Background Light gradient boosting machine (LightGBM) has become a popular choice in prediction models due to its high efficiency and speed. However, the "black box" issues in machine learning models lead to poor model interpretability. At present, few studies have evaluated the severity of occupational injuries from the perspective of LightGBM model and model interpretability. Objective To evaluate the application value of LightGBM models and model interpretability methods in occupational injury prediction. Methods The Mine Safety and Health Administration (MSHA) occupational injury data set of mining industry workers from 1983 to 2022 was used. Injury severity (death/fatal occupational injury and permanent/partial disability) was used as the outcome variable, and the predictor variables included the month of occurrence, age, sex, time of accident, time since beginning of shift, accident time interval from shift start, total experience, total mining experience, experience at this mine, cause of injury, accident type, activity of injury, source of injury, body part of injury, work environment type, product category, and nature of injury. Feature sets were screened using least absolute shrinkage and selection operator (Lasso) regression. A LightGBM model was then employed to predict occupational injury, with area under curve (AUC) of the model serving as the primary evaluation metric; an AUC closer to 1 indicates better predictive performance of the model. The interpretability of the model was evaluated using Shapley additive explanations (SHAP). Results Through Lasso regression, 7 key influencing factors were identified, including accident time interval from shift start, experience at this mine, cause of injury, accident type, body part of injury, nature of injury, and work environment type. A LightGBM model, constructed based on feature selection via Lasso regression, demonstrated good predictive performance with an AUC value of 0.9941 (95%CI: 0.9917, 0.9966), accuracy of 0.9743, specificity of 0.9781, and sensitivity of 0.9640. The predicted probability of fatal occupational injuries showed high consistency with the actual probability of fatal occupational injuries. In the occupational injury prediction model, the importance of each indicator was analyzed through its SHAP value, and it was found that the body part of injury and the nature of injury were the two main features that affected the prediction results of the model, and the impacts of other features were relatively small. The distribution of SHAP values across body part of injury was broad, with significant impacts on the model's prediction of fatal risk, particularly for injuries to the head and neck, as well as multi-part injuries. The nature of injury also exerted influences on the model in different directions, with suffocation/drowning, crushing, and multi-part injuries having a greater impact on the risk of fatal occupational injuries. Conclusion LightGBM model is capable of efficiently processing large-scale data and providing high-precision prediction results. Research on model interpretability aids in more accurately exploring and analyzing various key risk factors for fatal occupational injuries among mining workers, and further reveals the complex interactions among these factors. This, in turn, enables better preventive intervention and protection measures, as well as optimal resource allocation for labor workers.

It is believed that retention due to deficient qi is an important pathogenesis of endometriosis （EMs）. Deficient qi is the root of the disease， mainly manifested as spleen deficiency， while retention is the branch pathogenesis of the disease， mainly with blood stasis， complicated with constraint， phlegm， heat， toxin and other pathological factors. Therefore， it is proposed to follow the treatment principle of supplementing deficiency and unblocking stagnation， and take the methods of replenishing qi and fortifying the spleen， removing stasis and eliminating concretions. Self-made Fuzheng Huayu Formula （扶正化瘀方） is taken as the basic formula， and can be modified with the symptoms in menstrual and non-menstrual periods. Additionally， the methods of moving qi， dispelling phlegm， clearing heat， relieving toxin and others can be combined， and it is recommended to treat the root and the branch simultaneously.

Objective:To explore the clinical outcomes of locking compression plating (LCP) in the treatment of periprosthetic fracture (PPF) of the distal femur in the aged patients.Methods:A retrospective study was performed to analyze the 31 aged patients who had been treated at Department of Orthopedic Surgery, The Affiliated Hospital to Nantong University for PPF of the distal femur with LCP between June 2012 and May 2023. There were 27 females and 4 males with an age of (80.2±6.1) years. According to the Unified Classification System (UCS), 18 PPFs were classified as type Ⅴ.3B1 and 6 PPFs as type Ⅴ.3B2 after total knee arthroplasty and 7 PPFs as type Ⅳ.3C after total hip arthroplasty. The patients were fixated with a lateral single plate in 25 cases, and with lateral and medial dual plates in 6 cases. The surgical time, intraoperative blood loss, hospitalization time, postoperative weight-bearing time, fracture healing time, and knee joint function and complications during follow-up were recorded.Results:For the 25 patients undergoing fixation with a lateral single plate, the surgical time was (58.7±7.9) minutes, the intraoperative blood loss (78.0±15.1) mL, the hospitalization time (6.9±1.6) days, the postoperative weight-bearing time (5.9±1.4) days, and the follow-up time 37 (15, 51) months. For the 6 patients undergoing fixation with lateral and medial dual plates, the surgical time was (186.6±9.8) minutes, the intraoperative blood loss (1,256.7±231.2) mL, the hospitalization time (17.8±3.3) days, the postoperative weight-bearing time (3.6±0.6) days, and the follow-up time 17 (16, 21) months. The fracture healing time was (14.9±2.0) and (18.7±2.6) weeks, respectively, for patients fixed with single and double steel plates. By the scoring criteria of the American Hospital for Special Surgery (HSS), the knee joint function was evaluated at the last follow-up as excellent in 10 cases and as good in 15 cases for the 25 patients undergoing fixation with a lateral single plate, and as good for all the 6 patients undergoing fixation with lateral and medial dual plates. No patient experienced such complications as incision infection, bone nonunion, or internal fixation failure during the follow-up period.Conclusions:LCP fixation can achieve satisfactory outcomes in the treatment of PPF of the distal femur in the aged patients. As fixation with a single lateral femoral plate is suitable for most of the aged patients with PPF of the distal femur, it can be used as the first choice. Fixation with dual plates can provide stronger stability, but its indications should be strictly controlled.

A popular use of marginal donor organs requires an optimization of organ preservation strategies. The current standards of organ preservation and static cold storage are insufficient to fulfill the demands of marginal donor organ preservation. Machine perfusion has been a primary development direction in organ preservation. Capable of improving preservation effectiveness and prolonging preservation time, it has the potential of becoming a practical platform for ex-vivo organ assessment and injury restoring. This review summarized the latest advances in organ preservation and restoration techniques.

Objective:To evaluate the efficacy of individualized removal therapeutic regimen for donor-specific antibodies (DSA) and examine its related influencing factors.Method:From January 2016 to January 2021, 34 recipients of kidney transplant (KT) underwent regular DSA testing and the results were positive. DSA removal therapy based upon rituximab (RTX) plus intravenous immune globulin (IVIG) was offered. Correlation between DSA negative conversion rate and DSA types, time from start of treatment to transplantation, HLA loci targeted by DSA and DSA mean fluorescent intensity (MFI) were analyzed retrospectively. Changes of immunedominant DSA (iDSA) and serum creatinine in individuals with de novo DSA (dnDSA) before and after treatment were also examined.Results:At Month 3 post-treatment, antibodies turned negative in 17/34(50.0%) patients and DSA became negative in 19/34(55.9%) at the last follow-up. Then we identified 78 DSA from all patients. No significant difference existed in negative conversion rate of pfDSA and dnDSA at Month 3 post-treatment [62.9%(39/62) vs 37.5%(6/16)] and at the last follow-up [4.2%(46/62) vs 56.3%(9/16)]( P=0.067, 0.219). For pfDSA, negative conversion rate of pfDSA with different MFIs after 3-month treatment varied significantly [negative conversion rate of weak positive DSA was 78.6%(33/42) and positive and above DSA 30%(6/20), P<0.001]. It was an independent related factor of whether or not pfDSA could turn negative (48.6%, 95% CI: 22.3%-66.8%, P=0.001). At the last follow-up, negative conversion rate of pfDSA differed markedly at different timepoints from start of treatment to transplantation [treated within 30 days post-operation was 79.2%(42/53) and over 30 days post-operation was 44.4%(4/9), P=0.042] and among different DSA MFI [88.1%(37/42) of weakly positive DSA and 45%(9/20) of positive and above DSA, P<0.001] and they were independent related factors for negative conversion of pfDSA (34.8%, 95% CI: 3.2%-61.8%, P=0.008; 43.1%, 95% CI: 18.5%-63.4%, P=0.001). Mean decline rate in iDSA was 66.67% at Month 3 post-treatment and 77.90% at the last follow-up. The difference was statistically significant ( P=0.035). Serum level of creatinine of 9 patients with dnDSA was (110.2±26.9) μmol/L pre-treatment, (178.8±90.5) μmol/L during treatment, (153.9±72.8) μmol/L at Month 3 post-treatment and (213.6±185.8) μmol/L at the last follow-up. Serum creatinine rose during treatment ( t=-2.794, P=0.023), declined at Month 3 post-treatment ( t=3.430, P=0.009) and spiked again at the last follow-up ( P=0.028). Conclusion:After DSA removal therapy based upon RTX plus IVIG, negative conversion rate of pfDSA is correlated with its MFI and time from start of treatment to transplantation. There is no significant rebound in DSA MFI and graft function of dnDSA patients improves immediately after treatment.

China has made remarkable advances in the field of organ donation and transplantation. However, with surging demands for organ transplantation services, there is still a large gap. Thus the Chinese development of organ donation and transplantation has a lot of catch-ups. The new Regulations on Human Organ Donation and Transplantation accorded with domestic conditions, culture and ethics. It specified that organ donation and transplantation should adhere to the general principle of "People Foremost & Life Primary" and strengthen the top-level designs of five operating systems of organ donation, acquisition & distribution, transplant clinical services, transplant quality control and supervising & optimizing. Upholding the protection of the rights and interests of both donors and recipients, it strengthened the supervision of the whole process of organ donation & transplantation, emphasized the importance of publicity & education of organ donation, provided a more solid legal guarantees for standardizing and promoting organ donation & transplantation and ushered in new opportunities for further developments of human organ donation & transplantation.

Objective:To explore the application effect of the teaching method combining process-oriented-guided inquiry learning (POGIL) theory and micro-class in orthopedic clinical internship.Methods:The 118 interns who completed internship from January 2022 to December 2022 were randomly divided into a control group (58) and an experimental group (60). The control group received traditional teaching, while the experimental group received a teaching method combining POGIL theory and micro-class. After the internship, the two groups were compared for assessment scores (basic theoretical knowledge and professional theoretical knowledge), learning status (classroom performance and self-learning ability), clinical practice ability (Leicester Assessment Scale), and teaching satisfaction. The t-test and chi-square test were performed using SPSS 21.0. Results:After the internship, the assessment scores, classroom performance, self-directed learning ability scores, clinical skills, case writing scores, and teaching satisfaction of the experimental group were all higher than those of the control group ( t/ χ2=5.01, 3.72, 2.20, 6.57, 3.56, 4.52, P<0.05). Conclusions:The teaching method combining POGIL theory and micro-class can enhance the master of theoretical knowledge by orthopedic interns, optimize classroom performance, cultivate self-learning ability, and improve clinical practice ability and teaching satisfaction.

OBJECTIVE: To assess the value of non-invasive prenatal testing (NIPT) for detecting fetal chromosomal microdeletion/microduplication syndromes by carrying out prenatal diagnoses for two fetuses with Xp22.31 microdeletion indicated by NIPT. METHODS: Two pregnant women suspected for fetal Xp22.31 microdeletion syndrome who presented at Zaozhuang Maternal and Child Health Care Hospital on December 5, 2017 and October 15, 2020 were selected as the study subjects. Clinical data of the two women were collected, and peripheral venous blood samples were collected for NIPT testing. Amniotic fluid samples were taken for G-banding chromosomal karyotyping analysis and copy number variation sequencing (CNV-seq) for fetus 1, while G-banding chromosomal karyotyping and single nucleotide polymorphism microarray analysis (SNP array) were carried out for fetus 2. Peripheral venous blood samples of couple 1 were collected for CNV-seq to verify the origin of copy number variation . RESULTS: NIPT indicated that fetus 1 had harbored a 1.3 Mb deletion in the Xp22.31 region, while G-banding chromosomal karyotyping had found no abnormality. CNV-seq analysis verified the fetus to be seg[GRCh37]del(X)(p22.31)chrX:g.6800001_7940000del, with a 1.14 Mb deletion at Xp22.31, which was derived from its mother. NIPT indicated that fetus 2 had harbored a 1.54 Mb deletion in the Xp22.31 region, while G-banding chromosomal karyotyping had found no abnormality. SNP array analysis indicated arr[GRCh37]Xp22.31(6458940_8003247)×0, with a 1.54 Mb deletion in Xp22.31 region. CONCLUSION NIPT not only has a good performance for detecting fetal trisomies 21, 18 and 13, but also has the potential for detecting chromosomal microdeletion/microduplications. For high risk fetuses indicated by NIPT, prenatal diagnosis needs to be carry out to verify the chromosomal abnormalities.
Child ; Female ; Pregnancy ; Humans ; DNA Copy Number Variations ; Prenatal Diagnosis ; Down Syndrome/diagnosis* ; Chromosome Aberrations ; Fetus

OBJECTIVE: To assess the value of non-invasive prenatal testing (NIPT) for trisomy 21 (T21), trisomy 18 (T18), trisomy 13 (T13), sex chromosome aneuploidies, chromosomal microdeletions and microduplications using cell-free fetal DNA from peripheral blood samples of pregnant women. METHODS: A total of 15 237 pregnant women who had undergone NIPT testing at the Maternity and Child Health Care Hospital of Zaozhuang from February 2015 to December 2021 were enrolled in this study. For those with a high risk by NIPT, amniotic fluid samples were collected for G-banding chromosomal karyotyping analysis and chromosomal microarray analysis to verify the consistency of NIPT with results of prenatal diagnosis. All of the women were followed up by telephone for pregnancy outcomes. RESULTS: Among the 15 237 pregnant women, 266 (1.75%) were detected with a high risk for fetal chromosomal abnormality were detected. Among these, 79 (29.7%) were at a high risk for T21, 26 (9.77%) were at a high risk for T18, 9 (3.38%) were at a high risk for T13, 74 (27.82%) were at a high risk for sex chromosome aneuploidies, 12 (4.51%) were at a high risk for other autosomal aneuploidies, and 66 (24.81%) were at a high risk for chromosomal microdeletions or microduplications. 217 women had accepted invasive prenatal diagnosis and respectively 50, 13, 1, 25, 1 and 18 were confirmed with T21, T18, T13, sex chromosome aneuploidies, autosomal aneuploidies and microdeletions/microduplications, and the positive predictive values were 75.76%, 68.42%, 11.11%, 40.32%, 10% and 35.29%, respectively. For 13 042 women (85.59%), the outcome of pregnancy were successfully followed up. During the follow-up, one false negative case of T21 was discovered. No false positive cases for T13 and T18 were found. CONCLUSION NIPT has a sound performance for screening T13, T18 and T21, and is also valuable for screening other autosomal aneuploidies, sex chromosome aneuploidies and chromosomal microdeletions/microduplications.
Child ; Female ; Pregnancy ; Humans ; Retrospective Studies ; Cell-Free Nucleic Acids ; Chromosome Disorders/genetics* ; Prenatal Diagnosis/methods* ; Down Syndrome/genetics* ; Sex Chromosome Aberrations ; Trisomy 18 Syndrome/genetics* ; Trisomy 13 Syndrome/diagnosis* ; Aneuploidy ; DNA/genetics* ; Trisomy/genetics*

Background Identification and analysis of influencing factors of occupational injury is an important research content of feature selection. In recent years, with the rise of machine learning algorithms, feature selection combined with Boosting algorithm provides a new analysis idea to construct occupational injury prediction models. Objective To evaluate applicability of Boosting algorithm-based model in predicting severity of miners' non-fatal occupational injuries, and provide a basis for rationally predicting the severity level of miners' non-fatal occupational injuries. Methods The publicly available data of the US Mine Safety and Health Administration (MSHA) from 2001 to 2021 on metal miners' non-fatal occupational injuries were used, and the outcome variables were lost working days < 105 d (minor injury) and ≥ 105 d (serious injury). Four different feature sets were screened out by four feature selection methods including least absolute shrinkage and selection operator (Lasso) regression, stepwise regression, single factor + Lasso regression, and single factor + stepwise regression. Logistic regression, gradient boosting decision tree (GBDT), and extreme gradient boosting (XGBoost) were selected to construct prediction models by training with the four feature sets. A total of 12 prediction models of severity of miners' non-fatal occupational injuries were built and their area under the curve (AUC), sensitivity, specificity, and Youden index were calculated for model evaluation. Results According to the results of four feature selection methods, age, time of accident occurrence, total length of service, cause of injury, activities that triggered injury occurrence, body part of injury, nature of injury, and outcome of injury were identified as influencing factors of non-fatal occupational injury severity in miners. Feature set 4 was the optimal set screened out by single factor+stepwise regression and the GBDT model presented the best predictive performance in predicting the severity of non-fatal occupational injuries. The associated specificity, sensitivity, and Youden index were 0.7530, 0.9490, and 0.7020, respectively. The AUC values of logistic regression, GBDT, and XGBoost models trained by feature set 4 were 0.8526 (95%CI: 0.8387, 0.8750), 0.8640 (95%CI: 0.8474, 0.8806), and 0.8603 (95%CI: 0.8439, 0.8773), respectively, higher than the AUC values trained by feature set 2 [0.8487 (95%CI: 0.8203, 0.8669), 0.8110 (95%CI: 0.8012, 0.8344), and 0.8439 (95%CI: 0.8245, 0.8561), respectively] . The AUC values of GBDT and XGBoost models trained by feature set 4 were higher than that of logistic regression model. Conclusion The performance of the prediction models constructed by predictors screened out by two feature selection methods is better than those by single feature selection methods. At the same time, under the condition of optimal feature set, the performance of model prediction based on Boosting is better than that of traditional logistic regression model.