ObjectiveTo investigate the value of predictive models established based on machine learning methods in predicting the risk of metabolic associated fatty liver disease （MAFLD）， and to analyze its key risk factors. MethodsA retrospective analysis was performed for the 50 variables of 2 168 healthy individuals who underwent physical examination in Department of Health Assessment， Xiyuan Hospital， China Academy of Chinese Medical Sciences， from January 2021 to December 2024， including body composition， past history， and laboratory tests， and according to whether they were diagnosed with MAFLD or not， they were divided into MAFLD group with 265 individuals and non-MAFLD group with 1 903 individuals. The Mann-Whitney U test was used for comparison of continuous data between two groups， and the chi-square test was used for comparison of categorical data between two groups. Randomly split the research data into a training set and a validation set in a 70% to 30% ratio. Predictive factors were screened from the training set data using univariate analysis， LASSO regression， and multivariate Logistic regression analysis. Predictive models were then constructed using seven machine learning methods： Logistic regression， decision tree， random forest （RF）， eXtreme gradient boosting， light gradient boosting machine， support vector machine， and artificial neural network. Model performance was evaluated by plotting receiver operating characteristic curve for the validation set and calculating the area under the curve （AUC）， sensitivity， specificity， and Youden index for each model. Furthermore， the SHapley Additive exPlanation （SHAP） method was used to analyze the contribution of variables in the optimal model. ResultsThe prevalence rate of MAFLD among the 2 168 subjects was 12.22% （265/2 168）. Smoking， diastolic blood pressure， phase angle， visceral fat area， muscle fat ratio， waist-to-hip ratio， aspartate aminotransferase， non-HDL-C/HDL-C ratio， triglyceride-glucose index， and gallstones were independent risk factors for MAFLD （all P<0.05）. The seven predictive models of support vector machine， eXtreme gradient boosting， decision tree， light gradient boosting machine， artificial neural network， RF， and Logistic regression had an AUC of 0.738， 0.754， 0.757， 0.786， 0.795， 0.796， and 0.815， respectively， in the validation set， among which the RF model had the best discriminatory ability （AUC=0.796， 95% confidence interval： 0.754 — 0.839）， with a sensitivity of 81.01%， a specificity of 63.16%， and a Youden index of 44.17%. The SHAP analysis showed that visceral fat area， waist-to-hip ratio， and diastolic blood pressure were the top three predictive factors in terms of importance. ConclusionThe RF model， constructed based on body composition and clinical indicators， has a good performance in predicting the risk of MAFLD， and its interpretability can help to identify high-risk individuals in the early stage in clinical practice.

Objective:To summarize and analyze the clinical characteristics of pediatric pulmonary hypertension (PH) and the related factors affecting the prognosis，to provide a basis for the early diagnosis and treatment of the disease.Methods:The clinical data of 80 PH children hospitalized in the intensive care department of Children's Hospital of Capital Pediatric Research Institute from January 1,2019 to December 31,2022 were retrospectively analyzed,and general data,clinical symptoms, echocardiography, laboratory examination and treatment indicators were collected. According to survival death groups, multivariate Logistic regression was applied to analyze independent associated risk factors for PH death.Results:（1）Clinical characteristics of childhood PH: more common in infants, the average age of treatment was 0.9(0.3-5.3)years, the male to female ratio was 1.3∶1, and the average time from first symptoms to first diagnosis was 6.5 (2,14) days. The etiology of PH in children was complex, with arterial PH (PAH) (40%), pulmonary disease and(or) hypoxia (33.8%) being the most common. The main clinical manifestations were dyspnea, decreased activity endurance, poor appetite, and positive heart examination. Severe PH accounted for 53.8%, 30% of pulmonary hypertensive crisis.（2）Factors affecting the prognosis of childhood PH: childhood PH mortality was 20.8%, compared with the survival group, ICU length of stay, loss of appetite, decreased urine volume, cardiac function classification, right heart size, main pulmonary artery diameter/ascending aorta diameter ratio(MPAD/MAD), vasoactive inotropic score(VIS), use of invasive ventilator treatment had statistical significance (all P<0.05). A Logistic regression analysis of death-related factors showed that right heart enlargement ( OR=0.193,95% CI 0.040-0.919, P=0.039), higher MPAD/MAD value ( OR =11.883,95% CI 1.347-104.869, P=0.026), and higher VIS score ( OR= 1.029,95% CI 1.003-1.056, P=0.028) were independent risk factors for poor prognosis. Conclusion:（1）Children PH is mainly infants, the causes of PAH and pulmonary diseases, severe PH accounted for 53.8%, 30% of which have pulmonary hypertensive crisis.（2）An enlarged right heart, higher MPAD/MAD values, and higher VIS score are independent risk factors for death in children with PH.

BACKGROUND:Adolescent lumbar disc herniation is the main cause of low back pain in adolescents. At present,most of them are treated by conservativetreatment. When long-term non-surgical treatment attempts,surgery may be necessary to prevent further injury when the patient's symptoms are notsufficiently relieved or when the patient has symptoms of single nerve paralysis or compression of the cauda equina,it is very important to choose a suitable interbody fusion device for the surgical treatment of the patients.OBJECTIVE:To explore the effects of minimally invasive interbody fusion with different heights on lumbar biomechanics in patients with adolescent lumbar disc herniation.METHODS:CT scans of a 17-year-old male patient with adolescent lumbar disc herniation (L4-5 segment herniation) were collected. After the three-dimensional reconstruction of MIMICS,the interbody fusion device equal to and 3 mm higher than the intervertebral space was selected for analysis,so two expandablemixed material interbody fusion devices were designed and reconstructed. Fusion device L:11 mm high front,9 mm high posterior,9 mm wide,28 mmlong,and fusion device H:14 mm high front,11 mm high posterior,11 mm wide,28 mm long and the lumbar fusion device was modeled. The fusion deviceand lumbar spine model were optimized,inversely modeled,and then imported into ABAQUS,and finally the 3D model of lumbar fusion was obtained.The physiological activities of the human body were simulated,such as lumbar extension,forward bending,right bending,and left bending,to obtain thecorresponding stress contours. The biomechanical characteristics of the L4-5 vertebra under seven different working conditions were observed.RESULTS AND CONCLUSION:(1) The maximum stress of the two kinds of fuses was in the condition of forward bending and backward extension,the stress value of H fuses was (18.27±3.80) Mpa and (15.02±3.24) Mpa;the stress value of L fuses was (9.16±0.05) Mpa and (9.17±1.83) Mpa. The stress values of the end plate of the H-fusion in the extension station were (19.11±4.03) Mpa and (16.32±3.72) Mpa respectively. The stress values of the L-fusion end plate were (9.13±0.01) Mpa and (4.92±1.01) Mpa respectively. (2) The stress of H-type fusing end plate was higher than that of L-type fusing end plate except for L-5 end plate at neutral position (P<0.05). (3) Choosing an interbody fusion device with a height of more than 3 mm in the same intervertebral space has a more stable biomechanics.

Objective:To investigate the changes in thyroid hormone levels and inflammatory markers in critically ill children，analyze their correlation with disease severity，and explore their potential impact on prognosis,providing references for clinical management and prognosis assessment in critical illness.Methods:A retrospective cohort study was conducted involving 394 pediatric patients admitted to the ICU of the Capital Pediatric Institute Affiliated Children's Hospital from 2019 to 2023.Based on the pediatric critical illness score,patients were divided into three groups:the extremely critical group (score ≤ 70, n=81),the critical group (score 71–80, n=150),and the non-critical group (score>80, n=163).Data collected included thyroid function indicators，inflammatory markers[C-reactive protein（CRP)，procalcitonin(PCT),tumor necrosis factor(TNF)-α，interleukin (IL)，etc.]，clinical information，and outcomes.The correlation between thyroid function indicators and inflammatory markers were analyzed.The predictive value of thyroid function indicators and inflammatory markers for prognosis in critically ill pediatric patients was assessed. Results:Of the 394 children,non-thyroidal disease syndrome occurred in 321 cases,with an overall incidence of 81.5%,which increased with disease severity.Thyroid hormone [total triiodothyronine (TT3),free triiodothyronine (FT3),and total tetraiodothyronine (TT4)] levels were significantly lower in the extremely critical group than in the other groups ( P<0.05).Inflammatory markers such as CRP,PCT,TNF-α,IL-6,IL-8,and IL-10 were significantly higher in the extremely critical group than in the other groups ( P<0.05).Thyroid hormones were negatively correlated with inflammatory markers,and the receivor operating characteristic curves analysis indicated that TT3,FT3,IL-6 and IL-8 levels,could effectively differentiate disease prognosis.Univariate regression model showed significant associations between TT3,FT3,TT4,PCT,IL-8,and IL-10 and disease prognosis.The multivariate Logistic regression model showed IL-6 and IL-8 were independent predictors of disease prognosis. Conclusion:Significant reductions in thyroid hormone levels are closely related to disease severity and poor prognosis.Changes in inflammatory markers reflect the inflammatory state and severity of the disease and impact prognosis.Monitoring thyroid function and inflammatory status is important in clinical management，which provids new insights into prognosis assessment and treatment strategies for critically ill children.

The efficacy of preoperative neoadjuvant chemoradiotherapy(nCRT)in locally advanced rectal cancer(LARC)is predicted using radiomic features of the target areas in radiotherapy for rectal cancer and an interpretable machine learning model.The clinical data are collected from 290 LARC patients who are divided into effective and ineffective groups based on tumor regression grade.The extracted radiomic features and clinicopathological data are used to develop prediction models.The optimal model is determined based on AUC performance evaluation,and the explanatory analysis is conducted using nomogram and decision curve.A total of 223 patients are included in the study,with 48 in the effective group.There are 156 patients in the training set(34 in the effective group)and 67 patients in the validation set(14 in the effective group).The nomogram model shows the best performance,with AUC of 0.858 in the training set and 0.844 in internal test set,and decision curve analysis demonstrated its superior net clinical benefit across most threshold ranges than other models.Combining radiomics and clinical variables,the nomogram can effectively predict nCRT outcomes and support clinical decision-making.

BACKGROUND:Adolescent lumbar disc herniation is the main cause of low back pain in adolescents. At present,most of them are treated by conservativetreatment. When long-term non-surgical treatment attempts,surgery may be necessary to prevent further injury when the patient's symptoms are notsufficiently relieved or when the patient has symptoms of single nerve paralysis or compression of the cauda equina,it is very important to choose a suitable interbody fusion device for the surgical treatment of the patients.OBJECTIVE:To explore the effects of minimally invasive interbody fusion with different heights on lumbar biomechanics in patients with adolescent lumbar disc herniation.METHODS:CT scans of a 17-year-old male patient with adolescent lumbar disc herniation (L4-5 segment herniation) were collected. After the three-dimensional reconstruction of MIMICS,the interbody fusion device equal to and 3 mm higher than the intervertebral space was selected for analysis,so two expandablemixed material interbody fusion devices were designed and reconstructed. Fusion device L:11 mm high front,9 mm high posterior,9 mm wide,28 mmlong,and fusion device H:14 mm high front,11 mm high posterior,11 mm wide,28 mm long and the lumbar fusion device was modeled. The fusion deviceand lumbar spine model were optimized,inversely modeled,and then imported into ABAQUS,and finally the 3D model of lumbar fusion was obtained.The physiological activities of the human body were simulated,such as lumbar extension,forward bending,right bending,and left bending,to obtain thecorresponding stress contours. The biomechanical characteristics of the L4-5 vertebra under seven different working conditions were observed.RESULTS AND CONCLUSION:(1) The maximum stress of the two kinds of fuses was in the condition of forward bending and backward extension,the stress value of H fuses was (18.27±3.80) Mpa and (15.02±3.24) Mpa;the stress value of L fuses was (9.16±0.05) Mpa and (9.17±1.83) Mpa. The stress values of the end plate of the H-fusion in the extension station were (19.11±4.03) Mpa and (16.32±3.72) Mpa respectively. The stress values of the L-fusion end plate were (9.13±0.01) Mpa and (4.92±1.01) Mpa respectively. (2) The stress of H-type fusing end plate was higher than that of L-type fusing end plate except for L-5 end plate at neutral position (P<0.05). (3) Choosing an interbody fusion device with a height of more than 3 mm in the same intervertebral space has a more stable biomechanics.

The efficacy of preoperative neoadjuvant chemoradiotherapy(nCRT)in locally advanced rectal cancer(LARC)is predicted using radiomic features of the target areas in radiotherapy for rectal cancer and an interpretable machine learning model.The clinical data are collected from 290 LARC patients who are divided into effective and ineffective groups based on tumor regression grade.The extracted radiomic features and clinicopathological data are used to develop prediction models.The optimal model is determined based on AUC performance evaluation,and the explanatory analysis is conducted using nomogram and decision curve.A total of 223 patients are included in the study,with 48 in the effective group.There are 156 patients in the training set(34 in the effective group)and 67 patients in the validation set(14 in the effective group).The nomogram model shows the best performance,with AUC of 0.858 in the training set and 0.844 in internal test set,and decision curve analysis demonstrated its superior net clinical benefit across most threshold ranges than other models.Combining radiomics and clinical variables,the nomogram can effectively predict nCRT outcomes and support clinical decision-making.

BACKGROUND:The asymmetrical biomechanical environment of adolescent idiopathic scoliosis can lead to further wedge deformation of the vertebral body,which may affect cardiopulmonary function and compress nerves in severe cases.Adolescent idiopathic scoliosis with different degrees of scoliosis should be treated with exercise,bracing,and surgery.However,the mechanical mechanism of selecting an orthopedic approach remains unclear due to the individual variability of patients.OBJECTIVE:To investigate the biomechanical mechanism of different orthopedic modalities for the treatment of adolescent idiopathic scoliosis to provide a basis for clinical selection of treatment modalities based on the spine model of adolescent idiopathic scoliosis patients.METHODS:Based on the CT images of an adolescent idiopathic scoliosis patient,a scoliosis model(C7-L5)was reconstructed in Mimics software in three dimensions,and lateral thrust force was applied at the T8/T9 thorax and vertical distraction force was applied over the C7 vertebra with the magnitude of 20,40,60,80,100,and 120 N.The intervertebral disc stress and vertebral displacement in concave and convex sides,and Cobb angle of the spine were analyzed under two orthopedic modalities.RESULTS AND CONCLUSION:(1)With lateral thrust,there was no significant change in the C7T1-T7T8 intervertebral disc.The concave and convex stress of T7T8-L4L5 segment decreased first and then increased with the increase of lateral thrust force.The correction effect of lateral thrust on the segment near T8T9 was obvious and weakened with the extension of the segment to the cephalic and caudal ends.At 120 N of lateral thrust,the thoracic Cobb angle changed from 53.2° to 32.5° and the lumbar Cobb angle changed from 50.2° to 43.9°.(2)With the vertical distraction,the thoracic intervertebral disc stresses first decreased and then increased,and all the lumbar disc stresses decreased.The C7 displacement was the most obvious,and the correction effect gradually diminished with the segment extended to the caudal end.At a vertical distraction force of 120 N,the thoracic Cobb angle changed from 53.2° to 39.4° and the lumbar Cobb angle changed from 50.2° to 47.6°.(3)It is concluded that both orthopedic modalities provide improvement in the degree of scoliosis,with the thoracic correction being greater than the lumbar correction.Also,the asymmetric stress distribution on the concave and convex sides is improved,which contributes to normal bone growth.A vertical distraction approach is appropriate for larger Cobb angles,and a lateral thrust approach is appropriate for smaller Cobb angles.The results of this study help to understand the mechanism of spinal orthosis and provide a theoretical basis for the choice of orthopedic approach.

Objective:To summarize and analyze the clinical characteristics of pediatric pulmonary hypertension (PH) and the related factors affecting the prognosis，to provide a basis for the early diagnosis and treatment of the disease.Methods:The clinical data of 80 PH children hospitalized in the intensive care department of Children's Hospital of Capital Pediatric Research Institute from January 1,2019 to December 31,2022 were retrospectively analyzed,and general data,clinical symptoms, echocardiography, laboratory examination and treatment indicators were collected. According to survival death groups, multivariate Logistic regression was applied to analyze independent associated risk factors for PH death.Results:（1）Clinical characteristics of childhood PH: more common in infants, the average age of treatment was 0.9(0.3-5.3)years, the male to female ratio was 1.3∶1, and the average time from first symptoms to first diagnosis was 6.5 (2,14) days. The etiology of PH in children was complex, with arterial PH (PAH) (40%), pulmonary disease and(or) hypoxia (33.8%) being the most common. The main clinical manifestations were dyspnea, decreased activity endurance, poor appetite, and positive heart examination. Severe PH accounted for 53.8%, 30% of pulmonary hypertensive crisis.（2）Factors affecting the prognosis of childhood PH: childhood PH mortality was 20.8%, compared with the survival group, ICU length of stay, loss of appetite, decreased urine volume, cardiac function classification, right heart size, main pulmonary artery diameter/ascending aorta diameter ratio(MPAD/MAD), vasoactive inotropic score(VIS), use of invasive ventilator treatment had statistical significance (all P<0.05). A Logistic regression analysis of death-related factors showed that right heart enlargement ( OR=0.193,95% CI 0.040-0.919, P=0.039), higher MPAD/MAD value ( OR =11.883,95% CI 1.347-104.869, P=0.026), and higher VIS score ( OR= 1.029,95% CI 1.003-1.056, P=0.028) were independent risk factors for poor prognosis. Conclusion:（1）Children PH is mainly infants, the causes of PAH and pulmonary diseases, severe PH accounted for 53.8%, 30% of which have pulmonary hypertensive crisis.（2）An enlarged right heart, higher MPAD/MAD values, and higher VIS score are independent risk factors for death in children with PH.

Objective To systematically retrieve,evaluate and summarise the best available evidence on prevention and management of diagnostic blood loss in critically ill adult patients and to provide guidance for standardising diagnostic blood sampling in clinical practice.Methods A structured evidence question was created using the PIPOST framework(Population,Intervention,Professional,Outcome,Setting and Type of evidence).Guided by the"5S"levels-of-evidence pyramid,a top-down systematic search was conducted on databases of BMJ Best Practice,UpToDate,the Joanna Briggs Institute(JBI)EBP Database,GIN,SIGN,RNAO,NICE,Medlive Guideline,WHO,National Blood Authority(Australia),National Health Commission of China,Cochrane Library,PubMed,EMbase,CINAHL,Web of Science,Wanfang Data,CNKI,VIP,and SinoMed.Searched literature included clinical decision aids,guidelines,evidence summaries,systematic reviews Meta analysis,RCTs,quasi-experimental,cross-sectional,cohort studies and expert consensus/opinions.Search period covered between 1st January 2015 and 10th February 2025.Quality appraisal,evidence extraction,synthesis and grading were performed according to JBI and GRADE approaches.Results Nineteen articles were retrieved including five guidelines,five systematic reviews,one RCT,two quasi-experimental studies,two cross-sectional studies,one professional standard and three expert consensuses.A total of 26 recommendations were extracted and they were organised into five domains:education and training,blood-sampling assessment,frequency of sampling,strategies to minimise blood volume drawn,and quality control.Conclusion This evidence summary provides the best current guidance for preventing and managing iatrogenic blood loss caused by diagnostic testing in critically ill adults,providing evidence-based basis for standardizing blood tests by medical staff.