Predicting gait events from tibial acceleration in rearfoot running: A structured machine learning approach

BackgroundGait event detection of the initial contact and toe off is essential for running gait analysis, allowing the derivation of parameters such as stance time. Heuristic-based methods exist to estimate these key gait events from tibial accelerometry. However, these methods are tailored to very specific acceleration profiles, which may offer complications when dealing with larger data sets and inherent biological variability.Research questionCan a structured machine learning approach achieve a more accurate prediction of running gait event timings from tibial accelerometry, compared to the previously utilised heuristic approaches?MethodsForce-based event detection acted as the criterion measure in order to assess the accuracy, repeatability and sensitivity of the predicted gait events. 3D tibial acceleration and ground reaction force data from 93 rearfoot runners were captured. A heuristic method and two structured machine learning methods were employed to derive initial contact, toe off and stance time from tibial acceleration signals.ResultsBoth a structured perceptron model (median absolute error of stance time estimation: 10.00 ± 8.73 ms) and a structured recurrent neural network model (median absolute error of stance time estimation: 6.50 ± 5.74 ms) significantly outperformed the existing heuristic approach (median absolute error of stance time estimation: 11.25 ± 9.52 ms). Thus, results indicate that a structured recurrent neural network machine learning model offers the most accurate and consistent estimation of the gait events and its derived stance time during level overground running.SignificanceThe machine learning methods seem less affected by intra- and inter-subject variation within the data, allowing for accurate and efficient automated data output during rearfoot overground running. Furthermore offering possibilities for real-time monitoring and biofeedback during prolonged measurements, even outside the laboratory.     

State-of-the-art Tools for Computational Site of Metabolism Predictions: Comparative Analysis,Mechanistical Insights,and Future Applications

In drug design, it is crucial to have reliable information on how a chemical entity behaves in the presence of metabolizing enzymes. This requires substantial experimental efforts. Consequently, being able to predict the likely site/s of metabolism in any compound, synthesized or virtual, would be highly beneficial and time efficient.

In this work, six different methodologies for predictions of the site of metabolism (SOM) have been compared and validated using structurally diverse data sets of drug-like molecules with well-established metabolic pattern in CYP3A4, CYP2C9, or both. Three of the methods predict the SOM based on the ligand's chemical structure, two additional methods use structural information of the enzymes, and the sixth method combines structure and ligand similarity and reactivity. The SOM is correctly predicted in 50 to 90% of the cases, depending on method and enzyme, which is an encouraging rate. We also discuss the underlying mechanisms of cytochrome P450 metabolism in the light of the results from this comparison.     

Recognition of the critically ill patient and escalation of therapy

Critical illness often involves multiple organ failures and is associated with significant morbidity and mortality. In the vast majority of patients, there is a recognizable period of physiological deterioration which heralds the development of organ failure and critical illness. Despite efforts to improve the detection and management of critical illness, signs of deterioration are often missed and decisions to move patients to critical care units are delayed. Standardized approaches which implement an effective ‘chain of response’ are now utilized worldwide. They focus on attempting to reduce the incidence of serious adverse events (SAEs) such as in-hospital cardiac arrest and unplanned intensive care unit (ICU) admission using preventative measures. These systems should include: accurate recording and documentation of vital signs, recognition and interpretation of abnormal values, rapid bedside patient assessment by trained teams and appropriate interventions. Early warning systems (EWS) are an important part of this and can help identify patients at risk of deterioration and SAEs. Assessment of the critically ill patient should be undertaken by an appropriately trained clinician and follow a structured ABCDE (airway, breathing, circulation, disability and exposure) format. This facilitates correction of life-threatening problems by priority and provides a standardized communication framework between professionals. Lastly, timely support and input from members of the critical care team are vital to ensure optimal outcomes for critically ill patients.     

Structural Response Prediction of Thin-Walled Additively Manufactured Parts Considering Orthotropy,Thickness Dependency and Scatter

Besides the design freedom offered by additive manufacturing, another asset lies within its potential to accelerate product development processes by rapid fabrication of functional prototypes. The premise to fully exploit this benefit for lightweight design is the accurate structural response prediction prior to part production. However, the peculiar material behavior, characterized by anisotropy, thickness dependency and scatter, still constitutes a major challenge. Hence, a modeling approach for finite element analysis that accounts for this inhomogeneous behavior is developed by example of laser-sintered short-fiber-reinforced polyamide 12. Orthotropic and thickness-dependent Young’s moduli and Poisson’s ratios were determined via quasi-static tensile tests. Thereof, material models were generated and implemented in a property mapping routine for finite element models. Additionally, a framework for stochastic finite element analysis was set up for the consideration of scatter in material properties. For validation, thin-walled parts on sub-component level were fabricated and tested in quasi-static three-point bending experiments. Elastic parameters showed considerable anisotropy, thickness dependency and scatter. A comparison of the predicted forces with experimentally evaluated reaction forces disclosed substantially improved accuracy when utilizing the novel inhomogeneous approach instead of conventional homogeneous approaches. Furthermore, the variability observed in the structural response of loaded parts could be reproduced by the stochastic simulations.     

Prediction of Oncotype Dx recurrence score using clinical parameters: A comparison of available tools and a simple predictor based on grade and progesterone receptor

Objective/BackgroundThe Oncotype Dx test is a genomic test currently used in clinical practice to predict the risk of disease recurrence in estrogen receptor (ER)-positive, HER2-negative breast cancer patients with axillary lymph node-negative or micrometastatic disease. The test is one of several similar genomically based tests available. Although it has a good predictive value, it is expensive and thus constitutes a significant financial burden for health systems. Thus, several attempts have been made to devise low-cost tools that could predict the recurrence score derived from the genomic evaluation using easily obtainable clinical parameters.MethodsTwo previously proposed predictive tools were evaluated in a cohort of 201 patients that had undergone the Oncotype Dx test for their efficacy in predicting the Oncotype Dx Recurrence Score (RS). A simple predictor, named GR-PR, based on two available pathologic parameters, grade and progesterone receptor status was devised and also evaluated.ResultsThe sensitivity, specificity, positive predictive value, negative predictive value, and accuracy of all three tools were compared and found to be similar for all cutoff points of Oncotype Dx RS. The accuracy of GR-PR was comparable to the best performing of the two other prediction tools for all four cutoff points.ConclusionThe simple GR-PR predictor proposed in this study seems to be at least as accurate as more complex tools and should be the preferred tool for the prediction of Oncotype Dx RS from clinicopathologic parameters when the Oncotype Dx test is not available.     

早期症状改善预测焦虑患者rTMS治疗的疗效

目的 探讨重复经颅磁刺激(Repetitive transcranial magnetic stimulation,rTMS)治疗焦虑障碍患者早期症状的改善能否预测最终的临床疗效。方法 选择40例2017年7月-2019年11月本院焦虑障碍患者进行rTMS治疗,早期症状改善的界限值定义为治疗1或2周后汉密尔顿焦虑量表(Hamilton anxiety scale,HAMA)减分率15%～40%,分别计算其预测治疗4周后最终临床疗效的灵敏度、特异度、阳性预报值、阴性预报值,并通过受试者工作特征曲线(Receiver operating characteristic curve,ROC曲线)评估其预测效应。结果 治疗总有效率为62.5%; 以rTMS治疗1周后HAMA减分率15%及20%或治疗2周后HAMA减分率15%、20%、25%、30%及35%为界限值预测临床疗效有相对较高的灵敏度和阴性预报值; 以rTMS治疗1周后HAMA减分率30%、35%及40%或治疗2周后HAMA减分率35%及40%为界限值预测临床疗效有相对较高的特异度和阳性预报值; 以治疗1和2周后HAMA减分率预测治疗4周后临床疗效的ROC曲线下面积分别为0.712(P<0.05)和0.856(P<0.01)。结论 rTMS治疗焦虑障碍早期症状改善可有效预测最终临床疗效。     

SAPS 3 is not superior to SAPS 2 in cardiac surgery patients

Objectives. Cardiac surgery patients are excluded from SAPS2 but included in SAPS3. Neither score is evaluated for this exclusive population; however, they are used daily. We hypothesized that SAPS3 may be superior to SAPS2 in outcome prediction in cardiac surgery patients. Design. All consecutive patients undergoing cardiac surgery between January 2007 and December 2010 were included in our prospective study. Both models were tested with calibration and discrimination statistics. We compared the AUC of the ROC curves by DeLong's method and calculated OCC values. Results. A total of 5207 patients with mean age of 67.2 ± 10.9 years were admitted to the ICU. The mean length of ICU stay was 4.6 ± 7.0 days and the ICU mortality was 5.9%. The two tested models had acceptable discriminatory power (AUC: SAPS2: 0.777–0.875; SAPS3: 0.757–893). SAPS3 had a low AUC and poor calibration on admission day. SAPS2 had poor calibration on Days 1–6 and 8. Conclusions. Despite including cardiac surgery patients, SAPS3 was not superior to SAPS2 in our analysis. In this large cohort of ICU cardiac surgery patients, performance of both SAPS models was generally poor. In this subset of patients, neither scoring system is recommended.     

DVH预测模型在VMAT计划培训中的应用

目的:以宫颈癌为例，探索使用剂量体积直方图（DVH）预测模型培训放疗物理师容积旋转调强（VMAT）计划设计的可行性及其效果。方法:随机选取20例宫颈癌测试病例对3名见习物理师进行两个阶段培训（第一阶段15例，第二阶段5例）。每位物理师分别采用两种方法设计VMAT计划:传统人工计划（MP）和基于DVH预测模型引导的自动计划（KBP）。对比不同阶段两种计划靶区和危及器官的各种剂量学参数，并做相应统计分析。结果:与人工计划相比，自动计划在明显提高PGTV靶区V60覆盖（P<0.001），改善高剂量控制（V66）（P=0.027）的情况下，显著降低膀胱（P<0.001）、直肠（P<0.001）、左右肾（P=0.001和P<0.001）以及左右侧股骨头（P<0.001和P<0.001）等绝大部分正常组织器官的受照剂量。在提高计划合格率的同时，亦减小了计划者间的质量差异。结论:DVH预测模型有助于深化物理师对VMAT初始优化参数设置的理解，加快培训进度，提升VMAT计划设计水平。