Objective:To explore the value of spectral CT parameters combined with dynamic contrast enhanced magnetic resonance imaging（DCE-MRI） parameters in the short-term efficacy of concurrent chemoradiotherapy for nasopharyngeal carcinoma. Methods: A total of 110 cases with nasopharyngeal carcinoma Ⅲ-Ⅳ staging who received synchronous radiotherapy and chemotherapy at our Hospital from October 2022 to October 2024 were regarded as the study subjects. Complying with the evaluation results after radiotherapy and chemotherapy, they were divided into a complete remission（CR） group of 53 cases and a non CR group of 57 cases. All patients underwent DCE-MRI and energy dispersive CT scans to obtain parameters, such as iodine concentration（IC）, volume transfer constant（Ktrans）, slope of spectral HU curve（λHU）, rate constant（Kep）, and normalized iodine concentration（NIC）. Logistic regression analysis was used to screen for influencing factors. ROC curve was used to analyze the evaluation value of various parameters. In addition, Z-test was used to compare area under the curve（AUC）. Results:The proportion of retropharyngeal lymph node metastasis and λHUvalue in the non CR group were higher than those in the CR group, while Ktrans, Kep, IC value, and NIC value were lower than those in the CR group（P<0.05）. Retropharyngeal lymph node metastasis, Ktrans, Kep, IC value, λHUvalue, and NIC value were all influencing factors（P<0.05）. The AUC of individual prediction of Ktrans, Kep, IC value, λHUvalue, and NIC value was 0.817, 0.800, 0.785, 0.783, and 0.835, respectively. The AUC of the combination of DCE-MRI parameters, the combination of spectral CT parameters, and the combination of the five parameters were 0.874, 0.900, and 0.980, respectively, the AUC of the combination of the five parameters was significantly higher than the AUC of each indicator alone, the AUC of the combination of DCE-MRI parameters, and the AUC of the combination of spectral CT parameters（P<0.05）. Conclusion:The DCE-MRI, and spectral CT parameters （Ktrans, Kep, IC value, λHUvalue, and NIC value）can be used to evaluate concurrent radiotherapy and chemotherapy short-term efficacy for nasopharyngeal carcinoma. And the combination of various parameters can greatly improve the predictive value of efficacy, which has important clinical application value.
Humans ; Chemoradiotherapy ; Nasopharyngeal Neoplasms/diagnostic imaging* ; Magnetic Resonance Imaging ; Nasopharyngeal Carcinoma ; Tomography, X-Ray Computed ; Male ; Female ; Contrast Media ; Middle Aged ; Adult ; Lymphatic Metastasis ; Dynamic Contrast Enhanced Magnetic Resonance Imaging

Objective:To construct a machine learning model based on localization CT-based radiomics, dosiomics and clinical features for predicting radiotherapy response in non-small cell lung cancer (NSCLC) and validate its application value.Methods:A retrospective case series study was conducted. A total of 138 NSCLC patients who received radiotherapy at the Affiliated Hospital of Jining Medical University from January 2016 to December 2022 were selected. The efficacy was evaluated according to the Response Evaluation Criteria in Solid Tumors (RECIST) 1.1, and the patients were stratified according to the objective remission (complete remission+partial remission). Random stratified sampling was used to divide the 138 patients into a training group (96 cases) and an internal validation group (42 cases) at a ratio of 7∶3. Additionally, 33 patients who received radiotherapy at Jining Cancer Hospital from January 2019 to December 2022 were included as the external validation group. Based on the pre-radiotherapy data of the radiotherapy planning system, PyRadiomics software package was used to extract 107 radiomics features and 107 dosiomics features for each patient. Pearson correlation analysis and LASSO regression analysis were used for dimensionality reduction screening; the final selected features were weighted and integrated to generate radiomics-dosiomics scores (RDS), which were then input into logistic regression (LR), support vector machine (SVM), extremely randomized forest (Extra Trees), K-nearest neighbor algorithm (KNN), lightweight gradient boosting machine (Light GBM), and multi-layer perceptron (MLP) machine learning algorithms to construct 6 radiomics-dosiomics models (RDM) for predicting the objective remission. RECIST 1.1 standard was used to evaluate objective remission as the gold standard, receiver operating characteristic (ROC) curve of 6 RDM for predicting objective remission was plotted, and the optimal algorithm for RDM was selected. Univariate and multivariate logistic regression were performed on demographic characteristics, hematological indicators and radiotherapy parameters of the training group to screen independent risk factors for NSCLC patients who received radiotherapy but did not achieve objective remission. These factors were input into the optimal machine learning algorithm to construct a clinical model (CM). Combined with features from RDS and CM, the clinical feature-radiomics-dosiomics combined model (CRDM) was established, and the nomogram of the model for predicting objective remission in NSCLC patients with radiotherapy was drawn. ROC curves were used to evaluate the efficacy of CM, RDM and CRDM in predicting the objective remission in NSCLC patients with radiotherapy in the training group, internal validation group and external validation group.Results:Four radiomics features (including grayscale variance, low grayscale long-range operation emphasis, low grayscale area emphasis, and small area low grayscale area emphasis, all of which were texture features) and 6 dosiomics features [including 1 first-order feature (robust mean absolute deviation), 4 texture features (grayscale non-uniformity, large area emphasis, large area high grayscale emphasis, contrast) and 1 shape feature (shortest axis length)] were selected. ROC curve analysis showed that the area under the curve (AUC) of the RDM constructed using SVM algorithm for judging the objective remission in the training group and the internal validation group was 0.907 (95% CI: 0.836-0.977) and 0.822 (95% CI: 0.685-0.959), which were higher than RDM constructed using other algorithms, and the sensitivity (96.2% and 91.7%), specificity (78.6% and 76.7%) and accuracy (83.3% and 81.0%) at the optimal cut-off values were all higher. Considering the stability and generalization ability of the model, SVM algorithm was ultimately used to construct RDM, CM and CRDM uniformly. Based on training group data, univariate and multivariate logistic regression analysis showed that elevated platelet-to-lymphocyte ratio (PLR) ( OR = 1.001, 95% CI: 1.000-1.003, P = 0.035) and increased target volume of radiotherapy plan ( OR = 1.001, 95% CI: 1.000-1.001, P = 0.008) were independent risk factors for failure to achieve objective remission. ROC curve analysis showed that in the training group and the internal validation group, the AUC of CRDM predicting objective remission were 0.914 (95% CI: 0.856-0.972) and 0.864 (95% CI: 0.754-0.974), respectively, which were better than CM [AUC were 0.735 (95% CI: 0.612-0.857) and 0.697 (95% CI: 0.507-0.888)] and RDM, respectively. In the external validation group, the AUC of CRDM, CM and RDM were 0.778 (95% CI: 0.500-1.000), 0.667 (95% CI: 0.434-0.899) and 0.741 (95% CI: 0.463-1.000), respectively. Conclusions:The CRDM constructed by combining radiomics, dosiomics and clinical features can comprehensively and accurately evaluate the radiotherapy response of NSCLC patients, and may have important clinical application value in achieving precision medicine and optimizing treatment strategies.

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 develop and validate a combined model integrating radiomics, dosiomics, and clinical parameters based on CT simulation and dosimetric images in order to predict the occurrence of radiation pneumonitis (RP) in patients with non-small cell lung cancer (NSCLC).Methods:A retrospective study was conducted on the clinic data of 143 NSCLC patients who received radiotherapy at the Affiliated Hospital of Jining Medical University from January 2016 to December 2022. Patients were randomly stratified into a training group ( n = 100) and an internal validation group ( n = 43) at a 7∶3 ratio. Moreover, clinic data were collected from 34 NSCLC patients who received radiotherapy at the Jining Cancer Hospital between January 2019 and December 2022 as an external validation group. All three groups (the training group, internal validation, and external validation groups) were further categorized into two groups based on the RP severity (i.e., RP ≥ grade 2 and RP < grade 2). Their radiotherapy dose, CT simulation, and 3D dose distribution images were collected. Then, the total lung minus planning target volume (TL-PTV) was defined as the region of interest (ROI) for radiomics and dosiomic feature extraction, followed by feature dimensionality reduction. Consequently, key features associated with RP were determined. Four predictive models were developed using machine learning approaches (especially multilayer perceptron, MLP): a clinical model (CM), a radiomics model (RM), a dosiomics model (DM), and a radiomics and dosiomics nomogram (RDN), with a nomogram subsequently constructed. Ultimately, the performance and clinical feasibility of these models were assessed using receiver operating characteristic (ROC), area under the curve (AUC), and decision curve analysis (DCA). Results:A total of 1 834 radiomic features and 1 834 dosiomic features were extracted. Using the occurrence of RP ≥ grade 2 as the marker variable, 14 radiomic features, 15 dosiomic features, and three clinical features were selected from the training group to construct the prediction models (CM, RM, DM, and RDN). The performance and generalizability of these models were subsequently validated in both the internal validation and external validation groups. Specifically, the RDN exhibited AUCs of 0.915 (95% CI: 0.852-0.978), 0.879 (95% CI: 0.777-0.982), and 0.838 (95% CI: 0.701-0.975) in the three groups, respectively. A nomogram was established for RDN by integrating the radiomics score (R-score), dosiomics score (D-score), mean lung dose (MLD), V20, and V30. This nomogram allowed for individualized risk estimation of RP and facilitated personalized radiotherapy planning. Conclusions:The RDN model that is developed based on CT simulation and 3D dose distribution images and integrates radiomics, dosiomics, and clinical features can effectively predict the RP risk of NSCLC patients. The integration of multidimensional data contributes to the formation of the optimal predictive model, offering guidance for clinicians.

To clarify the current situation of ketosis in dairy cattle on large-scale pastures in China and provide new insights,a questionnaire survey was conducted to analyze the incidence,preven-tion,treatment methods,and associated costs of ketosis in 79 large-scale pastures.The results showed that the average incidence of ketosis in dairy cows was 3.97％,with a cure rate of 92.40％.The order of importance of methods for preventing and controlling ketosis was as follows:feed for-mulation optimization＞blood ketone monitoring＞negative energy balance monitoring＞feed in-take monitoring＞milk yield monitoring.The most important treatment methods are intravenous glucose＞propylene glycol butyl phosphate＞vitamins＞choline.The most important diagnostic methods are blood ketone testing＞milk ketone testing＞negative energy balance testing＞clinical symptoms＞blood glucose testing.Economic analysis revealed that treatment costs were lower on larger farms and higher milk yields farms.Continuous optimization of feeding management,preven-tion,and control measures should be implemented on large-scale farms in China to reduce the oc-currence of ketosis in dairy cows.Additionally,more effective diagnostic and treatment methods should be employed to improve the cure rate and overall farm income.

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.

To clarify the current situation of ketosis in dairy cattle on large-scale pastures in China and provide new insights,a questionnaire survey was conducted to analyze the incidence,preven-tion,treatment methods,and associated costs of ketosis in 79 large-scale pastures.The results showed that the average incidence of ketosis in dairy cows was 3.97％,with a cure rate of 92.40％.The order of importance of methods for preventing and controlling ketosis was as follows:feed for-mulation optimization＞blood ketone monitoring＞negative energy balance monitoring＞feed in-take monitoring＞milk yield monitoring.The most important treatment methods are intravenous glucose＞propylene glycol butyl phosphate＞vitamins＞choline.The most important diagnostic methods are blood ketone testing＞milk ketone testing＞negative energy balance testing＞clinical symptoms＞blood glucose testing.Economic analysis revealed that treatment costs were lower on larger farms and higher milk yields farms.Continuous optimization of feeding management,preven-tion,and control measures should be implemented on large-scale farms in China to reduce the oc-currence of ketosis in dairy cows.Additionally,more effective diagnostic and treatment methods should be employed to improve the cure rate and overall farm income.

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 develop and validate a combined model integrating radiomics, dosiomics, and clinical parameters based on CT simulation and dosimetric images in order to predict the occurrence of radiation pneumonitis (RP) in patients with non-small cell lung cancer (NSCLC).Methods:A retrospective study was conducted on the clinic data of 143 NSCLC patients who received radiotherapy at the Affiliated Hospital of Jining Medical University from January 2016 to December 2022. Patients were randomly stratified into a training group ( n = 100) and an internal validation group ( n = 43) at a 7∶3 ratio. Moreover, clinic data were collected from 34 NSCLC patients who received radiotherapy at the Jining Cancer Hospital between January 2019 and December 2022 as an external validation group. All three groups (the training group, internal validation, and external validation groups) were further categorized into two groups based on the RP severity (i.e., RP ≥ grade 2 and RP < grade 2). Their radiotherapy dose, CT simulation, and 3D dose distribution images were collected. Then, the total lung minus planning target volume (TL-PTV) was defined as the region of interest (ROI) for radiomics and dosiomic feature extraction, followed by feature dimensionality reduction. Consequently, key features associated with RP were determined. Four predictive models were developed using machine learning approaches (especially multilayer perceptron, MLP): a clinical model (CM), a radiomics model (RM), a dosiomics model (DM), and a radiomics and dosiomics nomogram (RDN), with a nomogram subsequently constructed. Ultimately, the performance and clinical feasibility of these models were assessed using receiver operating characteristic (ROC), area under the curve (AUC), and decision curve analysis (DCA). Results:A total of 1 834 radiomic features and 1 834 dosiomic features were extracted. Using the occurrence of RP ≥ grade 2 as the marker variable, 14 radiomic features, 15 dosiomic features, and three clinical features were selected from the training group to construct the prediction models (CM, RM, DM, and RDN). The performance and generalizability of these models were subsequently validated in both the internal validation and external validation groups. Specifically, the RDN exhibited AUCs of 0.915 (95% CI: 0.852-0.978), 0.879 (95% CI: 0.777-0.982), and 0.838 (95% CI: 0.701-0.975) in the three groups, respectively. A nomogram was established for RDN by integrating the radiomics score (R-score), dosiomics score (D-score), mean lung dose (MLD), V20, and V30. This nomogram allowed for individualized risk estimation of RP and facilitated personalized radiotherapy planning. Conclusions:The RDN model that is developed based on CT simulation and 3D dose distribution images and integrates radiomics, dosiomics, and clinical features can effectively predict the RP risk of NSCLC patients. The integration of multidimensional data contributes to the formation of the optimal predictive model, offering guidance for clinicians.