Peri-implant femoral fractures:Challenges,outcomes,and proposal of a treatment algorithm

Purpose:Non-prosthetic peri-implant fractures are challenging injuries.Multiple factors must be care-fully evaluated for an adequate therapeutic strategy,such as the state of bone healing,the type of implant,the time and performed personnel of previous surgery,and the stability of fixation.The aim of this study is to propose a rationale for the treatment.Methods:The peri-implant femoral fractures(PIFFs)system,a therapeutic algorithm was developed for the management of all patients presenting a subtype A PIFF,based on the type of the original implant(extra-vs.intra-medulllary),implant length and fracture location.The adequacy and reliability of the proposed algorithm and the fracture healing process were assessed at the last clinical follow-up using the Parker mobility score and radiological assessment,respectively.In addition,all complications were noticed.Continuous variables were expressed as mean and standard deviation,or median and range according to their distribution.Categorical variables were expressed as frequency and percentages.Results:This is a retrospective case series of 33 PIFFs,and the mean post-operative Parker mobility score was(5.60±2.54)points.Five patients(15.1%)achieved complete mobility without aids(9 points)and 1(3.0%)patient was not able to walk.Two other patients(6.1%)were non-ambulatory prior to PPIF.The mean follow-up was(21.51±9.12)months(range 6-48 months).There were 7(21.2%)complications equally distributed between patients managed either with nailing or plating.There were no cases of nonunion or mechanical failure of the original implant.Conclusion:The proposed treatment algorithm shows adequate,reliable and straightforward to assist the orthopaedic trauma surgeon on the difficult decision-making process regarding the management of PIFF occurring in previously healed fractures.In addition,it may become a useful tool to optimize the use of the classification,thus potentially improving the outcomes and minimizing complications.

Harnessing the Power of Artificial Intelligence in Neuromuscular Disease Rehabilitation: A Comprehensive Review and Algorithmic Approach

Neuromuscular diseases present profound challenges to individuals and healthcare systems worldwide, profoundly impacting motor functions. This research provides a comprehensive exploration of how artificial intelligence (AI) technology is revolutionizing rehabilitation for individuals with neuromuscular disorders. Through an extensive review, this paper elucidates a wide array of AI-driven interventions spanning robotic-assisted therapy, virtual reality rehabilitation, and intricately tailored machine learning algorithms. The aim is to delve into the nuanced applications of AI, unlocking its transformative potential in optimizing personalized treatment plans for those grappling with the complexities of neuromuscular diseases. By examining the multifaceted intersection of AI and rehabilitation, this paper not only contributes to our understanding of cutting-edge advancements but also envisions a future where technological innovations play a pivotal role in alleviating the challenges posed by neuromuscular diseases. From employing neural-fuzzy adaptive controllers for precise trajectory tracking amidst uncertainties to utilizing machine learning algorithms for recognizing patient motor intentions and adapting training accordingly, this research encompasses a holistic approach towards harnessing AI for enhanced rehabilitation outcomes. By embracing the synergy between AI and rehabilitation, we pave the way for a future where individuals with neuromuscular disorders can access tailored, effective, and technologically-driven interventions to improve their quality of life and functional independence.

A clinicoradiological classification and a treatment algorithm for traumatic triceps tendon avulsion in adults

Triceps tendon avulsion(TTA)is an uncommon injury,and there are no classifications or treatment guidelines available.This study aims to describe a clinicoradiological classification and treatment algorithm for traumatic TTA in adults.The functional outcome of surgical repair has been evaluated too.;A retrospective analysis of adult patients with traumatic TTA treated in our institution between 2012 and 2017 was done.We only included complete TTA injuries.Children below 15 years,open injuries,associated fractures,and partial TTA were excluded.The data were obtained from hospital records.The intraoperative findings were correlated with the clinicoradiological presentation for classifying TTA.The functional outcome was analyzed using the Mayo Elbow Performance index and Hospital for Special Surgery elbow score.ANOVA test was used to assess the statistical significance.;There were 15 patients included,including 11 males and 4 females.The mean age was(31.5±9.15)years,and the mean follow-up was(22.4±8.4)months.Fall on outstretched hand was the mode of injury.In 6 patients,diagnosis was missed on the initial visit.TTA were classified as Type 1:palpable soft-tissue defect without bony mass;Type 2:palpable soft-tissue defect with a wafer-thin/comminuted bony fragment on X-ray;Type 3:palpable soft-tissue defect with a bony mass and a large bony fragment on X-ray without extension to the articular surface;and Type 4:an olecranon fracture with less than 25%of the articular surface.An algorithm for treatment was recommended,i.e.transosseous suture repair/suture anchor for Type 1,transosseous suture repair for Type 2,and tension band wiring or steel wire sutures for Types 3 and 4.All the patients achieved good to excellent outcome:the mean Mayo Elbow Performance index was 100 and Hospital for Special Surgery score was 98.26±2.60 on final follow-up.;Our clinicoradiological classification and treatment algorithm for TTAs is simple.Surgical treatment results in excellent functions of the elbow.Since it is a single-center study involving a very small number of cases,a multicenter study with a larger number of patients is required for external validation of our classification and treatment recommendations.

A Practical Method to Evaluate and Verify Dose Calculation Algorithms in the Treatment Planning System of Radiation Therapy

Purpose: To introduce a practical method of using an Electron Density Phantom (EDP) to evaluate different dose calculation algorithms for photon beams in a treatment planning system (TPS) and to commission the Anisotropic Analytical Algorithm (AAA) with inhomogeneity correction in Varian Eclipse TPS. Methods and Materials: The same EDP with various tissue-equivalent plugs (water, lung exhale, lung inhale, liver, breast, muscle, adipose, dense bone, trabecular bone) used to calibrate the computed tomography (CT) simulator was adopted to evaluate different dose calculation algorithms in a TPS by measuring the actual dose delivered to the EDP. The treatment plans with a 6-Megavolt (MV) single field of 20 × 20, 10 × 10, and 4 × 4 cm2 field sizes were created based on the CT images of the EDP. A dose of 200 cGy was prescribed to the exhale-lung insert. Dose calculations were performed with AAA with inhomogeneity correction, Pencil Beam Convolution (PBC), and AAA without inhomogeneity correction. The plans were delivered and the actual doses were measured using radiation dosimetry devices MapCheck, EDR2-film, and ionization chamber respectively. Measured doses were compared with the calculated doses from the treatment plans. Results: The calculated dose using the AAA with inhomogeneity correction was most consistent with the measured dose. The dose discrepancy for all types of tissues covered by beam fields is at the level of 2%. The effect of AAA inhomogeneity correction for lung tissues is over 14%. Conclusions: The use of EDP and Map Check to evaluate and commission the dose calculation algorithms in a TPS is practical. In Varian Eclipse TPS, the AAA with inhomogeneity correction should be used for treatment planning especially when lung tissues are involved in a small radiation field.

基于遗传算法的溶洞智慧处治决策方法

为了应对多因素影响导致溶洞处理方案决策困难的问题,提出以价值工程为依据的智慧处治决策方法,综合考虑处理方案适应性和施工成本2个评价目标,并基于遗传算法构建多方案最优决策模型。结果表明:在决策过程方面,该决策模型在兼顾决策精度的同时具有较好的收敛性和收敛速度,简化决策过程,节省决策时间;在决策结果方面,相较于方案适应度单目标决策结果,该决策方法通过价值优化,将方案的适应度降低9.05,使得施工成本节省937064.71元,最终方案价值指数提升2.76。与方案成本单目标决策结果相比,该决策方法仅通过增加成本38215.78元,将方案适应度提升3.35,最终方案价值指数提升0.2,其优化成效在一定程度上解决了溶洞处理过程中成本浪费或者处理方案功能过剩的问题。

考虑移动式处理的医疗废物回收网络优化

现有的医疗废物回收网络中未能结合移动式处理技术,存在过度依赖场外集中处置、源头处医疗废物产量大、偏远地区的医疗机构回收不及时等问题。为提高医疗废物的现场处置能力,减少运输过程中的感染风险和回收成本,提出“集中处置+移动式处理”的协同回收模式,构建了多车型两级车辆路径问题模型,通过改进的大邻域搜索算法(ALNS)得到最优回收方案。以武汉市的回收网络为例,设计并求解了大量算例,证明了算法的求解性能优于Gurobi。相较于现行的回收模式,协同回收最高能减少28.79%的感染风险,有利于回收网络的稳定运行。

基于自适应宽度学习算法的城市污水处理污泥膨胀识别

针对污水处理过程的污泥膨胀难以精准识别的问题,提出了一种基于自适应宽度学习算法(adaptive broad learning algorithm,ABLA)的污泥膨胀识别方法。首先,结合城市污水处理过程的运行数据,采用主元分析法选取与污泥体积指数(sludge volume index,SVI)相关的特征变量;其次,建立了一种基于ABLA的污泥膨胀识别模型,利用自适应伪逆算法更新模型参数,提高了识别精度,并验证了模型的收敛性;最后,将所提模型应用于实际的污水处理过程中,利用污水处理厂的实际运行数据对其进行实验验证。实验结果表明,基于ABLA的污泥膨胀识别模型能够实现污泥膨胀的精准识别。

基于动态混合遗传算法的配送路径优化

随着越来越多的突发性卫生事件爆发,人们对应急医疗物资的需求量与日俱增,但应急医疗物资配送效率低下等问题依旧存在。文中研究建立多配送点配送模型,该模型对多个应急医疗物资配送中心到多个配送点的配送路径进行有效地优化,并在计算过程中考虑客户时间窗与交通拥堵情况,达到提高客户满意度、节约成本、减少配送过程中所产生的碳排放量的目标,如同此类问题都归类为VRP问题(车辆路径规划问题)。在该模型的计算过程中采用动态混合遗传算法(DHGA),在改进的遗传算法中加入大规模领域搜索算法,解决遗传算法求解精确度过低、易陷入局部最优循环的缺点。最后将计算结果与传统遗传算法(GA)、粒子群算法(ACO)以及蚁群算法(ACO)进行对比,结果表明该算法相对于其他算法的各项指标都得到明显提升。

废水处理中水质监测参数的实时预测研究

针对污水处理厂生化池中参数监测智能化水平不高、人力耗费较大的问题,提出基于麻雀算法-长短期记忆神经网络(Sparrow Search Algorithm-Long Short Term Memory Network,SSA-LSTM)的水质参数预测模型。以污水处理过程中好氧区溶解氧(Dissolved Oxygen,DO)、好氧区混合液悬浮固体(Mixed Liquid Suspended Solids,MLSS)质量浓度、缺氧区DO、缺氧区氧化还原电位(Oxidation-Reduction Potential,ORP)、厌氧区DO和厌氧区ORP 6个关键指标为数据样本,进行实例研究。将SSA-LSTM的预测结果与长短期记忆神经网络(Long Short-Term Memory Network,LSTM)、粒子群算法(Particle Swarm optimization-Long Short Term Memory Network,PSO-LSTM)、深度森林以及支持向量机进行对比分析,结果显示:SSA-LSTM在6个参数上的均方误差(EMSE)和决定系数(R2)均表现出更好的预测性,预测精度最高。

基于人工蜂群算法的支持向量回归建模及其在污水处理中的应用

污水处理过程具有大时滞、非线性、多扰动等特点,运行过程中存在生化需氧量(Biochemical Oxygen Demand,BOD)等重要水质参数难以实时测量问题,软测量技术为解决该问题提供了有效方法。对此,文章提出基于人工蜂群算法的支持向量回归(Support Vector Regression,SVR)建模方法。该方法利用蜂群算法对支持向量机的参数gamma和C进行寻优,找到使均方误差最小的超参数组合,以提高模型预测精度。同时,利用加州大学欧文分校(University of California Irvine,UCI)数据库中的污水生产数据验证该方法的有效性,结果表明该方法的实际应用效果好,可为工业生产中难以测量变量的监测提供技术支持。

基于模式识别技术的光电探测器故障辨识研究

当前光电探测器故障辨识错误率高,为提升光电探测器故障辨识效果,设计了基于模式识别技术的光电探测器故障辨识方法。首先采集光电探测器状态信号,并从光电探测器状态信号中提取特征,然后利用主成分分析算法对特征进行降维处理,得到最优光电探测器状态辨识特征,最后将光电探测器状态特征作为支持向量机的输入,光电探测器状态作为支持向量机输出,通过支持向量机学习设计光电探测器状态辨识器,实验结果表明,本方法可以有效辨识光电探测器辨识故障,光电探测器故障辨识正确率超过了90%,光电探测器故障辨识时间控制在20 ms以内,为光电探测器状态分析提供了理论依据。

面向造纸污水处理的故障诊断复合算法研究

故障诊断是保障系统稳定性与安全性的关键节点。在造纸污水处理过程中,系统硬件设备由于长期处于恶劣环境极易引发系统故障,因此准确诊断故障以避免不可挽回的损失至关重要。基于此,针对造纸污水处理过程的特点,以主成分分析技术提取故障主元而明确故障诊断模型输入量,以粒子群优化算法优化机器学习算法支持向量机而构成故障诊断复合算法,由此搭建了面向造纸污水处理的故障诊断模型,并进行了仿真分析。结果发现,面向造纸污水处理的故障诊断复合算法正确率可达96.9%,且稳定性与鲁棒性较高,可广泛推广至多工业污水处理领域。

人工智能在骨质疏松症诊疗中的应用进展

骨质疏松症是一种以低骨量和骨微结构退化为特点的代谢性疾病,从而导致骨折风险增加。骨质疏松性骨折通常发生在脊椎、髋关节、前臂远端和肱骨近端,但其他部位骨骼也可受累。尽管骨质疏松症的诊断是基于双能X射线吸收仪测量的骨密度(BMD)上,但多数发生骨质疏松性骨折患者的BMD尚未达到骨质疏松症的诊断标准。不管有无发生脆性骨折,骨质疏松症的诊断率仍然很低。此外,对于骨质疏松症的治疗时机、治疗对象和药物选择等诸多方面尚无标准指南。在此背景下,人工智能(AI)研发人员根据骨质疏松症的特点开发出多种算法,有望提高该疾病的诊疗水平。现就AI在骨质疏松症诊断和治疗中的最新应用进行简要概述。

基于人工智能技术的斜视诊疗进展

斜视是由于中枢管制失调、眼外肌力量失衡,导致双眼不能同时注视目标的一种眼病,通常在儿童期发病,可造成弱视、视功能损害、斜颈等发育不良和心理障碍。该病对患者、家庭乃至社会都会产生消极影响。早诊断、早治疗可避免造成视力和立体视的永久损害。然而,目前斜视的诊断高度依赖眼科医师专业检查,效率低、覆盖面小,而常规的入校筛查无法反映斜视度,且准确率低。因此如何提高斜视筛检效率是具有重要意义的热点问题。该文从人工智能技术发展的角度,基于近年来国内外的斜视诊疗现状,综述斜视领域中人工智能模型和算法的研究进展及不足,为进一步探索人工智能辅助的斜视诊疗前景提供参考。

慢性心力衰竭气虚血瘀证潜在亚组人群特征探索研究

目的探索慢性心力衰竭(CHF)气虚血瘀证潜在亚组人群,为心力衰竭的中医精准辨治提供客观依据。方法收集126例CHF气虚血瘀证患者的19种症状/体征指标和21种生化指标,利用R和Python软件进行K-mediods聚类算法分析,以轮廓系数确定最佳的聚类数目。组间比较,连续变量采用Kruskal-Wallis检验,分类变量采用Pearson's chi-squared检验或者Fisher's exact检验。结果CHF气虚血瘀证患者被聚类为3组,组间比较发现,气喘、不寐、颈脉怒张、纳差、畏寒5个症状/体征以及NYHA分级、氨基末端脑钠肽前体(NT-proBNP)、红细胞比容、尿素氮4个临床指标差异具有统计学意义(P<0.05)。第1组人群整体各症状/体征发生频率和临床指标严重程度相对较低;第2组人群以颈脉怒张发生频率较其他组高为特征,且促甲状腺激素、总胆固醇及低密度脂蛋白有偏高趋势,血小板有偏低的趋势;第3组人群以畏寒、纳差、不寐的发生率较其他组显著升高为特征,伴随尿素氮增高、红细胞比容降低。结论CHF气虚血瘀证潜在3种亚型,分别是气虚血瘀证本证型、气虚血瘀兼痰浊型、气虚血瘀兼阳虚型。

主吸收塔整体热处理遗传算法优化及全流程研究

为明确主吸收塔热处理作用效果,研究塔壁温度分布及传热特性,以主吸收塔为对象建立热-流耦合模型,对热处理中升温-保温-降温全流程进行数值模拟。提出升温均匀度概念,结合多目标遗传优化算法,分析热处理时入口烟气参数对升温均匀度的影响,得出最优化热处理工艺技术。结果表明:热处理时壁面高温区与低温区分别位于封头及人孔处,升温速率和壁面温差与火焰高度、外焰面角度正相关;升温速率与烟气流速正相关,温差随着烟气流速先减小后增大。热处理全过程耗时32.43 h,升温速率34.17—74.34℃/h,降温速率15.60—31.57℃/h,升温阶段末壁面平均温度606.62℃,最大壁面温差106.07℃;保温阶段末壁面温差15℃;降温阶段最大壁面温差111.01℃。壁面温度完全满足热处理规程要求,证明以升温均匀度为优化目标,可有效对主吸收塔热处理过程进行工艺设计和优化。

基于数据挖掘的中医特色治疗绩效考核指标研究

基于现行三级公立中医医院绩效考核办法,使用数据挖掘技术对中医特色治疗相关指标进行深入分析。采用无监督学习算法,将中医特色治疗项目数据进行分类,实现对科室绩效考核目标的多维度评价。该研究通过构建CK-means聚类模型,使用三种特征工程方法对中医特色治疗相关指标进行预处理,然后使用优化后的CK-means模型进行无监督的聚类训练。改变传统科室考核划分模式,将全院科室分为5类。根据分类结果,制定并优化更具有中医特色的科室考核方法,为三级中医医院的良好发展提供支持与保障。

基于遗传算法优化BP神经网络的曝气量预测

针对城市污水处理厂生化池曝气量的冗余问题,从节能降耗角度出发,提出了一种精确预测生化池曝气量的方法。首先,对从山东某污水厂采集的数据做预处理;其次,经相关性分析,建立以进出水指标和历史曝气量为输入、以当前曝气量为输出的反向传播(back propagation,BP)神经网络模型,并利用遗传算法优化BP神经网络的权值和阈值;最后,为了验证所提方法的有效性,将其与传统BP神经网络模型进行对比。实验结果表明,所提方法的均方根误差减小了39.88%,计算时间缩减了31.00%;且与实际测试数据相比,每月的曝气电费可节约892.80元。因此,所提方法对生化池曝气量的预测是有效和可行的。

基于遗传-卷积神经网络算法的废水处理预测模型研究

在废水生物处理过程建立出水COD与出水SS的预测模型中,针对卷积神经网络在设计时没有规律遵循并很难保证网络最优化的问题,提出了一种基于遗传算法降维的卷积神经网络优化方法｡本文将遗传算法(GA)与卷积神经网络(CNN)耦合起来形成一种新颖的混合算法--GA-CNN算法,并将该算法与CNN算法和BP神经网络的预测效果进行对比｡仿真结果表明,对于出水COD的浓度预测,GA-CNN的预测性能相比于CNN提升了13.66%,相比于BP提升了19.40%,其中GA-CNN算法的最优预测效果如下:均方根误差(RMSE)为3.5303,平均绝对百分比误差(MAPE)为3.92%,决定系数(R^(2))为0.7195。对于出水SS的浓度预测,GA-CNN的预测性能相比于CNN提升了9.26%,相比于BP提升了13.43%,其中GA-CNN算法的最优预测效果如下:均方根误差(RMSE)为0.5883,平均绝对百分比误差为1.99%,决定系数(R^(2))为0.6770。

调强技术、治疗部位以及剂量体积算法对调强放疗计划三维剂量验证结果的影响研究

目的:研究调强技术、治疗部位以及剂量体积算法对调强放疗(intensity-modulated radiation therapy,IMRT)计划三维剂量验证结果的影响,探究建立个体化放疗计划质量保证(quality assurance,QA)评估标准的重要性。方法:回顾性选取2017年1月—2022年2月在某院接受放疗的350例肿瘤患者IMRT计划的三维剂量验证结果,通过COMPASS系统进行数据采集,分别以不同调强技术(固定射束调强放疗、容积旋转调强放疗)、治疗部位(颈部、胸部和腹部)和剂量体积算法(各向异性解析算法和坍缩锥卷积算法)进行分组。比较各组3%/2 mm标准下的10%处方剂量区域的Gamma通过率(GP_(10%))、50%处方剂量区域的Gamma通过率(GP_(50%))和50%处方剂量区域的平均Gamma指数(μGI_(50%)),95%靶区体积的剂量D_(95%)、5%靶区体积的剂量D_(5%)和靶区平均剂量Dmean,头颈部放疗计划下腮腺的平均剂量D_(mean)、1%脊髓体积的剂量D_(1%)和1%脑干体积的剂量D_(1%),胸部放疗计划下肺、心脏的平均剂量D_(mean)和1%脊髓体积的剂量D_(1%),腹部放疗计划下膀胱、直肠和股骨头的平均剂量D_(mean)。采用SPSS 26.0软件进行统计学分析。结果:对于不同调强技术,除了腹部放疗计划的GP_(50%)之外,其余QA结果差异有统计学意义(P<0.05)。对于不同治疗部位,头颈部和腹部放疗计划、胸部和腹部放疗计划的QA结果差异有统计学意义(P<0.05),头颈部和胸部放疗计划的QA结果差异无统计学意义(P>0.05)。对于不同剂量体积算法,除了腹部放疗计划计划靶区(planning target volume,PTV)的D5%和胸部放疗计划PTV的D_(mean)和脊髓的D1%之外,其余的QA结果差异有统计学意义(P<0.05)。结论:剂量验证结果会因调强技术、治疗部位和剂量体积算法的不同而产生差异。当通用评估阈值不适用时,可考虑采用AAPM TG-218号报告所推荐的统计过程控制方法建立符合实际情况的放疗计划个性化QA评估标准。