Objective To compare the performance and efficacy of prognostic models constructed by different machine learning algorithms in predicting the survival period of lung transplantation (LTx) recipients. Methods Data from 483 recipients who underwent LTx were retrospectively collected. All recipients were divided into a training set and a validation set at a ratio of 7:3. The 24 collected variables were screened based on variable importance (VIMP). Prognostic models were constructed using random survival forest (RSF) and extreme gradient boosting tree (XGBoost). The performance of the models was evaluated using the integrated area under the curve (iAUC) and time-dependent area under the curve (tAUC). Results There were no significant statistical differences in the variables between the training set and the validation set. The top 15 variables ranked by VIMP were used for modeling and the length of stay in the intensive care unit (ICU) was determined as the most important factor. Compared with the XGBoost model, the RSF model demonstrated better performance in predicting the survival period of recipients (iAUC 0.773 vs. 0.723). The RSF model also showed better performance in predicting the 6-month survival period (tAUC _{6 months} 0.884 vs. 0.809, P = 0.009) and 1-year survival period (tAUC _{1 year} 0.896 vs. 0.825, P = 0.013) of recipients. Based on the prediction cut-off values of the two algorithms, LTx recipients were divided into high-risk and low-risk groups. The survival analysis results of both models showed that the survival rate of recipients in the high-risk group was significantly lower than that in the low-risk group (P<0.001). Conclusions Compared with XGBoost, the machine learning prognostic model developed based on the RSF algorithm may preferably predict the survival period of LTx recipients.

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: Neoadjuvant chemoradiotherapy followed by radical surgery has been a common practice for patients with locally advanced rectal cancer, but the response rate varies among patients. This study aimed to develop a ResNet-Vision Transformer based magnetic resonance imaging (MRI)-endoscopy fusion model to precisely predict treatment response and provide personalized treatment. METHODS: In this multicenter study, 366 eligible patients who had undergone neoadjuvant chemoradiotherapy followed by radical surgery at eight Chinese tertiary hospitals between January 2017 and June 2024 were recruited, with 2928 pretreatment colonic endoscopic images and 366 pelvic MRI images. An MRI-endoscopy fusion model was constructed based on the ResNet backbone and Transformer network using pretreatment MRI and endoscopic images. Treatment response was defined as good response or non-good response based on the tumor regression grade. The Delong test and the Hanley-McNeil test were utilized to compare prediction performance among different models and different subgroups, respectively. The predictive performance of the MRI-endoscopy fusion model was comprehensively validated in the test sets and was further compared to that of the single-modal MRI model and single-modal endoscopy model. RESULTS: The MRI-endoscopy fusion model demonstrated favorable prediction performance. In the internal validation set, the area under the curve (AUC) and accuracy were 0.852 (95% confidence interval [CI]: 0.744-0.940) and 0.737 (95% CI: 0.712-0.844), respectively. Moreover, the AUC and accuracy reached 0.769 (95% CI: 0.678-0.861) and 0.729 (95% CI: 0.628-0.821), respectively, in the external test set. In addition, the MRI-endoscopy fusion model outperformed the single-modal MRI model (AUC: 0.692 [95% CI: 0.609-0.783], accuracy: 0.659 [95% CI: 0.565-0.775]) and the single-modal endoscopy model (AUC: 0.720 [95% CI: 0.617-0.823], accuracy: 0.713 [95% CI: 0.612-0.809]) in the external test set. CONCLUSION The MRI-endoscopy fusion model based on ResNet-Vision Transformer achieved favorable performance in predicting treatment response to neoadjuvant chemoradiotherapy and holds tremendous potential for enabling personalized treatment regimens for locally advanced rectal cancer patients.
Humans ; Rectal Neoplasms/diagnostic imaging* ; Magnetic Resonance Imaging/methods* ; Male ; Female ; Middle Aged ; Neoadjuvant Therapy/methods* ; Aged ; Adult ; Chemoradiotherapy/methods* ; Endoscopy/methods* ; Treatment Outcome

OBJECTIVE: To explore the early clinical efficacy of a three-stage external treatment with traditional Chinese medicine (TCM) in the treatment of talar bone contusion caused by acute ankle sprain. METHODS: A retrospective analysis was performed on 360 patients with primary lateral ankle sprain admitted from September 2021 to July 2024. Patients with talar bone contusion were selected based on MRI examination, and 73 cases were finally included. According to different treatment methods, they were divided into the observation group and the control group. The observation group consisted of 35 cases, including 16 males and 19 females, aged 24 to 37 years old with an average of (30.34±2.68) years old, and received the three-stage external TCM treatment combined with the "POLICE" protocol. The control group included 38 cases, including 18 males and 20 females, aged 24 to 35 years old with an average of (29.87±2.57) years old, and was treated with the "POLICE" protocol alone. The volume of bone marrow edema (BME) area shown by MRI before treatment and 6 weeks after treatment was measured using 3D Slicer software, and the BME improvement rate was calculated. The "Figure of 8" measurement method was used to assess ankle swelling before treatment and at 1 and 3 weeks after treatment. The visual analogue scale (VAS) was used to evaluate ankle pain before treatment and at 1 and 6 weeks after treatment. At 6 weeks after treatment, the American Orthopaedic Foot and Ankle Society (AOFAS) ankle-hindfoot score and Karlsson ankle function score system were used to evaluate the improvement of ankle function. RESULTS: A total of 73 patients with talar bone contusion caused by ankle sprain completed the 6-week follow-up. At 6 weeks after treatment, the BME improvement rate in the observation group was (39.18±0.06)%, which was higher than (26.75±0.03)% in the control group, with a statistically significant difference (P<0.05). After 1 week of treatment, the VAS score in the observation group was (2.89±0.72) points, lower than (3.37±0.79) points in the control group, and the difference was statistically significant (P<0.05). The ankle swelling degree in the observation group was (50.20±3.19) cm, lower than (52.00±3.60) cm in the control group, with a statistically significant difference (P<0.05). After 3 weeks of treatment, there was no statistically significant difference in ankle swelling between the two groups. At 6 weeks after treatment, there was no statistically significant difference in VAS scores between the two groups. At 6 weeks after treatment, the AOFAS ankle-hindfoot score and Karlsson score in the observation group were (87.43±4.18) and (82.77±5.93) points, respectively, which were higher than (82.92±4.87) and (76.45±6.85) points in the control group, with statistically significant differences (P<0.05). According to the AOFAS ankle-hindfoot score, 8 cases were excellent and 27 cases were good in the observation group;2 cases were excellent, 33 cases were good, and 3 cases were fair in the control group. The difference between the two groups was statistically significant (χ²=7.089, P=0.029). CONCLUSION The three-stage external TCM treatment combined with the "POLICE" protocol has a significant early clinical efficacy. It can significantly reduce ankle pain and swelling in patients with bone contusion caused by acute lateral ankle sprain, promote the absorption of bone marrow edema, and accelerate the recovery of ankle function.
Ankle Injuries/drug therapy* ; Drugs, Chinese Herbal/administration & dosage* ; Talus/injuries* ; Retrospective Studies ; Administration, Cutaneous ; Magnetic Resonance Imaging ; Humans ; Male ; Female ; Young Adult ; Adult ; Contusions/etiology* ; Visual Analog Scale ; Musculoskeletal Pain/etiology* ; Recovery of Function/drug effects* ; Treatment Outcome ; Follow-Up Studies

Neuropathic pain, a debilitating condition caused by dysfunction of the somatosensory nervous system, remains difficult to treat due to limited understanding of its molecular mechanisms. Bioinformatics analysis identified cerebellin 2 (CBLN2) as highly enriched in human and murine proprioceptive and nociceptive neurons. We found that CBLN2 expression is persistently upregulated in dorsal root ganglia (DRG) following spinal nerve ligation (SNL) in mice. In addition, transcription factor SOX11 binds to 12 cis-regulatory elements within the Cbln2 promoter to enhance its transcription. SNL also induced SOX11 upregulation, with SOX11 and CBLN2 co-localized in nociceptive neurons. The siRNA-mediated knockdown of Sox11 or Cbln2 attenuated SNL-induced mechanical allodynia and thermal hyperalgesia. High-throughput sequencing of DRG following intrathecal injection of CBLN2 revealed widespread gene expression changes, including upregulation of numerous NF-κB downstream targets. Consistently, CBLN2 activated NF-κB signaling, and inhibition with pyrrolidine dithiocarbamate reduced CBLN2-induced pain hypersensitivity, proinflammatory cytokines and chemokines production, and neuronal hyperexcitability. Together, these findings identified the SOX11/CBLN2/NF-κB axis as a critical mediator of neuropathic pain and a promising target for therapeutic intervention.
Animals ; Neuralgia/metabolism* ; Ganglia, Spinal/metabolism* ; Up-Regulation ; Mice ; NF-kappa B/metabolism* ; SOXC Transcription Factors/genetics* ; Male ; Neuroinflammatory Diseases/metabolism* ; Mice, Inbred C57BL ; Nerve Tissue Proteins/genetics* ; Hyperalgesia/metabolism* ; Signal Transduction ; Spinal Nerves

Hepatocellular carcinoma (HCC) expresses abundant glycolytic enzymes and displays comprehensive glucose metabolism reprogramming. Aldolase A (ALDOA) plays a prominent role in glycolysis; however, little is known about its role in HCC development. In the present study, we aim to explore how ALDOA is involved in HCC proliferation. HCC proliferation was markedly suppressed both in vitro and in vivo following ALDOA knockout, which is consistent with ALDOA overexpression encouraging HCC proliferation. Mechanistically, ALDOA knockout partially limits the glycolytic flux in HCC cells. Meanwhile, ALDOA translocated to nuclei and directly interacted with c-Jun to facilitate its Thr93 phosphorylation by P21-activated protein kinase; ALDOA knockout markedly diminished c-Jun Thr93 phosphorylation and then dampened c-Jun transcription function. A crucial site Y364 mutation in ALDOA disrupted its interaction with c-Jun, and Y364S ALDOA expression failed to rescue cell proliferation in ALDOA deletion cells. In HCC patients, the expression level of ALDOA was correlated with the phosphorylation level of c-Jun (Thr93) and poor prognosis. Remarkably, hepatic ALDOA was significantly upregulated in the promotion and progression stages of diethylnitrosamine-induced HCC models, and the knockdown of A ldoa strikingly decreased HCC development in vivo. Our study demonstrated that ALDOA is a vital driver for HCC development by activating c-Jun-mediated oncogene transcription, opening additional avenues for anti-cancer therapies.