scholarly journals Machine learning enabled subgroup analysis with real-world data to inform better clinical trial design

2021 ◽  
Author(s):  
Jie Xu ◽  
Hao Zhang ◽  
Hansi Zhang ◽  
Jiang Bian ◽  
Fei Wang
Keyword(s):  
Machine Learning ◽  
Clinical Trial ◽  
Clinical Trials ◽  
Real World ◽  
Clinical Manifestations ◽  
Research Network ◽  
Real World Data ◽  
Eligibility Criteria ◽  
World Data ◽  
Patient Subgroups

Restrictive eligibility criteria for clinical trials may limit the generalizability of treatment effectiveness and safety to real-world patients. In this paper, we propose a machine learning approach to derive patient subgroups from real-world data (RWD), such that the patients within the same subgroup share similar clinical characteristics and safety outcomes. The effectiveness of our approach was validated on two existing clinical trials with the electronic health records (EHRs) from a large clinical research network. One is the donepezil trial for Alzheimer's disease (AD), and the other is the Bevacizumab trial on colon cancer (CRC). The results show that our proposed algorithm can identify patient subgroups with coherent clinical manifestations and similar risk levels of encountering severe adverse events (SAEs). We further exemplify that potential rules for describing the patient subgroups with less SAEs can be derived to inform the design of clinical trial eligibility criteria.

scholarly journals Real-World Data for Planning Eligibility Criteria and Enhancing Recruitment: Recommendations from the Clinical Trials Transformation Initiative

2021 ◽  
Author(s):  
Scott R. Evans ◽  
Dianne Paraoan ◽  
Jane Perlmutter ◽  
Sudha R. Raman ◽  
John J. Sheehan ◽  
...  
Keyword(s):  
Clinical Trials ◽  
Real World ◽  
Real World Data ◽  
Eligibility Criteria ◽  
World Data ◽  
Study Planning ◽  
Efficiency And Effectiveness ◽  
Multi Stakeholder ◽  
Functional Teams ◽  
Data Driven Decisions

AbstractThe growing availability of real-world data (RWD) creates opportunities for new evidence generation and improved efficiency across the research enterprise. To varying degrees, sponsors now regularly use RWD to make data-driven decisions about trial feasibility, based on assessment of eligibility criteria for planned clinical trials. Increasingly, RWD are being used to support targeted, timely, and personalized outreach to potential trial participants that may improve the efficiency and effectiveness of the recruitment process. This paper highlights recommendations and resources, including specific case studies, developed by the Clinical Trials Transformation Initiative (CTTI) for applying RWD to planning eligibility criteria and recruiting for clinical trials. Developed through a multi-stakeholder, consensus- and evidence-driven process, these actionable tools support researchers in (1) determining whether RWD are fit for purpose with respect to study planning and recruitment, (2) engaging cross-functional teams in the use of RWD for study planning and recruitment, and (3) understanding patient and site needs to develop successful and patient-centric approaches to RWD-supported recruitment. Future considerations for the use of RWD are explored, including ensuring full patient understanding of data use and developing global datasets.

The rate of tumor growth, g, as a biomarker for overall survival (OS) in prostate cancer (PC) in clinical trials as well as in real-world data from the Veterans Administration Medical Centers (VAMCs).

2019 ◽  
Vol 37 (15_suppl) ◽  
pp. 5074-5074
Author(s):  
Harshraj Leuva ◽  
Mengxi Zhou ◽  
Julia Wilkerson ◽  
Keith Sigel ◽  
Ta-Chueh Hsu ◽  
...  
Keyword(s):  
Prostate Cancer ◽  
Clinical Trial ◽  
Overall Survival ◽  
Clinical Trials ◽  
Tumor Growth ◽  
Real World ◽  
Clinical Trial Data ◽  
Trial Data ◽  
Real World Data ◽  
World Data

5074 Background: Novel assessments of efficacy are needed to improve determination of treatment outcomes in clinical trials and in real-world settings. Methods: Cancer treatments usually lead to concurrent regression and growth of the drug-sensitive and drug-resistant fractions of a tumor, respectively. We have exploited novel methods of analysis that assess these two simultaneous processes and have estimated rates of tumor growth ( g) and regression ( d) in over 30,000 patients (pts) with diverse tumors. Results: In prostate cancer (PC) we have analyzed both clinical trial and real-world data from Veterans. Using clinical trial data from 6819 pts enrolled in 15 treatment arms we have established separately and by combining all the data that g correlates highly (p<0.0001) with overall survival (OS) – slower g associated with better OS. In PC, abiraterone (ABI) and docetaxel (DOC) are superior to placebo, prednisone and mitoxantrone. ABI (median g =0.0017) is superior to DOC ( g=0.0021) in first line (p=0.0013); and ABI in 2nd line ( g=0.0034) is inferior to ABI in 1st line ( g=0.0017; p<0.0001). Finally, using combined clinical trial data as a benchmark we could assess the efficacy of novel therapies in as few as 30-40 patients. Amongst 7457 Veterans, the median g on a taxane ( g=0.0022) was similar to that from clinical trials ( g=0.0012). Although only 258 Veterans received cabazitaxel (CAB), g values for CAB ( g=0.0018) and DOC ( g=0.0023) were indistinguishable (p=0.3) consistent with their identical mechanism of action. Finally, outcomes with DOC in African American (AA) ( g=0.00212) and Caucasian ( g=0.00205) Veterans were indistinguishable (p=0.9) and comparable across all VAMCs. Conclusions: The rate of tumor growth, g, is an excellent biomarker for OS both in clinical trials and in real-world settings. g allows comparisons between trials and for large trial data sets to be used as benchmarks of efficacy. Real-world outcomes in the VAMCs are similar to those in clinical trials. In the egalitarian VAMCs DOC efficacy in PC is comparable in AA and Caucasian Veterans -- indicating inferior outcomes reported in AAs are likely due to differential health care access, not differences in biology.

scholarly journals Exploring the Feasibility of Using Real-World Data from a Large Clinical Data Research Network to Simulate Clinical Trials of Alzheimer’s Disease

2020 ◽  
Author(s):  
Zhaoyi Chen ◽  
Hansi Zhang ◽  
Yi Guo ◽  
Thomas J George ◽  
Mattia Prosperi ◽  
...  
Keyword(s):  
Alzheimer’S Disease ◽  
Alzheimer's Disease ◽  
Clinical Trials ◽  
Clinical Data ◽  
Real World ◽  
Large Scale ◽  
Research Network ◽  
Real World Data ◽  
World Data ◽  
Trial Simulation

AbstractClinical trials are essential but often have high financial costs and long execution time. Trial simulation using real world data (RWD) could potentially provide insights on a treatment’s efficacy and safety before running a large-scale trial. In this work, we explored the feasibility of using RWD from a large clinical data research network to simulate a randomized controlled trial of Alzheimer’s disease considering two different scenarios: an one-arm simulation of the standard-of-care control arm; and a two-arm simulation comparing treatment safety between the intervention and control arms with proper patient matching algorithms. We followed original trial’s design and addressed some key questions, including how to translate trial criteria to database queries and establish measures of safety (i.e., serious adverse events) from RWD. Our simulation generated results comparable to the original trial, but also exposed gaps in both trial simulation methodology and the generalizability issue of clinical trials.

Assessing the relationship in relapsed-refractory multiple myeloma between response, progression, and survival between pooled clinical trial subjects and a real-world electronic medical record data source.

2020 ◽  
Vol 38 (15_suppl) ◽  
pp. e20525-e20525
Author(s):  
Mark Layton Watson ◽  
Charlie Hurmiz ◽  
Jordan Smith ◽  
Suresh Marada ◽  
Aaron Galaznik ◽  
...  
Keyword(s):  
Clinical Trial ◽  
Multiple Myeloma ◽  
Real World ◽  
Survival Rates ◽  
Research Network ◽  
Pool Data ◽  
Real World Data ◽  
World Data ◽  
Refractory Multiple Myeloma ◽  
Depth Of Response

e20525 Background: Despite new treatments, Relapsed-Refractory Multiple Myeloma (RRMM) remains an incurable disease1. In a recent study by Moreau et al, there was a demonstrated survival benefit to treatment with pomalidomide in RRMM patients2. To better understand how the relationships between initial depth of response and long-term prognosis can inform clinical decision making and guide new compound development, we performed an analysis of standardized clinical trial patient pool data compared with Real-World Data (RWD), across multiple studies. Methods: Pooled clinical trial data was obtained from a Study Data Tabulation Model (SDTM) dataset (n=1,815) from the Medidata Enterprise Data Store. De-identified Oncology EMR data was sourced from the Guardian Research Network™ (GRN)5 of integrated delivery systems from 2010-2018, with robust clinical endpoint extraction and curation to enable outcomes comparisons (n=962). Subject selection was refined based on the inclusion/exclusion criteria from the NIMBUS trial2. Response, Progression-free survival (PFS), and Overall Survival (OS) were extracted. Patients were stratified by age, gender, and prior regimens. Log-rank tests were conducted to compare PFS and OS in patient sub-populations at 90, 180, and 240 days from most recent treatment start. Cox proportional hazard models assessed predictors of survival. Rates were estimated for common adverse events, including leukopenia, neutropenia, and thrombocytopenia. Factors associated with neutropenia were assessed using logistic regression. Results: Within pooled trial and RWD patients, the majority were on regimens with proteasome inhibitors, followed by immunomodulators, and approximately one third on monoclonal antibodies. Within the pooled trial analysis, survival rates were consistent with published literature rates, at ~4 months and ~12 months, respectively. EMR data analysis showed overall longer times to progression with an increased depth of response, with similar associations. Frequency-Factored Time-to-Progression also decreased. Conclusions: The use of SDTM for pooled clinical trial analyses, together with real-world data, can overcome individual trial sample size limitations and biases. Together this approach can expand the range of populations, relative treatment comparisons, and clinical events that can be studied to more comprehensively understand the complexity of the oncology treatment landscape.

scholarly journals Contemporary use of real-world data for clinical trial conduct in the United States: a scoping review

2020 ◽  
Author(s):  
James R Rogers ◽  
Junghwan Lee ◽  
Ziheng Zhou ◽  
Ying Kuen Cheung ◽  
George Hripcsak ◽  
...  
Keyword(s):  
Clinical Trial ◽  
Clinical Trials ◽  
Electronic Health Records ◽  
Scoping Review ◽  
Real World ◽  
Administrative Claims ◽  
Real World Data ◽  
Health Records ◽  
World Data ◽  
Trial Process

Abstract Objective Real-world data (RWD), defined as routinely collected healthcare data, can be a potential catalyst for addressing challenges faced in clinical trials. We performed a scoping review of database-specific RWD applications within clinical trial contexts, synthesizing prominent uses and themes. Materials and Methods Querying 3 biomedical literature databases, research articles using electronic health records, administrative claims databases, or clinical registries either within a clinical trial or in tandem with methodology related to clinical trials were included. Articles were required to use at least 1 US RWD source. All abstract screening, full-text screening, and data extraction was performed by 1 reviewer. Two reviewers independently verified all decisions. Results Of 2020 screened articles, 89 qualified: 59 articles used electronic health records, 29 used administrative claims, and 26 used registries. Our synthesis was driven by the general life cycle of a clinical trial, culminating into 3 major themes: trial process tasks (51 articles); dissemination strategies (6); and generalizability assessments (34). Despite a diverse set of diseases studied, &lt;10% of trials using RWD for trial process tasks evaluated medications or procedures (5/51). All articles highlighted data-related challenges, such as missing values. Discussion Database-specific RWD have been occasionally leveraged for various clinical trial tasks. We observed underuse of RWD within conducted medication or procedure trials, though it is subject to the confounder of implicit report of RWD use. Conclusion Enhanced incorporation of RWD should be further explored for medication or procedure trials, including better understanding of how to handle related data quality issues to facilitate RWD use.

scholarly journals Comparing SDTM and FHIR® for Real World Data from Electronic Health Records for Clinical Trial Submissions

2021 ◽  
Author(s):  
Sarah Riepenhausen ◽  
Cornelia Mertens ◽  
Martin Dugas
Keyword(s):  
Clinical Trial ◽  
Clinical Trials ◽  
Electronic Health Records ◽  
Real World ◽  
Clinical Trial Data ◽  
Trial Data ◽  
Real World Data ◽  
Health Records ◽  
World Data ◽  
Data Submission

Real world data for use in clinical trials is promising. We compared the SDTM for clinical trial data submission with FHIR® for routine documentation. After categorization of variables by relevance, clinically relevant SDTM items were mapped to FHIR®. About 30% in both were seen as clinically relevant. The majority of these SDTM items were mappable to FHIR® Observation resource.

Using real-world cohorts to assess the generalizability and relevance of randomized clinical trials (RCTs).

2019 ◽  
Vol 37 (15_suppl) ◽  
pp. 6540-6540 ◽  
Author(s):  
Caroline Savage Bennette ◽  
Nathan Coleman Nussbaum ◽  
Melissa D. Curtis ◽  
Neal J. Meropol
Keyword(s):  
Clinical Trials ◽  
Real World ◽  
Randomized Clinical Trials ◽  
Treatment Options ◽  
Metastatic Breast ◽  
Standard Of Care ◽  
Real World Data ◽  
Eligibility Criteria ◽  
Relevance Score ◽  
World Data

6540 Background: RCTs are the gold standard for understanding the efficacy of new treatments, however, patients (pts) in RCTs often differ from those treated in the real-world. Further, selecting a standard of care (SOC) arm is challenging as treatment options may evolve during the course of a RCT. Our objective was to assess the generalizability and relevance of RCTs supporting recent FDA approvals of anticancer therapies. Methods: RCTs were identified that supported FDA approvals of anticancer therapies (1/1/2016 - 4/30/2018). Relevant pts were selected from the Flatiron Health longitudinal, EHR-derived database, where available. Two metrics were calculated: 1) a trial’s pt generalizability score (% of real-world pts receiving treatment consistent with the control arm therapy for the relevant indication who actually met the trial's eligibility criteria) and 2) a trial’s SOC relevance score (% of real-world pts with the relevant indication and meeting the trial's eligibility criteria who actually received treatment consistent with the control arm therapy). All analyses excluded real-world pts treated after the relevant trial’s enrollment ended. Results: 14 RCTs across 5 cancer types (metastatic breast, advanced non-small cell lung cancer, metastatic renal cell carcinoma, multiple myeloma, and advanced urothelial) were included. There was wide variation in the SOC relevance and pt generalizability scores. The median pt generalizability score was 63% (range 35% - 88%), indicating that most real-world pts would have met the RCT eligibility criteria. The median SOC relevance score was 37% (range 15% - 74%), indicating that most RCT control arms did not reflect the way trial-eligible real-world pts in the US were actually treated. Conclusions: There is great variability across recent RCTs in terms of pt generalizability and relevance of SOC arms. Real-world data can be used to inform selection of control arms, predict impact of inclusion/exclusion criteria, and also assess the generalizability of the results of completed trials. Incorporating real-world data in planning and interpretation of prospective clinical trials could improve accrual and enhance relevance of RCT outcomes.

Sign in / Sign up

Export Citation Format

Share Document