Large language models (LLMs) such as ChatGPT, Claude, Llama, and Qwen are emerging as transformative technologies for the diagnosis and treatment of various diseases. With their exceptional long-context reasoning capabilities, LLMs are proficient in clinically relevant tasks, particularly in medical text analysis and interactive dialogue. They can enhance diagnostic accuracy by processing vast amounts of patient data and medical literature and have demonstrated their utility in diagnosing common diseases and facilitating the identification of rare diseases by recognizing subtle patterns in symptoms and test results. Building on their image-recognition abilities, multimodal LLMs (MLLMs) show promising potential for diagnosis based on radiography, chest computed tomography (CT), electrocardiography (ECG), and common pathological images. These models can also assist in treatment planning by suggesting evidence-based interventions and improving clinical decision support systems through integrated analysis of patient records. Despite these promising developments, significant challenges persist regarding the use of LLMs in medicine, including concerns regarding algorithmic bias, the potential for hallucinations, and the need for rigorous clinical validation. Ethical considerations also underscore the importance of maintaining the function of supervision in clinical practice. This paper highlights the rapid advancements in research on the diagnostic and therapeutic applications of LLMs across different medical disciplines and emphasizes the importance of policymaking, ethical supervision, and multidisciplinary collaboration in promoting more effective and safer clinical applications of LLMs. Future directions include the integration of proprietary clinical knowledge, the investigation of open-source and customized models, and the evaluation of real-time effects in clinical diagnosis and treatment practices.
Humans ; Large Language Models ; Tomography, X-Ray Computed

Objective:To investigate the current situation and influencing factors of patients′ satisfaction with nursing humanistic care, and to provide reference for improving the quality of such care provided by hospitals.Methods:From July to August 2022, outpatients and inpatients in 30 provinces were selected by multi-stage stratified sampling as the survey objects. A cross-sectional survey was conducted on an online platform, using the general information questionnaire and Chinese version of methodist health care system nurse caring instrument revised by the research group. The latter instrument consists of 12 dimensions. namely care coordination, competence, teaching/learning, emotional support, respect for individuality, physical comfort, availability, helping/trusting relationship, patient/family engagement, physical environment, spiritual environment and outcomes. Descriptive analysis was performed on the data collected by the questionnaires, and independent sample t-test and one-way ANOVA were used to analyze the influencing factors of patient satisfaction. Results:A total of 107 hospitals were selected for questionnaire survey, including 86 tertiary hospitals and 21 secondary hospitals, and 29 108 valid questionnaires were recovered. The patient satisfaction with nursing humanistic care scored (5.40±0.86); the top three dimensions were competence (5.50±0.89), emotional support (5.47±0.88) and helping/trusting relationship (5.46±0.86); the lowest scoring dimensions were teaching/learning (5.38±1.01), spiritual environment (5.36±1.04) and patient/family engagement (5.11±1.28). Differences with gender, age, marital status, child status, educational level, occupation, place of residence, economic region, per capita monthly income of the family, type of medical insurance, medical department visited and surgery or not presented significant differences on the patient satisfaction with nursing humanistic care scores ( P<0.05). Conclusions:The satisfaction of patients with hospital′s nursing humanistic care in China was at the middle to upper level. In the future, health education for patients should be strengthened, and a mode of family-engaged nursing humanistic care should be constructed in line with the Chinese cultural background. In the process of nursing services, the particularity of patient groups should be considered to better meet their needs.

Objective:To analyze factors related to clinic attendance for contracted residents in a community health service center in Shanghai.Methods:It was a cross-sectional study. Through the 'Cloud Management of the Community' APP and the 'Service Fee of Contracted Residents' APP, the basic information, contracted time, hospital visits, number of visits, and medical insurance expenses of the contracted residents in Shanggang Community Health Service Center in 2021 were collected, the visiting rate to the contracted community health center and the contracted medical combination hospitals were analyzed.Results:In 2021, the contracting rate of all residents in the community was 49.96% (51 478/103 033). The contracting rate of the key population was 84.59% (43 545/51 478),among whom 66.28% (34 118/51 478) were over 60 years, 49.93% (25 702/51 478) had been contracted for more than 3 years, and 37.43% (19 270/51 478) had hypertension and/or diabetes. The number of contracted general practitioners was 4.89 times of contracted TCM doctors (1 345.17/274.81). Among all contracted residents 78.75% (40 540/51 478) had at least one visit annually, and 65.00% (33 463/51 478) had at least one visit to community health service center and the average number of visits was 17.63(5.00, 24.00)annually. The rate of visit to contracted the community health service center was (46.97±38.37) %, and 41.78% (16 937/40 540) had≥60% visit to contracted community center; the average visiting rate to the combination hospitals was (70.59±34.57) %, and 55.75% (22 602/40 540) had consultation rate≥80%. These residents were older in age, had longer contract time, higher proportion of hypertension and diabetes, and higher medical expenses, compared to those with less visits to contracted community health center and combination hospitals ( P<0.01). Meanwhile, 11 736 residents (35.07%) only visited to the contracted community health service center. Conclusion:The contracted residents are mainly the elderly and the sick ones in the community, but the use of contracted service is inadequate. Improving the visiting rate to community health center is a challenge for make a full use of the contracted health facilities.

Objective:To compare the knowledge of endoscopic screening of gastrointestinal cancers between digestive healthcare workers and new chatbots (chatGPT and new Bing).Methods:A test with twenty-three questions of endoscopic screening of gastrointestinal cancers was conducted, focusing on the appropriate age of screening, high-risk factors, the follow-up time, and the advantages and risks of digestive endoscopy. Digestive healthcare workers were invited to complete the test through electronic questionnaires. New Bing and chatGPT were used to answer each question for 10 rounds. The primary endpoint was the correct rate of all answers. The answer accuracy between digestive healthcare workers and new chatbots were compared using variance analysis, and the factors that affected the accuracy of the answers in digestive healthcare workers were explored using univariate and multivariable liner regression analysis.Results:The results of the test completed by 76 digestive healthcare workers (21 residents, 28 digestive nurses, and 27 digestive doctors) were analyzed. The accuracies were 36.4%±10.9%, 34.5%±10.2%, 52.2%± 12.6%, 46.3%±9.8% and 67.1%±9.3% in residents, digestive nurses, digestive doctors, chatGPT, and new Bing, respectively, with significant difference ( F=22.6, P<0.001). The accuracy was highest in new Bing ( P<0.001). The accuracy was comparable between chatGPT and digestive doctors (LSD- t=-1.398, P=0.166), and both higher than that of digestive nurses (LSD- t=2.956, P=0.004; LSD- t=5.955, P<0.001) and residents (LSD- t=2.402, P=0.018; LSD- t=4.951, P<0.001). Furthermore, the accuracy was comparable between digestive nurses and residents (LSD- t=-0.574, P=0.567). Compared with new Bing, digestive doctors had lower accuracy in answering questions related to adverse events of screening, follow-up recommendation of intestinal metaplasia, high risk factors and screening methods for colon cancer ( P<0.05), but higher accuracy in answering questions related to endoscopic adverse events and screening methods for esophageal cancer ( P<0.05). Multivariable liner regression analysis showed that being digestive doctors ( β=11.7, t=3.054, P=0.003) and questionnaire response time (≥7.6 min) ( β=7.8, t=2.894, P=0.005) were independent factors for the answer accuracy of digestive healthcare workers. Conclusion:Compared with digestive healthcare workers, New chatbots—new Bing has higher accuracy in answering gastrointestinal cancer screening-related questions, but performs poorly in answering questions such as adverse events of endoscopy and screening methods for esophageal cancer.

The biological samples of oral genetic diseases and rare diseases are extremely precious. Collecting and preserving these biological samples are helpful to elucidate the mechanisms and improve the level of diagnose and treatment of oral genetic diseases and rare diseases. The standardized construction of biobanks for oral genetic diseases and rare diseases is important for achieving these goals. At present, there is very little information on the construction of these biobanks, and the standards or suggestions for the classification and coding of biological samples from oral and maxillofacial sources, and this is not conducive to the standardization and information construction of biobanks for special oral diseases. This consensus summarizes the background, necessity, principles, and key points of constructing the biobank for oral genetic diseases and rare diseases. On the base of the group standard "Classification and Coding for Human Biomaterial" (GB/T 39768-2021) issued by the National Technical Committee for Standardization of Biological Samples, we suggest 76 new coding numbers for different of biological samples from oral and maxillofacial sources. We hope the consensus may promote the standardization, and smartization on the biobank construction as well as the overall research level of oral genetic diseases and rare diseases in China.

OBJECTIVES: Accurate breast lesion surface localization can guarantee accurate biopsy and local treatment. But there is no guideline to regular equipment and methods for the localization of breast lesions. The conventional non-invasive localization method is marker-based localization. The advantages of this method are simple and efficient. The disadvantages are that markers disappear easily under coupling agents; the positioning length of markers cannot last long on skin; and healthcare associated infection due to many patients using the same marker pen is potentially unavoidable. Breast lesion sticker (called sticker for short) is a new-type localization medical instrument in 2020. Our study aims to explore the clinical value of a new lesion stickers in breast lesion surface localization via comparison of the sticker and marker pen localization methods. METHODS: This was a prospective cohort study. It was conducted in 67 patients who needed breast lesion surface localization before biopsy. The patients were randomly assigned into 2 groups. One group of patients used marker pen to mark breast lesion surface location by ultrasonography. The other group of patients used stickers. Patients labeled with markers on skin were swabbed agents before marking. Then the markers were checked by ultrasound scan. If the surface positions of breast lesion were not correct, the above procedure was repeated. In the sticker group, the stickers were released synchronously after the lesions were detected by ultrasound scan. Then locations were checked via scanning hole. If the surface positions of breast lesion were not correct, the above procedure was repeated. The accuracy of positioning, the length of positioning time and satisfaction of patients between the 2 groups were compared. The length of positioning time was calculated from the time when ultrasound detected the lesion to the time when the surface position of breast lesion was confirmed. The total score of patients' satisfaction was 5 points according to Service Quality Evaluation of SERVQUAL Scale, including sonographers' service attitude and their technical proficiency, other medical staffs' service attitude and their technical proficiency, hospital service procedures, positioning comfort, and positioning effects. RESULTS: All 67 patients were females, aged 18-66 (39.73±13.10). There were 35 patients in the marker pen group and 32 patients in the sticker group. The time length of group used marker pen to localization was 22-88 (52.20±2.90) s, and the sticker group was 3-15 (9.22±0.58) s in length. The length of positioning time for the stickers was significantly shorter than that of the marker (P<0.01). Both methods were accurate in the surface localization of lesions before operation. The total scores of patients' satisfaction was 4-5 (4.92±0.02) in the stickers group, and 1-5 (3.35±0.10) in the marker pen group. The patients' satisfaction scores with the sticker were significantly higher than those with the marker pen (P<0.01). The length of positioning time and patients' satisfication scores for sonographer with 20 years' working experience were shorter and higher than those of sonographer with 10 years' working experience, respectively (both P<0.05). CONCLUSIONS The new breast lesion positioning stickers have more advantages than the marker pen in localization efficiency. It could reduce the workload of medical workers and increase patients' satisfaction to some extent. The stickers can be used not only in the breast lesions surface localization, but also in the skin location of pleural effusion and ascites, the skin location of surface masses, the skin location of thyroid nodule, and many other clinical marker areas, to further expand the scope of clinical application and value of the stickers.
Breast/diagnostic imaging* ; Breast Neoplasms/diagnostic imaging* ; Female ; Humans ; Male ; Prospective Studies ; Skin

Objective:To investigate the normal reference values of spinal bone mineral density measured by quantitative computed tomography (QCT) and the differences of bone mineral density (BMD) in different regions of in Chinese adult males.Methods:Men who underwent low-dose CT lung scan for cancer screening in regions of Northeast, North, East, South, Central and Southwest of China from January 2018 to December 2019 were selected. And the lumbar vertebrae BMD values in the male subjects were measured by the QCT system (Mindways Software, Inc.). The mean BMD values and their decline rates were calculated at an age interval of 10 years, and the prevalence of osteoporosis was calculated according to the American College of Radiology spine QCT osteoporosis diagnostic criteria.Results:A total of 50 682 males with a mean age of (50.22±12.79) years (ranged 20 to 98 years) were included in this study. The peak BMD of (173.11±28.56) mg/cm 3 in the healthy Chinese adult male population appeared in the age group of 20 to 29 years and then declined with age. Before the age of 70 years, the BMD was relatively higher in males in South China, and it was lower in Central China and Southwest China, and it was intermediate in Northeast, North and East of China, with statistically significant differences. There was no significant differences in BMD in the males in the two age groups of 70 to 79 years and 80 and older among the regions in China. The overall decline rate of spinal BMD in Chinese males under QCT was about 46.92% over the lifetime, and it declined obviouslyin the 40-49 age group. The overall prevalence of osteoporosis in Chinese male population aged 50 years and above was approximately 11.42%, with the highest prevalence in Southwest China and Central China (14.72% and 13.87%, respectively) and the lowest in North China and South China (8.53% and 7.71%, respectively). Conclusions:A reference of lumbar spine BMD values for healthy males in China based on QCT is established. BMD values were highest in South China and Lowest in Central China.

Objective:To analyzed the characteristics of the cognitive domains of the montreal cognitive assessment(MOCA)scale in cognitively impaired or normal elderly people from the perspective of structural equation modeling(SEM).Methods:There were 335 old individuals in this study, including 166 cognitively normal individuals, 130 patients with mild cognitive impairment(MCI)and 39 individuals with dementia.The average age of the individuals was 81.5±9.0.Data on the Montreal cognitive assessment(MoCA, Beijing version)were gathered.Following exploratory factor analysis and selection of latent and manifest variables, a structural equation model was established.After assessment of data from the domains of the scale in the elderly, participants were divided into a normal group and a patient group, which formed the basis of the model.Results:The KMO value of the data calculated by exploratory factor analysis was 0.762.The dimensions measured by the scale were divided into four main latent variables: memory, visuospatial execution, language ability and attention.The CMIN value of the overall model was 44.039 and the P value was 0.168.The parameters of the overall model and individual dimensions all indicated a good fit.The model showed that visuospatial execution had the largest impact on cognitive function, with a path coefficient of 0.742, and language ability had the least impact, with a path coefficient of only 0.091.As a latent variable, attention had path coefficients of 0.372 and 0.236 for memory, 1.663 and 1.102 for visuospatial execution, and 1.090 and 0.798 for language ability, respectively, for the two groups, with clear statistically significant differences between the groups(all P<0.05). Conclusions:SEM can improve researchers' overall understanding of the impacts of the individual components of the scale and their use and interpretation of the scale.

Objective:To investigate the clinical efficacy and safety of modified Shaoyao Gancao decoction in the treatment of hyperprolactinemia caused by amisulpride. Methods:Ninety patients with hyperprolactinemia caused by amisulpride who received treatment in Kangci Hospital from June 2018 to October 2019 were included in this study. They were randomly divided into the placebo control, control and observation groups ( n = 30/group). The placebo control group was treated with the decoction with the taste and color (without drug ingredients) similar to that of modified Shaoyao Gancao decoction. The control group was treated with Shaoyao Gancao decoction. The observation group was treated with modified Shaoyao Gancao decoction. All patients were treated for 8 weeks. Clinical efficacy, serum prolactin level and Positive and Negative Syndrome Scale score before and after treatment, Treatment Emergent Symptom Scale score after treatment, glucose and lipid metabolism, liver and kidney function before and after treatment were compared among the three groups. Results:The effective rate in the placebo control, control and observation groups was 90.0% (27/30), 96.7% (29/30) and 100.0% (30/30), respectively, and the difference among the three groups was statistically significant (χ 2 = 7.027, P < 0.05). After treatment, serum prolactin level in the observation group [(48.2 ± 15.7) μg/L] was significantly lower than that in the control group [(52.5 ± 13.7) μg/L] and placebo control group [(57.7 ± 16.9) μg/L, t = 7.134, 7.034, both P < 0.05]. After treatment, Positive and Negative Syndrome Scale score in the observation group [(51.02 ± 3.98) points] was significantly lower than that in the control group [(54.07 ± 4.19) points] and placebo control group [(58.13 ± 4.24) points, t = 5.813, 6.317, both P < 0.05]. After treatment, Treatment Emergent Symptom Scale score in the observation group [(5.2 ± 1.3) points] was significantly higher than that in the control group [(4.9 ± 1.4) points] and placebo control group [(4.4 ± 1.2) points, t = 7.011, 7.231, both P < 0.05]. After treatment, blood glucose, low-density lipoprotein cholesterol, triglyceride, total cholesterol, alanine aminotransferase, aspartate aminotransferase levels in the observation group were significantly lower than those in the placebo control and control groups (all P < 0.05). Serum level of high-density lipoprotein cholesterol in the observation group was significantly higher than that in the placebo control and control groups (both P < 0.05). Conclusion:Modified Shaoyao Gancao decoction is highly effective in the treatment of hyperprolactinemia caused by amisulpride. It can reduce serum prolactin level and has good safety.