Use of hyperspectral imaging to predict healing of diabetic foot ulceration

Our main objective was to validate that hyperspectral imaging via a new portable camera carries the potential to provide a reliable clinical biomarker that can predict DFU healing. We recruited patients with diabetic foot ulceration (DFU) without peripheral arterial disease, infection or other serious illness. Using an hyperspectral imaging (HSI) apparatus, post-debridement hyperspectral images were taken evaluating the ulcer size, periwound oxyhemoglobin (OxyHb), deoxyhemoglobin level (DeoxyHb) and oxygen saturation (O₂Sat) for four consecutive visits. Twenty-seven patients were followed, out of whom seven healed their DFU while the remaining 20 failed to heal their DFU. The average time between each visit was 3 weeks. Binary logistic regression of healers versus non-healers on Visit 1 oxyHb and on Visit 2 showed a significant inverse association, OR = 0.85 (95% CI: 0.73–0.98, p < 0.001). An inverse correlation was observed between the Visit 1 oxyHb and the percentage of ulcer size reduction between Visit 1 and Visit 4 (r = −0.46, p = 0.02) and between the Visit 2 oxyHb and the percentage of ulcer size reduction between Visits 2 and 4 (r = −0.65, p = 0.001). Using oxyHb 50 as the cut-off point to predict DFU complete healing, Visit 1 oxyHb measurement provided 85% sensitivity, 70% specificity, 50% positive predictive value and 93% negative predictive value. For Visit 2, oxyHb had 85% sensitivity, 85% specificity, 66% positive predictive value and 94% negative predictive value. We conclude that this preliminary study, which involved a relatively small number of patients, indicates that hyperspectral imaging is a simple exam that can easily be added to daily clinical practice and has the potential to provide useful information regarding the healing potential of DFU over a short period of time.     

Prediction of the length of service at the onset of coal workers’ pneumoconiosis based on neural network

Abstract

Three environmental parameters, i.e. dust concentrations, dust dispersion, and free silica content, were introduced into the traditional indices of the neural network model in order to construct a new prediction index and explore a new method for preventing the incidence of pneumoconiosis with intelligent accuracy and universality. Data of the pneumoconiosis patients from Huabei Mining Group (HBMG) of China from 1980 to 2017 were collected. SPSS22.0 was used to develop the combined models based on Back Propagation (BP) neural network model, Radial Basis Function (RBF) neural network model, and Multiple Linear Regression (MLR) model. The paired sample t-test was performed between the real and predicted values. According to this model, it was predicted that 382 coal workers in HBMG were likely to suffer from pneumoconiosis in 2022 and the incidence rate was 4.48%. It is necessary to take prevention measures and transfer these workers from their current positions. In four combined models, the BP-MLR combined model achieved the optimal error parameters and the most accurate prediction. This study provided a scientific basis for effective control and prevention of the incidence of the pneumoconiosis.     

全面二孩政策下贵州省人口与医疗资源需求预测分析

目的为响应"全面二孩"生育政策,通过预测未来人口总数,合理规划医疗资源发展,以充分应对新一轮的生育高潮.方法首先基于系统动力学建立了针对"全面二孩"政策的人口数量预测模型,然后以贵州省为例进行实证研究,分析了贵州省现阶段医疗资源总量、布局现状及未来10年人口发展趋势,再根据国务院和原国家卫生部颁布的医疗资源配置标准对贵州省医疗资源需求进行合理预测.结果根据相关标准,到2027年,需增加床位3.24万张,执业(助理)医师4.65万人,注册护士11.04万人.结论贵州省医疗卫生资源配置不公平现象凸显,且需求量不断增大,针对这一问题,提出贵州省"一点两带"医疗资源发展战略,并对贵州省医疗卫生资源发展做出计划安排.     

PTX-3对肾综合征出血热患者疾病严重程度及预后的预测价值研究

目的　分析肾综合征出血热（hemorrhagic fever with renal syndrome, HFRS）患者血浆正五聚素-3（pentraxin-3, PTX-3）的水平变化,探讨其对HFRS病情严重程度及预后的预测价值。方法　随机纳入105例2012年10月—2014年12月空军军医大学第二附属医院传染科收治的HFRS患者,依据HFRS临床分型标准,将纳入患者分为轻型、中型、重型和危重型4组。采集患者急性期静脉血标本96份,恢复期65份,同时采集27名健康志愿者静脉血标本作为对照,分离血浆,应用ELISA法检测PTX-3水平。分析PTX-3水平在不同分型患者急性期及恢复期的表达变化,以及与对照组的差异,评估其在重症HFRS早期预警中的价值;分析急性期PTX-3与常规实验室指标及预后的相关性,采用ROC曲线评估急性期PTX-3水平对HFRS患者预后（死亡）的预测价值。结果　105例患者中,轻型17例、中型27例、重型26例、危重型35例。各型患者及对照组之间性别、年龄比较,差异均无统计学意义（P均＞0.05）。各型患者急性期血浆PTX-3水平均显著高于同型恢复期和对照组（P均＜0.05）,危重型患者急性期PTX-3水平显著高于其他分型（P均＜0.05）。患者急性期PTX-3水平与WBC、AST、APTT呈正相关,与PLT、ALB、血浆纤维蛋白原水平呈负相关（|rs|＞0.500,P＜0.05）。ROC曲线分析急性期PTX-3水平对HFRS患者预后（死亡）的预测价值,AUC为0.753（95%CI：0.593～0.914,P=0.003）。结论　PTX-3可作为重症HFRS的早期预警指标,其有助于评估HFRS疾病严重程度及预测患者预后。     

我国各省份卫生投入空间分布及预测研究

目的:分析我国2007—2017年人均政府卫生投入的空间分布,观察政府卫生投入的公平性,提出改善和优化的建议,促进政府卫生投入的优化配置。方法:利用空间自相关法、LISA指数法、Getis-Ord Gi^和Kriging插值预测法等对政府卫生投入空间分布进行分析,并对政府卫生投入分布的公平性进行预测与评价。结果:我国人均政府卫生投入省际间存在明显差异;2007—2017年人均政府卫生投入的全局Moran’s I指数为正值(0.216),具有统计学意义(P=0.001,Z=3.092)。LISA指数研究显示,我国人均政府卫生投入省际间存在局部聚集性;Getis-Ord*Gi进一步研究显示,中南部省份为人均政府卫生投入的热点聚集区,无明显的冷点聚集区。Kriging插值预测分析显示,未来人均政府卫生投入的冷热点将发生明显的变化,热点区集中在中部地区,而冷点区集中在西部和东部地区。结论:我国人均政府卫生投入省际间分布存在局部空间自相关,人均政府卫生投入存在聚集区,仍需进一步优化财政支付手段,因地制宜制定不同的财政帮扶政策。     

基于灰色系统GM(1,1)模型的湖北省卫生人力资源需求预测研究

[目的]对湖北省卫生人力资源需求进行预测,为区域卫生规划提供科学参考和依据。[方法]运用灰色系统GM(1,1)模型,预测湖北省2018-2020年卫生人力资源需求,并与湖北省"十三五"规划发展指标进行比较分析。[结果]运用灰色系统GM(1,1)模型拟合的方程等级均为1级(P>0.95),拟合精度较好。模型拟合结果与2008-2017年的实际值比较卫生人员总数、卫生技术人员数、执业(助理)医师数、注册护士数、管理人员数的平均误差值分别为1.17%、1.57%、1.72%、2.07%、2.22%;预测2020年湖北省每千常住人口卫生总人员数、卫生技术人员数、执业(助理)医师数、注册护士数,管理人员数分别为10.17人、8.22人、2.94人、3.69人、0.37人,医护比为1∶1.45。[结论]灰色系统GM(1,1)模型适用于卫生人力资源需求的预测,2020年湖北省每千人执业(助理)医师数、注册护士数和医护比等预测值均符合规划要求。     

中性粒细胞明胶酶相关脂质运载蛋白、白细胞介素33、肿瘤坏死因子α对非常早产儿支气管肺发育不良的早期预测作用

目的 研究血清中性粒细胞明胶酶相关质运载蛋白(NGAL)、白介素33(IL-33)、肿瘤坏死因子α(TNF-α)对非常早产儿支气管肺发育不良(BPD)的早期预测作用。方法 选取安徽医科大学附属妇幼保健院2018年3月-2019年9月收治的非常早产儿,根据诊断标准分为BPD组和非BPD组。分别检测生后第1、14、28天血清IL-33、TNF-α和NGAL的水平,进行比较分析;并制作受试者工作特征曲线(ROC),判断各个指标早期预测效能。结果 1)共纳入非常早产儿66例,BPD组25例,发生率37.9%,其中轻度15例,中度8例,重度2例;2)不同时间段BPD组血清IL-33、TNF-α和NGAL水平均明显高于非BPD组,差异均有统计学意义(P＜0.05),且三者在出生后14 d内的表达水平逐渐升高(P＜0.05);3)重度BPD组患儿在第14、28天血清IL-33的表达水平明显高于轻、中度BPD患儿,差异有统计学意义(F＝8.220、15.763,P＜0.05); 4)ROC 曲线显示NGAL(第1天)、IL-33(第1天)、TNF-α(第1天)、NGAL(第14天)、IL-33(第14天)、TNF-α(第14天)AUC值分别为 0.768、0.752、0.760、0.875、0.978、0.975。结论 IL-33、NGAL、TNF-α均可早期预测BPD的发生,且在生后第1天NGAL早期预测效能最高,第14天IL-33预测效能最高,IL-33还可能是作为评估BPD严重程度的一项指标。     

Development and Validation of a Nomogram for Predicting the 6-Year Risk of Cognitive Impairment Among Chinese Older Adults

ObjectiveAlthough some people with mild cognitive impairment may not suffer from dementia lifelong, about 5% of them will progress to dementia within 1 year in community settings. However, a general tool for predicting the risk of cognitive impairment was not adequately studied among older adults.DesignProspective cohort study.SettingCommunity-living, older adults from 22 provinces in China.ParticipantsWe included 10,066 older adults aged 65 years and above (mean age, 83.2 ± 11.1 years), with normal cognition at baseline in the 2002–2008 cohort and 9354 older adults (mean age, 83.5 ± 10.8 years) in the 2008–2014 cohort of the Chinese Longitudinal Healthy Longevity Survey.MethodsWe measured cognitive function using the Chinese version of the Mini-Mental State Examination. Demographic, medical, and lifestyle information was used to develop the nomogram via a Lasso selection procedure using a Cox proportional hazards regression model. We validated the nomogram internally with 2000 bootstrap resamples and externally in a later cohort. The predictive accuracy and discriminative ability of the nomogram were measured by area-under-the-curves and calibration curves, respectively.ResultsEight factors were identified with which to construct the nomogram: age, baseline of the Mini-Mental State Examination, activities of daily living and instrumental activities of daily living score, chewing ability, visual function, history of stroke, watching TV or listening to the radio, and growing flowers or raising pets. The area-under-the-curves for internal and external validation were 0.891 and 0.867, respectively, for predicting incident cognitive impairment. The calibration curves showed good consistency between nomogram-based predictions and observations.Conclusions and ImplicationsThe nomogram-based prediction yielded consistent results in 2 separate large cohorts. This feasible prognostic nomogram constructed using readily ascertained information may assist public health practitioners or physicians to provide preventive interventions of cognitive impairment.     

Case study of the prediction of elective surgery durations in a New Zealand teaching hospital

We present an elective surgery redesign project involving several New Zealand hospitals that is primarily data-driven. One of the project objectives is to improve the predictions of surgery durations. We address this task by considering two approaches: (a) linear regression modelling, and (b) improvement of the data quality. For (a) we evaluate the accuracy of predictions using two performance measures. These predictions are compared to the surgeons' estimates that may subsequently be adjusted. We demonstrate using the historical surgical lists that the estimates from our prediction techniques improve the scheduling of elective surgeries by minimising the occurrences of list under- and over-runs. For (b), we discuss how the surgical data motivates a review of the surgery procedure classification which takes into account the design of the electronic booking form. The proposed hierarchical classification streamlines the specification of surgery types and therefore retains the potential for improved predictions.