Testing causal effects in observational survival data using propensity score matching design

Sensitivity Analysis for Observational Studies with Recurrent Events

We conduct an observational study of the effect of sickle cell trait Haemoglobin AS (HbAS) on the hazard rate of malaria fevers in children. Assuming no unmeasured confounding, there is strong evidence that HbAS reduces the rate of malarial fevers. Since this is an observational study, however, the no unmeasured confounding assumption is strong. A sensitivity analysis considers how robust a conclusion is to a potential unmeasured confounder. We propose a new sensitivity analysis method for recurrent event data and apply it to the malaria study. We find that for the causal conclusion that HbAS is protective against malarial fevers to be overturned, the hypothesized unmeasured confounder must be as influential as all but one of the measured confounders.

Unmeasured confounding in nonrandomized studies: quantitative bias analysis in health technology assessment

Evidence generated from nonrandomized studies (NRS) is increasingly submitted to health technology assessment (HTA) agencies. Unmeasured confounding is a primary concern with this type of evidence, as it may result in biased treatment effect estimates, which has led to much criticism of NRS by HTA agencies. Quantitative bias analyses are a group of methods that have been developed in the epidemiological literature to quantify the impact of unmeasured confounding and adjust effect estimates from NRS. Key considerations for application in HTA proposed in this article reflect the need to balance methodological complexity with ease of application and interpretation, and the need to ensure the methods fit within the existing frameworks used to assess nonrandomized evidence by HTA bodies.

Statistical methods of indirect comparison with real-world data for survival endpoint under non-proportional hazards

In clinical studies that utilize real-world data, time-to-event outcomes are often germane to scientific questions of interest. Two main obstacles are the presence of non-proportional hazards and confounding bias. Existing methods that could adjust for NPH or confounding bias, but no previous work delineated the complexity of simultaneous adjustments for both. In this paper, a propensity score stratified MaxCombo and weighted Cox model is proposed. This model can adjust for confounding bias and NPH and can be pre-specified when NPH pattern is unknown in advance. The method has robust performance as demonstrated in simulation studies and in a case study.

Stratified Restricted Mean Survival Time Model for Marginal Causal Effect in Observational Survival Data

Time to event outcomes is commonly encountered in epidemiologic research. Multiple papers have discussed the inadequacy of using the hazard ratio as a causal effect measure due to its noncollapsibility and the time-varying nature. In this paper, we further clarified that the hazard ratio might be used as a conditional causal effect measure, but it is generally not a valid marginal effect measure, even under randomized design. We proposed to use the restricted mean survival time (RMST) difference as a causal effect measure, since it essentially measures the mean difference over a specified time horizon and has a simple interpretation as the area under survival curves. For observational studies, propensity score adjustment can be implemented with RMST estimation to remove observed confounding bias. We proposed a propensity score stratified RMST estimation strategy, which performs well in our simulation evaluation and is relatively easy to implement for epidemiologists in practice. Our stratified RMST estimation includes two different versions of implementation, depending on whether researchers want to involve regression modeling adjustment, which provides a powerful tool to examine the marginal causal effect with observational survival data.

Development and Validation of a Nomogram for Predicting Albumin Transfusion After Spinal Tuberculosis Surgery: Based on Propensity Score Matching Analysis

BACKGROUND

There have been few literature reports on the use of perioperative parameters to predict the risk of albumin transfusion after spinal tuberculosis surgery based on the application of nomogram and propensity score matching (PSM) analysis.

OBJECTIVE

The purpose was to predict the risk of albumin transfusion after spinal tuberculosis surgery based on a combination of PSM and nomogram.

METHODS

The clinical data of the patients were collected in our hospital, including preoperative clinical data, preoperative laboratory tests, and postoperative clinical data. All data were divided into 2 groups, including the albumin transfusion group and the non-albumin transfusion group. The PSM analysis was used to adjust the baseline data of the 2 groups. The nomogram was further constructed. The practicability and predictive ability of the model were evaluated.

RESULTS

A total of 494 cases were collected in this article; 102 pairs by PSM analysis were used to construct the nomogram. There were statistical differences in surgical approach, aspartate aminotransferase/alanine aminotransferase levels, drainage, and kyphosis by logistic analysis, and these parameters were included in the construction of the nomogram. The C-index of the prediction model was 0.734. The area under the curve was 0.73 and the net benefit was between 0.13 and 0.99. The calculated C-index was 0.71 by the internal verification method.

CONCLUSIONS

The PSM analysis had a good matching effect and the nomogram had a good predictive ability. Surgical approach, aspartate aminotransferase/alanine aminotransferase levels, drainage, and kyphosis might be predictors of albumin transfusion after spinal tuberculosis surgery.

Prognostic factors of patients with initially diagnosed T1a glottic cancer: Novel nomograms and a propensity-score matched cohort analysis

The option of T1a glottic cancer treatments remarkably varied in different countries. This study aimed to construct predictive models to predict overall survival (OS) and cancer-specific survival (CSS) of patients with initially diagnosed T1a glottic cancer. And we used propensity score matching (PSM) to reassess the effect of treatments.Data of patients with initially diagnosed T1a glottic cancer were extracted from the Surveillance, Epidemiology, and End Results database. Patients with complete information were randomly divided into the training and the validation cohorts (7:3). Cox regression was conducted to screen significant predictors of the OS and the CSS. PSM was performed to mimic randomized controlled trials. Survival analyses were performed by Kaplan-Meier survival methods, and log-rank tests were utilized.A total of 2342 patients met the inclusion criteria. Survival analyses showed that patients who underwent primary site surgery would have better OS and CSS. Univariate analyses and multivariate analyses proved that stage, N stage, primary site surgery, and chemotherapy significantly affected both the OS and the CSS. Predictive nomograms were established to predict patients' prognosis. Finally, the OS and the CSS for patients who underwent primary site surgery alone were significantly longer than those who underwent radiation alone before and after PSM.We constructed nomograms predicting the OS and the CSS of patients with initially diagnosed T1a glottic cancer. Compared to our previous studies, this study indicated that primary site surgery may be superior to radiation and chemotherapy. At present, chemotherapy should be not recommended for T1a glottic cancer patients.

Propensity score matching for treatment delay effects with observational survival data

In observational studies with a survival outcome, treatment initiation may be time dependent, which is likely to be affected by both time-invariant and time-varying covariates. In situations where the treatment is necessary for the study population, all or most subjects may be exposed to the treatment sooner or later. In this scenario, the causal effect of interest is the delay in treatment reception. A simple comparison of those receiving treatment early vs. those receiving treatment late might not be appropriate, as the timing of the treatment reception is not randomized. Extending Lu's matching design with time-varying covariates, we propose a propensity score matching strategy to estimate the treatment delay effect. The goal is to balance the covariate distribution between on-time treatment and delayed treatment groups at each time point using risk set matching. Our simulation study shows that, in the presence of treatment delay effects, the matching-based analyses clearly outperform the conventional regression analysis using the naive Cox proportional hazards model. We apply this method to study the treatment delay effect of 17 alpha-hydroxyprogesterone caproate (17P) for patients with recurrent preterm birth.

Systematic assessment of complications after robotic-assisted total versus distal gastrectomy for advanced gastric cancer: A retrospective propensity score-matched study using Clavien-Dindo classification

BACKGROUND

Despite increasing evidence demonstrated robot-assisted distal gastrectomy (RADG) is safe and feasible for the treatment of advanced gastric cancer (AGC), robot-assisted total gastrectomy (RATG) remains a challenging procedure due to its technical difficulties and possible postoperative complications (POCs). This study aimed to systematically evaluate POCs following RATG.

METHODS

Between January 2017 and January 2019, 319 AGC patients with pathological stage T2-4aN0-3M0 who underwent RADG or RATG were enrolled. POCs were stratified using the Clavien-Dindo classification. One-to-one propensity score matching was performed to reduce confounding differences.

RESULTS

After matching, 266 patients met the criteria for further analysis. Ultimately, 64 patients (24.1%) who developed POCs had 126 clinical manifestation events. Overall the POCs rate was significantly greater after RATG in comparison with RADG (29.3% vs. 18.8%; P = 0.045), and more major POCs (Clavien-Dindo grade ≥ IIIa) were observed in the RATG group (14.3% vs. 5.3%; P = 0.013). The POCs were then classified into local and systemic POCs. The rates of local POCs (35.3% vs. 19.5%; P = 0.004) and systemic POCs (24.8% vs. 15.0%; P = 0.046) were significantly higher in the RATG group than the RADG group. Subgroup analysis showed that the anastomotic leakage rate was higher after RATG (5.3% vs. 0.8%; P = 0.031), whereas the remaining POCs were similar between the two groups. Patients with higher POCs significantly had longer postoperative length of stay (R = 0.895, P = 0.003). Multivariate analysis confirmed age, extent of resection, and TNM stage were risk factors for all POCs.

CONCLUSIONS

These findings demonstrated that RATG is technically feasible and safe for treatment of AGC with acceptable morbidity and mortality rates. The POCs rate of RATG was higher than RADG, especially for anastomotic leakage. More effective anastomotic techniques are needed in RATG to prevent leakage.