Propensity score estimation using variational method on spatial logistic regression

2021 ◽  
Author(s):  
H. N. Rizka ◽  
Y. Widyaningsih
Keyword(s):  
Logistic Regression ◽  
Propensity Score ◽  
Variational Method

scholarly journals Effect of fluid administration on scene to traffic accident patients by EMS personnel: a propensity score-matched study using population-based ambulance records and nationwide trauma registry in Japan

2021 ◽  
Author(s):  
Yusuke Katayama ◽  
Tetsuhisa Kitamura ◽  
Kosuke Kiyohara ◽  
Kenichiro Ishida ◽  
Tomoya Hirose ◽  
...  
Keyword(s):  
Logistic Regression ◽  
Propensity Score ◽  
Hospital Mortality ◽  
Regression Model ◽  
Traffic Accident ◽  
Logistic Regression Model ◽  
Cardiopulmonary Arrest ◽  
Population Based ◽  
Fluid Administration ◽  
Secondary Outcome

Abstract Purpose The aim of this study was to assess the effect of fluid administration by emergency life-saving technicians (ELST) on the prognosis of traffic accident patients by using a propensity score (PS)-matching method. Methods The study included traffic accident patients registered in the JTDB database from January 2016 to December 2017. The main outcome was hospital mortality, and the secondary outcome was cardiopulmonary arrest on hospital arrival (CPAOA). To reduce potential confounding effects in the comparisons between two groups, we estimated a propensity score (PS) by fitting a logistic regression model that was adjusted for 17 variables before the implementation of fluid administration by ELST at the scene. Results During the study period, 10,908 traffic accident patients were registered in the JTDB database, and we included 3502 patients in this study. Of these patients, 142 were administered fluid by ELST and 3360 were not administered fluid by ELST. After PS matching, 141 patients were selected from each group. In the PS-matched model, fluid administration by ELST at the scene was not associated with discharge to death (crude OR: 0.859 [95% CI, 0.500–1.475]; p = 0.582). However, the fluid group showed statistically better outcome for CPAOA than the no fluid group in the multiple logistic regression model (adjusted OR: 0.231 [95% CI, 0.055–0.967]; p = 0.045). Conclusion In this study, fluid administration to traffic accident patients by ELST was associated not with hospital mortality but with a lower proportion of CPAOA.

scholarly journals Effect of Preoperative Urodynamic Study on Urinary Outcomes after Transobturator Sling

2021 ◽  
Author(s):  
Pedro Rincon Cintra da Cruz ◽  
Aderivaldo Cabral Dias Filho ◽  
Gabriel Nardi Furtado ◽  
Rhaniellen Silva Ferreira ◽  
Ceres Nunes Resende
Keyword(s):  
Logistic Regression ◽  
Urinary Incontinence ◽  
Stress Urinary Incontinence ◽  
Propensity Score ◽  
Urinary Continence ◽  
Urodynamic Study ◽  
Transobturator Sling ◽  
Continence Status ◽  
And Performance

Abstract Objective To evaluate whether performing preoperative urodynamic study influences postoperative urinary symptoms of women with stress urinary incontinence that underwent transobturator sling. Methods Retrospective analysis of patients treated for stress urinary incontinence by transobturator sling from August 2011 to October 2018. Predictor variables included preoperative urodynamic study, age, incontinence severity, body mass index, preoperative storage symptoms and previous anti-urinary incontinence procedure. Outcome variables were postoperative subjective continence status, storage symptoms and complications. Logistic regression after propensity score was employed to compare outcomes between patients who underwent or not pre-operative urodynamic study. Results The present study included 88 patients with an average follow-up of 269 days. Most patients (n = 52; 59.1%) described storage symptoms other than stress urinary incontinence, and 38 patients (43.2%) underwent preoperative urodynamic studies. Logistic regression after propensity score did not reveal an association between urinary continence outcomes and performance of preoperative urodynamic study (odds ratio 0.57; confidence interval [CI]: 0.11–2.49). Among women that did not undergo urodynamic study, there was a subjective improvement in urinary incontinence in 92% of the cases versus 87% in those that underwent urodynamic study (p = 0.461). Furthermore, postoperative storage symptoms were similar between women who did not undergo urodynamic study and those who underwent urodynamic study, 13.2% versus 18.4%, respectively (p = 0.753). Conclusion Preoperative urodynamic study had no impact on urinary incontinence cure outcomes as well as on urinary storage symptoms after the transobturator sling in women with stress urinary incontinence.

Attributable Cost of Clostridium difficile Infection in Pediatric Patients

2017 ◽  
Vol 38 (12) ◽  
pp. 1472-1477 ◽  
Author(s):  
Preeti Mehrotra ◽  
Jisun Jang ◽  
Courtney Gidengil ◽  
Thomas J. Sandora
Keyword(s):  
Logistic Regression ◽  
Clostridium Difficile ◽  
Propensity Score ◽  
Regression Model ◽  
Generalized Linear Model ◽  
Logistic Regression Model ◽  
Propensity Scores ◽  
Healthcare Research ◽  
Design And Methods ◽  
Inpatient Database

OBJECTIVESThe attributable cost of Clostridium difficile infection (CDI) in children is unknown. We sought to determine a national estimate of attributable cost and length of stay (LOS) of CDI occurring during hospitalization in children.DESIGN AND METHODSWe analyzed discharge records of patients between 2 and 18 years of age from the Agency for Healthcare Research and Quality (AHRQ) Kids’ Inpatient Database. We created a logistic regression model to predict CDI during hospitalization based on demographic and clinical characteristics. Predicted probabilities from the logistic regression model were then used as propensity scores to match 1:2 CDI to non-CDI cases. Charges were converted to costs and compared between patients with CDI and propensity-score–matched controls. In a sensitivity analysis, we adjusted for LOS as a confounder by including it in both the propensity score and a generalized linear model predicting cost.RESULTSWe identified 8,527 pediatric hospitalizations (0.53%) with a diagnosis of CDI and 1,597,513 discharges without CDI. In our matched cohorts, the attributable cost of CDI occurring during a hospitalization ranged from $1,917 to $8,317, depending on whether model was adjusted for LOS. When not adjusting for LOS, CDI-associated hospitalizations cost 1.6 times more than non-CDI associated hospitalizations. Attributable LOS of CDI was approximately 4 days.CONCLUSIONSClostridium difficile infection in hospitalized children is associated with an economic burden similar to adult estimates. This finding supports a continued focus on preventing CDI in children as a priority. Pediatric CDI cost analyses should account for LOS as an important confounder of cost.Infect Control Hosp Epidemiol 2017;38:1472–1477

Abstract 67: Effects of Single vs Dual Antiplatelet Therapy on Long Term Stroke and Death After Carotid Endarterectomy

Stroke ◽  
2020 ◽  
Vol 51 (Suppl_1) ◽  
Author(s):  
Nathan Belkin ◽  
Alexander S Fairman ◽  
Benjamin M Jackson ◽  
Paul J Foley ◽  
Scott M Damrauer ◽  
...  
Keyword(s):  
Logistic Regression ◽  
Propensity Score ◽  
Carotid Endarterectomy ◽  
Propensity Score Matching ◽  
Antiplatelet Therapy ◽  
Dual Antiplatelet Therapy ◽  
Long Term Effects ◽  
Kaplan Meier ◽  
One Year

Introduction: Current evidence suggests that dual antiplatelet therapy (DAPT) reduces perioperative stroke, but increases bleeding after carotid endarterectomy (CEA). The long term effects of antiplatelet therapy after CEA have yet to be studied. Methods: A retrospective review of patients undergoing CEA in the national Vascular Quality Initiative database (2003-2018) was performed. Based on antiplatelet regimen at discharge, patients were propensity score matched on aspirin monotherapy vs. DAPT. Multivariable logistic regression and Kaplan-Meier analyses were used to investigate the long term effects of antiplatelet regimen on mortality and stroke/TIA. Results: Of the 72,122 patients undergoing CEA, 64.6% were discharged on aspirin, and 35.4% on DAPT. The DAPT group had higher frequencies of comorbidities (COPD, HTN, CHF, smoking, diabetes) as well as atherosclerotic diseases (PAD, CAD, prior PCI, prior CABG). After propensity score matching, two groups of 8,722 patients with comparable comorbidities were formed. While unmatched Kaplan-Meier analysis showed the DAPT cohort to have higher mortality (p=0.001), this difference dissipated after matching. The resultant matched DAPT cohort did not differ from the aspirin group in one year stroke/TIA (1.7% vs. 1.6%, p=0.70), or mortality (3.1% vs. 3.3%, p=0.55). At 5 years, however, patients treated with DAPT did exhibit a mortality benefit (6.4% vs. 7.3%, p=0.02) with multivariable logistic regression identifying DAPT as an independent predictor of reduced mortality (OR 0.94, 95% CI 0.88-0.99, p=0.04). Conclusions: Patients discharged on DAPT after CEA represent a significantly different cohort than those discharged on aspirin monotherapy. After propensity score matching, there was no difference at one year stroke/TIA or mortality outcomes, but DAPT was found to be protective against long-term mortality. Further study is warranted to investigate this finding.

Effects of Targeted Temperature Management in Patients with Post-Cardiac Arrest Syndrome after an Out-Of-Hospital Cardiac Arrest Caused by Hanging: A Prospective Observational Cohort Study in Japan

2021 ◽  
Author(s):  
Ryuichiro Kakizaki ◽  
Naofumi Bunya ◽  
Shuji Uemura ◽  
Takehiko Kasai ◽  
Keigo Sawamoto ◽  
...  
Keyword(s):  
Logistic Regression ◽  
Cardiac Arrest ◽  
Propensity Score ◽  
Multivariate Logistic Regression Analysis ◽  
Targeted Temperature Management ◽  
Temperature Management ◽  
Matched Cohort ◽  
Neurological Outcomes ◽  
Post Cardiac Arrest Syndrome ◽  
Hospital Cardiac Arrest

Abstract Background: Targeted temperature management (TTM) is recommended for unconscious patients after a cardiac arrest. However, its effectiveness in patients with post-cardiac arrest syndrome (PCAS) by hanging remains unclear. Therefore, this study aimed to investigate the relationship between TTM and favorable neurological outcomes in patients with PCAS by hanging.Methods: This study was a retrospective analysis of the Japanese Association for Acute Medicine out-of-hospital cardiac arrest (OHCA) registry between June 2014 and December 2017 among patients with PCAS admitted to the hospitals after an OHCA caused by hanging. A multivariate logistic regression analysis was performed to estimate the propensity score and to predict whether patients with PCAS by hanging receive TTM. We compared patients with PCAS by hanging who received TTM (TTM group) and those who did not (non-TTM group) using propensity score analysis.Results: A total of 199 patients with PCAS by hanging were enrolled in this study. Among them, 43 were assigned to the TTM group and 156 to the non-TTM group. Logistic regression model adjusted for propensity score revealed that TTM was not associated with favorable neurological outcome at 1-month (adjusted odds ratio [OR]: 1.38, 95% confidence interval [CI]: 0.27–6.96). Moreover, no difference was observed in the propensity score-matched cohort (adjusted OR: 0, 73, 95% CI: 0.10–4.71) and in the inverse probability of treatment weighting-matched cohort (adjusted OR: 0.63, 95% CI: 0.15–2.69).Conclusions: TTM was not associated with increased favorable neurological outcomes at 1-month in patients with PCAS after OHCA by hanging.

scholarly journals Effect of Hypothermia in the Emergency Department on the Outcome of Trauma Patients: A Cross-Sectional Analysis

2018 ◽  
Vol 15 (8) ◽  
pp. 1769 ◽  
Author(s):  
Ting-Min Hsieh ◽  
Pao-Jen Kuo ◽  
Shiun-Yuan Hsu ◽  
Peng-Chen Chien ◽  
Hsiao-Yun Hsieh ◽  
...  
Keyword(s):  
Logistic Regression ◽  
Regression Analysis ◽  
Body Temperature ◽  
Propensity Score ◽  
Logistic Regression Analysis ◽  
Multivariate Logistic Regression Analysis ◽  
Trauma Patients ◽  
Body Temperatures ◽  
Multivariate Logistic Regression ◽  
Mortality Outcome

This study aimed to assess whether hypothermia is an independent predictor of mortality in trauma patients in the condition of defining hypothermia as body temperatures of <36 °C. Data of all hospitalized adult trauma patients recorded in the Trauma Registry System at a level I trauma center between 1 January 2009 and 12 December 2015 were retrospectively reviewed. A multivariate logistic regression analysis was performed in order to identify factors related to mortality. In addition, hypothermia and normothermia were defined as temperatures <36 °C and from 36 °C to 38 °C, respectively. Propensity score-matched study groups of hypothermia and normothermia patients in a 1:1 ratio were grouped for mortality assessment after adjusting for potential confounders such as age, sex, preexisting comorbidities, and injury severity score (ISS). Of 23,705 enrolled patients, a total of 401 hypothermic patients and 13,368 normothermic patients were included in this study. Only 3.0% of patients had hypothermia upon arrival at the emergency department (ED). Compared to normothermic patients, hypothermic patients had a significantly higher rate of abbreviated injury scale (AIS) scores of ≥3 in the head/neck, thorax, and abdomen and higher ISS. The mortality rate in hypothermic patients was significantly higher than that in normothermic patients (13.5% vs. 2.3%, odds ratio (OR): 6.6, 95% confidence interval (CI): 4.86–9.01, p < 0.001). Of the 399 well-balanced propensity score-matched pairs, there was no significant difference in mortality (13.0% vs. 9.3%, OR: 1.5, 95% CI: 0.94–2.29, p = 0.115). However, multivariate logistic regression analysis revealed that patients with low body temperature were significantly associated with the mortality outcome. This study revealed that low body temperature is associated with the mortality outcome in the multivariate logistic regression analysis but not in the propensity score matching (PSM) model that compared patients with hypothermia defined as body temperatures of <36 °C to those who had normothermia. These contradicting observations indicated the limitation of the traditional definition of body temperature for the diagnosis of hypothermia. Prospective randomized control trials are needed to determine the relationship between hypothermia following trauma and the clinical outcome.

Geriatric Patients on Antithrombotic Agents who Fall: Does Trauma Team Activation Improve Outcomes?

2019 ◽  
Vol 85 (7) ◽  
pp. 721-724
Author(s):  
Peter Hwang ◽  
Adrian W. Ong ◽  
Alison Muller ◽  
Amanda Mcnicholas ◽  
Anthony Martin ◽  
...  
Keyword(s):  
Logistic Regression ◽  
Propensity Score ◽  
Geriatric Patients ◽  
Propensity Score Analysis ◽  
Trauma Team ◽  
The Elderly ◽  
Severely Injured ◽  
Severely Injured Patients ◽  
Trauma Team Activation ◽  
Injured Patients

Despite the incorporation of anticoagulant and antiplatelet (ACAP) drugs in our trauma triage criteria, it is unclear whether trauma team activation (TTA) impacts outcomes in geriatric patients on ACAP drugs sustaining falls. We hypothesized that TTA in this cohort was associated with improved outcomes. The hospital electronic database was queried to identify normotensive, awake patients aged ≥65 years on ACAP agent from 2014 to 2018 presenting to the emergency department after falls. The outcome was in-hospital mortality. The association between TTA and mortality was examined using logistic regression analysis and 1:1 propensity score matching analysis. In this study, 4540 patients on ACAP drugs were analyzed, with TTA occurring in 500 (11%). TTA occurred in younger but more severely injured patients with lower Glasgow Coma Score. Logistic regression revealed that TTA was not associated with mortality (odds ratio [95% confidence intervals], 2.04 [0.89–4.25]). The 1:1 propensity score analysis revealed similar mortality for the matched groups (non-TTA, 1.6% vs TTA, 2.2%, P = 0.64). In the elderly patients on ACAP agents, the current triage criteria resulted in the appropriate use of TTA for more severely injured patients. The lack of outcome benefit suggests that ACAP drug use as a criterion for TTA should be re-evaluated.

Trendelenburg Positioning in Large Vessel Ischaemic Stroke: A Pre-Post Observational Study Using Propensity Score Matching

2018 ◽  
Vol 46 (1-2) ◽  
pp. 24-32 ◽  
Author(s):  
Alexandre Gauthier ◽  
Patrick Gérardin ◽  
Pauline Renou ◽  
Sharmila Sagnier ◽  
Sabrina Debruxelles ◽  
...  
Keyword(s):  
Logistic Regression ◽  
Propensity Score ◽  
Ischaemic Stroke ◽  
Multiple Logistic Regression Analysis ◽  
Primary Outcome Measure ◽  
Large Vessel ◽  
Large Artery ◽  
Multiple Logistic Regression ◽  
Nihss Score ◽  
Arterial Blood

Background: Along with pharmacological and mechanical recanalization, improving cerebral perfusion through the recruitment of collateral vessels during the acute phase of ischaemic stroke (IS) is a clinical challenge. Our objective was to assess the effectiveness and safety of Trendelenburg positioning (TP), a procedure intended to increase cerebral blood flow, on the outcome of IS. Methods: Two cohorts of patients with an acute supratentorial IS related to a large artery occlusion were compared. In the first cohort (n = 119), we used standard positioning (0 to +30°); in the second cohort (n = 90), we used TP (0 to –15°). The primary outcome measure was the improvement of National Institutes of Health Stroke Scale (NIHSS) score between admission and day 2. Factors associated with an improvement ≥4 points of NIHSS score were assessed using multiple logistic regression and propensity score (PS) matching analyses. Results: TP was significantly associated with a greater improvement of NIHSS score within 48 h following stroke onset (4.0 ± 5.7 vs. 1.8 ± 5.9, p = 0.011) but also at discharge (p = 0.005). Multiple logistic regression analysis suggested that TP was an independent predictor of early neurological improvement (adjusted OR 1.81, 95% CI 1.00–3.27) in a model controlling recanalization and haemoglobin level. In addition, PS matching analysis confirmed the possible effectiveness of TP (unadjusted OR 1.99, 95% CI 1.04–3.82), especially in male subjects. The effect of TP was more pronounced in patients with admission mean arterial blood pressure ≥100 mm Hg, those exhibiting a good collateral vessel network on admission CT-angiography or experiencing an effective recanalization. Furthermore, TP was not associated with life-threatening complications. Conclusion: TP could be an effective and safe strategy in patients with large IS resulting from the proximal occlusion of a large vessel.

scholarly journals Relationship between formulaic breast volume and risk of breast cancer based on linear measurements

BMC Cancer ◽  
2020 ◽  
Vol 20 (1) ◽  
Author(s):  
Xiaoxia Li ◽  
Chunlan Zhou ◽  
Yanni Wu ◽  
Xiaohong Chen
Keyword(s):  
Breast Cancer ◽  
Logistic Regression ◽  
Propensity Score ◽  
Propensity Score Matching ◽  
Conditional Logistic Regression ◽  
Control Group ◽  
Case Group ◽  
Breast Volume ◽  
Linear Measurements ◽  
Significant Difference

Abstract Background Whether breast volume is a risk factor for breast cancer is controversial. This study aimed to evaluate whether a significant association between breast volume and risk of breast cancer, based on linear measurements, was present by applying propensity score matching (PSM). Methods The study was designed as a hospital-based case-control study. Between March 2018 and May 2019, 208 cases and 340 controls were retrospectively reviewed. Information on menarche, smoking, feeding mode, oral contraceptives, reproductive history and family history was obtained through a structured questionnaire. Breast volume was calculated using a formula based on linear measurements of breast parameters. Cox regression and PSM were used to estimate odds ratios and 95% confidence intervals for breast cancer using risk factors adjusted for potential confounders. Results There was a significant difference in breast volume between the two groups before propensity score matching (P = 0.014). Binary logistic regression showed that the risk of breast cancer was slightly higher in the case group with larger breast volumes than in the control group(P = 0.009, OR = 1.002, 95%CI:1.000 ~ 1.003). However, there was no significant statistical difference between the two groups using an independent sample Mann-Whitney U test (P = 0.438) or conditional logistic regression (P = 0.446). Conclusions After PSM for potential confounding factors, there is no significant difference in breast volume estimated by BREAST-V formula between the case group and the control group. The risk of breast cancer may not be related to breast volume in Chinese women.

scholarly journals Estimation of propensity score using spatial logistic regression

2019 ◽  
Vol 546 ◽  
pp. 052048
Author(s):  
Hilwin Nisa’ ◽  
Maria B T Mitakda ◽  
Suci Astutik
Keyword(s):  
Logistic Regression ◽  
Propensity Score
Sign in / Sign up

Export Citation Format

Share Document