster trust and support effective decision-making, as well as enhanced data accuracy, reliable and timely service delivery, cost management, and clear regulatory standards.

Conclusions: This formative, preimplementation qualitative study highlights the importance of involving users in system design and future implementation to meet the needs of health care professionals and patients. Reducing input errors and improving system reliability are critical to building trust and supporting effective point-of-care decision-making and, in later phases, facility-level monitoring as part of public health surveillance. Adherence to regulatory standards and the establishment of standardized guidelines will be key to enabling broader implementation. Further usability, feasibility, and pilot studies are required before any evaluation of effectiveness.

Background: Effective pain management is a cornerstone of cancer palliative care, yet it remains challenging in low- and middle-income countries due to limited resources, regulatory constraints, and a lack of objective tools. While wearable technologies offer promise for augmenting pain-related patient-reported outcomes with physiological data, their usability in palliative settings in low- and middle-income countries is underexplored.

Objective: This study aimed to evaluate the technology usability and implementation feasibility of the NEST (Non-intrusive Devices for Telemedicine) system, a low-cost, smartwatch-based pain monitoring solution for palliative cancer care co-designed with health care staff from a cancer hospital in Ecuador.

Methods: An observational usability study was conducted with 7 patients with cancer receiving palliative care treatment, combining hospital- and home-based monitoring phases. We used a qualitative and quantitative approach to assess the usability of the NEST system and to identify sociotechnical factors affecting feasibility using the NASSS (Nonadoption, Abandonment, Scale-up, Spread, and Sustainability) framework.

Results: Quantitative results showed a strong preference for the smartwatch over the mobile phone for submitting patient-reported outcomes (246/296, 83%), with wear-time adherence of the smartwatch ranging from 36% to 92% of the time. Qualitative feedback from patients and health care staff indicated good usability and perceived clinical value, though technical and organizational challenges, such as charging habits, training needs, and dashboard integration into the daily workflow of health care staff, were noted. As for feasibility, most of the complexity was found in the dynamics of the health condition, while the technology shows clear promising signs of having value to patients and health care staff.

Conclusions: Our findings suggest that the commonly reported usability hurdles of a smartwatch-based sociotechnical health solution are surmountable given fluid communication between stakeholders during all stages of design and deployment. The primary threats to feasibility in our context seem to lie in the highly complex and dynamic environment of palliative cancer care, regulatory ambiguity regarding the use of medical devices, and the workload burden on health care staff.