Predictive modeling of clinical trial terminations using feature engineering and embedding learning

Elkin, Magdalyn E.; Zhu, Xingquan

doi:10.1038/s41598-021-82840-x

Cited by 28 publications

(44 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Overall, embedding features are least informative. This is different from our previous study [10], where statistics features are found to be more informative than keyword features and embedding features. Nevertheless, our experiments in the next section will show that, despite of the individual importance, all four types of features contribute to the accurate prediction of COVID-19 trials.…”

Section: Plos Onecontrasting

confidence: 99%

“…These models can also be applied to current or planned trials to understand their probability of completion vs termination. Previous termination prediction studies [15,16], along with our previous research [10] demonstrate the predictive power of structured and unstructured variables in order to predict if a clinical trial is likely to terminate.…”

Section: Related Workmentioning

confidence: 88%

“…In our previous research [10], we designed a predictive model to predict completed vs. terminated trials using a large testbed collected from the entire clinicaltrials.gov database. In this study, we propose to design new features to characterize COVID-19 trials, and understand factors associated to clinical completion vs. cessation.…”

Section: Related Workmentioning

confidence: 99%

“…Statistics features. Statistics features model clinical trials with respect to administrative, study information, study design, and eligibility criteria, which are extracted from the clinical trial reports by taking different part of information into consideration [10].…”

Section: Covid-19 Clinical Trial Featuresmentioning

confidence: 99%

“…Unfortunately, not all trials are completed and achieve the intended goals. Researchers, in previous studies, have found that 10-12% of clinical trials are terminated [8][9][10] due to numerous reasons, such as insufficient enrollment, scientific data from the trial, safety/efficacy concerns, administrative reasons, external information from a different study, lack of funding/resources, and business/sponsor decisions, etc. [8,9,11].…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Understanding and predicting COVID-19 clinical trial completion vs. cessation

Elkin

Zhu

2021

PLoS ONE

Self Cite

View full text Add to dashboard Cite

As of March 30 2021, over 5,193 COVID-19 clinical trials have been registered through Clinicaltrial.gov. Among them, 191 trials were terminated, suspended, or withdrawn (indicating the cessation of the study). On the other hand, 909 trials have been completed (indicating the completion of the study). In this study, we propose to study underlying factors of COVID-19 trial completion vs. cessation, and design predictive models to accurately predict whether a COVID-19 trial may complete or cease in the future. We collect 4,441 COVID-19 trials from ClinicalTrial.gov to build a testbed, and design four types of features to characterize clinical trial administration, eligibility, study information, criteria, drug types, study keywords, as well as embedding features commonly used in the state-of-the-art machine learning. Our study shows that drug features and study keywords are most informative features, but all four types of features are essential for accurate trial prediction. By using predictive models, our approach achieves more than 0.87 AUC (Area Under the Curve) score and 0.81 balanced accuracy to correctly predict COVID-19 clinical trial completion vs. cessation. Our research shows that computational methods can deliver effective features to understand difference between completed vs. ceased COVID-19 trials. In addition, such models can also predict COVID-19 trial status with satisfactory accuracy, and help stakeholders better plan trials and minimize costs.

show abstract

Section: Plos Onecontrasting

confidence: 99%

Section: Related Workmentioning

confidence: 88%

Section: Related Workmentioning

confidence: 99%

Section: Covid-19 Clinical Trial Featuresmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Understanding and predicting COVID-19 clinical trial completion vs. cessation

Elkin

Zhu

2021

PLoS ONE

Self Cite

View full text Add to dashboard Cite

show abstract

Early Termination of Oncology Clinical Trials in the United States

Zhang

DuBois

2022

Cancer Medicine

View full text Add to dashboard Cite

Interventional clinical trials play a vital role in advancing new therapeutic approaches in medicine. Prior work has shown that a significant portion of clinical trials are terminated early. 1,2 Early termination can happen due to reasons that include, but are not limited to, poor accrual, funding issues, and emerging safety and/or efficacy signals. In the setting of safety or efficacy considerations, early termination may be appropriate, and this approach is

show abstract

Prediction of Clinical Trials Outcomes Based on Target Choice and Clinical Trial Design with Multi‐Modal Artificial Intelligence

Aliper¹,

Kudrin²,

Polykovskiy³

et al. 2023

Clin Pharma and Therapeutics

View full text Add to dashboard Cite

Drug discovery and development is a notoriously risky process with high failure rates at every stage, including disease modeling, target discovery, hit discovery, lead optimization, preclinical development, human safety, and efficacy studies. Accurate prediction of clinical trial outcomes may help significantly improve the efficiency of this process by prioritizing therapeutic programs that are more likely to succeed in clinical trials and ultimately benefit patients. Here, we describe inClinico, a transformer‐based artificial intelligence software platform designed to predict the outcome of phase II clinical trials. The platform combines an ensemble of clinical trial outcome prediction engines that leverage generative artificial intelligence and multimodal data, including omics, text, clinical trial design, and small molecule properties. inClinico was validated in retrospective, quasi‐prospective, and prospective validation studies internally and with pharmaceutical companies and financial institutions. The platform achieved 0.88 receiver operating characteristic area under the curve in predicting the phase II to phase III transition on a quasi‐prospective validation dataset. The first prospective predictions were made and placed on date‐stamped preprint servers in 2016. To validate our model in a real‐world setting, we published forecasted outcomes for several phase II clinical trials achieving 79% accuracy for the trials that have read out. We also present an investment application of inClinico using date stamped virtual trading portfolio demonstrating 35% 9‐month return on investment.

show abstract

Predictive modeling of clinical trial terminations using feature engineering and embedding learning

Cited by 28 publications

References 24 publications

Understanding and predicting COVID-19 clinical trial completion vs. cessation

Understanding and predicting COVID-19 clinical trial completion vs. cessation

Early Termination of Oncology Clinical Trials in the United States

Prediction of Clinical Trials Outcomes Based on Target Choice and Clinical Trial Design with Multi‐Modal Artificial Intelligence

Contact Info

Product

Resources

About