Impact of prior malignancies on outcome of colorectal cancer; revisiting clinical trial eligibility criteria

Abstract Background Eligibility criteria are the primary strategy for screening the target participants of a clinical trial. Automated classification of clinical trial eligibility criteria text by using machine learning methods improves recruitment efficiency to reduce the cost of clinical research. However, existing methods suffer from poor classification performance due to the complexity and imbalance of eligibility criteria text data. Methods An ensemble learning-based model with metric learning is proposed for eligibility criteria classification. The model integrates a set of pre-trained models including Bidirectional Encoder Representations from Transformers (BERT), A Robustly Optimized BERT Pretraining Approach (RoBERTa), XLNet, Pre-training Text Encoders as Discriminators Rather Than Generators (ELECTRA), and Enhanced Representation through Knowledge Integration (ERNIE). Focal Loss is used as a loss function to address the data imbalance problem. Metric learning is employed to train the embedding of each base model for feature distinguish. Soft Voting is applied to achieve final classification of the ensemble model. The dataset is from the standard evaluation task 3 of 5th China Health Information Processing Conference containing 38,341 eligibility criteria text in 44 categories. Results Our ensemble method had an accuracy of 0.8497, a precision of 0.8229, and a recall of 0.8216 on the dataset. The macro F1-score was 0.8169, outperforming state-of-the-art baseline methods by 0.84% improvement on average. In addition, the performance improvement had a p-value of 2.152e-07 with a standard t-test, indicating that our model achieved a significant improvement. Conclusions A model for classifying eligibility criteria text of clinical trials based on multi-model ensemble learning and metric learning was proposed. The experiments demonstrated that the classification performance was improved by our ensemble model significantly. In addition, metric learning was able to improve word embedding representation and the focal loss reduced the impact of data imbalance to model performance.

Download Full-text

A Framework for Systematic Assessment of Clinical Trial Population Representativeness Using Electronic Health Records Data

Applied Clinical Informatics ◽

10.1055/s-0041-1733846 ◽

2021 ◽

Vol 12 (04) ◽

pp. 816-825

Author(s):

Yingcheng Sun ◽

Alex Butler ◽

Ibrahim Diallo ◽

Jae Hyun Kim ◽

Casey Ta ◽

...

Keyword(s):

Clinical Trial ◽

Clinical Trials ◽

Electronic Health Records ◽

The United States ◽

Design Stage ◽

Common Data Model ◽

Free Text ◽

Eligibility Criteria ◽

Health Records ◽

Electronic Health

Abstract Background Clinical trials are the gold standard for generating robust medical evidence, but clinical trial results often raise generalizability concerns, which can be attributed to the lack of population representativeness. The electronic health records (EHRs) data are useful for estimating the population representativeness of clinical trial study population. Objectives This research aims to estimate the population representativeness of clinical trials systematically using EHR data during the early design stage. Methods We present an end-to-end analytical framework for transforming free-text clinical trial eligibility criteria into executable database queries conformant with the Observational Medical Outcomes Partnership Common Data Model and for systematically quantifying the population representativeness for each clinical trial. Results We calculated the population representativeness of 782 novel coronavirus disease 2019 (COVID-19) trials and 3,827 type 2 diabetes mellitus (T2DM) trials in the United States respectively using this framework. With the use of overly restrictive eligibility criteria, 85.7% of the COVID-19 trials and 30.1% of T2DM trials had poor population representativeness. Conclusion This research demonstrates the potential of using the EHR data to assess the clinical trials population representativeness, providing data-driven metrics to inform the selection and optimization of eligibility criteria.

Download Full-text

Functional precision medicine in colorectal cancer based on patient-derived tumoroids and in-vitro sensitivity drug testing.

Journal of Clinical Oncology ◽

10.1200/jco.2021.39.15_suppl.e15567 ◽

2021 ◽

Vol 39 (15_suppl) ◽

pp. e15567-e15567

Author(s):

Lars Henrik Jensen ◽

Anders Kristian Moeller Jakobsen ◽

Birgitte Mayland Havelund ◽

Cecilie Abildgaard ◽

Chris Vagn-Hansen ◽

...

Keyword(s):

Colorectal Cancer ◽

Clinical Trial ◽

Primary Endpoint ◽

Drug Testing ◽

Progression Free Survival ◽

Patient Specific ◽

Precision Oncology ◽

Sensitivity Testing ◽

In Vitro Sensitivity

e15567 Background: Precision oncology based on in-vitro, functional assays has potential advantages compared to the much more common molecular approach, but the clinical benefit is unknown. We here report the results from the largest prospective interventional clinical trial testing the clinical outcome in colorectal cancer patients treated with drugs showing cytotoxic effect in matched patient-derived tumoroids. Methods: This single-center, phase II trial included patients with metastatic colorectal cancer previously exposed to all standard therapies. Specimens from one to three 18-16 G core needle biopsies were manually dissected, enzymatically treated, cultivated, and incubated to form 3D spherical microtumors, i.e. tumoroids. In the assay for in-vitro sensitivity testing, the tumoroids were challenged with single drugs and combinations thereof to determine patient-specific responses. Using tumoroid screening technology (IndiTreat, 2cureX, Copenhagen, Denmark), results were generated by comparing the sensitivity of the individual patient’s tumoroids with a reference panel from other patients. The testing included standard cytostatics and drugs with proven effect in previous early-phase clinical trials, a total of 15 drugs. The primary endpoint was the fraction of patients with progression-free survival (PFS) at two months. Based on placebo arms in randomized last-line trials, a minimal relevant difference of 20% (20% to 40%) was stated. Using Simon's two-stage design, a sample size of 45 patients was calculated with at least 14 PFS at two months (significance 5%, power 90%). Results: Ninety patients were enrolled from 9/2017 to 9/2020. Biopsies from 82 patients were obtained and sent for tumoroid formation of which 44 (54%, 95% CI 42-65) were successful and at least one treatment was suggested. Thirty-four patients initiated treatment according to the response obtained in the drug assays within a median of 51 days from inclusion (IQR 39-63). The primary endpoint, PFS at two months, was met in 17 of 34 patients (50%, 95%CI 32-68). There were no radiological responses. Median PFS was 81 days (95% CI 51-112) and median OS was 189 days (95% CI 103-277). Conclusions: Precision oncology using a functional approach with patient-derived tumoroids and in-vitro drug sensitivity testing seems feasible. The approach is limited by the fraction of patients with successful tumoroid development. The primary endpoint was met, as half of the patients were without progression at two months. Further clinical studies are justified. Clinical trial information: NCT03251612.

Download Full-text

Study of Pre-trained Language Models for Named Entity Recognition in Clinical Trial Eligibility Criteria from Multiple Corpora

10.1109/ichi52183.2021.00095 ◽

2021 ◽

Author(s):

Jianfu Li ◽

Qiang Wei ◽

Omid Ghiasvand ◽

Miao Chen ◽

Victor Lobanov ◽

...

Keyword(s):

Clinical Trial ◽

Named Entity Recognition ◽

Entity Recognition ◽

Language Models ◽

Eligibility Criteria ◽

Named Entity

Download Full-text

Are clinical trial eligibility criteria an accurate reflection of a real-world population of advanced non-small-cell lung cancer patients?

Current Oncology ◽

10.3747/co.25.3978 ◽

2018 ◽

Vol 25 (4) ◽

Cited By ~ 12

Author(s):

K. Al-Baimani ◽

H. Jonker ◽

T. Zhang ◽

G.D. Goss ◽

S.A. Laurie ◽

...

Keyword(s):

Lung Cancer ◽

Clinical Trial ◽

Clinical Trials ◽

Small Cell Lung Cancer ◽

Cell Lung Cancer ◽

Advanced Nsclc ◽

Small Cell ◽

Small Cell Lung ◽

Eligibility Criteria ◽

Ecog Ps

Background Advanced non-small-cell lung cancer (nsclc) represents a major health issue globally. Systemic treatment decisions are informed by clinical trials, which, over years, have improved the survival of patients with advanced nsclc. The applicability of clinical trial results to the broad lung cancer population is unclear because strict eligibility criteria in trials generally select for optimal patients.Methods We performed a retrospective chart review of all consecutive patients with advanced nsclc seen in outpatient consultation at our academic institution between September 2009 and September 2012, collecting data about patient demographics and cancer characteristics, treatment, and survival from hospital and pharmacy records. Two sets of arbitrary trial eligibility criteria were applied to the cohort. Scenario A stipulated Eastern Cooperative Oncology Group performance status (ecog ps) 0–1, no brain metastasis, creatinine less than 120 μmol/L, and no second malignancy. Less-strict scenario B stipulated ecog ps 0–2 and creatinine less than 120 μmol/L. We then used the two scenarios to analyze treatment and survival of patients by trial eligibility status.Results The 528 included patients had a median age of 67 years, with 55% being men and 58% having adenocarcinoma. Of those 528 patients, 291 received at least 1 line of palliative systemic therapy. Using the scenario A eligibility criteria, 73% were trial-ineligible. However, 46% of “ineligible” patients actually received therapy and experienced survival similar to that of the “eligible” treated patients (10.2 months vs. 11.6 months, p = 0.10). Using the scenario B criteria, only 35% were ineligible, but again, the survival of treated patients was similar in the ineligible and eligible groups (10.1 months vs. 10.9 months, p = 0.57).Conclusions Current trial eligibility criteria are often strict and limit the enrolment of patients in clinical trials. Our results suggest that, depending on the chosen drug, its toxicities and tolerability, eligibility criteria could be carefully reviewed and relaxed.

Download Full-text