Highway safety researchers focus on crash injury severity,utilizing deep learning—specifically,deep neural networks(DNN),deep convolutional neural networks(D-CNN),and deep recurrent neural networks(D-RNN)—as the pre...Highway safety researchers focus on crash injury severity,utilizing deep learning—specifically,deep neural networks(DNN),deep convolutional neural networks(D-CNN),and deep recurrent neural networks(D-RNN)—as the preferred method for modeling accident severity.Deep learning’s strength lies in handling intricate relation-ships within extensive datasets,making it popular for accident severity level(ASL)prediction and classification.Despite prior success,there is a need for an efficient system recognizing ASL in diverse road conditions.To address this,we present an innovative Accident Severity Level Prediction Deep Learning(ASLP-DL)framework,incorporating DNN,D-CNN,and D-RNN models fine-tuned through iterative hyperparameter selection with Stochastic Gradient Descent.The framework optimizes hidden layers and integrates data augmentation,Gaussian noise,and dropout regularization for improved generalization.Sensitivity and factor contribution analyses identify influential predictors.Evaluated on three diverse crash record databases—NCDB 2018–2019,UK 2015–2020,and US 2016–2021—the D-RNN model excels with an ACC score of 89.0281%,a Roc Area of 0.751,an F-estimate of 0.941,and a Kappa score of 0.0629 over the NCDB dataset.The proposed framework consistently outperforms traditional methods,existing machine learning,and deep learning techniques.展开更多
BACKGROUND Pedicled abdominal flaps are a widely used surgical technique for forearm reconstruction in patients with soft tissue defects.However,some drawbacks include restricted flap size,partial flap loss,and donor-...BACKGROUND Pedicled abdominal flaps are a widely used surgical technique for forearm reconstruction in patients with soft tissue defects.However,some drawbacks include restricted flap size,partial flap loss,and donor-site morbidity.To address these concerns,we present a case of a pedicled abdominal flap using the deep inferior epigastric artery perforators(DIEP)for forearm reconstruction in a patient with a large soft tissue defect.CASE SUMMARY A 46-year-old male patient was admitted to our hospital with forearm injury caused by a pressing machine.A 15 cm×10 cm soft tissue defect with complete rupture of the ulnar side structures of the forearm was found.One week after orthopedic management of the neurovascular injury and fractures using the first stage of Masquelet technique,the patient was referred to the plastic and recon-structive surgery department for wound coverage.Surgical debridement and negative-pressure wound therapy revealed a 20 cm×15 cm soft tissue defect.A pedicle abdominal flap with the DIEP was used to cover the defect.Three weeks later,the flap was detached from the abdomen,and the abdominal defect was directly closed.Subsequently,the second stage of Masquelet technique was performed at the fracture site at week 10.Finally,all donor and recipient sites healed without complications,such as flap dehiscence,infection,hematoma,or necrosis.Fracture site osteosynthesis was achieved without complications.CONCLUSION Pedicled abdominal flap using the DIEP provides a reliable option for forearm reconstruction in patients with large soft tissue defects.展开更多
Background:LL-37 peptide is a member of the human cathelicidin family,and has been shown to promote the healing of pressure ulcers.However,the low stability of this peptide within the wound environment limits its clin...Background:LL-37 peptide is a member of the human cathelicidin family,and has been shown to promote the healing of pressure ulcers.However,the low stability of this peptide within the wound environment limits its clinical use.Chitosan(CS)hydrogel is commonly used as a base material for wound dressing material.Methods:CS hydrogel(2.5%w/v)was encapsulated with LL-37.Cytotoxicity of the product was examined in cultured NIH3 T3 fibroblasts.Effects on immune response was examined by measuring tumor necrosis factor-α(TNF-α)release from RAW 264.7 macrophages upon exposure to lipopolysaccharides.Antibacterial activity was assessed using Staphylococcus aureus.Potential effect on pressure ulcers was examined using a mouse model.Briefly,adult male C57 BL/6 mice were subjected to skin pressure using magnets under a 12/12 h schedule for 21 days.Mice were randomized to receive naked LL-37(20μg),chitosan gel containing 20μg LL-37(LL-37/CS hydrogel)or hydrogel alone under the ulcer bed(n=6).A group of mice receiving no intervention was also included as a control.Results:LL-37/CS hydrogel did not affect NIH3 T3 cell viability.At a concentration of 1–5μg/ml,LL-37/CS inhibited TNF-αrelease from macrophage.At 5μg/ml,LL-37/CS inhibited the growth of Staphylococcus aureus.The area of the pressure ulcers was significantly lower in mice receiving LL-37/CS hydrogel in comparison to all other 3 groups on days 11(84.24%±0.25%),13(56.22%±3.91%)and 15(48.12%±0.28%).Histological examination on days 15 and 21 showed increased epithelial thickness and density of newly-formed capillary with naked LL-37 and more so with LL-37/CS.The expression of key macromolecules in the process of angiogenesis(i.e.,hypoxia inducible factor-1α(HIF-1α)and vascular endothelial growth factor-A(VEGF-A))in wound tissue was increased at both the mRNA and protein levels.Conclusion:Chitosan hydrogel encapsulated with LL-37 is biocompatible and could promote the healing of pressure ulcers.展开更多
BACKGROUND Thermal injuries on free transferred or replanted tissues resulting from loss of sensibility are an infrequent occurrence.They require immediate and appropriate management before they progress to an irrever...BACKGROUND Thermal injuries on free transferred or replanted tissues resulting from loss of sensibility are an infrequent occurrence.They require immediate and appropriate management before they progress to an irreversible condition.Although negative pressure wound therapy(NPWT)can prevent wound progression by increasing microcirculation,the inappropriate application of NPWT on complicationthreatened transferred and replanted tissues can induce an adverse effect.CASE SUMMARY A 48-year-old woman who underwent immediate breast reconstruction with a deep inferior epigastric artery perforator free flap.While applying a heating pad directly to the flap site,she sustained a deep second to third-degree contact burn over 30%of the transferred flap on postoperative 7 d.As the necrotic changes had progressed,we applied an NPWT dressing over the burned area after en-bloc debridement of the transferred tissues on postoperative 21 d.After 4 d of NPWT application,the exposed fatty tissues of the flap changed to dry and browncolored necrotic tissues.Upon further debridement,we noted that the wound gradually reached total necrosis with a collapsed vascular pedicle of deep inferior epigastric artery.CONCLUSION Although NPWT has been shown to be successful for treating various wound types,the significant risk of NPWT application in short-lasting reconstructed flap wounds after thermal injury should be reminded.展开更多
Objective: To evaluate the risk factors for hemoglobinuria and acute kidney injury(AKI) after percutaneous mechanical thrombectomy(MT) with or without catheter-directed thrombolysis(CDT) for iliofemoral deep vein thro...Objective: To evaluate the risk factors for hemoglobinuria and acute kidney injury(AKI) after percutaneous mechanical thrombectomy(MT) with or without catheter-directed thrombolysis(CDT) for iliofemoral deep vein thrombosis(IFDVT).Methods: Patients with IFDVT who had MT with the Angio Jet catheter(group A), MT plus CDT(group B), or CDT alone(group C) from January 2016 to March 2020 were retrospectively evaluated. Hemoglobinuria was monitored throughout the treatment course, and postoperative AKI was assessed by comparing the preoperative(baseline) and postoperative serum creatinine(sCr) levels from the electronic medical records of all patients. AKI was defined as an elevation in the sCr level exceeding 26.5 μmol/L within 72 h after the operation according to the Kidney Disease Improving Global Outcomes criteria.Results: A total of 493 consecutive patients with IFDVT were reviewed, of which 382(mean age, 56 ± 11 years;41% of them were females;97 in group A, 128 in group B, and 157 in group C) were finally analyzed. Macroscopic hemoglobinuria was evident in 44.89% of the patients of the MT groups(101/225, 39 in group A, and 62 in group B), with no significant difference between the groups(P = 0.219), but not in the patients in group C. None of the patients developed AKI(mean sCr difference-2.76 ± 13.80 μmol/L, range =-80.20 to 20.60 μmol/L) within 72h after surgery.Conclusions: Rheolytic MT is an independent risk factor for hemoglobinuria. A proper aspiration strategy, hydration, and alkalization following thrombectomy are particularly favorable for preventing AKI.展开更多
背景:运动医学界广泛呼吁采用机器学习技术高效处理庞大、冗杂的运动数据资源,构建智能化的运动损伤预警模型,以实现运动损伤的精准预警。对此类研究成果进行综合归纳与评述,对把握预警模型改进方向,指导中国损伤预警模型构建工作均具...背景:运动医学界广泛呼吁采用机器学习技术高效处理庞大、冗杂的运动数据资源,构建智能化的运动损伤预警模型,以实现运动损伤的精准预警。对此类研究成果进行综合归纳与评述,对把握预警模型改进方向,指导中国损伤预警模型构建工作均具有重要意义。目的:系统梳理基于机器学习技术的运动损伤预警模型相关研究,为中国运动损伤预警模型构建工作提供借鉴。方法:对中国知网、Web of Science和EBSCO数据库进行文献检索,主要检索机器学习技术和运动损伤相关文献,最终纳入61篇运动损伤预警模型相关文献进行分析。结果与结论:①在纳入文献的外部风险特征指标中,缺乏比赛场景类指标,后续需进一步完善相关特征指标的纳入工作,以进一步丰富模型训练的数据集维度;此外,运动损伤预警模型的纳入特征权重方法以过滤法为主,需强化嵌入法及包裹法等权重方法的运用,以增强多风险因素交互效应的分析。②在模型主体训练方面,模型主体训练算法多以监督式学习算法为主,此类算法对样本标注信息的完整度有较高要求,应用场景易受限,后期可增加无监督式与半监督式算法的应用。③在模型性能评估优化方面,现研究主要采用了HoldOut交叉与k-交叉两种验证方式评估模型性能,模型的AUC值范围(0.76±0.12),灵敏度范围(75.92±11.03)%,特异度范围(80.03±4.54)%,F1分数值范围(80.60±10.63)%,准确度范围(69.96±13.10)%,精确度范围(70±14.71)%,数据增强与特征优化为最常见的模型优化操作。当前运动损伤预警模型准确度及精确度均约为70%,预警效果良好,但模型优化操作较单一,多采用数据增强方法提升模型性能,需强化对模型算法、超参数的调整,以进一步提升模型性能。④在模型特征提取方面,纳入的内部风险特征指标多以人体测量学、训练负荷、训练年限和损伤史等指标为主,缺乏运动恢复类指标与身体机能类指标。展开更多
文摘Highway safety researchers focus on crash injury severity,utilizing deep learning—specifically,deep neural networks(DNN),deep convolutional neural networks(D-CNN),and deep recurrent neural networks(D-RNN)—as the preferred method for modeling accident severity.Deep learning’s strength lies in handling intricate relation-ships within extensive datasets,making it popular for accident severity level(ASL)prediction and classification.Despite prior success,there is a need for an efficient system recognizing ASL in diverse road conditions.To address this,we present an innovative Accident Severity Level Prediction Deep Learning(ASLP-DL)framework,incorporating DNN,D-CNN,and D-RNN models fine-tuned through iterative hyperparameter selection with Stochastic Gradient Descent.The framework optimizes hidden layers and integrates data augmentation,Gaussian noise,and dropout regularization for improved generalization.Sensitivity and factor contribution analyses identify influential predictors.Evaluated on three diverse crash record databases—NCDB 2018–2019,UK 2015–2020,and US 2016–2021—the D-RNN model excels with an ACC score of 89.0281%,a Roc Area of 0.751,an F-estimate of 0.941,and a Kappa score of 0.0629 over the NCDB dataset.The proposed framework consistently outperforms traditional methods,existing machine learning,and deep learning techniques.
基金Supported by The Bio&Medical Technology Development Program of the National Research Foundation(NRF)funded by the Korean government(MSIT),No.RS-2023-00220408.
文摘BACKGROUND Pedicled abdominal flaps are a widely used surgical technique for forearm reconstruction in patients with soft tissue defects.However,some drawbacks include restricted flap size,partial flap loss,and donor-site morbidity.To address these concerns,we present a case of a pedicled abdominal flap using the deep inferior epigastric artery perforators(DIEP)for forearm reconstruction in a patient with a large soft tissue defect.CASE SUMMARY A 46-year-old male patient was admitted to our hospital with forearm injury caused by a pressing machine.A 15 cm×10 cm soft tissue defect with complete rupture of the ulnar side structures of the forearm was found.One week after orthopedic management of the neurovascular injury and fractures using the first stage of Masquelet technique,the patient was referred to the plastic and recon-structive surgery department for wound coverage.Surgical debridement and negative-pressure wound therapy revealed a 20 cm×15 cm soft tissue defect.A pedicle abdominal flap with the DIEP was used to cover the defect.Three weeks later,the flap was detached from the abdomen,and the abdominal defect was directly closed.Subsequently,the second stage of Masquelet technique was performed at the fracture site at week 10.Finally,all donor and recipient sites healed without complications,such as flap dehiscence,infection,hematoma,or necrosis.Fracture site osteosynthesis was achieved without complications.CONCLUSION Pedicled abdominal flap using the DIEP provides a reliable option for forearm reconstruction in patients with large soft tissue defects.
基金supported by the National Natural Science Foundation of China(No.81701838)the China Postdoctoral Science Foundation(2018M632628)
文摘Background:LL-37 peptide is a member of the human cathelicidin family,and has been shown to promote the healing of pressure ulcers.However,the low stability of this peptide within the wound environment limits its clinical use.Chitosan(CS)hydrogel is commonly used as a base material for wound dressing material.Methods:CS hydrogel(2.5%w/v)was encapsulated with LL-37.Cytotoxicity of the product was examined in cultured NIH3 T3 fibroblasts.Effects on immune response was examined by measuring tumor necrosis factor-α(TNF-α)release from RAW 264.7 macrophages upon exposure to lipopolysaccharides.Antibacterial activity was assessed using Staphylococcus aureus.Potential effect on pressure ulcers was examined using a mouse model.Briefly,adult male C57 BL/6 mice were subjected to skin pressure using magnets under a 12/12 h schedule for 21 days.Mice were randomized to receive naked LL-37(20μg),chitosan gel containing 20μg LL-37(LL-37/CS hydrogel)or hydrogel alone under the ulcer bed(n=6).A group of mice receiving no intervention was also included as a control.Results:LL-37/CS hydrogel did not affect NIH3 T3 cell viability.At a concentration of 1–5μg/ml,LL-37/CS inhibited TNF-αrelease from macrophage.At 5μg/ml,LL-37/CS inhibited the growth of Staphylococcus aureus.The area of the pressure ulcers was significantly lower in mice receiving LL-37/CS hydrogel in comparison to all other 3 groups on days 11(84.24%±0.25%),13(56.22%±3.91%)and 15(48.12%±0.28%).Histological examination on days 15 and 21 showed increased epithelial thickness and density of newly-formed capillary with naked LL-37 and more so with LL-37/CS.The expression of key macromolecules in the process of angiogenesis(i.e.,hypoxia inducible factor-1α(HIF-1α)and vascular endothelial growth factor-A(VEGF-A))in wound tissue was increased at both the mRNA and protein levels.Conclusion:Chitosan hydrogel encapsulated with LL-37 is biocompatible and could promote the healing of pressure ulcers.
文摘BACKGROUND Thermal injuries on free transferred or replanted tissues resulting from loss of sensibility are an infrequent occurrence.They require immediate and appropriate management before they progress to an irreversible condition.Although negative pressure wound therapy(NPWT)can prevent wound progression by increasing microcirculation,the inappropriate application of NPWT on complicationthreatened transferred and replanted tissues can induce an adverse effect.CASE SUMMARY A 48-year-old woman who underwent immediate breast reconstruction with a deep inferior epigastric artery perforator free flap.While applying a heating pad directly to the flap site,she sustained a deep second to third-degree contact burn over 30%of the transferred flap on postoperative 7 d.As the necrotic changes had progressed,we applied an NPWT dressing over the burned area after en-bloc debridement of the transferred tissues on postoperative 21 d.After 4 d of NPWT application,the exposed fatty tissues of the flap changed to dry and browncolored necrotic tissues.Upon further debridement,we noted that the wound gradually reached total necrosis with a collapsed vascular pedicle of deep inferior epigastric artery.CONCLUSION Although NPWT has been shown to be successful for treating various wound types,the significant risk of NPWT application in short-lasting reconstructed flap wounds after thermal injury should be reminded.
基金supported by the Medical and Health Science and Technology Development Plan of Shandong Province, China (Grant No.2017WS688)。
文摘Objective: To evaluate the risk factors for hemoglobinuria and acute kidney injury(AKI) after percutaneous mechanical thrombectomy(MT) with or without catheter-directed thrombolysis(CDT) for iliofemoral deep vein thrombosis(IFDVT).Methods: Patients with IFDVT who had MT with the Angio Jet catheter(group A), MT plus CDT(group B), or CDT alone(group C) from January 2016 to March 2020 were retrospectively evaluated. Hemoglobinuria was monitored throughout the treatment course, and postoperative AKI was assessed by comparing the preoperative(baseline) and postoperative serum creatinine(sCr) levels from the electronic medical records of all patients. AKI was defined as an elevation in the sCr level exceeding 26.5 μmol/L within 72 h after the operation according to the Kidney Disease Improving Global Outcomes criteria.Results: A total of 493 consecutive patients with IFDVT were reviewed, of which 382(mean age, 56 ± 11 years;41% of them were females;97 in group A, 128 in group B, and 157 in group C) were finally analyzed. Macroscopic hemoglobinuria was evident in 44.89% of the patients of the MT groups(101/225, 39 in group A, and 62 in group B), with no significant difference between the groups(P = 0.219), but not in the patients in group C. None of the patients developed AKI(mean sCr difference-2.76 ± 13.80 μmol/L, range =-80.20 to 20.60 μmol/L) within 72h after surgery.Conclusions: Rheolytic MT is an independent risk factor for hemoglobinuria. A proper aspiration strategy, hydration, and alkalization following thrombectomy are particularly favorable for preventing AKI.
文摘背景:运动医学界广泛呼吁采用机器学习技术高效处理庞大、冗杂的运动数据资源,构建智能化的运动损伤预警模型,以实现运动损伤的精准预警。对此类研究成果进行综合归纳与评述,对把握预警模型改进方向,指导中国损伤预警模型构建工作均具有重要意义。目的:系统梳理基于机器学习技术的运动损伤预警模型相关研究,为中国运动损伤预警模型构建工作提供借鉴。方法:对中国知网、Web of Science和EBSCO数据库进行文献检索,主要检索机器学习技术和运动损伤相关文献,最终纳入61篇运动损伤预警模型相关文献进行分析。结果与结论:①在纳入文献的外部风险特征指标中,缺乏比赛场景类指标,后续需进一步完善相关特征指标的纳入工作,以进一步丰富模型训练的数据集维度;此外,运动损伤预警模型的纳入特征权重方法以过滤法为主,需强化嵌入法及包裹法等权重方法的运用,以增强多风险因素交互效应的分析。②在模型主体训练方面,模型主体训练算法多以监督式学习算法为主,此类算法对样本标注信息的完整度有较高要求,应用场景易受限,后期可增加无监督式与半监督式算法的应用。③在模型性能评估优化方面,现研究主要采用了HoldOut交叉与k-交叉两种验证方式评估模型性能,模型的AUC值范围(0.76±0.12),灵敏度范围(75.92±11.03)%,特异度范围(80.03±4.54)%,F1分数值范围(80.60±10.63)%,准确度范围(69.96±13.10)%,精确度范围(70±14.71)%,数据增强与特征优化为最常见的模型优化操作。当前运动损伤预警模型准确度及精确度均约为70%,预警效果良好,但模型优化操作较单一,多采用数据增强方法提升模型性能,需强化对模型算法、超参数的调整,以进一步提升模型性能。④在模型特征提取方面,纳入的内部风险特征指标多以人体测量学、训练负荷、训练年限和损伤史等指标为主,缺乏运动恢复类指标与身体机能类指标。
