A standardized framework for risk-based assessment of treatment effect heterogeneity in observational healthcare databases

Characterizing Treatment Effect Heterogeneity Using Real-World Data

Characterizing heterogeneity of treatment effects (HTE) is a fundamental goal of pharmacoepidemiology, addressing why medications work differently across patient populations. This paper reviews state-of-the-art methods for studying HTE using real-world data (RWD), which offer larger study sizes and more diverse patient populations compared to randomized clinical trials. The paper first defines HTE and discusses its measurement. It then examines three leading approaches to studying HTE: subgroup analysis, disease risk score (DRS) methods, and effect modeling methods. Subgroup analyses offer simplicity, transparency, and provide insights into drug mechanisms. However, they face difficulties in resolving which subgroup or combination of characteristics should be the basis for clinical decision making when multiple effect modifiers are present. DRS methods address some of these limitations by incorporating multiple patient characteristics into a summary score of outcome risk but may obscure insights into mechanisms. Effect modeling methods directly predict individual treatment effects, offering potential for precise HTE characterization, but are prone to model misspecification and may not provide mechanistic insights. The methods each have tradeoffs. Subgroup analysis is straightforward but can lead to spurious associations and does not account for multiple characteristics at once. DRS methods are relatively simple to implement and clinically useful, but may not completely describe HTE or provide mechanistic insight. Effect modeling approaches have great potential for characterizing HTE but are still being developed. Understanding HTE is essential for personalizing treatment strategies to improve patient outcomes. Researchers must weigh the strengths and limitations of each approach when using RWD to study HTE.

Systematic construction of composite radiation therapy dataset using automated data pipeline for prognosis prediction

BACKGROUND

Existing research on medical data has primarily focused on single time-points or single-modality data. This study aims to collect all data generated during radiotherapy comprehensively to improve the treatment and prognosis of patients with malignant tumors.

METHODS

The data collected from each medical institution were transmitted to the lead organization, where they underwent a file integrity check and were processed using a data pipeline. The key metadata of the collected data were compiled into a database, which were examined by data analysts to identify outliers based on theoretical and institution-specific characteristics. Appropriate filters were applied and the filtered data were subsequently reviewed by artificial intelligence (AI)-based models and researchers for radiotherapy organ slides. Finally, they were annotated by specialists.

RESULTS

The final dataset included 30,136 three-dimensional cone-beam computed tomography scans and 5,019 tabular data entries collected from 5,019 patients. It comprised 2,043,162 Digital Imaging and Communications in Medicine-format files with a total file size of 832 GB. Quality verification of the data using AI models revealed high classification performance for most organs, with relatively poor performance for the rectum. Overall, the macro AUROC value was 0.947.

CONCLUSIONS

This study implemented an automated data pipeline and AI-based verification to enhance the quality of collected radiotherapy data. The constructed dataset can be utilized for various types of future research and is expected to contribute to the improvement of radiotherapy efficiency.

Step-by-step causal analysis of EHRs to ground decision-making

Causal inference enables machine learning methods to estimate treatment effects of medical interventions from electronic health records (EHRs). The prevalence of such observational data and the difficulty for randomized controlled trials (RCT) to cover all population/treatment relationships make these methods increasingly attractive for studying causal effects. However, researchers should be wary of many pitfalls. We propose and illustrate a framework for causal inference estimating the effect of albumin on mortality in sepsis using an Intensive Care database (MIMIC-IV) and comparing various sensitivity analyses to results from RCTs as gold-standard. The first step is study design, using the target trial concept and the PICOT framework: Population (patients with sepsis), Intervention (combination of crystalloids and albumin for fluid resuscitation), Control (crystalloids only), Outcome (28-day mortality), Time (intervention start within 24h of admission). We show that too large treatment-initiation times induce immortal time bias. The second step is selection of the confounding variables based on expert knowledge. Increasingly adding confounders enables to recover the RCT results from observational data. As the third step, we assess the influence of multiple models with varying assumptions, showing that a doubly robust estimator (AIPW) with random forests proved to be the most reliable estimator. Results show that these steps are all important for valid causal estimates. A valid causal model can then be used to individualize decision making: subgroup analyses showed that treatment efficacy of albumin was better for patients >60 years old, males, and patients with septic shock. Without causal thinking, machine learning is not enough for optimal clinical decision on an individual patient level. Our step-by-step analytic framework helps avoiding many pitfalls of applying machine learning to EHR data, building models that avoid shortcuts and extract the best decision-making evidence.

Comparative Effectiveness and Safety of Atorvastatin Versus Rosuvastatin : A Multi-database Cohort Study

BACKGROUND

Rosuvastatin and atorvastatin are the most widely prescribed moderate- to high-intensity statins. However, evidence on their efficacy and safety during actual use is limited.

OBJECTIVE

To compare the real-world effectiveness and safety of rosuvastatin and atorvastatin.

DESIGN

Active comparator cohort study using target trial emulation.

SETTING

The China Renal Data System (CRDS) and UK Biobank (UKB) databases.

PARTICIPANTS

Adults newly prescribed rosuvastatin or atorvastatin.

MEASUREMENTS

The primary outcome was all-cause mortality. Cox proportional hazards regressions were used after 1:1 multilevel propensity score matching.

RESULTS

Among the 285 680 eligible participants in both databases, 6-year all-cause mortality was lower for rosuvastatin than for atorvastatin (2.57 vs. 2.83 per 100 person-years in the CRDS database and 0.66 vs. 0.90 per 100 person-years in the UKB database), with differences in cumulative incidence of -1.03% (95% CI, -1.44% to -0.46%) in the CRDS database and -1.38% (CI, -2.50% to -0.21%) in the UKB database. For secondary outcomes in both databases, rosuvastatin conferred lower risks for major adverse cardiovascular events and major adverse liver outcomes. In the UKB database, the risk for development of type 2 diabetes mellitus was higher with rosuvastatin, and the 2 medications carried similar risks for development of chronic kidney disease and other statin-related adverse effects.

LIMITATION

Possible residual confounding.

CONCLUSION

This study found differences in risks for some important outcomes associated with rosuvastatin and atorvastatin. The differences were relatively small, and many did not meet traditional standards for statistical significance. Further research is needed to understand whether these findings can be used with confidence in clinical practice.

PRIMARY FUNDING SOURCE

National Key R&D Program of China and National Natural Science Foundation of China.

The R.O.A.D. to precision medicine

We propose a novel framework that addresses the deficiencies of Randomized clinical trial data subgroup analysis while it transforms ObservAtional Data to be used as if they were randomized, thus paving the road for precision medicine. Our approach counters the effects of unobserved confounding in observational data through a two-step process that adjusts predicted outcomes under treatment. These adjusted predictions train decision trees, optimizing treatment assignments for patient subgroups based on their characteristics, enabling intuitive treatment recommendations. Implementing this framework on gastrointestinal stromal tumors (GIST) data, including genetic sub-cohorts, showed that our tree recommendations outperformed current guidelines in an external cohort. Furthermore, we extended the application of this framework to RCT data from patients with extremity sarcomas. Despite initial trial indications of universal treatment necessity, our framework identified a subset of patients who may not require treatment. Once again, we successfully validated our recommendations in an external cohort.

Comparative effectiveness of 6x R-CHOP21 versus 6x R-CHOP21 + 2 R for patients with advanced-stage diffuse large B-cell lymphoma

First-line treatment for advanced-stage diffuse large B-cell lymphoma (DLBCL) typically involves 6x R-CHOP21 or 6x R-CHOP21 with two additional rituximab administrations (6x R-CHOP21 + 2 R). In contemporary practice, this treatment choice might be guided by interim PET scan results. This nationwide, population-based study investigates the comparative effectiveness of these treatment regimens in an era where interim PET-guided treatment decisions were not standard practice. Utilizing the Netherlands Cancer Registry, we identified 1577 adult patients diagnosed with advanced-stage DLBCL between 2014-2018 who completed either 6x R-CHOP21 (43%) or 6x R-CHOP21 + 2 R (57%). We used propensity scores to assess differences in event-free survival (EFS) and overall survival (OS). At five years, EFS (hazard ratio of 6x R-CHOP21 + 2 R versus 6x R-CHOP21 [HR] = 0.89; 95% confidence interval [CI], 0.72-1.09) and OS (HR = 0.93; 95% CI, 0.73-1.18) were not significantly different between both regimens. In exploratory risk-stratified analysis according to the International Prognostic Index (IPI), high-IPI patients (i.e., scores of 4-5) benefit most from 6x R-CHOP21 + 2 R (5-year absolute risk difference of EFS = 16.8%; 95% CI, -0.4%-34.1% and OS = 12.1%; 95% CI, -5.4-29.6%). Collectively, this analysis reveals no significant differences on average in EFS and OS between the two treatments. However, the potential benefits for high-risk patients treated with 6x R-CHOP21 + 2 R underscore the need for future research.

Making causal inferences from transactional data: A narrative review of opportunities and challenges when implementing the target trial framework

The target trial framework has emerged as a powerful tool for addressing causal questions in clinical practice and in public health. In the healthcare sector, where decision-making is increasingly data-driven, transactional databases, such as electronic health records (EHR) and insurance claims, present an untapped potential for answering complex causal questions. This narrative review explores the potential of the integration of the target trial framework with real-world data to enhance healthcare decision-making processes. We outline essential elements of the target trial framework, and identify pertinent challenges in data quality, privacy concerns, and methodological limitations, proposing solutions to overcome these obstacles and optimize the framework's application.