BACKGROUND: This study aims to determine the satisfaction and future training needs of general practice residents participating in a novel model of ambulatory teaching aligned with the specifications for standardized residency training in outpatient management issued by the Chinese Medical Doctor Association (CMDA).
METHODS: A cross-sectional survey of the satisfaction and training needs was conducted among general practice residents at West China Hospital, Sichuan University. Patient characteristics and preceptors\' feedback on the residents\' performance were also analyzed.
RESULTS: The study involved 109 residents (30.28% men) and 161 patients (34.78% men; age: 52.63 ± 15.87 years). Residents reported an overall satisfaction score of 4.28 ± 0.62 with the ambulatory teaching program. Notably, residents scored lower in the Subjective-Objective-Assessment-Plan (SOAP) evaluation when encountering patients with the greater the number of medical problems (P < 0.001). Residents encountering patients with a shorter duration of illness (< 3 months) achieved higher scores than those with longer illness durations (≥ 3 months, P = 0.044). Residency general practitioners (GPs) were most challenged by applying appropriate and effective patient referrals (43/109; 39.45%). GPs expressed a strong desire to learn how to make decisions when facing challenging patient situations (4.51 ± 0.63).
CONCLUSIONS: This study suggests selecting patients with multiple comorbidities for ambulatory teaching and enhancing training on practical problem-solving abilities for GPs. The findings provide insights for the development of future ambulatory teaching programs.

OBJECTIVE: To assess the influence of supply and demand factors on the contract behavior of occupational populations with general practitioner (GP) teams.
METHODS: We employed a system dynamics approach to assess and predict the effect of the general practitioner service package (GPSP) and complementary incentive policies on the contract rate for 2015-2030. First, the GPSP is designed to address the unique needs of occupational populations, enhancing the attractiveness of GP contracting services, including three personalized service contents tailored to demand-side considerations: work-related disease prevention (WDP), health education & counseling (HEC), and health-care service (HCS). Second, the complementary incentive policies on the supply-side included income incentives (II), job title promotion (JTP), and education & training (ET). Considering the team collaboration, the income distribution ratio (IDR) was also incorporated into supply-side factors.
RESULTS: The contract rate is predicted to increase to 57.8% by 2030 after the GPSP intervention, representing a 15.4% increase on the non-intervention scenario. WDP and HEC have a slightly higher (by 2%) impact on the contract rate than that from HCS. Regarding the supply-side policies, II have a more significant impact on the contract rate than JTP and ET by 3-5%. The maximum predicted contract rate of 75.2% is expected by 2030 when the IDR is 0.5, i.e., the GP receives 50% of the contract income and other members share 50%.
CONCLUSIONS: The GP service package favorably increased the contract rate among occupational population, particularly after integrating the incentive policies. Specifically, for a given demand level, the targeted content of the package enhanced the attractiveness of contract services. On the supply side, the incentive policies boost GPs\' motivation, and the income distribution motivated other team members.

BACKGROUND: Hypertension is one of the most common chronic diseases with a low control rate globally. The effect of communication skills training contributing to hypertension control remains uncertain. The aim of the present study was to assess the effectiveness of an educational intervention based on the Calgary-Cambridge guide in improving hypertensive management.
METHODS: A cluster randomized controlled trial enrolled 27 general practitioners (GPs) and 540 uncontrolled hypertensive patients attending 6 community health centers in Chengdu, China. GPs allocated to the intervention group were trained by an online communication course and two face-to-face workshops based on Calgary-Cambridge guides. The primary outcome was blood pressure (BP) control rates and reductions in systolic and diastolic BP from baseline to 3 months. The secondary outcome was changes in GPs\' communication skills after one month, patients\' knowledge and satisfaction after 3 months. Bivariate analysis and the regression model assessed whether the health provider training improved outcomes.
RESULTS: After the communication training, the BP control rate was significantly higher (57.2% vs. 37.4%, p < 0.001) in the intervention groups. Compared to the control group, there was a significant improvement in GP\'s communication skills (13.0 vs 17.5, p < 0.001), hypertensive patients\' knowledge (18.0 vs 20.0, p < 0.001), and systolic blood pressure (139.1 vs 134.7, p < 0.001) after 3 months of follow-up. Random effects least squares regression models showed significant interactions between the intervention group and time period in the change of GP\'s communication skills (Parameter Estimated (PE): 0.612, CI:0.310,0.907, p = 0.006), hypertensive patient\'s knowledge (PE:0.233, CI: 0.098, 0.514, p < 0.001), satisfaction (PE:0.495, CI: 0.116, 0.706, p = 0.004), SBP (PE:-0.803, CI: -1.327, -0.389, p < 0.001) and DBP (PE:-0.918, CI: -1.694, -0.634, p < 0.001), from baseline to follow-up.
CONCLUSIONS: Communication training based on the Calgary-Cambridge guide for GPs has shown to be an efficient way in the short term to improve patient-provider communication skills and hypertension outcomes among patients with uncontrolled BPs.
BACKGROUND: The trial was registered on Chinese Clinical Trials Registry on 2019-04-03. (ChiCTR1900022278).

General practice teaching clinics play a crucial role in the training of general practitioners, as they are more likely to enhance reception skills compared to traditional training methods. The quality of teaching clinics is largely determined by the level of patient acceptance. In recent years, the Kano model has become increasingly popular in the healthcare industry and has been used to enhance patient satisfaction. The objective of this study is to apply the Kano model to investigate the needs of patients in general practice teaching clinics and to rank the significance of each demand. This study will serve as a reference for enhancing the service quality of teaching clinics and advancing the field of general practice.
A total of 101 patients of general practice at the Affiliated Hospital of Yangzhou University in Jiangsu province were selected using a random convenience sampling method to participate in a questionnaire survey. The questionnaire was designed by members of our team and was based on the Kano model. The study defined the service demand, assessed the impact of both satisfaction and dissatisfaction and created a matrix bubble diagram.
The study findings revealed that out of the 14 items of the general practice teaching clinic service demands, 1 item was categorized as a must-be requirement, 4 items were categorized as one-dimensional requirements, 2 items were categorized as an attractive requirement, 2 items were categorized as an indifferent requirement, and 5 items were categorized as mixed attributes. The findings of the matrix analysis showed that 4 items were situated in the area of one-dimensional attributes quadrant, 3 items were situated in the area of attractive attributes quadrant, 5 items were situated in the area of indifferent attributes quadrant, and 2 items were situated in the area of must-be attributes quadrant.
The patients of general practice have positive attitudes toward teaching clinics. The findings can offer valuable insights for enhancing the quality of service and patient experience in general practice teaching clinics as well as for advancing the field of general practice.

General practitioners are supposed to be better diagnostics to detect patients with serious diseases earlier, and conduct early interventions and appropriate referrals of patients. However, in the current general practice, primary general practitioners lack sufficient clinical experiences, and the correct rate of general disease diagnosis is low. To assist general practitioners in diagnosis, this paper proposes a multi-label hierarchical classification method based on graph neural network, which integrates medical knowledge and electronic health record (EHR) data to build a disease prediction model. The experimental results based on data consist of 231,783 visits from EHR show that the proposed model outperforms all baseline models in the general disease prediction task with a top-3 recall of 0.865. The interpretable results of the model can effectively help clinicians understand the basis of the model\'s decision-making.

BACKGROUND: The new Scottish GP contract commenced in April 2018 with a stated aim of mitigating health inequalities.
OBJECTIVE: To determine the health characteristics and experiences of patients consulting GPs in deprived urban (DU), affluent urban (AU), and remote and rural (RR) areas of Scotland.
METHODS: In 2022, a postal survey of a random sample of adult patients from 12 practices who had consulted a GP within the previous 30 days was undertaken.
METHODS: Patient characteristics and consultation experiences in the three areas (DU, AU, RR) were evaluated using validated measures including the Consultation and Relational Empathy (CARE) Measure and Patient Enablement Instrument (PEI).
RESULTS: In total, 1053 responses were received. In DU areas, multimorbidity was more common (78% versus 58% AU versus 68% RR, P<0.01), complex presentations (where the consultation addressed both psychosocial and physical problems) were more likely (16% versus 10% AU versus 11% RR, P<0.05), and more consultations were conducted by telephone (42% versus 31% AU versus 31% RR, P<0.01). Patients in DU areas reported lower satisfaction (82% DU completely, very, or fairly satisfied versus 90% AU versus 86% RR, P<0.01), lower perceived GP empathy (mean CARE score 38.9 versus 42.1 AU versus 40.1 RR, P<0.05), lower enablement (mean PEI score 2.6 versus 3.2 AU versus 2.8 RR, P<0.01), and less symptom improvement (P<0.01) than those in AU or RR areas. Face-to-face consultations were associated with significantly higher satisfaction, enablement, and perceived GP empathy than telephone consultations in RR areas (all P<0.05).
CONCLUSIONS: Four years after the start of the new GP contract in Scotland, patients\' experiences of GP consultations suggest that the inverse care law persists.

Diagnostic errors have become the biggest threat to the safety of patients in primary health care. General practitioners, as the \"gatekeepers\" of primary health care, have a responsibility to accurately diagnose patients. However, many general practitioners have insufficient knowledge and clinical experience in some diseases. Clinical decision making tools need to be developed to effectively improve the diagnostic process in primary health care. The long-tailed class distributions of medical datasets are challenging for many popular decision making models based on deep learning, which have difficulty predicting few-shot diseases. Meta-learning is a new strategy for solving few-shot problems.
In this study, a few-shot disease diagnosis decision making model based on a model-agnostic meta-learning algorithm (FSDD-MAML) is proposed. The MAML algorithm is applied in a knowledge graph-based disease diagnosis model to find the optimal model parameters. Moreover, FSDD-MAML can learn learning rates for all modules of the knowledge graph-based disease diagnosis model. For n-way, k-shot learning tasks, the inner loop of FSDD-MAML performs multiple gradient update steps to learn internal features in disease classification tasks using n×k examples, and the outer loop of FSDD-MAML optimizes the meta-objective to find the associated optimal parameters and learning rates. FSDD-MAML is compared with the original knowledge graph-based disease diagnosis model and other meta-learning algorithms based on an abdominal disease dataset.
Meta-learning algorithms can greatly improve the performance of models in top-1 evaluation compared with top-3, top-5, and top-10 evaluations. The proposed decision making model FSDD-MAML outperforms all the other models, with a precision@1 of 90.02 %. We achieve state-of-the-art performance in the diagnosis of all diseases, and the prediction performance for few-shot diseases is greatly improved. For the two groups with the fewest examples of diseases, FSDD-MAML achieves relative increases in precision@1 of 29.13 % and 21.63 % compared with the original knowledge graph-based disease diagnosis model. In addition, we analyze the reasoning process of several few-shot disease predictions and provide an explanation for the results.
The decision making model based on meta-learning proposed in this paper can support the rapid diagnosis of diseases in general practice and is especially capable of helping general practitioners diagnose few-shot diseases. This study is of profound significance for the exploration and application of meta-learning to few-shot disease assessment in general practice.

暂无摘要。

Direct-to-consumer (DTC) health care artificial intelligence (AI) apps hold the potential to bridge the spatial and temporal disparities in health care resources, but they also come with individual and societal risks due to AI errors. Furthermore, the manner in which consumers interact directly with health care AI is reshaping traditional physician-patient relationships. However, the academic community lacks a systematic comprehension of the research overview for such apps.
This paper systematically delineated and analyzed the characteristics of included studies, identified existing barriers and design recommendations for DTC health care AI apps mentioned in the literature and also provided a reference for future design and development.
This scoping review followed the Preferred Reporting Items for Systematic Reviews and Meta-Analyses Extension for Scoping Reviews guidelines and was conducted according to Arksey and O\'Malley\'s 5-stage framework. Peer-reviewed papers on DTC health care AI apps published until March 27, 2023, in Web of Science, Scopus, the ACM Digital Library, IEEE Xplore, PubMed, and Google Scholar were included. The papers were analyzed using Braun and Clarke\'s reflective thematic analysis approach.
Of the 2898 papers retrieved, 32 (1.1%) covering this emerging field were included. The included papers were recently published (2018-2023), and most (23/32, 72%) were from developed countries. The medical field was mostly general practice (8/32, 25%). In terms of users and functionalities, some apps were designed solely for single-consumer groups (24/32, 75%), offering disease diagnosis (14/32, 44%), health self-management (8/32, 25%), and health care information inquiry (4/32, 13%). Other apps connected to physicians (5/32, 16%), family members (1/32, 3%), nursing staff (1/32, 3%), and health care departments (2/32, 6%), generally to alert these groups to abnormal conditions of consumer users. In addition, 8 barriers and 6 design recommendations related to DTC health care AI apps were identified. Some more subtle obstacles that are particularly worth noting and corresponding design recommendations in consumer-facing health care AI systems, including enhancing human-centered explainability, establishing calibrated trust and addressing overtrust, demonstrating empathy in AI, improving the specialization of consumer-grade products, and expanding the diversity of the test population, were further discussed.
The booming DTC health care AI apps present both risks and opportunities, which highlights the need to explore their current status. This paper systematically summarized and sorted the characteristics of the included studies, identified existing barriers faced by, and made future design recommendations for such apps. To the best of our knowledge, this is the first study to systematically summarize and categorize academic research on these apps. Future studies conducting the design and development of such systems could refer to the results of this study, which is crucial to improve the health care services provided by DTC health care AI apps.

Practice-based research networks (PBRNs) have been recognized as essential laboratories and mechanisms for developing primary care research. This scoping review aims to examine and map the features and development trends of productivity, research categories, and methods in original primary care research conducted by global PBRNs between 1991 and 2023.
We have assembled an interdisciplinary team that will undertake this scoping review, following the framework developed by Arksey and O\'Malley. Targeted literature includes original primary care research conducted by PBRNs, published from January 1, 1991, to December 31, 2023. An integrated search strategy will gather publications from 3 electronic databases (PubMed, Web of Science, and Embase), 16 major primary health care journals, and 364 relevant organizations. Two experienced researchers will independently screen the titles, keywords, and abstracts of all references and extract data regarding eight key elements. Disagreements between the reviewers will be resolved through group discussions, moderated by a third reviewer. Articles to be included will (1) be conducted in the primary care context, (2) be led by PBRNs, (3) provide a full report of original research, and (4) be published in a peer-reviewed journal between the aforementioned dates in any language. Exclusions encompass reviews, letters, commentaries, case reports, and conference papers. Final data will be displayed using tables and charts according to different conceptual categories.
This scoping review is one of the initial attempts to delineate the development trends and features of primary care research conducted by PBRNs. This study will provide reference information for researchers in countries/regions that are building their research infrastructure and capacity in general practice, family medicine, and primary care.
Registered in OSF on July 25, 2022 ( https://osf.io/zgv9c ).