With the rapid development of medical big data and artificial intelligence,Clinical Prediction Models(CPMs)have become pivotal tools for disease prevention,diagnosis,and treatment.Current research predominantly focuses on the economic analysis of pharmacological or public health interventions,yet a comprehensive methodological framework for the economic evaluation of CPMs has been notably absent.The Guidelines for Economic Evaluation of Clinical Prediction Models(hereafter the Guidelines),jointly initiated by the Chinese Research Hospital Association and Peking University,Tsinghua University,and Capital Medical University,adheres to the WHO Handbook for Guideline Development and the Reporting Items for Practice Guidelines in Healthcare(RIGHT)standards.A multidisciplinary collaboration,including a steering committee,expert panel,secretariat,and external review group,was established to develop the guideline following evidence-based principles and procedures.Consensus recommendations were formulated through the Delphi method.It describes the background,objectives,target group,and the development methodology and process,ensuring the entire compilation process of the Guidelines is transparent and standardized.Through comprehensive evidence retrieval,systematic evidence appraisal,and a scientific approach to forming recommendations,the scientific rigor and validity of the Guidelines were further enhanced.

Objective:To analyze the incidence and risk factors of ocular surface disease among power grid construction workers in plateau.Methods:A total of 11 132 construction personnel from the Ngari prefecture-central Tibet power grid interconnection project were included from 2019 to 2020.Baseline characteristics including age, gender, body mass index, developmental and nutritional status, relevant clinical indicators, etc.and follow-up data regarding incidence of ocular surface diseases were obtained from the medical records of Ali interconnection project staff medical station.The altitude of workplace and residence of the study population were obtained from the website (https: //zh-cn.topographic-map.com/legal/).The mean age of the subjects was (36.17±10.48) years, of which 95.33%(10, 612 subjects) were male.The median follow-up time was 1.53 years.The altitude of the residence and workplace were (1 954.77±940.64) and (4 535.09±232.71) meters, respectively.The incidence of ocular surface diseases in groups with different characteristics was calculated.Differential variables for the incidence of ocular surface diseases were screened by univariate Cox proportional hazards regression model.Influencing factors of ocular surface diseases multivariate were explored by Cox proportional hazards model.This study was approved by the Ethics Committee of Peking University Health Science Center (No.IRB00001052-21066).Results:During the follow-up period, the incidence of ocular surface disease was 9.27% (1 032 cases), and the incidence of conjunctivitis and keratitis was 6.58% (733 cases) and 1.80% (200 cases), respectively.Multivariate Cox proportional hazards regression analysis showed that for every 1 000 meters increase in altitude of residence, the risk of ocular surface disease decreased by 15% ( HR[95% CI]: 0.85[0.80~0.91], P<0.001).For every 100 meters increase in altitude of workplace, the risk of ocular surface disease increased by 5% ( HR[95% CI]: 1.04[1.01~1.07], P=0.006).Decreased blood oxygen saturation ( HR[95% CI]: 1.09[1.02~1.16], P=0.007), hearing pulmonary dry rales (hazard ratio ( HR)[95% CI]: 1.53[1.12~2.09], P=0.007) and heart murmurs ( HR[95% CI]: 4.44[1.43~13.83], P=0.010) were associated with ocular surface disease. Conclusions:The incidence of ocular surface disease in personnel engaged in electric grid construction at high altitudes should not be ignored.High working altitude, low residence altitude, pulmonary dry rales, heart murmurs and low blood oxygen saturation are factors associated with the incidence of ocular surface disease.

With the rapid development of medical big data and artificial intelligence,Clinical Prediction Models(CPMs)have become pivotal tools for disease prevention,diagnosis,and treatment.Current research predominantly focuses on the economic analysis of pharmacological or public health interventions,yet a comprehensive methodological framework for the economic evaluation of CPMs has been notably absent.The Guidelines for Economic Evaluation of Clinical Prediction Models(hereafter the Guidelines),jointly initiated by the Chinese Research Hospital Association and Peking University,Tsinghua University,and Capital Medical University,adheres to the WHO Handbook for Guideline Development and the Reporting Items for Practice Guidelines in Healthcare(RIGHT)standards.A multidisciplinary collaboration,including a steering committee,expert panel,secretariat,and external review group,was established to develop the guideline following evidence-based principles and procedures.Consensus recommendations were formulated through the Delphi method.It describes the background,objectives,target group,and the development methodology and process,ensuring the entire compilation process of the Guidelines is transparent and standardized.Through comprehensive evidence retrieval,systematic evidence appraisal,and a scientific approach to forming recommendations,the scientific rigor and validity of the Guidelines were further enhanced.

The emergence of artificial intelligence(AI)has had a significant impact on medical research and practice,both in terms of the number of studies and research paradigms,and has become an important tool for the development of pharmacoepidemiology.However,traditional AI has faced many challenges,while facilitating pharmacoepidemiology research,such as complex data processing,difficulty in identifying drug exposures and potential outcomes,and time-consuming and laborious study design and implementation.The rapid development of generative AI,represented by large language models(LLMs),has demonstrated a unique potential to enhance research efficiency,shift research paradigms,and facilitate knowledge discovery.LLMs are equipped with natural language understanding and generation capabilities.Through deep mining of multi-dimensional data resources,LLMs can quickly and accurately extract,analyze,summarize,and present the required information,which can not only help drug discovery,drug repurposing,pharmacovigilance and other pharmacoepidemiological tasks,but also provide powerful support for the whole process of research protocol design,data analysis,result interpretation and paper publication.Driven by LLMs,pharmacoepidemiology research is gradually moving into a new stage based on big data and automated analysis.Of course,LLMs also have problems of data bias,"illusion"of results,and ethical and legal regulation.By strengthening interdisciplinary cooperation,establishing a standardized evaluation system,improving ethical and regulatory guidance,enhancing data quality,strengthening practitioner training and capacity building,and promoting human-machine collaborative research modes,it is expected that the potential of LLMs in pharmacoepidemiology will be fully released,and it will provide a more scientific,rapid,and efficient technological support for drug regulation and public health decision-making.

Objective:To describe the hotspots and application trends of artificial intelligence (AI) in epidemiology in the past decade and analyze its advantages and challenges.Methods:The literatures with AI and epidemiology related keywords were systematically retrieved from Web of Science and China National Knowledge Infrastructure from 2014 to 2024. CiteSpace was used for bibliometric analysis of publication volume, keyword co-occurrence, clustering, emergence and cited literature co-occurrence analysis.Results:A total of 5 389 English papers and 1 659 Chinese papers were included, showing an increasing publication trend. High-frequency Chinese keywords included prediction, influencing factor, and machine learning, while English keywords frequently used were machine learning, prediction, and artificial intelligence. The Chinese keywords formed 14 clusters such as epidemiological characteristic, dietary pattern, and elderly individual, and the English keywords formed 21 clusters including prediction model, risk factor, and adult. In international studies, health policy, COVID-19, and digital health were the emerging frontier keywords. Eleven core papers were selected, covering key areas like traffic accident risk assessment, public health big data application, and deep learning in medical diagnosis.Conclusions:This study systematically summarized the research hotspots and development trends of AI applications in epidemiology over the past decade by using bibliometric methods, which indicated that current AI-based epidemiological studies are still in the exploratory phase, with the coexisting of both advantages and challenges. Continued attention should be paid to the future development of this field.

Objective:To analyze the incidence and risk factors of ocular surface disease among power grid construction workers in plateau.Methods:A total of 11 132 construction personnel from the Ngari prefecture-central Tibet power grid interconnection project were included from 2019 to 2020.Baseline characteristics including age, gender, body mass index, developmental and nutritional status, relevant clinical indicators, etc.and follow-up data regarding incidence of ocular surface diseases were obtained from the medical records of Ali interconnection project staff medical station.The altitude of workplace and residence of the study population were obtained from the website (https: //zh-cn.topographic-map.com/legal/).The mean age of the subjects was (36.17±10.48) years, of which 95.33%(10, 612 subjects) were male.The median follow-up time was 1.53 years.The altitude of the residence and workplace were (1 954.77±940.64) and (4 535.09±232.71) meters, respectively.The incidence of ocular surface diseases in groups with different characteristics was calculated.Differential variables for the incidence of ocular surface diseases were screened by univariate Cox proportional hazards regression model.Influencing factors of ocular surface diseases multivariate were explored by Cox proportional hazards model.This study was approved by the Ethics Committee of Peking University Health Science Center (No.IRB00001052-21066).Results:During the follow-up period, the incidence of ocular surface disease was 9.27% (1 032 cases), and the incidence of conjunctivitis and keratitis was 6.58% (733 cases) and 1.80% (200 cases), respectively.Multivariate Cox proportional hazards regression analysis showed that for every 1 000 meters increase in altitude of residence, the risk of ocular surface disease decreased by 15% ( HR[95% CI]: 0.85[0.80~0.91], P<0.001).For every 100 meters increase in altitude of workplace, the risk of ocular surface disease increased by 5% ( HR[95% CI]: 1.04[1.01~1.07], P=0.006).Decreased blood oxygen saturation ( HR[95% CI]: 1.09[1.02~1.16], P=0.007), hearing pulmonary dry rales (hazard ratio ( HR)[95% CI]: 1.53[1.12~2.09], P=0.007) and heart murmurs ( HR[95% CI]: 4.44[1.43~13.83], P=0.010) were associated with ocular surface disease. Conclusions:The incidence of ocular surface disease in personnel engaged in electric grid construction at high altitudes should not be ignored.High working altitude, low residence altitude, pulmonary dry rales, heart murmurs and low blood oxygen saturation are factors associated with the incidence of ocular surface disease.

Objective The aim is to understand the common scenarios of non-medical use of prescription opioids(NMUPO)and analyze the potential facilitating and hindering factors in the regulatory process of NMUPO from the perspective of healthcare professionals.Methods Healthcare professionals in local hospitals were surveyed through a two-stage purposive sampling from June to August 2022 in Ningbo,China.The survey was conducted using a semi-structured questionnaire on topics,and thematic analysis were used to identify and summarise key themes and patterns.Results A total of 75 participants were included,the average age was(43.9±7.2)years,and 54(72.0%)were male.The most common NMUPO scenarios involved middle-aged males pretending acute severe pain to obtain injectable opioids.The facilitating and hindering factors related to the regulation of NMUPO can be categorized into three types:institutional governance,technical support,and individual behaviors.At the institutional level,facilitating factors included strict national prescribing policies and local"narcotic drug card"systems,while barriers comprised incomplete lists of controlled substances.At the technological support level,facilitating factors included the establishment of regional health information platforms,while barriers included the lack of standardized prescription guidelines and diagnostic decision-support tools.At the individual level,facilitating factors included the public's cautious attitude toward drug misuse,while barriers included strained doctor-patient relationships.Conclusion China still faces significant challenges in addressing NMUPO and urgently needs to improve the existing regulatory system.It is recommended that reforms be carried out in areas such as pharmaceutical control mechanisms,drug treatment and rehabilitation services,preventive health education activities,and the optimized use of health information systems.

Pneumocystis jirovecii pneumonia (PJP) is an opportunistic pulmonary infection that commonly occurs in immunocompromised children. We report a case of infantile leukemia complicated by PJP and review the relevant literature. A summary and analysis of 10 infantile leukemia patients with PJP infection (9 cases reported in the literature and 1 case from our center) showed that PJP mostly occurred in the early stages of chemotherapy (80%, 8/10). The main clinical manifestations were dyspnea (100%, 10/10) and hypoxemia (50%, 5/10), while pulmonary imaging findings lacked specificity. In most cases (50%, 5/10), diagnosis was established by identifying pathogens in bronchoalveolar lavage fluid under microscopy. In our case, diagnosis was confirmed using targeted next-generation sequencing (tNGS) of bronchoalveolar lavage fluid. Treatment with intravenous sulfamethoxazole complex was administered in 8 patients, all of whom eventually recovered. PJP may occur in the early stages of chemotherapy for infantile leukemia, thus early prevention is necessary. tNGS facilitates early diagnosis of PJP, and sulfamethoxazole complex remains an effective therapeutic option.
Humans ; Infant ; Bronchoalveolar Lavage Fluid/microbiology* ; Immunocompromised Host ; Leukemia/complications* ; Pneumocystis carinii/isolation & purification* ; Pneumonia, Pneumocystis/diagnosis* ; Trimethoprim, Sulfamethoxazole Drug Combination/therapeutic use*

Our study aims at systematically summarizing and evaluating the applications of digital intelligence technologies in the field of rare disease medical care insurance now and in the future and at constructing a conceptual framework for the digital powered mechanism for the medical care insurance for rare diseases. By using Chinese keywords of " rare disease" " medical insurance"" artificial intelligence"" prediction model"" machine learning"" big data"" algorithm" and their English equivalents, we searched the databases of PubMed, Embase, Web of Science, CNKI, Wanfang, and VIP, collected relevant literature, and decided the criteria of inclusion and exclusion. The finding of our study shows that medical care insurance mechanism of rare disease in China faces significant challenges in drug accessbility and the funding sustainability. Meanwhile, our study shows that the digital intelligence technologies have broad potential in applications-in financing, accessbility, payment, and supervision. Specifically, dynamic simulation models and big data analysis can make precise prediction of the demand for funding of medical care insurance. The machine learning algorithms improve the dynamic evaluation of drug safety and cost-effectiveness. The personalized payment models enhance the efficiency in identifying the cohort with high expenditure so as to alleviate fund expenditure pressures. The intelligent monitoring technologies can accurately detect the abnormal behaviors in funds of medical care insurance. These technologies provide systematic and scientific solutions for improving the medical care mechanism for rare diseases. Even though further investigation is needed, the digital intelligence technologies have shown remarkable potential in enhancing the flexibility, efficiency, and sustainability of the medical care insurance system and a promising future in meeting the needs of patients with rare diseases.

Objective:To describe the hotspots and application trends of artificial intelligence (AI) in epidemiology in the past decade and analyze its advantages and challenges.Methods:The literatures with AI and epidemiology related keywords were systematically retrieved from Web of Science and China National Knowledge Infrastructure from 2014 to 2024. CiteSpace was used for bibliometric analysis of publication volume, keyword co-occurrence, clustering, emergence and cited literature co-occurrence analysis.Results:A total of 5 389 English papers and 1 659 Chinese papers were included, showing an increasing publication trend. High-frequency Chinese keywords included prediction, influencing factor, and machine learning, while English keywords frequently used were machine learning, prediction, and artificial intelligence. The Chinese keywords formed 14 clusters such as epidemiological characteristic, dietary pattern, and elderly individual, and the English keywords formed 21 clusters including prediction model, risk factor, and adult. In international studies, health policy, COVID-19, and digital health were the emerging frontier keywords. Eleven core papers were selected, covering key areas like traffic accident risk assessment, public health big data application, and deep learning in medical diagnosis.Conclusions:This study systematically summarized the research hotspots and development trends of AI applications in epidemiology over the past decade by using bibliometric methods, which indicated that current AI-based epidemiological studies are still in the exploratory phase, with the coexisting of both advantages and challenges. Continued attention should be paid to the future development of this field.