非线性立体脑图像配准中的机器学习方法

针对基于属性向量的非线性配准算法，提出用机器学习的方法寻找脑图像中各个点上的最优几何特征向量。通过定义一个能量函数把寻找最优属性向量的过程归结为一个最优化问题。把训练得到的最优属性向量与HAMMER（一种基于属性向量的非线性配准算法）相结合，对模拟的MR脑图像进行了实验，与HAMMER相比，位移场的精度提高了10％。改进后的算法对真实的MR脑图像的配准结果，也有很大的改善。     

Inter-Professional Clinical Practice Guideline for Vocational Evaluation Following Traumatic Brain Injury: A Systematic and Evidence-Based Approach

Introduction This paper introduces an inter-professional clinical practice guideline for vocational evaluation following traumatic brain injury. This guideline aims to explicate the processes and factors relevant to vocational evaluation to assist evaluators (i.e. health care teams, individuals and employers) in collaboratively determining if clients are able to work and to make recommendations for work entry, re-entry or vocational planning. Methods Methods in the Canadian Medical Association’s (CMA) Handbook on Clinical Practice Guideline and the Appraisal of Guidelines for Research and Evaluation (AGREE) instrument were utilized to ensure rigour. Steps in the CMA handbook were followed and included: (1) identifying the guideline’s objective and questions; (2) systematic literature review; (3) study selection and quality appraisal; (4) development of clear recommendations by key stakeholders; (5) guideline pilot testing and endorsement. Results The resulting guideline includes 17 key recommendations within the seven domains: (1) evaluation purpose and rationale; (2) initial intake process; (3) assessment of the personal domain; (4) assessment of the environment; (5) assessment of occupational/job requirements; (6) analysis and synthesis; (7) evaluation recommendations. Conclusions The guideline may be useful to individually practicing clinicians, health care teams, employers and individuals with TBI. Future research will formally examine the success of the guideline’s implementation.     

Development and Validation of an Insulin Resistance Model for a Population with Chronic Kidney Disease Using a Machine Learning Approach

Background: Chronic kidney disease (CKD) is a complex syndrome without a definitive treatment. For these patients, insulin resistance (IR) is associated with worse renal and patient outcomes. Until now, no predictive model using machine learning (ML) has been reported on IR in CKD patients. Methods: The CKD population studied was based on results from the National Health and Nutrition Examination Survey (NHANES) of the USA from 1999 to 2012. The homeostasis model assessment of IR (HOMA-IR) was used to assess insulin resistance. We began the model building process via the ML algorithm (random forest (RF), eXtreme Gradient Boosting (XGboost), logistic regression algorithms, and deep neural learning (DNN)). We compared different receiver operating characteristic (ROC) curves from different algorithms. Finally, we used SHAP values (SHapley Additive exPlanations) to explain how the different ML models worked. Results: In this study population, 71,916 participants were enrolled. Finally, we analyzed 1,229 of these participants. Their data were segregated into the IR group (HOMA IR > 3, n = 572) or non-IR group (HOMR IR ≤ 3, n = 657). In the validation group, RF had a higher accuracy (0.77), specificity (0.81), PPV (0.77), and NPV (0.77). In the test group, XGboost had a higher AUC of ROC (0.78). In addition, XGBoost also had a higher accuracy (0.7) and NPV (0.71). RF had a higher accuracy (0.7), specificity (0.78), and PPV (0.7). In the RF algorithm, the body mass index had a much larger impact on IR (0.1654), followed by triglyceride (0.0117), the daily calorie intake (0.0602), blood HDL value (0.0587), and age (0.0446). As for the SHAP value, in the RF algorithm, almost all features were well separated to show a positive or negative association with IR. Conclusion: This was the first study using ML to predict IR in patients with CKD. Our results showed that the RF algorithm had the best AUC of ROC and the best SHAP value differentiation. This was also the first study that included both macronutrients and micronutrients. We concluded that ML algorithms, particularly RF, can help determine risk factors and predict IR in patients with CKD.     

An Innovative Machine Learning Approach to Predict the Dietary Fiber Content of Packaged Foods

Underconsumption of dietary fiber is prevalent worldwide and is associated with multiple adverse health conditions. Despite the importance of fiber, the labeling of fiber content on packaged foods and beverages is voluntary in most countries, making it challenging for consumers and policy makers to monitor fiber consumption. Here, we developed a machine learning approach for automated and systematic prediction of fiber content using nutrient information commonly available on packaged products. An Australian packaged food dataset with known fiber content information was divided into training (n = 8986) and test datasets (n = 2455). Utilization of a k-nearest neighbors machine learning algorithm explained a greater proportion of variance in fiber content than an existing manual fiber prediction approach (R² = 0.84 vs. R² = 0.68). Our findings highlight the opportunity to use machine learning to efficiently predict the fiber content of packaged products on a large scale.     

手术治疗重症颅脑外伤患者的效果分析

目的探讨不同手术治疗重症颅脑外伤患者的效果。方法选取我院2016年3月至2017年1月收治的72例重症颅脑外伤患者,随机分为对照组与观察组各36例。对照组采用传统开颅减压术治疗,观察组采用双侧相继去骨瓣减压术治疗,对比两组患者的临床治疗效果。结果两组患者术后的GCS评分均优于术前(P <0.05),但组间比较差异无统计学意义(P>0.05)。观察组的术后住院时间明显短于对照组(P <0.05)。观察组术后并发症发生率为11.11%,明显低于对照组的30.56%(P <0.05)。观察组GOS评分为5分的比例高于对照组(P <0.05)。结论与传统开颅减压术相比,采用双侧相继去骨瓣减压术治疗重症颅脑外伤患者的效果显著,值得优先考虑。     

A Bootstrap Confidence Interval Procedure for the Treatment Effect Using Propensity Score Subclassification

In the analysis of observational studies, propensity score subclassification has been shown to be a powerful method for adjusting unbalanced covariates for the purpose of causal inferences. One practical difficulty in carrying out such an analysis is to obtain a correct variance estimate for inference, while reducing bias in the estimate of the treatment effect due to an imbalance in the measured covariates. In this paper, we propose a bootstrap procedure for the inferences concerning the average treatment effect; our bootstrap method is based on an extension of Efron's bias-corrected accelerated (BCa) bootstrap confidence interval to a two-sample problem. Unlike the currently available inference procedures based on propensity score subclassifications, the validity of the proposed method does not rely on a particular form of variance estimation. A brief simulation study is included to evaluate the operating characteristics of the proposed procedure. We conclude the paper by illustrating the new procedure through a clinical application comparing the renal effects of two non-steroidal anti-inammatory drugs (NSAIDs).     

Adults with Acquired Traumatic Brain Injury: A Theoretical Analysis from a Social Recognition Perspective

The purpose of this study is to illuminate the changeover process experienced by people with traumatic brain injury (TBI) and increase the understanding of social recognition occurring after injury. Fifteen persons, ages 28–56, with TBI have been in-depth interviewed. Data were first analyzed by latent-content analysis using a hermeneutic approach, and later re-contextualized within a matrix constructed from theories of social recognition. Results were initially structured into six themes and then re-described in terms of recognition, that is, the individual dimension, the legal dimension, and the value dimension. The conclusions suggest that people with TBI experience both recognition and non-recognition during the recovery process and later in life, living in society with the sequel of TBI. Such experiences are described on all dimensions.     

Promoting Resilience Following Traumatic Brain Injury: Application of an Interdisciplinary,Evidence‐Based Model for Intervention

With an increasing instance of traumatic brain injury and little advancement over recent decades in the rehabilitation of brain injury survivors and their family members, focus has shifted toward the establishment of effective whole‐family resilience promotion interventions. Using the Brain Injury Family Intervention as a model, clinicians constructed two curriculum‐based interventions grounded in resilience theory and drawing from the interdisciplinary approaches of neuropsychology and marriage and family therapy: (a) the Resilience and Adjustment Intervention, for individual survivors of traumatic brain jury, and (b) the Therapeutic Couples Intervention, designed to increase relational satisfaction in couples following a traumatic brain injury. The present study outlines the need for the integration of resilience tenets into rehabilitation techniques, summarizes the empirical justification for the use of an interdisciplinary approach, and offers an overview with implementation specifics regarding these two newly designed interventions.     

A Service Mapping Approach to the Analysis of Service Use for People with Acquired Brain Injury

SUMMARY

This research study is a retrospective study which uses a novel graphical approach to visually present information about the duration and types of services provided to people with acquired brain injury in a university teaching hospital. It illustrates a method for using practitioners' knowledge of this client group and requisite interventions to develop a method of documenting the intensity and extensiveness of social work intervention. It provides a useful tool for social work, particularly in interdisciplinary settings, where the social work role in areas such as case management and counselling is rendered less visible by factors such as exception-based reporting which discourages detailed documentation of practice processes and outcomes.     

Economic Evaluations in the Diagnosis and Management of Traumatic Brain Injury: A Systematic Review and Analysis of Quality

BackgroundEconomic evaluations provide a unique opportunity to identify the optimal strategies for the diagnosis and management of traumatic brain injury (TBI), for which uncertainty is common and the economic burden is substantial.ObjectiveThe objective of this study was to systematically review and examine the quality of contemporary economic evaluations in the diagnosis and management of TBI.MethodsTwo reviewers independently searched MEDLINE, EMBASE, Cochrane Central Register of Controlled Trials, NHS Economic Evaluation Database, Health Technology Assessment Database, EconLit, and the Tufts CEA Registry for comparative economic evaluations published from 2000 onward (last updated on August 30, 2013). Data on methods, results, and quality were abstracted in duplicate. The results were summarized quantitatively and qualitatively.ResultsOf 3539 citations, 24 economic evaluations met our inclusion criteria. Nine were cost-utility, five were cost-effectiveness, three were cost-minimization, and seven were cost-consequences analyses. Only six studies were of high quality. Current evidence from high-quality studies suggests the economic attractiveness of the following strategies: a low medical threshold for computed tomography (CT) scanning of asymptomatic infants with possible inflicted TBI, selective CT scanning of adults with mild TBI as per the Canadian CT Head Rule, management of severe TBI according to the Brain Trauma Foundation guidelines, management of TBI in dedicated neurocritical care units, and early transfer of patients with TBI with nonsurgical lesions to neuroscience centers.ConclusionsThreshold-guided CT scanning, adherence to Brain Trauma Foundation guidelines, and care for patients with TBI, including those with nonsurgical lesions, in specialized settings appear to be economically attractive strategies.     

开颅术联合高压氧对重型颅脑损伤患者昏迷指数的影响

目的探讨开颅术联合高压氧对重型颅脑损伤患者昏迷指数的影响。方法选择2009年1月—2011年10月在我院住院治疗的60例重型颅脑损伤患者,按照随机数字表法将患者分为对照组和观察组,每组30例。在常规药物治疗基础上,对照组采用开颅术治疗,观察组采用开颅术联合高压氧治疗,术后对两组患者的临床疗效、昏迷指数(Glasgow comascale,GCS)评分,并与高压氧治疗前、治疗4周及治疗3个月随访时治疗结果分级(GOS)进行对比分析。结果观察组和对照组临床有效率分别为86.67%(26/30)和76.67%(23/30),两组患者临床有效率比较差异有显著性(P<0.05);高压氧治疗后1周GCS评分无明显差异,第2、3、4周高压氧治疗后GCS评分比较有统计学差异(P<0.05);两组患者第4周、3个月随访阶段的GOS预后评分比较有统计学意义(P<0.05)。结论开颅术联合高压氧治疗不仅对重型颅脑损伤患者早期意识改善和预后有显著效果,而且提高了患者的生活质量,可以促使患者早日康复。     

Analyzing risk factors for post-acute recovery in older adults with Alzheimer's disease and related dementia: A new semi-parametric model for large-scale medicare claims

Nearly 300,000 older adults experience a hip fracture every year, the majority of which occur following a fall. Unfortunately, recovery after fall-related trauma such as hip fracture is poor, where older adults diagnosed with Alzheimer's disease and related dementia (ADRD) spend a particularly long time in hospitals or rehabilitation facilities during the post-operative recuperation period. Because older adults value functional recovery and spending time at home versus facilities as key outcomes after hospitalization, identifying factors that influence days spent at home after hospitalization is imperative. While several individual-level factors have been identified, the characteristics of the treating hospital have recently been identified as contributors. However, few methodological rigorous approaches are available to help overcome potential sources of bias such as hospital-level unmeasured confounders, informative hospital size, and loss to follow-up due to death. This article develops a useful tool equipped with unsupervised learning to simultaneously handle statistical complexities that are often encountered in health services research, especially when using large administrative claims databases. The proposed estimator has a closed form, thus only requiring light computation load in a large-scale study. We further develop its asymptotic properties with stabilized inference assisted by unsupervised clustering. Extensive simulation studies demonstrate superiority of the proposed estimator compared to existing estimators.     

脑卒中患者连续性护理的应用及效果评价

目的探讨对脑卒中患者应用连续性护理的效果。方珐构建连续性护理模式,从入院开始进行连续性护理干预,通过患者住院天数、住院费用、再入院率、护理服务满意度、Bl指数等指标,评价应用效果。结果连续性护理干预减少了患者住院天数、住院费用、再入院率（．P〈0．01,P〈0．01,P〈0．05）,提高了患者对护理服务的满意度及BI指数（P〈0．05）。结论连续性护理是脑卒中患者护理的有效途径,值得推广应用。     

Evaluation of an intervention programme to support mothers and babies at psychosocial risk: assessment of mother/child interaction and mother's perceptions of benefit

The outcome of a short-term intervention programme for mothers at psychosocial risk was evaluated. The study included 63 mothers and their 0-6-month-old babies who participated in a 6-week intensive treatment programme. Mother-child interaction was assessed in the beginning and at the end of treatment by two independent staff members based on direct observation, and by two control raters who observed video recordings which were arranged in blind order. The mothers were interviewed about the treatment retrospectively. A positive change in several aspects of mother-child interaction, according to the assessments made by the raters and according to the mothers themselves. The number of mothers who were positive toward the treatment rose from 34 in the beginning of the treatment to 56 at the end. In conclusion, a short but intensive intervention seems to have a positive outcome on mother-child interaction, and was in most cases linked to a positive attitude.     

The Impact of Subsidized Health Insurance for the Poor: Evaluating the Colombian Experience Using Propensity Score Matching

This paper evaluates the impact of Colombia’s subsidized health insurance program (SUBS) on medical care utilization. Colombia’s SUBS program is a demand-side subsidy intended for low-income families, where the screening of beneficiaries takes place in decentralized locations across the country. Due to the self-selection problems associated with non-experimental data, we implement Propensity Score Matching (PSM) methods to measure the impact of this subsidy on medical care utilization. By combining unique household survey data with community and regional data, we are able to compute propensity scores in a way that is consistent with both the local government’s decision to offer the subsidy, and with the individual’s decision to accept the subsidy. Although the application of PSM using these rich datasets helps to achieve a balance between the treatment and control groups along observable dimensions, we also present instrumental variable estimates to control for the potential endogeneity of program participation. Using both methods, we find that Colombia’s subsidized insurance program greatly increased medical care utilization among the country’s poor and uninsured. This evidence supports the case for other Latin American countries implementing similar subsidy programs for health insurance for the poor.JEL classification:     

‘Shape-Up’, a Modified Cognitive-Behavioural Community Programme for Weight Management: Real-World Evaluation as an Approach for Delivering Public Health Goals

Obesity is widespread, with serious health consequences; addressing it requires considerable effort at a public health level, incorporating prevention and management along with policies to support implementation. Behavioural weight-management programmes are widely used by public health bodies to address overweight and obesity. Shape-Up is an evidence-based programme combining a structured behavioural intervention (targeting nutrition and physical activity behaviours) within a peer-learning framework. This study was a service-evaluation of Shape-Up, as delivered in Rotherham by a local leisure provider, and included a secondary analysis of data collected in the community by service providers. The RE-AIM (Reach Effectiveness Adoption Implementation Maintenance) framework was used to explore programme effectiveness, implementation, and whom it reached. A total of 141 participants were included. Compared to local demographics, participants were older, at 48.9 (SD 14.47) years, with a lower employment rate (41% employed) and greater proportion female (67% female). Mean BMI was 38.0 (SD 7.54) kg/m². Mean weight-change between baseline and endpoint (12 weeks, 10 group sessions) was −4.4 (SD 3.38) kg, and degree of weight change was associated with session attendance (F (9, 131) = 6.356, p < 0.0005). There were positive effects on participants’ weight, health-related behaviours, and quality of life. The intervention content (including the focus of nutritional recommendations) and structure were adapted during implementation to better suit national guidelines and local population needs. RE-AIM was found to be a useful framework for evaluating and adapting an existing evidence-based weight management programme in line with local population needs. This could be a more cost-effective approach, compared to developing new programmes, for delivering public health goals relating to obesity, nutrition, and physical activity.     

颅脑损伤患者远期生存质量评估

目的评估颅脑损伤患者伤后不同时期的生活质量。方法颅脑外伤患者55例获得随访。使用GCS、GOS和KPS等作为参照,同时使用世界卫生组织生存质量测定简表(WHOQOL-BREF),由患者自行填写评估。结果WHOQOL-BREF与GOS,GCS,KPS均有很好的相关性。结论颅脑外伤的生存质量与其主观感受存在显著的相关性,一种多维评估量表,也可用于各种治疗手段的疗效评价。     

Value of Nonpharmacological Interventions for People With an Acquired Brain Injury: A Systematic Review of Economic Evaluations

ObjectivesAcquired brain injury (ABI) has long-lasting effects, and patients and their families require continued care and support, often for the rest of their lives. For many individuals living with an ABI disorder, nonpharmacological rehabilitation treatment care has become increasingly important care component and relevant for informed healthcare decision making. Our study aimed to appraise economic evidence on the cost-effectiveness of nonpharmacological interventions for individuals living with an ABI.MethodsThis systematic review was registered in PROSPERO (CRD42020187469), and a protocol article was subject to peer review. Searches were conducted across several databases for articles published from inception to 2021. Study quality was assessed according the Consolidated Health Economic Evaluation Reporting Standards checklist and Population, Intervention, Control, and Outcomes criteria.ResultsOf the 3772 articles reviewed 41 publications met the inclusion criteria. There was a considerable heterogeneity in methodological approaches, target populations, study time frames, and perspectives and comparators used. Keeping these issues in mind, we find that 4 multidisciplinary interventions studies concluded that fast-track specialized services were cheaper and more cost-effective than usual care, with cost savings ranging from £253 to £6063. In 3 neuropsychological studies, findings suggested that meditated therapy was more effective and saved money than usual care. In 4 early supported discharge studies, interventions were dominant over usual care, with cost savings ranging from £142 to £1760.ConclusionsThe cost-effectiveness evidence of different nonpharmacological rehabilitation treatments is scant. More robust evidence is needed to determine the value of these and other interventions across the ABI care pathway.