Objective: Machine learning (ML) has been reported to have better predictive capability than traditional statistical techniques. The aim of this study was to assess the efficacy of ML algorithms and logistic regression (LR) for predicting depressive symptoms during the COVID-19 pandemic. Methods: Analyses were carried out in a national cross-sectional study involving 21,916 participants. The ML algorithms in this study included random forest (RF), support vector machine (SVM), neural network (NN), and gradient boosting machine (GBM) methods. The performance indices were sensitivity, specificity, accuracy, precision, F1-score, and area under the receiver operating characteristic curve (AUC). Results: LR and NN had the best performance in terms of AUCs. The risk of overfitting was found to be negligible for most ML models except for RF, and GBM obtained the highest sensitivity, specificity, accuracy, precision, and F1-score. Therefore, LR, NN, and GBM models ranked among the best models. Conclusion Compared with ML models, LR model performed comparably to ML models in predicting depressive symptoms and identifying potential risk factors while also exhibiting a lower risk of overfitting.

Objective: Machine learning (ML) has been reported to have better predictive capability than traditional statistical techniques. The aim of this study was to assess the efficacy of ML algorithms and logistic regression (LR) for predicting depressive symptoms during the COVID-19 pandemic. Methods: Analyses were carried out in a national cross-sectional study involving 21,916 participants. The ML algorithms in this study included random forest (RF), support vector machine (SVM), neural network (NN), and gradient boosting machine (GBM) methods. The performance indices were sensitivity, specificity, accuracy, precision, F1-score, and area under the receiver operating characteristic curve (AUC). Results: LR and NN had the best performance in terms of AUCs. The risk of overfitting was found to be negligible for most ML models except for RF, and GBM obtained the highest sensitivity, specificity, accuracy, precision, and F1-score. Therefore, LR, NN, and GBM models ranked among the best models. Conclusion Compared with ML models, LR model performed comparably to ML models in predicting depressive symptoms and identifying potential risk factors while also exhibiting a lower risk of overfitting.

Objective: Machine learning (ML) has been reported to have better predictive capability than traditional statistical techniques. The aim of this study was to assess the efficacy of ML algorithms and logistic regression (LR) for predicting depressive symptoms during the COVID-19 pandemic. Methods: Analyses were carried out in a national cross-sectional study involving 21,916 participants. The ML algorithms in this study included random forest (RF), support vector machine (SVM), neural network (NN), and gradient boosting machine (GBM) methods. The performance indices were sensitivity, specificity, accuracy, precision, F1-score, and area under the receiver operating characteristic curve (AUC). Results: LR and NN had the best performance in terms of AUCs. The risk of overfitting was found to be negligible for most ML models except for RF, and GBM obtained the highest sensitivity, specificity, accuracy, precision, and F1-score. Therefore, LR, NN, and GBM models ranked among the best models. Conclusion Compared with ML models, LR model performed comparably to ML models in predicting depressive symptoms and identifying potential risk factors while also exhibiting a lower risk of overfitting.

Objective: Machine learning (ML) has been reported to have better predictive capability than traditional statistical techniques. The aim of this study was to assess the efficacy of ML algorithms and logistic regression (LR) for predicting depressive symptoms during the COVID-19 pandemic. Methods: Analyses were carried out in a national cross-sectional study involving 21,916 participants. The ML algorithms in this study included random forest (RF), support vector machine (SVM), neural network (NN), and gradient boosting machine (GBM) methods. The performance indices were sensitivity, specificity, accuracy, precision, F1-score, and area under the receiver operating characteristic curve (AUC). Results: LR and NN had the best performance in terms of AUCs. The risk of overfitting was found to be negligible for most ML models except for RF, and GBM obtained the highest sensitivity, specificity, accuracy, precision, and F1-score. Therefore, LR, NN, and GBM models ranked among the best models. Conclusion Compared with ML models, LR model performed comparably to ML models in predicting depressive symptoms and identifying potential risk factors while also exhibiting a lower risk of overfitting.

Objective: Machine learning (ML) has been reported to have better predictive capability than traditional statistical techniques. The aim of this study was to assess the efficacy of ML algorithms and logistic regression (LR) for predicting depressive symptoms during the COVID-19 pandemic. Methods: Analyses were carried out in a national cross-sectional study involving 21,916 participants. The ML algorithms in this study included random forest (RF), support vector machine (SVM), neural network (NN), and gradient boosting machine (GBM) methods. The performance indices were sensitivity, specificity, accuracy, precision, F1-score, and area under the receiver operating characteristic curve (AUC). Results: LR and NN had the best performance in terms of AUCs. The risk of overfitting was found to be negligible for most ML models except for RF, and GBM obtained the highest sensitivity, specificity, accuracy, precision, and F1-score. Therefore, LR, NN, and GBM models ranked among the best models. Conclusion Compared with ML models, LR model performed comparably to ML models in predicting depressive symptoms and identifying potential risk factors while also exhibiting a lower risk of overfitting.

BACKGROUND: Severe stroke has high rates of mortality and morbidity. This study aimed to investigate the clinical course, causes of worsening, and outcomes of severe ischemic stroke. METHODS: This prospective, multicenter cohort study enrolled adult patients admitted ≤30 days after ischemic stroke from nine hospitals in China between September 2017 and December 2019. Severe stroke was defined as a score of ≥15 on the National Institutes of Health Stroke Scale (NIHSS). Clinical worsening was defined as an increase of 4 in the NIHSS score from baseline. Unfavorable functional outcome was defined as a modified Rankin scale score ≥3 at 3 months and 1 year after stroke onset, respectively. We performed Logistic regression to explore baseline features and reperfusion therapies associated with clinical worsening and functional outcomes. RESULTS: Among 4201 patients enrolled, 854 patients (20.33%) had severe stroke on admission. Of 3347 patients without severe stroke on admission, 142 (4.24%) patients developed severe stroke in hospital. Of 854 patients with severe stroke on admission, 33.95% (290/854) experienced clinical worsening (median time from stroke onset: 43 h, Q1-Q3: 20-88 h), with brain edema (54.83% [159/290]) as the leading cause; 24.59% (210/854) of these patients died by 30 days, and 81.47% (677/831) and 78.44% (633/807) had unfavorable functional outcomes at 3 months and 1 year respectively. Reperfusion reduced the risk of worsening (adjusted odds ratio [OR]: 0.24, 95% confidence interval [CI]: 0.12-0.49, P  <0.01), 30-day death (adjusted OR: 0.22, 95% CI: 0.11-0.41, P  <0.01), and unfavorable functional outcomes at 3 months (adjusted OR: 0.24, 95% CI: 0.08-0.68, P <0.01) and 1 year (adjusted OR: 0.17, 95% CI: 0.06-0.50, P  <0.01). CONCLUSIONS: Approximately one-fifth of patients with ischemic stroke had severe neurological deficits on admission. Clinical worsening mainly occurred in the first 3 to 4 days after stroke onset, with brain edema as the leading cause of worsening. Reperfusion reduced the risk of clinical worsening and improved functional outcomes. REGISTRATION ClinicalTrials.gov , NCT03222024.
Humans ; Male ; Female ; Prospective Studies ; Ischemic Stroke/mortality* ; Aged ; Middle Aged ; Aged, 80 and over ; Stroke ; Brain Ischemia

Hematologic malignancies, including leukemia, lymphoma, and multiple myeloma, are hazardous diseases characterized by the uncontrolled proliferation of cancer cells. Dysregulated cell cycle resulting from genetic and epigenetic abnormalities constitutes one of the central events. Importantly, cyclin-dependent kinases (CDKs), complexed with their functional partner cyclins, play dominating roles in cell cycle control. Yet, efforts in translating CDK inhibitors into clinical benefits have demonstrated disappointing outcomes. Recently, mounting evidence highlights the emerging significance of WEE1 G2 checkpoint kinase (WEE1) to modulate CDK activity, and correspondingly, a variety of therapeutic inhibitors have been developed to achieve clinical benefits. Thus, WEE1 may become a promising target to modulate the abnormal cell cycle. However, its function in hematologic diseases remains poorly elucidated. In this review, focusing on hematologic malignancies, we describe the biological structure of WEE1, emphasize the latest reported function of WEE1 in the carcinogenesis, progression, as well as prognosis, and finally summarize the therapeutic strategies by targeting WEE1.
Humans ; Protein-Tyrosine Kinases/physiology* ; Hematologic Neoplasms/drug therapy* ; Cell Cycle Proteins/antagonists & inhibitors* ; Nuclear Proteins/antagonists & inhibitors* ; Cyclin-Dependent Kinases ; Molecular Targeted Therapy ; Animals

Osteoporosis(OP) is a senile bone disease characterized by an imbalance between bone remodeling and bone formation. Targeting pathogenesis of kidney deficiency, spleen deficiency, and blood stasis, Bushen Jianpi Huoxue Decoction has a significant effect on the treatment of OP by tonifying kidney, invigorating spleen, and activating blood circulation. MicroRNA(miRNA) and the anti-apoptotic protein B-cell lymphoma-2-like protein 1(BCL2L1) are closely related to bone cell metabolism. Therefore, in this study, the binding of miR-140-5p to BCL2L1 was detected by dual luciferase assay and polymerase chain reaction(PCR). After silencing or overexpressing miR-140-5p, the apoptosis, autophagy, and osteogenic function of human fetal osteoblast cell line 1.19(HFOB1.19) were observed by flow cytometry and Western blot. Bushen Jianpi Huoxue Decoction-containing serum was prepared by intragastric administration of Bushen Jianpi Huoxue Decoction in rats. Different concentrations of Bushen Jianpi Huoxue Decoction-containing serum were used to treat HFOB1.19 with or without miR-140-5p mimic. The expression of osteogenic proteins in each group was observed, and the role of miR-140-5p/BCL2L1 in apoptosis and autophagy of HFOB1.19 was studied, along with the effect of Bushen Jianpi Huoxue Decoction on these processes. As indicated by the dual luciferase assay, miR-140-5p bound to BCL2L1. Flow cytometry and Western blot showed that miR-140-5p promoted apoptosis and inhibited autophagy in HFOB1.19. After intervention with high, medium, and low doses of Bushen Jianpi Huoxue Decoction-medicated serum, compared with the miR-140-5p NC group, the expression of osteocalcin(OCN), osteopontin(OPN), Runt-related transcription factor 2(RUNX2), and transforming growth factor beta 1(TGF-β1) decreased in the miR-140-5p mimic group, while the expression of bone morphogenetic protein 2(BMP2) showed no significant difference under high-dose intervention. Therefore, miR-140-5p/BCL2L1 can promote apoptosis and inhibit autophagy in HFOB1.19. Bushen Jianpi Huoxue Decoction can affect the osteogenic effect of miR-140-5p through BMP2.
MicroRNAs/metabolism* ; Autophagy/drug effects* ; Apoptosis/drug effects* ; Humans ; Drugs, Chinese Herbal/administration & dosage* ; Animals ; Cell Line ; bcl-X Protein/metabolism* ; Osteoblasts/metabolism* ; Rats ; Osteoporosis/physiopathology* ; Male ; Rats, Sprague-Dawley ; Osteogenesis/drug effects*

OBJECTIVE: To explore the effect of nano-hydroxyapatite/collagen composite (nHAC) on bone graft fusion after anterior cervical discectomy and fusion (ACDF) in patients with cervical spondylosis and low bone mass. METHODS: A retrospective analysis was conducted on 47 patients with low bone mass who underwent ACDF from 2017 to 2021. They were divided into the nHAC group and the allogeneic bone group according to different bone graft materials. The nHAC group included 26 cases, with 8 males and 18 females;aged 50 to 78 years old with an average of (62.81±7.79) years old;the CT value of C₂-C₇ vertebrae was (264.16±36.33) HU. The allogeneic bone group included 21 cases, with 9 males and 12 females;aged 54 to 75 years old with an average of (65.95±6.58) years old;the CT value of C₂-C₇ vertebrae was (272.39±40.44) HU. The visual analogue scale (VAS), neck disability index (NDI), and Japanese Orthopaedic Association (JOA) spinal cord function score were compared before surgery, 1 week after surgery, and at the last follow-up to evaluate the clinical efficacy. Imaging assessment included C₂-C₇ Cobb angle, surgical segment height, intervertebral fusion, and whether the cage subsidence occurred at 1 week after surgery and the last follow-up. RESULTS: The follow-up duration ranged from 26 to 39 months with an average of (33.27±3.34) months in the nHAC group and 26 to 41 months with an average of (31.86±3.57) months in the allogeneic bone group. At 1 week after surgery and the last follow-up, the VAS, NDI scores, and JOA scores in both groups were significantly improved compared with those before surgery, with statistically significant differences (P<0.05). At 1 week after surgery, the C₂-C₇ Cobb angles in the nHAC group and the allogeneic bone group were (14.26±10.32)° and (14.28±8.20)° respectively, which were significantly different from those before surgery (P<0.05). At the last follow-up, the C₂-C₇ Cobb angles in both groups were smaller than those at 1 week after surgery, with statistically significant differences (P<0.05). At 1 week after surgery, the height of the surgical segment in the nHAC group was (31.65±2.55) mm, and that in the allogeneic bone group was (33.63±3.26) mm, which were significantly different from those before surgery (P<0.05). At the last follow-up, the height of the surgical segment in both groups decreased compared with that at 1 week after surgery, with statistically significant differences (P<0.05). At the last follow-up, 39 surgical segments were fused and 6 cages subsided in the nHAC group;40 surgical segments were fused and 7 cages subsided in the allogeneic bone group;there was no statistically significant difference between the two groups (P>0.05). Compared with the CT value of vertebrae without cage subsidence, the CT value of vertebrae with cage subsidence in both groups was significantly lower, with a statistically significant difference (P<0.05). CONCLUSION The application of nHAC in ACDF for patients with low bone mass can achieve effective fusion of the surgical segment. There is no significant difference in improving clinical efficacy, intervertebral fusion, and cage subsidence compared with the allogeneic bone group. With the extension of follow-up time, the C₂-C₇ Cobb angle decreases, the height of the surgical segment is lost, and the cage subsides in both the nHAC group and the allogeneic bone group, which may be related to low bone mass. Low bone mass may be one of the risk factors for cervical spine sequence changes, surgical segment height loss, and cage subsidence after ACDF.
Humans ; Male ; Female ; Middle Aged ; Spondylosis/physiopathology* ; Spinal Fusion/methods* ; Cervical Vertebrae/surgery* ; Aged ; Diskectomy ; Durapatite ; Retrospective Studies ; Collagen/chemistry*

Trauma is an important cause of death in young- and middle-aged people. Trauma is comprehensive and includes many surgical specialties, and the surgical techniques of these specialties have long been mature. To reduce the mortality and disability rate of trauma patients, it is necessary to improve trauma management. Trauma has attracted attention in China and trauma treatment and care developed rapidly in recent years. To decrease traumatic mortality and disability rates, our team is committed to building an efficient trauma system in Shaanxi province and has successfully developed a trauma limb salvage map to address the high rates of amputation and disability in patients with limb injuries. This article elaborates on the construction experience of a trauma limb salvage map and its application details in Shaanxi province of China.
Humans ; China ; Limb Salvage/methods* ; Wounds and Injuries/surgery* ; Male ; Extremities/injuries* ; Adult ; Amputation, Surgical ; Middle Aged ; Female