Machine learning models for Parkinson’s disease detection and stage classification based on spatial-temporal gait parameters

BackgroundParkinson’s disease (PD) is a chronic and progressive neurodegenerative disease with no cure, presenting a challenging diagnosis and management. However, despite a significant number of criteria and guidelines have been proposed to improve the diagnosis of PD and to determine the PD stage, the gold standard for diagnosis and symptoms monitoring of PD is still mainly based on clinical evaluation, which includes several subjective factors. The use of machine learning (ML) algorithms in spatial-temporal gait parameters is an interesting advance with easy interpretation and objective factors that may assist in PD diagnostic and follow up.Research questionThis article studies ML algorithms for: i) distinguish people with PD vs. matched-healthy individuals; and ii) to discriminate PD stages, based on selected spatial-temporal parameters, including variability and asymmetry.MethodsGait data acquired from 63 people with PD with different levels of PD motor symptoms severity, and 63 matched-control group individuals, during self-selected walking speed, was study in the experiments.ResultsIn the PD diagnosis, a classification accuracy of 84.6 %, with a precision of 0.923 and a recall of 0.800, was achieved by the Naïve Bayes algorithm. We found four significant gait features in PD diagnosis: step length, velocity and width, and step width variability. As to the PD stage identification, the Random Forest outperformed the other studied ML algorithms, by reaching an Area Under the ROC curve of 0.786. We found two relevant gait features in identifying the PD stage: stride width variability and step double support time variability.SignificanceThe results showed that the studied ML algorithms have potential both to PD diagnosis and stage identification by analysing gait parameters.     

Self-reported outcomes of a randomized trial comparing three community health worker interventions for diabetes prevention among Cambodian Americans with depression

ObjectiveCambodian Americans have complex, interrelated and persistent medical and mental health problems stemming from genocide and the social determinants of health. We examined changes in multiple domains of self-reported health outcomes from a diabetes prevention trial. Methods: Cambodian Americans with depression and high risk for diabetes (n = 188) were randomized to one of three community health worker interventions: lifestyle vs lifestyle plus medication therapy management vs social services. Assessments were at baseline, 12- and 15-months. Results: The typical participant was 55 years old, female, earned below $20,000 annually, and had 7 years of education. About one-third were taking antidepressant medication and over half had elevated depressive symptoms. Relative to social services, lifestyle and lifestyle plus medication therapy management were both similarly effective at increasing diabetes knowledge, nutrition habits, sleep quality and decreasing pain; 2) lifestyle alone was superior to social services for self-reported health; and, 3) all three groups showed improved anxiety and insomnia. There were no effects on physical activity or physical functioning. Conclusion: Community health worker interventions have multiple benefits beyond delaying diabetes. Practice Implications: Health promotion programs that are designed and delivered appropriately can impact even hard to reach and hard to treat groups.     

Factors associated with provision of depot medroxyprogesterone acetate to adolescents by US health care providers

ObjectiveIdentify factors associated with healthcare providers' frequency of depot medroxyprogesterone acetate (DMPA) provision to adolescents.Study designWe analyzed data from surveys mailed to a nationally representative sample of public-sector providers and office-based physicians (n=1984). We estimated adjusted odds ratios (aORs) and 95% confidence intervals (CIs) of factors associated with frequent DMPA provision to adolescents in the past year.ResultsAlthough most providers (>95%) considered DMPA safe for adolescents, fewer reported frequent provision (89% of public-sector providers; 64% of office-based physicians). Among public-sector providers, factors associated with lower odds of frequent provision included working in settings without Title X funding (aOR 0.44, 95% CI 0.30–0.64), reporting primary care as their primary clinical focus versus reproductive or adolescent health (aOR 0.42, 95% CI 0.28–0.61), and providing fewer patients with family planning services. Among office-based physicians, factors associated with lower odds of frequent provision included specializing in obstetrics/gynecology (aOR 0.50, 95% CI 0.27–0.91) and family medicine (aOR 0.21, 95% CI 0.09–0.47) versus adolescent medicine, completing training ≥15 versus <5 years ago (aOR 0.27, 95% CI 0.09–0.83), and reporting that 0–24% of patients pay with Medicaid or other government healthcare assistance versus ≥50% (aOR 0.23, 95% CI 0.09–0.61). The reason most commonly reported by providers for infrequent DMPA provision was patient preference for another method.ConclusionsWhile most providers reported frequently providing DMPA to adolescents, training on evidence-based recommendations for contraception, focused on subgroups of providers with lower odds of frequent DMPA provision, may increase adolescents' access to contraception.ImplicationsAlthough >95% of providers considered depot medroxyprogesterone (DMPA) a safe contraceptive for adolescents, only 89% of public-sector providers and 64% of office-based physicians reported frequently providing DMPA to adolescents. Provider training on evidence-based recommendations for contraception counseling and provision may increase adolescents' access to DMPA and all methods of contraception.     

某医疗机构核医学工作场所劳务派遣保洁人员的职业健康管理

近几年，"劳务派遣"成了医疗机构终末消毒、保洁、垃圾回收等工作新的用工形式。由于多数用工单位和用人单位不清楚对劳务派遣人员职业健康管理中各自应承担的责任和义务，以至于劳务派遣工在劳动过程中应享有的劳动保护权益未获得切实保障。本文就某医疗机构核医学工作场所劳务派遣保洁人员的职业健康管理监督案例进行讨论。     

Effect of a multi-disciplinary program on anthropometric and biochemical parameters in obese and overweight elementary school girls: A randomized clinical trial

Background and aimsObesity and overweight in children are associated with an increased risk of several health issues. The present study aimed to assess the effects of a multi-disciplinary program (including nutrition education using a smartphone game, physical activity, and cognitive behavioral therapy [CBT]) on the management of obesity and overweight in elementary school girls.Methods and resultsSixty-two school girls above the 85th percentile of body mass index (BMI) for age were randomly assigned to two groups. During 10 weeks of study, the intervention group received a multi-disciplinary intervention, including nutrition education using a smartphone game, aerobic exercise, and CBT. The control group received usual traditional nutritional education. Biochemical and metabolic factors were assessed, including fasting blood sugar (FBS), lipid profile, serum leptin, and anthropometric measurements. The Dutch Eating Behavior Questionnaire (DEBQ) and metabolic equivalent test (MET) were also conducted. The intervention group showed more promising results in weight loss, waist circumference (WC), hip circumference (HC), total cholesterol (TC), low-density lipoprotein cholesterol (LDL-C), triglyceride (TG), and FBS compared to the control group (P < 0.05). In addition, MET and DEBQ scores in all three sections of emotions, stimuli, and restriction were better in the intervention group than in the control group (P < 0.05). However, there was no significant difference between groups regarding the results of serum leptin and waist-to-hip ratio (WHR; p > 0.05).ConclusionsThe results indicated that education through smartphone games could possibly affect performance in real life. In addition, the multi-disciplinary approach to childhood obesity might have better performance in most areas than the single-intervention approach in obesity management.     

Constructing queer mother‐knowledge and negotiating medical authority in online lesbian pregnancy journals

Medical interactions around reproduction are increasingly extending beyond the physician's office and onto the Internet, where negotiation with medical authority occurs in complex and dynamic ways. Recently, scholars have noted the Internet's potential for creating spaces where women can dialogue with and reconstruct medical authority, yet this growing body of work is overwhelming heteronormative. This paper thus interrogates how lesbian women use the Internet to challenge, deploy, and rework medical authority around reproduction while navigating the transition to parenthood. I draw from 17 online journals authored by lesbian couples during the conception, pregnancy, and birth of their first child, each spanning between 18 months and 2 years, in order to understand how the transition process unfolds over time. I argue that lesbian couples engage with medical authority when seeking affirmation and normalisation yet discard and publicly reject the heteronormative assumptions that accompany reproductive medicine. Further, they chart a new process that I term ‘constructing queer mother‐knowledge’, in which they critique and balance knowledges from institutionalised medicine, their own bodies, and their queer communities. With this new concept, I complicate understandings of lesbian mothers‐to‐be and their interactions with medical authority as they build subversive families.     

Dengue vaccine: WHO position paper,September 2018 – Recommendations

This article presents the World Health Organization’s (WHO) recommendations on the use of dengue vaccine excerpted from the WHO position paper on dengue vaccine – September 2018, published in the Weekly Epidemiological Record [1]. This position paper replaces the July 2016 WHO position paper concerning the first licensed dengue vaccine, CYD-TDV [2]. The position paper presents new evidence that became available in November 2017. A retrospective analysis of data from clinical trials, using a new serological assay classified trial participants according to their dengue serostatus prior to receipt of the first vaccine dose. The analysis revealed an excess risk of severe dengue in seronegative vaccine recipients compared to seronegative non-vaccinated individuals, while confirming long-term protection in seropositive individuals [3]. The paper provides revised guidance on dengue vaccination strategies from a population health perspective.Footnotes to this paper provide a number of core references including references to grading tables that assess the quality of the scientific evidence, and to the evidence-to-recommendation table. In accordance with its mandate to provide guidance to Member States on health policy matters, WHO issues a series of regularly updated position papers on vaccines and combinations of vaccines against diseases that have an international public health impact. These papers are concerned primarily with the use of vaccines in large-scale immunization programmes; they summarize essential background information on diseases and vaccines, and conclude with WHO's current position on the use of vaccines in the global context. Recommendations on the use of dengue vaccine CYD-TDV were discussed by SAGE in April 2018; evidence presented at the meeting can be accessed at: http://www.who.int/immunization/sage/meetings/2018/april/presentations_background_docs/en/