Maxillofacial fractures are common and frequently occurring diseases in Oral and Maxillofacial Surgery.The traditional clinical diagnosis and treatment process is easily affected by complex maxillofacial anatomy and differences in doctors' experience in reading X-rays and making diagnoses.In recent years,artificial intelligence technology has provided new solutions for the accurate diag-nosis and treatment planning of maxillofacial fractures.Automating image analysis through computer vision methods improves diagnostic accuracy and efficiency and assists in formulating treatment plans,showing broad application prospects and value.This article reviews and summarizes the research on the application of artificial intelligence in the auxiliary diagnosis and treatment of maxillofacial fractures at home and abroad,analyzes its advantages and disadvantages,and looks forward to future research trends.

Objective:To investigate the longitudinal stability of the Mini-Mental State Examination (MMSE), Montreal Cognitive Assessment (MoCA), and the Activity of Daily Living Scale (ADL).Methods:The longitudinal cognitive assessment results of 68 dementia patients admitted to the Dementia and Leukoencephalopathy Outpatient Clinic, Department of Neurology, Peking Union Medical College Hospital, from January 2021 to January 2024, were retrospectively analyzed, including the total and sub-items scores of the MMSE, MoCA, and ADL. Two different rules were applied to analyze the abnormality rates: rule 1, where the current test result being better than the previous one was considered an abnormality; rule 2, where the current test result being better than the previous average score was considered an abnormality (If a patient had only 2 cognitive assessments, rule 2 was considered the same as rule 1). Two rules were used to analyze the abnormality rates of the scales. The statistical analyses were repeated after excluding patients with possible anxiety and depression status.Results:In assessing the total score stability, MMSE showed the lowest abnormality rates [27.2% (31/114) under rule 1 and 29.8% (34/114) under rule 2], while MoCA had the highest abnormality rates [41.3% (26/63) and 46.0% (29/63), respectively]. The ADL abnormality rates were 27.7% (23/83) and 33.7% (28/83), respectively. Among MoCA sub-items, category cue, multiple choice cue, second memory trial, orientation, and clock showed higher abnormality rates [31.7%(20/63), 30.2%(19/63), 23.8%(15/63), 22.2%(14/63), 22.2%(14/63), respectively]. After excluding population with possible anxiety and depression status, the relative abnormality rates of MMSE and ADL sub-items did not significantly change, while the abnormality rate of orientation in MoCA sub-items decreased relatively.Conclusion:The MMSE and ADL exhibit good stability in long-term monitoring of dementia patients, serving as essential tools for assessing and following up cognitive changes.

Maxillofacial fractures are common and frequently occurring diseases in Oral and Maxillofacial Surgery.The traditional clinical diagnosis and treatment process is easily affected by complex maxillofacial anatomy and differences in doctors' experience in reading X-rays and making diagnoses.In recent years,artificial intelligence technology has provided new solutions for the accurate diag-nosis and treatment planning of maxillofacial fractures.Automating image analysis through computer vision methods improves diagnostic accuracy and efficiency and assists in formulating treatment plans,showing broad application prospects and value.This article reviews and summarizes the research on the application of artificial intelligence in the auxiliary diagnosis and treatment of maxillofacial fractures at home and abroad,analyzes its advantages and disadvantages,and looks forward to future research trends.

Objective:To investigate the longitudinal stability of the Mini-Mental State Examination (MMSE), Montreal Cognitive Assessment (MoCA), and the Activity of Daily Living Scale (ADL).Methods:The longitudinal cognitive assessment results of 68 dementia patients admitted to the Dementia and Leukoencephalopathy Outpatient Clinic, Department of Neurology, Peking Union Medical College Hospital, from January 2021 to January 2024, were retrospectively analyzed, including the total and sub-items scores of the MMSE, MoCA, and ADL. Two different rules were applied to analyze the abnormality rates: rule 1, where the current test result being better than the previous one was considered an abnormality; rule 2, where the current test result being better than the previous average score was considered an abnormality (If a patient had only 2 cognitive assessments, rule 2 was considered the same as rule 1). Two rules were used to analyze the abnormality rates of the scales. The statistical analyses were repeated after excluding patients with possible anxiety and depression status.Results:In assessing the total score stability, MMSE showed the lowest abnormality rates [27.2% (31/114) under rule 1 and 29.8% (34/114) under rule 2], while MoCA had the highest abnormality rates [41.3% (26/63) and 46.0% (29/63), respectively]. The ADL abnormality rates were 27.7% (23/83) and 33.7% (28/83), respectively. Among MoCA sub-items, category cue, multiple choice cue, second memory trial, orientation, and clock showed higher abnormality rates [31.7%(20/63), 30.2%(19/63), 23.8%(15/63), 22.2%(14/63), 22.2%(14/63), respectively]. After excluding population with possible anxiety and depression status, the relative abnormality rates of MMSE and ADL sub-items did not significantly change, while the abnormality rate of orientation in MoCA sub-items decreased relatively.Conclusion:The MMSE and ADL exhibit good stability in long-term monitoring of dementia patients, serving as essential tools for assessing and following up cognitive changes.

Objective To investigate the feasibility of the autoregressive integrated moving average model (ARIMA) in analyzing foodborne diseases in Hubei Province and predicting the future trend of foodborne diseases in Hubei Province. Methods Based on the number of reported cases of foodborne diseases in Hubei Province for eight consecutive years (2014-2021), an ARIMA model was constructed using Python software to fit the data. The model was validated and parameters were optimized with data from January 2022 to December 2022. The optimal fitting model was used to predict the incidence and trends of foodborne diseases in 2023. Results The incidence of foodborne diseases in Hubei Province showed seasonal periodicity, and the peak of epidemic was usually in July every year. SARIMA (0,1,0) (2,2,1)₁₂ was determined as the best fitting model. The model extrapolation effect was verified with 2022 data, and MAPE was 23.90 %, indicating that the model extrapolation effect was effective. Conclusion The SARIMA model is effective for short-term prediction of foodborne disease incidence trends in Hubei Province, and can provide a scientific basis for the formulation of foodborne disease prevention and control policies in the coming year.

Objective To evaluate the predictive and diagnostic value of plasma interleukin-6 (IL-6) and soluble suppression of tumorigenicity 2 (sST2) for acute respiratory distress syndrome (ARDS) in patients with abdominal sepsis. Methods A retrospective study method was adopted,clinical data from patients with abdominal sepsis admitted to the department of critical care medicine of China-Japan Friendship Hospital,between January 2022 and December 2023 were collected. These data included gender,age,sST2,IL-6,procalcitonin (PCT),C-reactive protein (CRP),white blood cell count (WBC),neutrophil ratio,hemoglobin (Hb),platelet count (PLT),lactate dehydrogenase (LDH),pH value,arterial partial pressure of oxygen (PaO2),fraction of inspired oxygen (FiO2),arterial partial pressure of carbon dioxide (PaCO2),oxygenation index (PaO2/FiO2),arterial blood lactate acid (Lac),prothrombin time (PT),activated partial thromboplastin time (APTT),D-dimer,acute physiology and chronic health evaluationⅡ(APACHEⅡ) score,and sequential organ failure assessment (SOFA) score. Patients were divided into two groups based on the presence or absence of ARDS. The differences in the above indices between the two groups were analyzed. Spearman correlation analysis was used to examine the relationship between plasma IL-6 and sST2 levels and clinical indicators in the ARDS group. Multivariate Logistic regression was conducted to identify risk factors for ARDS in patients with abdominal sepsis,and receiver operator characteristic curve (ROC curve) were used to assess the predictive value of IL-6 and sST2 for ARDS. Results A total of 89 patients with abdominal sepsis were included,with 41 in the ARDS group and 48 in the non-ARDS group. Compared with the non-ARDS group,the ARDS group showed significantly higher levels of sST2,IL-6,PaCO2,APACHEⅡ score,SOFA score,and FiO2[sST2 (μg/L):733.7 (370.1,1609.1) vs. 86.1 (64.1,129.1),IL-6 (ng/L):1106.79 (405.37,3848.00) vs. 101.00 (44.00,396.00),PaCO2 (mmHg,1 mmHg≈0.133 kPa):40.00 (35.50,45.50) vs. 36.00 (31.85,40.73),APACHEⅡ score:31.7±1.0 vs. 28.6±0.9,SOFA score:10.30±0.50 vs. 8.17±0.70,FiO2:0.600 (0.500,1.000) vs. 0.400 (0.400,0.575),all P<0.05],APTT was significantly prolonged in the ARDS group[s:49.70 (41.95,56.43) vs. 43.30 (39.40,49.60)],pH value,PaO2 and PaO2/FiO2 were significantly decreased[pH value:7.37 (7.30,7.43) vs. 7.41 (7.35,7.47),PaO2 (mmHg):82.00 (68.00,107.00) vs. 119.50 (101.25,154.00),PaO2/FiO2 (mmHg):157.00 (99.10,200.00) vs. 297.56 (228.00,386.00),all P<0.05]. Spearman correlation analysis showed in the sepsis-related ARDS group,plasma IL-6 was positively correlated with PCT,SOFA score,and Lac (r were 0.437,0.470,and 0.374,respectively;P value were 0.005,0.002,and 0.016,respectively),plasma sST2 levels were also positively correlated with PCT,SOFA score,and Lac (r were 0.492,0.454,and 0.441,respectively;P value were 0.009,0.013,and 0.015,respectively). Multivariate Logistic regression analysis indicated that plasma sST2 and IL-6 had diagnostic value for ARDS in patients with abdominal sepsis,with area under the curve (AUC) values of 0.978 and 0.719,respectively,and optimal cut-off values of 246.9 μg/L and 397.8 ng/L,both P<0.05,sensitivities were 86.2％ and 79.3％,and specificities were 100.0％ and 85.0％ for sST2 and IL-6,respectively. Conclusion Plasma sST2 and IL-6 are closely associated with ARDS in patients with abdominal sepsis and have high diagnostic value for identifying ARDS in this population.

Objective:To analyze the clinical and imaging features of patients with COVID-19-related osmotic demyelination syndrome (ODS).Methods:COVID-19-related ODS cases diagnosed in the Department of Neurology, Peking Union Medical College Hospital from January 2020 to September 2023 were retrospectively reviewed. And their past medical history, possible triggers, clinical manifestations, imaging manifestations, treatment and prognosis were summarized.Results:A total of 5 patients with COVID-19-related ODS were included. Electrolyte disturbances acted as an inducement of ODS in all patients (5/5),4 of whom with hyponatremia. Four of 5 patients first presented with disturbance of consciousness, followed by predominant dystonia. Imaging of all patients (5/5) showed isolated extrapontine myelinolysis (EPM). With the prolongation of the course of disease, such signal intensity could return to normal, and lesions showed atrophic changes in some patients. The patients′ clinical symptoms were partly relieved within a few days to a few months after treatment.Conclusions:COVID-19-related ODS is mostly associated with hyponatremia, and EPM is more common. COVID-19 should be considered as a risk factor for ODS.

Objective To evaluate the predictive and diagnostic value of plasma interleukin-6 (IL-6) and soluble suppression of tumorigenicity 2 (sST2) for acute respiratory distress syndrome (ARDS) in patients with abdominal sepsis. Methods A retrospective study method was adopted,clinical data from patients with abdominal sepsis admitted to the department of critical care medicine of China-Japan Friendship Hospital,between January 2022 and December 2023 were collected. These data included gender,age,sST2,IL-6,procalcitonin (PCT),C-reactive protein (CRP),white blood cell count (WBC),neutrophil ratio,hemoglobin (Hb),platelet count (PLT),lactate dehydrogenase (LDH),pH value,arterial partial pressure of oxygen (PaO2),fraction of inspired oxygen (FiO2),arterial partial pressure of carbon dioxide (PaCO2),oxygenation index (PaO2/FiO2),arterial blood lactate acid (Lac),prothrombin time (PT),activated partial thromboplastin time (APTT),D-dimer,acute physiology and chronic health evaluationⅡ(APACHEⅡ) score,and sequential organ failure assessment (SOFA) score. Patients were divided into two groups based on the presence or absence of ARDS. The differences in the above indices between the two groups were analyzed. Spearman correlation analysis was used to examine the relationship between plasma IL-6 and sST2 levels and clinical indicators in the ARDS group. Multivariate Logistic regression was conducted to identify risk factors for ARDS in patients with abdominal sepsis,and receiver operator characteristic curve (ROC curve) were used to assess the predictive value of IL-6 and sST2 for ARDS. Results A total of 89 patients with abdominal sepsis were included,with 41 in the ARDS group and 48 in the non-ARDS group. Compared with the non-ARDS group,the ARDS group showed significantly higher levels of sST2,IL-6,PaCO2,APACHEⅡ score,SOFA score,and FiO2[sST2 (μg/L):733.7 (370.1,1609.1) vs. 86.1 (64.1,129.1),IL-6 (ng/L):1106.79 (405.37,3848.00) vs. 101.00 (44.00,396.00),PaCO2 (mmHg,1 mmHg≈0.133 kPa):40.00 (35.50,45.50) vs. 36.00 (31.85,40.73),APACHEⅡ score:31.7±1.0 vs. 28.6±0.9,SOFA score:10.30±0.50 vs. 8.17±0.70,FiO2:0.600 (0.500,1.000) vs. 0.400 (0.400,0.575),all P<0.05],APTT was significantly prolonged in the ARDS group[s:49.70 (41.95,56.43) vs. 43.30 (39.40,49.60)],pH value,PaO2 and PaO2/FiO2 were significantly decreased[pH value:7.37 (7.30,7.43) vs. 7.41 (7.35,7.47),PaO2 (mmHg):82.00 (68.00,107.00) vs. 119.50 (101.25,154.00),PaO2/FiO2 (mmHg):157.00 (99.10,200.00) vs. 297.56 (228.00,386.00),all P<0.05]. Spearman correlation analysis showed in the sepsis-related ARDS group,plasma IL-6 was positively correlated with PCT,SOFA score,and Lac (r were 0.437,0.470,and 0.374,respectively;P value were 0.005,0.002,and 0.016,respectively),plasma sST2 levels were also positively correlated with PCT,SOFA score,and Lac (r were 0.492,0.454,and 0.441,respectively;P value were 0.009,0.013,and 0.015,respectively). Multivariate Logistic regression analysis indicated that plasma sST2 and IL-6 had diagnostic value for ARDS in patients with abdominal sepsis,with area under the curve (AUC) values of 0.978 and 0.719,respectively,and optimal cut-off values of 246.9 μg/L and 397.8 ng/L,both P<0.05,sensitivities were 86.2％ and 79.3％,and specificities were 100.0％ and 85.0％ for sST2 and IL-6,respectively. Conclusion Plasma sST2 and IL-6 are closely associated with ARDS in patients with abdominal sepsis and have high diagnostic value for identifying ARDS in this population.

Objective:To explore the efficacy of subcutaneous injection of granulocyte-macrophage colony-stimulating factor (GM-CSF) in preventing invasive fungal disease (IFD) in patients with multiple myeloma (MM).Methods:The clinical data of 222 patients who were admitted to the Second Hospital of Harbin Medical University from January 2015 to June 2021 were retrospectively analyzed. The patients was given GM-CSF (3-5 μg·kg -1·d -1, GM-CSF group) or granulocyte colony-stimulating factor (G-CSF, 2-5 μg·kg -1·d -1, G-CSF group) when neutrophils (ANC) ≤1.5×10 9/L after induction chemotherapy. Patients were discontinued when white blood cell count (WBC) ≥10.0×10 9/L. The incidence of IFD (including confirmed, clinical and proposed diagnosis) and breakthrough invasive fungal infections was compared between the two groups. Results:The incidence of IFD was 8.1% (18/222) in all patients. The incidence of IFD was 3.5% (3/85) and 10.9% (15/137) in the GM-CSF and G-CSF groups, respectively, and the difference between the two groups was statistically significant ( χ2 = 3.88, P = 0.049). In 9 patients of GM-CSF group receiving fungal infection prophylaxis and in 15 patients of G-CSF group receiving fungal infection prophylaxis, the incidence of breakthrough invasive fungal infections was 0 and 7 cases, respectively, and the difference between the two groups was statistically significant ( P = 0.022). Conclusions:GM-CSF application in MM patients can reduce the incidence of IFD and breakthrough invasive fungal infections.

Objective:To comprehensively describe the experience of economic toxicity in breast cancer patients by systematically integrating qualitative studies.Methods:Search the qualitative research literature on the economic toxicity experience of breast cancer patients from the PubMed, Web of Science, PsycINFQ, CINAHL, Embase, Cochrane Library, EBSCO, China National Knowledge Infratructure, Vip Network, Wanfang Patent Database and SinoMed from the warehouse until April 2023. Unified criteria were evaluated for the quality of the included literature, and the literature results were integrated by the pooled integration method.Results:A total of 11 articles were included, and 41 research results were summarized into 9 categories into 3 integrated results: the impact of economic toxicity on patients and families; adjust self-response to economic toxicity and achieve role growth; the needs and expectations for economic toxicity.Conclusions:Medical staff should pay attention to the economic burden and psychological pressure borne by breast cancer patients and their families during treatment, implement active psychological nursing intervention. Hospitals should build special social assistance channels, and social security departments should improve relevant medical insurance policies to reduce the economic toxicity of patients from multiple levels.