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.     

From the "what" to the "how": Teaching integrative medicine-related skills to medical students during COVID-19

ObjectiveTo examine the impact of an integrative medicine (IM) course on self-perceived IM-related communication and research skills.MethodsA 3-day mandatory "hybrid" (online and in-person) IM course was held within COVID-19 restrictions for 161 pre-clerkship medical students, with workshops facilitated by mentor healthcare professionals (IM and non-IM) and student-directed tasks. Self-perceived levels of 6 IM-related skills were scored (from 1 to 5) for history-taking; communicating with patients with "alternative" health-beliefs; referral to IM consultations; assessing risks/benefits; and working with non-medical IM practitioners.Results137 students (85.1%) completed pre-/post-course questionnaires, with overall scores improving from pre-course (1.98 ± 0.92) to post-course (3.31 ± 0.63; p < 0.0001), for the entire group and student subgroups (with vs. without prior IM experience). Multivariate analysis found no association between age, gender, primary language or prior experience with IM and improvement in skill scores.ConclusionsThe IM course increased self-perceived skill levels, reflecting the course curriculum and workshops. Further research needs to explore the application of these skills during clinical training.Practice implicationsTeaching medical students about IM in a course comprising communication and research skills was shown to be feasible and effective. The application of IM-related skills needs to be evaluated during the clinical clerkship.     

肿瘤的数字治疗北大核心

肿瘤治疗已经进入数字治疗时代。数字治疗是数字健康的重要部分,它是应用数字技术预防、控制和治疗疾病。人工智能分析由生物传感器发来的数据资料,远距离控制肿瘤患者进行虚拟治疗和数字临床试验,模拟现实在线治疗帮助肿瘤患者采取健康行为,这些技术正在改变现有的医学模式。     

薄层色谱法在当前中药质量标准中的应用探讨

薄层色谱鉴别在历版《中国药典》中的应用经历了从无到有、从少到多的过程；而薄层扫描含量测定在最近几版《中国药典》中的应用比例逐渐降低。随着对中药质量标准体系要求的进一步提高，薄层色谱法的不足之处陆续显现，如仪器普及率低、设备并不简单、结果重复性和稳定性较差、鉴别速度及准确性不及高效液相色谱法、展开剂毒性大等，逐渐不合时宜。在制定中药质量标准时，研究者不应该墨守成规，薄层色谱鉴别也不应该是雷打不动的定性鉴别必备选项。高效液相色谱法具备完全取代薄层色谱法的可行性，薄层色谱法可作为高效液相色谱法的补充。为充分降低检测成本、缩短检测周期、提高鉴别效率，笔者建议中药质量标准体系应该大幅减少薄层色谱鉴别方法的应用，增加高效液相特征图谱鉴定，尽量做到“一个条件，一张图谱”；除非确有必要，《中国药典》等国家质量标准体系应将薄层色谱鉴别作为推荐方法，而非强制标准。     

经鼻高流量氧气湿化治疗老年慢性阻塞性肺疾病急性加重合并呼吸衰竭的可行性研究

ObjectiveTo investigate the feasibility of transnasal heated humidified high flow nasal cannula oxygen therapy (HFNC) in the treatment of acute exacerbation of chronic obstructive pulmonary disease (AECOPD) with respiratory failure in elderly patients. MethodsA total of 176 elderly patients with AECOPD complicated with respiratory failure who were hospitalized at Peking University Shougang Hospital from December 2016 to January 2022 were enrolled, including 82 patients in an HFNC group and 94 patients in an NPPV group. After treatment, pulse oxygen saturation (SPO₂), arterial partial pressure of carbon dioxide (PaCO₂), oxygenation index (OI), respiratory rate (RR), heart rate (HR), mean arterial pressure (MAP), comfort score, discharge rate, rate of endotracheal intubation, rate of transfer to intensive care unit (ICU), and mortality were compared between the two groups. The independent sample t-test was used for comparison between the two groups. Statistical data are expressed in percentage or number of cases and the χ² test was used for their comparisons. ResultsThe SPO₂ values at 30 min, 1 h, and 6 h were significantly higher in the HFNC group than in the NPPV group (t=-2.049,-2.618, and -3.314, P=0.043, 0.010, and 0.001, respectively). SPO₂ before discharge was significantly lower than that of the NPPV group (t=2.162, P=0.033), but OI at each time point and before discharge had no statistical significance (P＞0.05). MAP at 6 h was significantly higher in the HFNC group than in the NPPV group (t=-2.209, P=0.029), but within the normal range. HRs at 2 h and 3 h in the HFNC group were significantly higher than those of the NPPV group (t=-2.199 and -2.336, P=0.030 and 0.021, respectively). There were no significant differences in RR, HR, or MAP between the two groups at other time points and before discharge (P＞0.05). There was no significant difference in PaCO2 between the two groups (P＞0.05). Comfort score in the HFNC group was significantly higher than that of the NPPV group (t=-46.807, P＜0.001). There were no significant differences in discharge rate, ICU transfer rate, endotracheal intubation rate, and mortality between the two groups (P＞0.05). ConclusionHFNC is as effective as NPPV in treating elderly patients with AECOPD complicated with type Ⅰ or mild type Ⅱ respiratory failure, and HFNC is more comfortable than NPPV.     

Neighborhood resources associated with frailty trajectories over time among community-dwelling older adults in China

Background and objectivesRecent research has identified neighborhoods as an important contributor to later-life frailty. However, little is known about how neighborhood resources are associated with frailty trajectories over time, especially in developing countries. This study examines the impact of neighborhood physical and social resources on the trajectories of frailty over time among older people in China.Research design and methodsUsing the four waves of the China Health and Retirement Longitudinal Study (2011–2018), 5673 respondents aged 60 and above at baseline were included for analyses. Multilevel growth modeling was fitted to estimate the effects of neighborhood resources on frailty trajectories over a 7-year period, controlling for individual-level characteristics.ResultsOlder Chinese people who lived in neighborhoods with better basic infrastructures and a greater number of voluntary organizations were less frail at baseline. Accessible exercise facilities were associated with a lower initial level of frailty only among rural older adults, while higher community-level socioeconomic status (SES) was associated with a lower initial level of frailty only among urban older adults. Over the 7-year follow-up period, better basic infrastructures and accessible exercise facilities were associated with a slower increase rate of frailty scores among rural residents.Discussion and implicationsNeighborhood resources are important contributors to the level of frailty among older Chinese people. Our findings of significant urban-rural differences have important implications for designing and implementing infrastructure development and community building programs in rural and urban China.     

理气中药组方对糖尿病大鼠胃排空延迟的作用

目的:观察理气中药经验组方对糖尿病大鼠胃排空延迟的干预作用。方法:雌雄各半成年SD大鼠110只,随机分为正常组(A组)、糖尿病中药组(B组)、糖尿病胃复安组(C组)、糖尿病组(D组)。A组、D组1次/d按10 mL/只予0.9%生理盐水灌胃,B组1次/d按8 mL/只予中药煎剂灌胃,C组1次/d按0.5 mg/只予胃复安片灌胃。喂养12周后,行13C胃排空实验及甲基橙水溶液胃排空实验,观察各组大鼠胃排空情况。结果:糖尿病大鼠胃排空较正常大鼠明显延迟(P0.01),糖尿病大鼠胃排空延迟模型制作成功。糖尿病中药组和糖尿病胃复安组大鼠胃排空较糖尿病组快(P0.01);糖尿病中药组大鼠胃排空较糖尿病胃复安组大鼠快(P0.05)。结论:常规喂养12周后糖尿病大鼠出现胃排空延迟。理气中药陈皮、枳实、木香、香附组方煎剂和胃复安均能促进糖尿病大鼠胃排空,理气中药组方煎剂的效果优于胃复安。