人工智能在面瘫识别与评估中的应用

回顾了近年来部分基于人工智能的面瘫识别及评估研究。研究方法可分为基于人工选取患者面部图像特征值和基于神经网络和患者面部图像的面瘫评估研究两大类。分析表明,人工选取特征值的方法适合小样本量的情况,但对面瘫相邻评级的分类效果有待进一步优化。而神经网络的方法能够相对较好地区分面瘫邻级,但对样本量有较高要求。两种方法均有不错的前景,人工选取与评估量表相关性更强的特征,而共同的发展方向可能是提取时间域特征,从而达到提升面瘫评估准确率的目的。     

Electrical Potentiometry with Intraoral Applications

Dental implants currently in use are mainly made of titanium or titanium alloys. As these metallic elements are immersed in an electrolytic medium, galvanic currents are produced between them or with other metals present in the mouth. These bimetallic currents have three potentially harmful effects on the patient: micro-discharges, corrosion, and finally, the dispersion of metal ions or their oxides, all of which have been extensively demonstrated in vitro. In this original work, a system for measuring the potentials generated in vivo is developed. Specifically, it is an electrogalvanic measurements system coupled with a periodontal probe that allows measurement of the potentials in the peri-implant sulcus. This device was tested and verified in vitro to guarantee its applicability in vivo. As a conclusion, this system is able to detect galvanic currents in vitro and it can be considered capable of being employed in vivo, so to assess the effects they may cause on dental implants.     

The effects of hydroxyapatite implantation with the autogenous sclera cap: A cohort study

We performed a novel hydroxyapatite (HA) prosthesis implantation method in which an HA implant was implanted into the scleral shell with an autogenous scleral cap.Twenty-six patients who had undergone the novel HA prosthesis implantation method and 32 patients who had undergone traditional HA prosthesis implantation were retrospectively reviewed. The postoperative activity of the artificial eye was measured by the Hirschberg test combined with arc perimetry. The visual analog score (VAS) was used to evaluate 2-month postoperative pain and 2-month postoperative discomfort. HA implant vascularization was measured with enhanced magnetic resonance imaging (MRI) 2 and 6 months after the operation. The enhancement volume (V_E) and the volume of the HA implant (V_HA) were measured. All cases were followed up for 2 years. Measurement data were processed using SAS 6.12.There was a statistically significant difference (P = .016) between the percentages of excellent grade in the two groups. Two months after implantation, the median pain scores of the study and control groups were 2 and 2.5, respectively, and there was a statistically significant difference (W = 585.0, P = .004); there was a statistically significant difference (W = 535.5, P = .000) between the median discomfort scores of the study group (score = 1) and control group (score = 2); the mean VE/VHA values of the study and control groups were 0.3075 and 0.1535, respectively, and there was a statistically significant difference (t = −8.196, P = .000). Six months after implantation, the V_E/V_HA values of the study and control groups were 0.9686 and 0.5934, respectively, and there was a statistically significant difference (W = 549.0, P = .000). Within 2 years of postoperative follow-up, there were no serious complications in the study group.In the study group, in which the hydroxyapatite implant was implanted into a preserved scleral shell with unaltered muscles and covered with an autogenous scleral cap, postoperative activity and the fibrovascularization of the HA implant were significantly increased, and postoperative pain and discomfort were significantly reduced.     

Evaluating the Effect of a COVID-19 Predictive Model to Facilitate Discharge: A Randomized Controlled Trial

Background  We previously developed and validated a predictive model to help clinicians identify hospitalized adults with coronavirus disease 2019 (COVID-19) who may be ready for discharge given their low risk of adverse events. Whether this algorithm can prompt more timely discharge for stable patients in practice is unknown. Objectives  The aim of the study is to estimate the effect of displaying risk scores on length of stay (LOS). Methods  We integrated model output into the electronic health record (EHR) at four hospitals in one health system by displaying a green/orange/red score indicating low/moderate/high-risk in a patient list column and a larger COVID-19 summary report visible for each patient. Display of the score was pseudo-randomized 1:1 into intervention and control arms using a patient identifier passed to the model execution code. Intervention effect was assessed by comparing LOS between intervention and control groups. Adverse safety outcomes of death, hospice, and re-presentation were tested separately and as a composite indicator. We tracked adoption and sustained use through daily counts of score displays. Results  Enrolling 1,010 patients from May 15, 2020 to December 7, 2020, the trial found no detectable difference in LOS. The intervention had no impact on safety indicators of death, hospice or re-presentation after discharge. The scores were displayed consistently throughout the study period but the study lacks a causally linked process measure of provider actions based on the score. Secondary analysis revealed complex dynamics in LOS temporally, by primary symptom, and hospital location. Conclusion  An AI-based COVID-19 risk score displayed passively to clinicians during routine care of hospitalized adults with COVID-19 was safe but had no detectable impact on LOS. Health technology challenges such as insufficient adoption, nonuniform use, and provider trust compounded with temporal factors of the COVID-19 pandemic may have contributed to the null result. Trial registration  ClinicalTrials.gov identifier: {"type":"clinical-trial","attrs":{"text":"NCT04570488","term_id":"NCT04570488"}}NCT04570488.     

Antibacterial Activity and Cell Responses of Vancomycin-Loaded Alginate Coating on ZSM-5 Scaffold for Bone Tissue Engineering Applications

Despite the significant advancement in bone tissue engineering, it is still challenging to find a desired scaffold with suitable mechanical and biological properties, efficient bone formation in the defect area, and antibacterial resistivity. In this study, the zeolite (ZSM-5) scaffold was developed using the space holder method, and a novel vancomycin-loaded alginate coating was developed on it to promote their characteristics. Our results demonstrated the importance of alginate coating on the microstructure, mechanical, and cellular properties of the ZSM-5 scaffold. For instance, a three-fold increase in the compressive strength of coated scaffolds was observed compared to the uncoated ZSM-5. After the incorporation of vancomycin into the alginate coating, the scaffold revealed significant antibacterial activity against Staphylococcus aureus (S. aureus). The inhibition zone increased to 35 mm. Resets also demonstrated 74 ± 2.5% porosity, 4.3 ± 0.07 MPa strength in compressive conditions, acceptable cellular properties (72.3 ± 0.2 (%control) cell viability) after 7 days, good cell attachment, and calcium deposition. Overall, the results revealed that this scaffold could be a great candidate for bone tissue engineering.     

New frontiers of retinal therapeutic intervention: a critical analysis of novel approaches

A recent wave of pharmacologic and technologic innovations has revolutionized our management of retinal diseases. Many of these advancements have demonstrated efficacy and can increase the quality of life while potentially reducing complications and decreasing the burden of care for patients. Some advances, such as longer-acting anti-vascular endothelial growth factor agents, port delivery systems, gene therapy, and retinal prosthetics have been approved by the US Food and Drug Administration, and are available for clinical use. Countless other therapeutics are in various stages of development, promising a bright future for further improvements in the management of the retinal disease. Herein, we have highlighted several important novel therapies and therapeutic approaches and examine the opportunities and limitations offered by these innovations at the new frontier.

KEY MESSAGES

• Numerous pharmacologic and technologic advancements have been emerging, providing a higher treatment efficacy while decreasing the burden and associated side effects.
• Anti-vascular endothelial growth factor (anti-VEGF) and its longer-acting agents have dramatically improved visual outcomes and have become a mainstay treatment in various retinal diseases.
• Gene therapy and retinal prosthesis implantation in the treatment of congenital retinal dystrophy can accomplish the partial restoration of vision and improved daily function in patients with blindness, an unprecedented success in the field of retina.

     

人工神经网络技术诊断肺心病的实验研究

笔者利用典型的人工神经(BP)网络反向传播模型构建了一个诊断肺心病的专家子系统.结果该专家子系统利用神经网络获取和表示临床有关数据和资料,较好地解决了自动知识的获取、表示、自学等问题,并对临床资料进行量化处理;实例测试表明,该系统有助于肺心病的早期诊断.     

Prediction of Compressive Strength of Sustainable Foam Concrete Using Individual and Ensemble Machine Learning Approaches

The entraining and distribution of air voids in the concrete matrix is a complex process that makes the mechanical properties of lightweight foamed concrete (LFC) highly unpredictable. To study the complex nature of aerated concrete, a reliable and robust prediction model is required, employing different machine learning (ML) techniques. This study aims to predict the compressive strength of LFC by using a support vector machine (SVM) as an individual learner along with bagging, boosting, and random forest (RF) as a modified ensemble learner. For that purpose, a database of 191 data points was collected from published literature, where the mix design ingredients, i.e., cement content, sand content, water to cement ratio, and foam volume, were chosen to predict the compressive strength of LFC. The 10-K fold cross-validation method and different statistical error and regression tools, i.e., mean absolute error (MAE), root means square error (RMSE), and coefficient of determinant (R²), were used to evaluate the performance of the developed ML models. The modified ensemble learner (RF) outperforms all models by yielding a strong correlation of R² = 0.96 along with the lowest statistical error values of MAE = 1.84 MPa and RMSE = 2.52 MPa. Overall, the result suggests that the ensemble learners would significantly enhance the performance and robustness of ML models.     

基于三维CT图像重建研制纳米仿生骨基质支架的研究

[目的]分析数字化影像学技术辅助研制生物支架的可行性,评估构筑生物支架的方法.[方法]通过对宿主部位图像扫描,获取该区域解剖数据,对相邻层匹配轮廓间三维表面进行重构来确定支架形貌,以纳米级无机成分为单位,附于壳聚糖及聚己内酯等天然-有机成分,研制纳米复合支架.观察支架形貌、测定支架的孔隙率、亲水性及降解力学特性.[结果]图像三维重构可提高支架外部轮廓的精确度,减少单纯理化制备过程的参数误差,使支架空间三维布局更加合理,孔径200～350 μm,孔隙率88.6%±0.43%的支架拥有稳定的降解速率及良好的亲水表面,可达到工程化骨支架的力学要求,能作为骨再生修复的载体框架.[结论]数字化影像学技术研制的支架具有稳定的理化性征,能解决与宿主部位相匹配的难题,具有潜在的研究空间.     

聚乙烯醇水凝胶髓核的生物力学特性

目的 对一种新型水凝胶人工髓核的生物力学特性进行研究,为将来临床开展人工髓核置换手术提供科学依据。方法 采用7具新鲜标本的L_(4-5)脊柱功能单元进行生物力学实验,在轴向压缩、前屈后伸和左右侧弯等运动工况下,观察正常椎间盘、髓核摘除以及人工髓核植入3种状态下椎间盘高度、应变和位移的变化。结果 与正常椎间盘相比较,髓核摘除后椎间盘的高度和刚度降低,应变和位移加大(P<0.05)。而人工髓核植入后各项指标恢复正常(P>0.05)。结论 这种新型水凝胶人工髓核置换可纠正髓核摘除后的生物力学紊乱,有望进行临床应用。