Machine Learning Algorithms to Predict Mortality and Allocate Palliative Care for Older Patients With Hip Fracture

ObjectivesTo evaluate a machine learning model designed to predict mortality for Medicare beneficiaries aged >65 years treated for hip fracture in Inpatient Rehabilitation Facilities (IRFs).DesignRetrospective design/cohort analysis of Centers for Medicare & Medicaid Services Inpatient Rehabilitation Facility–Patient Assessment Instrument data.Setting and ParticipantsA total of 17,140 persons admitted to Medicare-certified IRFs in 2015 following hospitalization for hip fracture.MeasuresPatient characteristics include sociodemographic (age, gender, race, and social support) and clinical factors (functional status at admission, chronic conditions) and IRF length of stay. Outcomes were 30-day and 1-year all-cause mortality. We trained and evaluated 2 classification models, logistic regression and a multilayer perceptron (MLP), to predict the probability of 30-day and 1-year mortality and evaluated the calibration, discrimination, and precision of the models.ResultsFor 30-day mortality, MLP performed well [acc = 0.74, area under the receiver operating characteristic curve (AUROC) = 0.76, avg prec = 0.10, slope = 1.14] as did logistic regression (acc = 0.78, AUROC = 0.76, avg prec = 0.09, slope = 1.20). For 1-year mortality, the performances were similar for both MLP (acc = 0.68, AUROC = 0.75, avg prec = 0.32, slope = 0.96) and logistic regression (acc = 0.68, AUROC = 0.75, avg prec = 0.32, slope = 0.95).Conclusion and ImplicationsA scoring system based on logistic regression may be more feasible to run in current electronic medical records. But MLP models may reduce cognitive burden and increase ability to calibrate to local data, yielding clinical specificity in mortality prediction so that palliative care resources may be allocated more effectively.     

A Multidisciplinary,Community-Based Program to Reduce Unplanned Hospital Admissions

ObjectivesTo evaluate the effect of Hospital Admission Risk Program (HARP) on unplanned hospitalization, bed days, and mortality of enrolled individuals and to evaluate the cost-effectiveness of HARP.DesignA retrospective longitudinal analysis of hospital administrative data.InterventionIndividuals at risk of hospitalization were provided with multidisciplinary, community-based care support managed by care coordinators including integrated care planning, education, monitoring, service linkages, and general practitioner liaison over 6-9 months.Setting and ParticipantsIndividuals who were enrolled into 1 of 8 HARP chronic disease management programs between July 1, 2017, and June 30, 2018, at the Royal Melbourne Hospital, Australia.MethodsHospital admissions between 18 months before and 18 months after HARP enrollment were analyzed. Total hospital costs were compared between 18 months before and 12 months after HARP enrollment.ResultsA total of 1553 individuals with a median age of 71 years (interquartile range 60-81), 63.4% males, were admitted to HARP. Both unplanned hospitalizations and bed days were reduced during the HARP intervention compared to within 3 months before enrollment in each of the HARP management programs. After the HARP intervention, cardiac coach, cardiac heart failure, chronic respiratory, diabetes comanagement, and medication management programs had higher hospitalizations and bed days than individuals’ baseline of at least 3 months before HARP enrollment. Individuals in cardiac heart failure and chronic respiratory management programs had a higher mortality rate than other HARP chronic disease management programs. Individuals in cardiac coach, diabetes comanagement, and medication management programs had lower hospital costs during the HARP intervention compared to within 3 months before HARP enrollment.Conclusions and ImplicationsHARP reduced unplanned hospitalization and bed days but did not return individuals’ hospital use to baseline before the intervention. The variations in mortality between HARP chronic disease management programs implies that condition-specific goals between programs is preferable.     

北京市胎儿及婴儿先天性脑积水发生情况及婴儿期转归

目的通过对北京市5年先天性脑积水(CH)监测资料分析,了解北京市胎儿及婴儿的CH发生率、诊断及转归。 方法选择2015年1月至2019年12月,北京市出生缺陷监测系统内监测对象(胎龄为13周至生后1岁)中,407例CH患儿(胎儿或婴儿)为研究对象。对其出生缺陷诊断资料进行分析。采用χ²检验,对孤立性与非孤立性CH活产儿婴儿期存活率进行统计学比较。本研究遵循的程序符合2013年新修订的《世界医学协会赫尔辛基宣言》要求。 结果本研究时间(5年)内,北京市胎儿及1岁内婴儿的CH发生率为3.60×10^-4(407/1 129 861)。这407例CH患儿中,82例(20.15%)合并颅外畸形,20例(4.91%)合并染色体异常;CH胎儿的产前诊断率为92.38%(376/407),超声检出CH胎儿时,其胎龄为24周(23~35周),其中胎龄≥28周者占26.06%(98/376)。376例产前被诊断的CH胎儿中,44例采取产前胎儿超声联合MRI检查,而且通过胎儿MRI检查对4例胎儿的颅内畸形具体类型进行了补充诊断。本研究未发现CH患儿的孕母合并宫内感染;103例CH活产儿中,73例孤立性CH患儿的婴儿期(1岁内)存活率为72.6%(53/73),高于30例非孤立性CH患儿的婴儿期存活率(60.0%,18/30),二者比较,差异无统计学意义(P>0.05)。 结论北京市在预防出生缺陷发生的三级防控体系中,对CH胎儿与婴儿的一级、二级防控已取得效果。对孕妇全孕期多次动态胎儿超声检查,必要时联合胎儿MRI检查,对非孤立性CH胎儿同时采取细胞遗传学和分子遗传学检测,可进一步提高CH患儿的防控效果。     

2015年四川省胃癌和食管癌发病及死亡分析

目的分析2015年四川省上消化道恶性肿瘤(胃癌和食管癌)发病、死亡和潜在减寿情况。方法收集四川省24个肿瘤登记处上报的2015年恶性肿瘤发病、死亡及人口资料。提取ICD-10编码C15-C16选择食管癌、胃癌的发病和死亡数据,用SAS 9.3软件分别计算性别、年龄别发病和死亡的粗率、标化率、构成比、累积率(0~74岁)、潜在减寿年数(potential years of life lost,PYLL)、潜在减寿率(potential years of life lost rate,PYLLR)和平均减寿年(average years of life lost,AYLL)。标准人口采用2000年全国普查人口年龄构成和Segi’s世界人口年龄构成。结果2015年四川省肿瘤登记地区食管癌和胃癌发病率分别为29.29/10万和28.60/10万,分别居发病第3位和第4位;胃癌和食管癌死亡率分别为23.90/10万和22.20/10万,分别居死亡第3位和第4位;根据上消化道恶性肿瘤发病率和死亡率的年龄性别分布,男女性45岁后发病率和50岁后死亡率均显著升高;无论城乡,男性食管癌和胃癌各项发病和死亡指标均高于女性。农村地区人群食管癌和胃癌疾病负担高于城市。食管癌潜在减寿年数为23399人年,平均减寿年数为15.41年,减寿率为1.92‰;胃癌潜在减寿年数为25390人年,平均减寿年数为16.74年,减寿率为2.09‰。结论四川省食管癌和胃癌发病与死亡水平相对较高,男性为食管癌和胃癌的高发人群,45岁以上的中老人群是上消化道恶性肿瘤高风险人群,农村地区人群的上消化道肿瘤疾病负担高于城市。     

High Case-Fatality Rate for Human Anthrax,Northern Ghana, 2005–2016

The human cutaneous anthrax case-fatality rate is ≈1% when treated, 5%–20% when untreated. We report high case-fatality rates (median 35.0%; 95% CI 21.1%–66.7%) during 2005–2016 linked to livestock handling in northern Ghana, where veterinary resources are limited. Livestock vaccination and access to human treatment should be evaluated.     

Can the Multidimensional Prognostic Index Improve the Identification of Older Hospitalized Patients with COVID-19 Likely to Benefit from Mechanical Ventilation? An Observational,Prospective, Multicenter Study

ObjectiveData on prognostic tools for indicating mechanical ventilation in older people with COVID-19 are still limited. The aim of this research was to evaluate if the Multidimensional Prognostic Index (MPI), based on the Comprehensive Geriatric Assessment (CGA), may help physicians in identifying older hospitalized patients affected by COVID-19 who might benefit from mechanical ventilation.DesignLongitudinal, multicenter study.Settings and Participants502 older people hospitalized for COVID-19 in 10 European hospitals.MethodsMPI was calculated using 8 different domains typical of the CGA. A propensity score, Cox's regression analysis was used for assessing the impact of mechanical ventilation on rehospitalization/mortality for 90 days' follow-up, stratified by MPI = 0.50. The accuracy of MPI in predicting negative outcomes (ie, rehospitalization/mortality) was assessed using the area under the curve (AUC), and the discrimination with several indexes like the Net Reclassification Improvement (NRI) and the Integrated Discrimination Improvement (IDI).ResultsAmong 502 older people hospitalized for COVID-19 (mean age: 80 years), 152 were treated with mechanical ventilation. In the propensity score analysis, during the 90-day follow-up period, there were 44 rehospitalizations and 95 deaths. Mechanical ventilation in patients with MPI values ≥ 0.50, indicating frailer participants, was associated with a higher risk of rehospitalization/mortality (hazard ratio 1.56, 95% CI 1.09-2.23), whereas in participants with MPI values < 0.50 this association was not significant. The accuracy of the model including age, sex, respiratory parameters, and MPI was good (AUC = 0.783) as confirmed by an NRI of 0.2756 (P < .001) and an IDI of 0.1858 (P < .001), suggesting a good discrimination of the model in predicting negative outcomes.Conclusions and ImplicationsMPI could be useful for better individualizing older people hospitalized by COVID-19 who could benefit from mechanical ventilation.     

河南居民常见癌症死亡率及其流行趋势分析(1974～1999)

目的 :研究河南人口常见恶性肿瘤死亡率及其流行特征。方法 :收集河南省 1974～ 1976年全人口死亡回顾调查资料和 1983～ 1999年 1/ 10人口 ( 15市县 )居民死亡登记报告资料 ,按《中国恶性肿瘤登记报告试行规范》的统计方法 ,分析常见恶性肿瘤死亡率及动态特征并对未来趋势进行预测。结果 :近 2 6年来 ,河南居民总癌死亡率变化不大 ,而食管癌则呈下降趋势 ,胃癌相对稳定 ,肝癌、肺癌上升明显 ,子宫颈癌下降很快。结论 :建立以人群为基础的癌症登记报告系统 ,对于了解和掌握恶性肿瘤流行动态及其进行肿瘤控制是非常必要的     

监护病室院内获得性败血症—常见致病菌株、危险因素及预后分析

目的：确定监护病室院内获得性败血症的发病率,致病菌的种类,对危重病患者预后的影响及诱发败血症的危险因素。方法：用单因素和多因素统计学方法确定败血症对危重患者预后的影响及诱发败血症的危险因素。结果：败血症在危重患者中有较高的发生率（8．07％）且致病菌以革兰氏阳性球菌为主。病死率亦较高（80．77％）,单因素检验[OR=4.32,95%可信区间（CI）1．58－11．72]及多因素logistic回归分析（OR＝4．97,1.21-20.37)均判定细菌性败血症显著影响危重病患者的病死率,此外,分析亦证实：监护病室血源性感染的发生与患者免疫功能低下,留置大静脉导管,气管切开,低白蛋白血症,感染发生前用过激素等因素密切相关。结论：败血症是监护病室常见并发症且对疾病预后有不利影响,应重视并针对其危险因素加以预防。     

我国近40年来死因构成的变迁及预防对策的思考

目的　为卫生主管部门的科学决策、确定疾病的防制重点、合理分配卫生资源提供可靠依据 ,并提出相应的预防对策。方法　通过收集、综合、整理我国部分城市及县的有关资料 ,应用Office 2 0 0 0进行图表处理 ,并作趋势卡方检验 ,对我国近 4 0年来死因构成比及主要死因死亡率的变化进行分析。结果　解放以来 ,我国人口死亡率显著下降 ;近 4 0年来城乡死因构成比发生了明显变化 ,恶性肿瘤、脑血管病、心脏病、呼吸系统疾病、损伤和中毒已成为前 5位死因 ,占总死亡的 80 %左右 ,城市以恶性肿瘤为首位 ,农村以呼吸系统疾病为首位 ;内分泌、营养、代谢及免疫疾病、精神病、神经病进入城市前 10位死因 ,新生儿病、传染病、肺结核仍处于农村前 10位死因之列。结论　我国医疗卫生事业取得了巨大成就 ,特别是在传染病、肺结核防治方面 ;恶性肿瘤、慢性病、损伤和中毒应作为今后我国疾病防治的重点之一 ;在农村 ,应进一步加强妇幼保健 ,降低新生儿病死亡率