Optimal Nonbipartite Matching and Its Statistical Applications

The effect of the WHO Safe Childbirth Checklist on essential delivery practices and birth outcomes: Evidence from a pair-wise matched randomized controlled trial in Pakistan

We study the effect of the Safe Childbirth Checklist (SCC) - a tool developed by the WHO to improve the quality of delivery care - on a range of provider- and patient-level outcomes. We conducted a clustered pair-wise matched randomized controlled trial among 166 health providers in two districts of Pakistan. This included primary and secondary health facilities as well as non-facility based rural health workers. We do not find positive effects on health outcomes, but on the adherence to some essential delivery practices, mostly to those conducted during the patient's admission to the delivery ward. We also find increased rates of referrals to higher-level facilities.

Teacher-Student Relationships in Childhood as a Protective Factor against Adolescent Delinquency up to Age 17: A Propensity Score Matching Approach

In this paper we examined the impact of the quality of teacher-student relationships at age 10 on young people's delinquency at ages 13, 15, and 17 utilizing propensity-score matching. The young people were matched based on 105 characteristics, measured at ages 7 to 10. The sample comprised 1483 (49.4% female) adolescents representing around 80 different countries of origin, residing in Zurich, Switzerland. We found that young people who reported a better relationship with their teacher at age 10, engaged in fewer delinquent acts at ages 13, 15, and 17. These findings suggest that when young people perceive a better relationship with their teachers this serves as a protective factor against their engagement in delinquency up to 7 years later.

Bridging preference-based instrumental variable studies and cluster-randomized encouragement experiments: Study design, noncompliance, and average cluster effect ratio

Instrumental variable (IV) methods are widely used in medical research to draw causal conclusions when the treatment and outcome are confounded by unmeasured confounding variables. One important feature of such studies is that the IV is often applied at the cluster level, for example, hospitals' or physicians' preference for a certain treatment where each hospital or physician naturally defines a cluster. This paper proposes to embed such observational IV data into a cluster-randomized encouragement experiment using nonbipartite matching. Potential outcomes and causal assumptions underpinning the design are formalized and examined. Testing procedures for two commonly used estimands, Fisher's sharp null hypothesis and the pooled effect ratio (PER), are extended to the current setting. We then introduce a novel cluster-heterogeneous proportional treatment effect model and the relevant estimand: the average cluster effect ratio. This new estimand is advantageous over the structural parameter in a constant proportional treatment effect model in that it allows treatment heterogeneity, and is advantageous over the PER estimand in that it does not suffer from Simpson's paradox. We develop an asymptotically valid randomization-based testing procedure for this new estimand based on solving a mixed-integer quadratically constrained optimization problem. The proposed design and inferential methods are applied to a study of the effect of using transesophageal echocardiography during coronary artery bypass graft surgery on patients' 30-day mortality rate. R package ivdesign implements the proposed method.

Association of Intraoperative Transesophageal Echocardiography and Clinical Outcomes After Open Cardiac Valve or Proximal Aortic Surgery

IMPORTANCE

Intraoperative transesophageal echocardiography (TEE) is used frequently in cardiac valve and proximal aortic surgical procedures, but there is a lack of evidence associating TEE use with improved clinical outcomes.

OBJECTIVE

To test the association between intraoperative TEE use and clinical outcomes following cardiac valve or proximal aortic surgery.

DESIGN, SETTING, AND PARTICIPANTS

This matched, retrospective cohort study used national registry data from the Society of Thoracic Surgeon (STS) Adult Cardiac Surgery Database (ACSD) to compare clinical outcomes among patients undergoing cardiac valve or proximal aortic surgery with vs without intraoperative TEE. Statistical analyses used optimal matching within propensity score calipers to conduct multiple matched comparisons including within-hospital and within-surgeon matches, a negative control outcome analysis, and sensitivity analyses. STS ACSD data encompasses more than 90% of all hospitals that perform cardiac surgery in the US. The study cohort consisted of all patients aged at least 18 years undergoing open cardiac valve repair or replacement surgery and/or proximal aortic surgery between 2011 and 2019. Statistical analysis was performed from October 2020 to April 2021.

EXPOSURES

The exposure was receipt of intraoperative TEE during the cardiac valve or proximal aortic surgery.

MAIN OUTCOMES AND MEASURES

The primary outcome was death within 30 days of surgery. The secondary outcomes were (1) a composite outcome of stroke or 30-day mortality and (2) a composite outcome of reoperation or 30-day mortality.

RESULTS

Of the 872 936 patients undergoing valve or aortic surgery, 540 229 (61.89%) were male; 63 565 (7.28%) were Black and 742 384 (85.04%) were White; 711 326 (81.5%) received TEE and 161 610 (18.5%) did not receive TEE; the mean (SD) age was 65.61 years (13.17) years. After matching, intraoperative TEE was significantly associated with a lower 30-day mortality rate compared with no TEE: 3.81% vs 5.27% (odds ratio [OR], 0.69 [95% CI, 0.67-0.72]; P < .001), a lower incidence of stroke or 30-day mortality: 5.56% vs 7.01% (OR, 0.77 [95% CI, 0.74-0.79]; P < .001), and a lower incidence of reoperation or 30-day mortality: 7.18% vs 8.87% (OR, 0.78 [95% CI, 0.76-0.80]; P < .001). Results were similar across all matched comparisons (including within-hospital, within-surgeon matched analyses) and were robust to a negative control and sensitivity analyses.

CONCLUSIONS AND RELEVANCE

Among adults undergoing cardiac valve or proximal aortic surgery, intraoperative TEE use was associated with improved clinical outcomes in this cohort study. These findings support routine use of TEE in these procedures.

Fair Teachers, Fair Police? Assessing the Pathways between Perceptions of Teacher and Police Authority in Childhood and Adolescence

Existing research has shown that the quality of the relationship between teacher and child is associated with more positive perceptions of school authorities. There has been relatively less attention to the processes that connect attitudes towards different sources of authority, such as between teachers and police. The current study uses a counterfactual approach to estimate the direct and indirect effects of teacher-child relationships on children's later perceptions of police legitimacy. Using data from a longitudinal study of youth in Zurich, Switzerland, this study applies non-bipartite propensity score matching to identify matched pairs (n = 232 pairs, 55% male) of children with better versus worse relationships with their teacher at age 11 following a teacher change. Matched pairs were then compared on potential mediators (moral norms about deviant behavior and low self-control) at age 13 and perceptions of police legitimacy at age 15. The results demonstrate the importance of the quality of the relationships between students and teachers in shaping young people's interpersonal characteristics as well as perceptions of the world around them. Namely, if young people feel that they are being treated fairly by their teachers, they are more likely to distinguish behaviors that are right or wrong (moral norms) and control their actions (self-control). Moreover, as a result they are also more likely to perceive authorities such as police as legitimate agents that facilitate societal order.

The Association of Hospital Magnet® Status and Pay-for-Performance Penalties

The Centers for Medicare and Medicaid Services' Pay-for-Performance (P4P) programs aim to improve hospital care through financial incentives for care quality and patient outcomes. Magnet^® recognition-a potential pathway for improving nurse work environments-is associated with better patient outcomes and P4P program scores, but whether these indicators of higher quality are substantial enough to avoid penalties and thereby impact hospital reimbursements is unknown. This cross-sectional study used a national sample of 2,860 hospitals to examine the relationship between hospital Magnet^® status and P4P penalties under P4P programs: Hospital Readmission Reduction Program, Hospital-Acquired Conditions (HAC) Reduction Program, Hospital Value-Based Purchasing (VBP) Program. Magnet^® hospitals were matched 1:1 with non-Magnet hospitals accounting for 13 organizational characteristics including hospital size and location. Post-match logistic regression models were used to compute a hospital's odds of penalties. In a national sample of hospitals, 77% of hospitals experienced P4P penalties. Magnet^® hospitals were less likely to be penalized in the VBP program compared to their matched non-Magnet counterparts (40% vs. 48%). Magnet^® status was associated with 30% lower odds of VBP penalties relative to non-Magnet hospitals. Lower P4P program penalties is one benefit associated with achieving Magnet^® status or otherwise maintaining high-quality nurse work environments.

How first-language instruction transfers to majority-language skills

With an increasing number of immigrant children in many countries, questions of how to prepare them for further education become highly salient. Few studies have examined the effect of first-language instruction on children's engagement in school and how that may later transfer into better majority-language outcomes. A randomized controlled trial in Denmark (n = 230) took an asset-based approach to students' cultural and linguistic backgrounds. We found that first-language instruction of majority-language learners (average age 7.1 years) reduced their behavioural problems in school and increased their school satisfaction and their parents' engagement. We saw no immediate effect on their spoken first-language skills, but one year after the intervention ended, their reading skills in the majority language were substantially improved. Half of this improvement could be explained by reduced behavioural problems. The results thereby indicate that an asset-based approach to students' linguistic and cultural backgrounds can help to ensure that first-language instruction transfers into majority-language skills.

The utility of clusters and a Hungarian clustering algorithm

Implicit in the k-means algorithm is a way to assign a value, or utility, to a cluster of points. It works by taking the centroid of the points and the value of the cluster is the sum of distances from the centroid to each point in the cluster. The aim in this paper is to introduce an alternative way to assign a value to a cluster. Motivation is provided. Moreover, whereas the k-means algorithm does not have a natural way to determine k if it is unknown, we can use our method of evaluating a cluster to find good clusters in a sequential manner. The idea uses optimizations over permutations and clusters are set by the cyclic groups; generated by the Hungarian algorithm.

Health care costs of rheumatoid arthritis: A longitudinal population study

Quantifying the contribution of rheumatoid arthritis to the acquisition of subsequent health care costs is an emerging focus of the rheumatologic community and payers of health care. Our objective was to determine the healthcare costs before and after diagnosis of rheumatoid arthritis (RA) from the public payer's perspective. The study design was a longitudinal observational administrative data-based cohort with RA cases from Ontario Canada (n = 104,933) and two control groups, matched 1:1 on year of cohort entry from 2001 to 2016. The first control group was matched on age, sex and calendar year of cohort entry (diagnosis year for those with RA); the second group added medical history to the match before RA diagnosis year. The main exposure was new onset RA. The secondary exposure was calendar year of RA diagnosis to compare attributable costs over the study observation window. Main outcomes were health care costs in 2015 Canadian dollars, overall and by cost category. We used attribution methods to classify costs into those associated with RA, those associated with comorbidities, and age/sex-related underlying costs. Health care costs associated with RA increased up to the year of diagnosis, where they reached $8,591: $4,142 in RA associated costs; $1,242 in RA comorbidity associated costs; and $3,207 in underlying costs. In the eighth-year post diagnosis, the RA costs declined to $2,567 while the RA comorbidity associated costs remained relatively constant at $1,142, and the underlying age/sex related cost increased to $4,426. RA patients had lower costs when diagnosed in later calendar years. Our results suggest a large proportion of disease related health care costs are a result of costs associated with RA comorbidities, which may appear many years before diagnosis.

Assessing the impact of group antenatal care on gestational length in Rwanda: A cluster-randomized trial

BACKGROUND

Research on group antenatal care in low- and middle-income contexts suggests high acceptability and preliminary implementation success.

METHODS

We studied the effect of group antenatal care on gestational age at birth among women in Rwanda, hypothesizing that participation would increase mean gestational length. For this unblinded cluster randomized trial, 36 health centers were pair-matched and randomized; half continued individual antenatal care (control), half implemented group antenatal care (intervention). Women who initiated antenatal care between May 2017 and December 2018 were invited to participate, and included in analyses if they presented before 24 weeks gestation, attended at least two visits, and their birth outcome was obtained. We used a generalized estimating equations model for analysis.

FINDINGS

In total, 4091 women in 18 control clusters and 4752 women in 18 intervention clusters were included in the analysis. On average, women attended three total antenatal care visits. Gestational length was equivalent in the intervention and control groups (39.3 weeks (SD 1.6) and 39.3 weeks (SD 1.5)). There were no significant differences between groups in secondary outcomes except that more women in control sites attended postnatal care visits (40.1% versus 29.7%, p = 0.003) and more women in intervention sites attended at least three total antenatal care visits (80.7% versus 71.7%, p = 0.003). No harms were observed.

INTERPRETATION

Group antenatal care did not result in a difference in gestational length between groups. This may be due to the low intervention dose. We suggest studies of both the effectiveness and costs of higher doses of group antenatal care among women at higher risk of preterm birth. We observed threats to group care due to facility staff shortages; we recommend studies in which antenatal care providers are exclusively allocated to group antenatal care during visits.

TRIAL REGISTRATION

ClinicalTrials.gov NCT03154177.

A machine learning compatible method for ordinal propensity score stratification and matching

Although machine learning techniques that estimate propensity scores for observational studies with multivalued treatments have advanced rapidly in recent years, the development of propensity score adjustment techniques has not kept pace. While machine learning propensity models provide numerous benefits, they do not produce a single variable balancing score that can be used for propensity score stratification and matching. This issue motivates the development of a flexible ordinal propensity scoring methodology that does not require parametric assumptions for the propensity model. The proposed method fits a one-parameter power function to the cumulative distribution function (CDF) of the generalized propensity score (GPS) vector resulting from any machine learning propensity model, and is henceforth called the GPS-CDF method. The estimated parameter from the GPS-CDF method, ã , is a scalar balancing score that can be used to group similar subjects in outcome analyses. Specifically, subjects who received different levels of the treatment are stratified or matched based on their ã value to produce unbiased estimates of the average treatment effect (ATE). Simulation studies presented show remediation of covariate balance, minimal bias in ATEs, and maintain coverage probability. The proposed method is applied to the Mexican-American Tobacco use in Children (MATCh) study to determine whether an ordinal treatment of exposure to smoking imagery in movies causes cigarette experimentation in Mexican-American adolescents.

A mHealth intervention to preserve and promote ideal cardiovascular health in college students: Design and protocol of a cluster randomized controlled trial

BACKGROUND

Cardiovascular disease (CVD) remains the leading cause of death globally. Seven health factors are associated with ideal cardiovascular health: being a non-smoker; not overweight; physically active; having a healthy diet; and normal blood pressure; fasting plasma glucose and cholesterol. Whereas approximately half of U.S. youth have ideal levels in at least 5 of the 7 components of cardiovascular health, this proportion falls to 16% by adulthood.

OBJECTIVE

We will evaluate whether the NUYou cardiovascular mHealth intervention is more effective than an active comparator to promote cardiovascular health during the transition to young adulthood.

METHODS

302 incoming freshmen at a midwest university will be cluster randomized by dormitory into one of two mHealth intervention groups: 1) Cardiovascular Health (CVH), addressing behaviors related to CVD risk; or 2) Whole Health (WH), addressing behaviors unrelated to CVD. Both groups will receive smartphone applications, co-designed with students to help them manage time, interact with other participants via social media, and report health behaviors weekly. The CVH group will also have self-monitoring features to track their risk behaviors. Cardiovascular health will be assessed at the beginning of freshman year and the end of freshman and sophomore years. Linear mixed models will be used to compare groups on a composite of the seven cardiovascular-related health factors.

SIGNIFICANCE

This is the first entirely technology-mediated multiple health behavior change intervention delivered to college students to promote cardiovascular health. Findings will inform the potential for primordial prevention in young adulthood.

TRIAL REGISTRATION NUMBER

clinicaltrials.gov #NCT02496728.

Comorbidities Before and After the Diagnosis of Rheumatoid Arthritis: A Matched Longitudinal Study

OBJECTIVE

To determine the contribution of rheumatoid arthritis (RA) to conditions and medical events. A secondary objective is to quantify this association before and after the introduction of biologic medications.

METHODS

All data were collected as health administrative data in Ontario, Canada. Patients with RA (n = 136 678) matched 1:1 to a pool of possible controls without RA from 1995 to 2016. The study was a retrospective longitudinal observational administrative data-based cohort study with cases (RA) and controls (two non-RA comparator groups). The main exposure was new-onset RA identified by a validated diagnosis algorithm. The secondary exposure was the calendar year, which provided a natural experiment to compare years in which biologics were unavailable (pre-2001) to increasing utilization over time. The main outcomes were counts of 27 Johns Hopkins Expanded Diagnostic Cluster Comorbid Conditions. Outcomes were reported as counts and percentage differences between cases and matched controls.

RESULTS

Patients experienced increases in conditions and medical events up to 5 years before RA disease incidence-4.9 conditions per patient-year compared with 4.6 conditions per patient-year in matched controls. Comorbidities increased to 8.7 conditions per patient-year in the year of RA incidence but were lower in the years after diagnosis-6.9 conditions per patient-year at 5 years postdiagnosis.

CONCLUSION

This study reframes the clinical manifestations of RA with detailed data on the marginal contribution of RA to conditions and medical events. These results show that a large portion of disease burden is due to the indirect effects of RA.

A novel approach for propensity score matching and stratification for multiple treatments: Application to an electronic health record-derived study

Currently, methods for conducting multiple treatment propensity scoring in the presence of high-dimensional covariate spaces that result from "big data" are lacking-the most prominent method relies on inverse probability treatment weighting (IPTW). However, IPTW only utilizes one element of the generalized propensity score (GPS) vector, which can lead to a loss of information and inadequate covariate balance in the presence of multiple treatments. This limitation motivates the development of a novel propensity score method that uses the entire GPS vector to establish a scalar balancing score that, when adjusted for, achieves covariate balance in the presence of potentially high-dimensional covariates. Specifically, the generalized propensity score cumulative distribution function (GPS-CDF) method is introduced. A one-parameter power function fits the CDF of the GPS vector and a resulting scalar balancing score is used for matching and/or stratification. Simulation results show superior performance of the new method compared to IPTW both in achieving covariate balance and estimating average treatment effects in the presence of multiple treatments. The proposed approach is applied to a study derived from electronic medical records to determine the causal relationship between three different vasopressors and mortality in patients with non-traumatic aneurysmal subarachnoid hemorrhage. Results suggest that the GPS-CDF method performs well when applied to large observational studies with multiple treatments that have large covariate spaces.

A conditional test with demonstrated insensitivity to unmeasured bias in matched observational studies

In an observational study matched for observed covariates, an association between treatment received and outcome exhibited may indicate not an effect caused by the treatment, but merely some bias in the allocation of treatments to individuals within matched pairs. The evidence that distinguishes moderate biases from causal effects is unevenly dispersed among possible comparisons in an observational study: some comparisons are insensitive to larger biases than others. Intuitively, larger treatment effects tend to be insensitive to larger unmeasured biases, and perhaps matched pairs can be grouped using covariates, doses or response patterns so that groups of pairs with larger treatment effects may be identified. Even if an investigator has a reasoned conjecture about where to look for insensitive comparisons, that conjecture might prove mistaken, or, when not mistaken, it might be received sceptically by other scientists who doubt the conjecture or judge it to be too convenient in light of its success with the data at hand. In this article a test is proposed that searches for insensitive findings over many comparisons, but controls the probability of falsely rejecting a true null hypothesis of no treatment effect in the presence of a bias of specified magnitude. An example is studied in which the test considers many comparisons and locates an interpretable comparison that is insensitive to larger biases than a conventional comparison based on Wilcoxon’s signed rank statistic applied to all pairs. A simulation examines the power of the proposed test. The method is implemented in the R package dstat, which contains the example and reproduces the analysis.

Using propensity score matching with doses in observational studies: An example from a child physical abuse and sleep quality study

Both physical abuse and poor sleep quality are public health concerns among adolescents, particularly in mainland China, but examining any causal effect of physical abuse on adolescents' sleep quality using a randomized controlled trial is not possible for obvious ethical reasons. Researchers have proposed the use of propensity score matching with doses to minimize overt bias and estimate the effect of multidose treatments or varying degrees of risk exposure in observational studies. In this paper, we demonstrate the propensity score methods with a focus on matching with doses in an examination of the relationship between physical abuse levels (frequency and number of perpetrators) and self-reported sleep quality among adolescents. Secondary analyses were conducted using data from the China Jintan Child Cohort. The sample comprised 707 adolescents (13.16 ± 0.90 years old) who had complete data on physical abuse, sleep, and covariates. Propensity scores were computed from eight covariates and used to carry out pair matching, matching with the frequency of abusive experience, and matching with the number of perpetrators. The standardized differences of covariates suggested an acceptable balance between groups after matching. The results derived from matching sets consistently indicated that adolescents being physically abused by parent(s) have worse sleep quality. Despite its inherent limitations, propensity score matching with doses provides a useful tool for nurse researchers analyzing observational data.

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.

The PRogram In Support of Moms (PRISM): study protocol for a cluster randomized controlled trial of two active interventions addressing perinatal depression in obstetric settings

BACKGROUND

Perinatal depression, the most common pregnancy complication, is associated with negative maternal-offspring outcomes. Despite existence of effective treatments, it is under-recognized and under-treated. Professional organizations recommend universal screening, yet multi-level barriers exist to ensuring effective diagnosis, treatment, and follow-up. Integrating mental health and obstetric care holds significant promise for addressing perinatal depression. The overall study goal is to compare the effectiveness of two active interventions: (1) the Massachusetts Child Psychiatry Access Program (MCPAP) for Moms, a state-wide, population-based program, and (2) the PRogram In Support of Moms (PRISM) which includes MCPAP for Moms plus a proactive, multifaceted, practice-level intervention with intensive implementation support.

METHODS

This study is conducted in two phases: (1) a run-in phase which has been completed and involved practice and patient participant recruitment to demonstrate feasibility for the second phase, and (2) a cluster randomized controlled trial (RCT), which is ongoing, and will compare two active interventions 1:1 with ten Ob/Gyn practices as the unit of randomization. In phase 1, rates of depressive symptoms and other demographic and clinical features among patients were examined to inform practice randomization. Patient participants to be recruited in phase 2 will be followed longitudinally until 13 months postpartum; they will have 3-5 total study visits depending on whether their initial recruitment and interview was at 4-24 or 32-40 weeks gestation, or 1-3 months postpartum. Sampling throughout pregnancy and postpartum will ensure participants with different depressive symptom onset times. Differences in depression symptomatology and treatment participation will be compared between patient participants by intervention arm.

DISCUSSION

This manuscript describes the full two-phase study protocol. The study design is innovative because it combines effectiveness with implementation research designs and integrates critical components of participatory action research. Our approach assesses the feasibility, acceptance, efficacy, and sustainability of integrating a stepped-care approach to perinatal depression care into ambulatory obstetric settings; an approach that is flexible and can be tailored and adapted to fit unique workflows of real-world practices.

TRIAL REGISTRATION

ClinicalTrials.gov Identifier: NCT02760004, registered prospectively on May 3, 2016.

Randomized Controlled Trial of an Intervention to Improve Nurses' Hazardous Drug Handling

OBJECTIVES

To evaluate whether a web-based educational intervention improved personal protective equipment (PPE) use among oncology nurses who handle hazardous drugs.

SAMPLE & SETTING

From 2015 to 2017, the authors partnered with 12 ambulatory oncology settings in the United States to enroll 396 nurses, 257 of whom completed baseline and primary endpoint surveys.

METHODS & VARIABLES

In a cluster randomized controlled trial, 136 nurses in control settings received a one-hour educational module on PPE use with quarterly reminders, and 121 nurses in treatment settings received the control intervention plus tailored messages to address perceived barriers and quarterly data gathered on hazardous drug spills across all study settings. The primary outcome was nurse-reported PPE use.

RESULTS

Control and intervention sites had suboptimal PPE use before and after the intervention. No significant differences were observed in PPE use knowledge or perceived barriers. Participants reported high satisfaction with the study experience.

IMPLICATIONS FOR NURSING

Hazardous drug exposure confers notable health risks to healthcare workers. To improve hazardous drug handling, occupational healthcare workers, health systems, and professional organizations should consider coordinated efforts to implement policy and practice changes.

Practice Style Variation in Medicaid and Non-Medicaid Children With Complex Chronic Conditions Undergoing Surgery

OBJECTIVES

With differential payment between Medicaid and Non-Medicaid services, we asked whether style-of-practice differs between similar Medicaid and Non-Medicaid children with complex chronic conditions (CCCs) undergoing surgery.

SUMMARY OF BACKGROUND DATA

Surgery in children with CCCs accounts for a disproportionately large percentage of resource utilization at major children's hospitals.

METHODS

A matched cohort design, studying 23,582 pairs of children with CCCs undergoing surgery (Medicaid matched to Non-Medicaid within the same hospital) from 2009 to 2013 in 41 Children's Hospitals. Patients were matched on age, sex, principal procedure, CCCs, and other characteristics.

RESULTS

Median cost in Medicaid patients was $21,547 versus $20,527 in Non-Medicaid patients (5.0% higher, P < 0.001). Median paired difference in cost (Medicaid minus Non-Medicaid) was $320 [95% confidence interval (CI): $208, $445], (1.6% higher, P < 0.001). 90th percentile costs were $133,640 versus $127,523, (4.8% higher, P < 0.001). Mean paired difference in length of stay (LOS) was 0.50 days (95% CI: 0.36, 0.65), (P < 0.001). ICU utilization was 2.8% higher (36.7% vs 35.7%, P < 0.001). Finally, in-hospital mortality pooled across all pairs was higher in Medicaid patients (0.38% vs 0.22%, P = 0.002). After adjusting for multiple testing, no individual hospital displayed significant differences in cost between groups, only 1 hospital displayed significant differences in LOS and 1 in ICU utilization.

CONCLUSIONS

Treatment style differences between Medicaid and Non-Medicaid children were small, suggesting little disparity with in-hospital surgical care for patients with CCCs operated on within Children's Hospitals. However, in-hospital mortality, although rare, was slightly higher in Medicaid patients and merits further investigation.

Near-Far Matching in R: The nearfar Package

Estimating the causal treatment effect of an intervention using observational data is difficult due to unmeasured confounders. Many analysts use instrumental variables (IVs) to introduce a randomizing element to observational data analysis, potentially reducing bias created by unobserved confounders. Several persistent problems in the field have served as limitations to IV analyses, particularly the prevalence of "weak" IVs, or instrumental variables that do not effectively randomize individuals to the intervention or control group (leading to biased and unstable treatment effect estimates), as well as IV-based estimates being highly model dependent, requiring parametric adjustment for measured confounders, and often having high mean squared errors in the estimated causal effects. To overcome these problems, the study design method of "near-far matching" has been devised, which "filters" data from a cohort by simultaneously matching individuals within the cohort to be "near" (similar) on measured confounders and "far" (different) on levels of an IV. To facilitate the application of near-far matching to analytical problems, we introduce the R package nearfar and illustrate its application to both a classical example and a simulated dataset. We illustrate how the package can be used to "strengthen" a weak IV by adjusting the "near-ness" and "far-ness" of a match, reduce model dependency, enable nonparametric adjustment for measured confounders, and lower mean squared error in estimated causal effects. We additionally illustrate how to utilize the nearfar package when analyzing either continuous or binary treatments, how to prioritize variables in the match, and how to calculate F statistics of IV strength with or without adjustment for measured confounders.

A Behavior-Based Intervention That Prevents Sexual Assault: the Results of a Matched-Pairs, Cluster-Randomized Study in Nairobi, Kenya

DESIGN

The study's design was a cluster-randomized, matched-pairs, parallel trial of a behavior-based sexual assault prevention intervention in the informal settlements.

METHODS

The participants were primary school girls aged 10-16. Classroom-based interventions for girls and boys were delivered by instructors from the same settlements, at the same time, over six 2-h sessions. The girls' program had components of empowerment, gender relations, and self-defense. The boys' program promotes healthy gender norms. The control arm of the study received a health and hygiene curriculum. The primary outcome was the rate of sexual assault in the prior 12 months at the cluster level (school level). Secondary outcomes included the generalized self-efficacy scale, the distribution of number of times victims were sexually assaulted in the prior period, skills used, disclosure rates, and distribution of perpetrators. Difference-in-differences estimates are reported with bootstrapped confidence intervals.

RESULTS

Fourteen schools with 3147 girls from the intervention group and 14 schools with 2539 girls from the control group were included in the analysis. We estimate a 3.7 % decrease, p = 0.03 and 95 % CI = (0.4, 8.0), in risk of sexual assault in the intervention group due to the intervention (initially 7.3 % at baseline). We estimate an increase in mean generalized self-efficacy score of 0.19 (baseline average 3.1, on a 1-4 scale), p = 0.0004 and 95 % CI = (0.08, 0.39).

INTERPRETATION

This innovative intervention that combined parallel training for young adolescent girls and boys in school settings showed significant reduction in the rate of sexual assault among girls in this population.

Unmeasured Confounding in Observational Studies with Multiple Treatment Arms: Comparing Emergency Department Mortality of Severe Trauma Patients by Trauma Center Level

Comparing emergency department mortality across different levels of trauma care (nontrauma centers, level I and II centers) is important in evaluating regionalized care. Patient population characteristics differ across different levels of trauma care and it is essential to adjust for baseline covariates to make valid comparisons. Propensity score matching has been established as a more robust method to infer causal relationship in observational studies than conventional regression adjustment. We designed and implemented a three group matching methodology. First, we conducted optimal pair matching between the treatment group (nontrauma centers) and the first control group (level I trauma centers); second, we conducted optimal pair matching between the nontrauma centers and the second control group (level II trauma centers); the final step was to link the two sets of matched pairs by the common treatment subjects to form matched triplets. We then implemented a sensitivity analysis with three treatment arms, Lu's imputation based method, to assess the impact due to potential unmeasured confounding. The results showed that if the most severe adult trauma patients treated in nontrauma centers were to be treated in level I or II trauma centers, the odds of emergency department death would be reduced dramatically (odds ratio [OR] = 0.61 and 0.49). There was no difference between being treated in level I or II trauma centers. The sensitivity analysis revealed that the positive association between being treated at level I or II trauma centers and the reduced odds of mortality would remain present even in the presence of strong unmeasured confounding.

Improving digital breast tomosynthesis reading time: A pilot multi-reader, multi-case study using concurrent Computer-Aided Detection (CAD)

PURPOSE

Evaluate concurrent Computer-Aided Detection (CAD) with Digital Breast Tomosynthesis (DBT) to determine impact on radiologist performance and reading time.

MATERIALS AND METHODS

The CAD system detects and extracts suspicious masses, architectural distortions and asymmetries from DBT planes that are blended into corresponding synthetic images to form CAD-enhanced synthetic images. Review of CAD-enhanced images and navigation to corresponding planes to confirm or dismiss potential lesions allows radiologists to more quickly review DBT planes. A retrospective, crossover study with and without CAD was conducted with six radiologists who read an enriched sample of 80 DBT cases including 23 malignant lesions in 21 women. Area Under the Receiver Operating Characteristic (ROC) Curve (AUC) compared the readings with and without CAD to determine the effect of CAD on overall interpretation performance. Sensitivity, specificity, recall rate and reading time were also assessed. Multi-reader, multi-case (MRMC) methods accounting for correlation and requiring correct lesion localization were used to analyze all endpoints. AUCs were based on a 0-100% probability of malignancy (POM) score. Sensitivity and specificity were based on BI-RADS scores, where 3 or higher was positive.

RESULTS

Average AUC across readers without CAD was 0.854 (range: 0.785-0.891, 95% confidence interval (CI): 0.769,0.939) and 0.850 (range: 0.746-0.905, 95% CI: 0.751,0.949) with CAD (95% CI for difference: -0.046,0.039), demonstrating non-inferiority of AUC. Average reduction in reading time with CAD was 23.5% (95% CI: 7.0-37.0% improvement), from an average 48.2 (95% CI: 39.1,59.6) seconds without CAD to 39.1 (95% CI: 26.2,54.5) seconds with CAD. Per-patient sensitivity was the same with and without CAD (0.865; 95% CI for difference: -0.070,0.070), and there was a small 0.022 improvement (95% CI for difference: -0.046,0.089) in per-lesion sensitivity from 0.790 without CAD to 0.812 with CAD. A slight reduction in specificity with a -0.014 difference (95% CI for difference: -0.079,0.050) and a small 0.025 increase (95% CI for difference: -0.036,0.087) in recall rate in non-cancer cases were observed with CAD.

CONCLUSIONS

Concurrent CAD resulted in faster reading time with non-inferiority of radiologist interpretation performance. Radiologist sensitivity, specificity and recall rate were similar with and without CAD.

Outcomes, ICU Use, and Length of Stay in Chronically Ill Black and White Children on Medicaid and Hospitalized for Surgery

BACKGROUND

With increasing Medicaid coverage, it has become especially important to determine whether racial differences exist within the Medicaid system. We asked whether disparities exist in hospital practice and patient outcomes between matched black and white Medicaid children with chronic conditions undergoing surgery.

STUDY DESIGN

We conducted a matched cohort study, matching 6,398 pairs within states on detailed patient characteristics using data from 25 states contributing adequate Medicaid Analytic eXtract claims for admissions of children with chronic conditions undergoing the same surgical procedures between January 1, 2009 and November 30, 2010 for ages 1 to 18 years.

RESULTS

The black patient 30-day revisit rate was 19.3% vs 19.8% in matched white patients (p = 0.61), 30-day readmission rates were 7.0% vs 6.9% (p = 0.43), and 30-day mortality rates were 0.38% vs 0.19% (p = 0.06), respectively. A higher percentage of black patients exceeded their own state's individual median length of stay (44.0% vs 39.6%; p < 0.001) and median ICU length of stay (25.9% vs 23.8%; p < 0.001). Intensive care unit use was higher in black patients (25.9% vs 23.8%; p < 0.001). After adjusting for multiple testing, only 2 states were found to differ significantly by race (New York for length of stay and New Jersey for ICU use).

CONCLUSIONS

We did not observe disparities in 30-day revisits and readmissions for chronically ill children in Medicaid undergoing surgery, and only slight differences in length of stay, ICU length of stay, and use of the ICU, where blacks displayed somewhat elevated rates compared with white controls.

Racial Disparities in Medicaid Asthma Hospitalizations

BACKGROUND AND OBJECTIVES

Black children with asthma comprise one-third of all asthma patients in Medicaid. With increasing Medicaid coverage, it has become especially important to monitor Medicaid for differences in hospital practice and patient outcomes by race.

METHODS

A multivariate matched cohort design, studying 11 079 matched pairs of children in Medicaid (black versus white matched pairs from inside the same state) admitted for asthma between January 1, 2009 and November 30, 2010 in 33 states contributing adequate Medicaid Analytic eXtract claims.

RESULTS

Ten-day revisit rates were 3.8% in black patients versus 4.2% in white patients (P = .12); 30-day revisit and readmission rates were also not significantly different by race (10.5% in black patients versus 10.8% in white patients; P = .49). Length of stay (LOS) was also similar; both groups had a median stay of 2.0 days, with a slightly lower percentage of black patients exceeding their own state's median LOS (30.2% in black patients versus 31.8% in white patients; P = .01). The mean paired difference in LOS was 0.00 days (95% confidence interval, -0.08 to 0.08). However, ICU use was higher in black patients than white patients (22.2% versus 17.5%; P < .001). After adjusting for multiple testing, only 4 states were found to differ significantly, but only in ICU use, where blacks had higher rates of use.

CONCLUSIONS

For closely matched black and white patients, racial disparities concerning asthma admission outcomes and style of practice are small and generally nonsignificant, except for ICU use, where we observed higher rates in black patients.

Adaptive pre-specification in randomized trials with and without pair-matching

In randomized trials, adjustment for measured covariates during the analysis can reduce variance and increase power. To avoid misleading inference, the analysis plan must be pre-specified. However, it is often unclear a priori which baseline covariates (if any) should be adjusted for in the analysis. Consider, for example, the Sustainable East Africa Research in Community Health (SEARCH) trial for HIV prevention and treatment. There are 16 matched pairs of communities and many potential adjustment variables, including region, HIV prevalence, male circumcision coverage, and measures of community-level viral load. In this paper, we propose a rigorous procedure to data-adaptively select the adjustment set, which maximizes the efficiency of the analysis. Specifically, we use cross-validation to select from a pre-specified library the candidate targeted maximum likelihood estimator (TMLE) that minimizes the estimated variance. For further gains in precision, we also propose a collaborative procedure for estimating the known exposure mechanism. Our small sample simulations demonstrate the promise of the methodology to maximize study power, while maintaining nominal confidence interval coverage. We show how our procedure can be tailored to the scientific question (intervention effect for the study sample vs. for the target population) and study design (pair-matched or not). Copyright © 2016 John Wiley & Sons, Ltd.

Targeted estimation and inference for the sample average treatment effect in trials with and without pair-matching

In cluster randomized trials, the study units usually are not a simple random sample from some clearly defined target population. Instead, the target population tends to be hypothetical or ill-defined, and the selection of study units tends to be systematic, driven by logistical and practical considerations. As a result, the population average treatment effect (PATE) may be neither well defined nor easily interpretable. In contrast, the sample average treatment effect (SATE) is the mean difference in the counterfactual outcomes for the study units. The sample parameter is easily interpretable and arguably the most relevant when the study units are not sampled from some specific super-population of interest. Furthermore, in most settings, the sample parameter will be estimated more efficiently than the population parameter. To the best of our knowledge, this is the first paper to propose using targeted maximum likelihood estimation (TMLE) for estimation and inference of the sample effect in trials with and without pair-matching. We study the asymptotic and finite sample properties of the TMLE for the sample effect and provide a conservative variance estimator. Finite sample simulations illustrate the potential gains in precision and power from selecting the sample effect as the target of inference. This work is motivated by the Sustainable East Africa Research in Community Health (SEARCH) study, a pair-matched, community randomized trial to estimate the effect of population-based HIV testing and streamlined ART on the 5-year cumulative HIV incidence (NCT01864603). The proposed methodology will be used in the primary analysis for the SEARCH trial. Copyright © 2016 John Wiley & Sons, Ltd.

Optimized design and analysis of preclinical intervention studies in vivo

Recent reports have called into question the reproducibility, validity and translatability of the preclinical animal studies due to limitations in their experimental design and statistical analysis. To this end, we implemented a matching-based modelling approach for optimal intervention group allocation, randomization and power calculations, which takes full account of the complex animal characteristics at baseline prior to interventions. In prostate cancer xenograft studies, the method effectively normalized the confounding baseline variability, and resulted in animal allocations which were supported by RNA-seq profiling of the individual tumours. The matching information increased the statistical power to detect true treatment effects at smaller sample sizes in two castration-resistant prostate cancer models, thereby leading to saving of both animal lives and research costs. The novel modelling approach and its open-source and web-based software implementations enable the researchers to conduct adequately-powered and fully-blinded preclinical intervention studies, with the aim to accelerate the discovery of new therapeutic interventions.

Superior outcomes of kidney transplantation compared with dialysis: An optimal matched analysis of a national population-based cohort study between 2005 and 2008 in Korea

Data regarding kidney transplantation (KT) and dialysis outcomes are rare in Asian populations. In the present study, we evaluated the clinical outcomes associated with KT using claims data from the Korean national public health insurance program. Among the 35,418 adult patients with incident dialysis treated between 2005 and 2008 in Korea, 1539 underwent KT. An optimal balanced risk set matching was attempted to compare the transplant group with the control group in terms of the overall survival and major adverse cardiac event-free survival. Before matching, the dialysis group was older and had more comorbidities. After matching, there were no differences in age, sex, dialysis modalities, or comorbidities. Patient survival was significantly better in the transplant group than in the matched control group (P < 0.001). In addition, the transplant group showed better major adverse cardiac event-free survival than the dialysis group (P < 0.001; hazard ratio, 0.49; 95% confidence interval, 0.32-0.75). Korean patients with incident dialysis who underwent long-term dialysis had significantly more cardiovascular events and higher all-cause mortality rates than those who underwent KT. Thus, KT should be more actively recommended in Korean populations.