Automatic recognition of self-acknowledged limitations in clinical research literature

Automatic categorization of self-acknowledged limitations in randomized controlled trial publications

OBJECTIVE

Acknowledging study limitations in a scientific publication is a crucial element in scientific transparency and progress. However, limitation reporting is often inadequate. Natural language processing (NLP) methods could support automated reporting checks, improving research transparency. In this study, our objective was to develop a dataset and NLP methods to detect and categorize self-acknowledged limitations (e.g., sample size, blinding) reported in randomized controlled trial (RCT) publications.

METHODS

We created a data model of limitation types in RCT studies and annotated a corpus of 200 full-text RCT publications using this data model. We fine-tuned BERT-based sentence classification models to recognize the limitation sentences and their types. To address the small size of the annotated corpus, we experimented with data augmentation approaches, including Easy Data Augmentation (EDA) and Prompt-Based Data Augmentation (PromDA). We applied the best-performing model to a set of about 12K RCT publications to characterize self-acknowledged limitations at larger scale.

RESULTS

Our data model consists of 15 categories and 24 sub-categories (e.g., Population and its sub-category DiagnosticCriteria). We annotated 1090 instances of limitation types in 952 sentences (4.8 limitation sentences and 5.5 limitation types per article). A fine-tuned PubMedBERT model for limitation sentence classification improved upon our earlier model by about 1.5 absolute percentage points in F1 score (0.821 vs. 0.8) with statistical significance (p<.001). Our best-performing limitation type classification model, PubMedBERT fine-tuning with PromDA (Output View), achieved an F1 score of 0.7, improving upon the vanilla PubMedBERT model by 2.7 percentage points, with statistical significance (p<.001).

CONCLUSION

The model could support automated screening tools which can be used by journals to draw the authors' attention to reporting issues. Automatic extraction of limitations from RCT publications could benefit peer review and evidence synthesis, and support advanced methods to search and aggregate the evidence from the clinical trial literature.

CONSORT-TM: Text classification models for assessing the completeness of randomized controlled trial publications

Objective

To develop text classification models for determining whether the checklist items in the CONSORT reporting guidelines are reported in randomized controlled trial publications.

Materials and Methods

Using a corpus annotated at the sentence level with 37 fine-grained CONSORT items, we trained several sentence classification models (PubMedBERT fine-tuning, BioGPT fine-tuning, and in-context learning with GPT-4) and compared their performance. To address the problem of small training dataset, we used several data augmentation methods (EDA, UMLS-EDA, text generation and rephrasing with GPT-4) and assessed their impact on the fine-tuned PubMedBERT model. We also fine-tuned PubMedBERT models limited to checklist items associated with specific sections (e.g., Methods) to evaluate whether such models could improve performance compared to the single full model. We performed 5-fold cross-validation and report precision, recall, F1 score, and area under curve (AUC).

Results

Fine-tuned PubMedBERT model that takes as input the sentence and the surrounding sentence representations and uses section headers yielded the best overall performance (0.71 micro-F1, 0.64 macro-F1). Data augmentation had limited positive effect, UMLS-EDA yielding slightly better results than data augmentation using GPT-4. BioGPT fine-tuning and GPT-4 in-context learning exhibited suboptimal results. Methods-specific model yielded higher performance for methodology items, other section-specific models did not have significant impact.

Conclusion

Most CONSORT checklist items can be recognized reasonably well with the fine-tuned PubMedBERT model but there is room for improvement. Improved models can underpin the journal editorial workflows and CONSORT adherence checks and can help authors in improving the reporting quality and completeness of their manuscripts.

Limitations in Medical Research: Recognition, Influence, and Warning

Background

As the number of limitations increases in a medical research article, their consequences multiply and the validity of findings decreases. How often do limitations occur in a medical article? What are the implications of limitation interaction? How often are the conclusions hedged in their explanation?

Objective

To identify the number, type, and frequency of limitations and words used to describe conclusion(s) in medical research articles.

Methods

Search, analysis, and evaluation of open access research articles from 2021 and 2022 from the Journal of the Society of Laparoscopic and Robotic Surgery and 2022 Surgical Endoscopy for type(s) of limitation(s) admitted to by author(s) and the number of times they occurred. Limitations not admitted to were found, obvious, and not claimed. An automated text analysis was performed for hedging words in conclusion statements. A limitation index score is proposed to gauge the validity of statements and conclusions as the number of limitations increases.

Results

A total of 298 articles were reviewed and analyzed, finding 1,764 limitations. Four articles had no limitations. The average was between 3.7% and 6.9% per article. Hedging, weasel words and words of estimative probability description was found in 95.6% of the conclusions.

Conclusions

Limitations and their number matter. The greater the number of limitations and ramifications of their effects, the more outcomes and conclusions are affected. Wording ambiguity using hedging or weasel words shows that limitations affect the uncertainty of claims. The limitation index scoring method shows the diminished validity of finding(s) and conclusion(s).

Is the future of peer review automated?

The rising rate of preprints and publications, combined with persistent inadequate reporting practices and problems with study design and execution, have strained the traditional peer review system. Automated screening tools could potentially enhance peer review by helping authors, journal editors, and reviewers to identify beneficial practices and common problems in preprints or submitted manuscripts. Tools can screen many papers quickly, and may be particularly helpful in assessing compliance with journal policies and with straightforward items in reporting guidelines. However, existing tools cannot understand or interpret the paper in the context of the scientific literature. Tools cannot yet determine whether the methods used are suitable to answer the research question, or whether the data support the authors' conclusions. Editors and peer reviewers are essential for assessing journal fit and the overall quality of a paper, including the experimental design, the soundness of the study's conclusions, potential impact and innovation. Automated screening tools cannot replace peer review, but may aid authors, reviewers, and editors in improving scientific papers. Strategies for responsible use of automated tools in peer review may include setting performance criteria for tools, transparently reporting tool performance and use, and training users to interpret reports.

Toward assessing clinical trial publications for reporting transparency

OBJECTIVE

To annotate a corpus of randomized controlled trial (RCT) publications with the checklist items of CONSORT reporting guidelines and using the corpus to develop text mining methods for RCT appraisal.

METHODS

We annotated a corpus of 50 RCT articles at the sentence level using 37 fine-grained CONSORT checklist items. A subset (31 articles) was double-annotated and adjudicated, while 19 were annotated by a single annotator and reconciled by another. We calculated inter-annotator agreement at the article and section level using MASI (Measuring Agreement on Set-Valued Items) and at the CONSORT item level using Krippendorff's α. We experimented with two rule-based methods (phrase-based and section header-based) and two supervised learning approaches (support vector machine and BioBERT-based neural network classifiers), for recognizing 17 methodology-related items in the RCT Methods sections.

RESULTS

We created CONSORT-TM consisting of 10,709 sentences, 4,845 (45%) of which were annotated with 5,246 labels. A median of 28 CONSORT items (out of possible 37) were annotated per article. Agreement was moderate at the article and section levels (average MASI: 0.60 and 0.64, respectively). Agreement varied considerably among individual checklist items (Krippendorff's α= 0.06-0.96). The model based on BioBERT performed best overall for recognizing methodology-related items (micro-precision: 0.82, micro-recall: 0.63, micro-F1: 0.71). Combining models using majority vote and label aggregation further improved precision and recall, respectively.

CONCLUSION

Our annotated corpus, CONSORT-TM, contains more fine-grained information than earlier RCT corpora. Low frequency of some CONSORT items made it difficult to train effective text mining models to recognize them. For the items commonly reported, CONSORT-TM can serve as a testbed for text mining methods that assess RCT transparency, rigor, and reliability, and support methods for peer review and authoring assistance. Minor modifications to the annotation scheme and a larger corpus could facilitate improved text mining models. CONSORT-TM is publicly available at https://github.com/kilicogluh/CONSORT-TM.

Sample size, study length, and inadequate controls were the most common self-acknowledged limitations in manual therapy trials: A methodological review

OBJECTIVES

The aim of this study was to quantify and analyze the presence and type of self-acknowledged limitations (SALs) in a sample of manual therapy (MT) randomized controlled trials.

STUDY DESIGN AND SETTING

We randomly selected 120 MT trials. We extracted data related to SALs from the original reports and classified them into 12 categories. After data extraction, specific limitations within each category were identified. A descriptive analysis was performed using frequencies and percentages for qualitative variables.

RESULTS

The number of SALs per trial article ranged from 0 to 8, and more than two-thirds of trials acknowledged at least two different limitations. Despite its small proportion, 9% of trials did not report SALs. The most common limitation declared, in almost half of our sample, related to sample size (47.5%) followed by limitations related to study length and follow-up (33.3%) and inadequate controls (32.5%).

CONCLUSION

Our results indicate that at least two different limitations are consistently acknowledged in MT trial reports, the most common being those related to sample size, study length, follow-up, and inadequate controls. Analysis of the reasons behind the SALs gives some insights about the main difficulties in conducting research in this field and may help develop strategies to improve future research.

Impact of peer review on discussion of study limitations and strength of claims in randomized trial reports: a before and after study

Background

In their research reports, scientists are expected to discuss limitations that their studies have. Previous research showed that often, such discussion is absent. Also, many journals emphasize the importance of avoiding overstatement of claims. We wanted to see to what extent editorial handling and peer review affects self-acknowledgment of limitations and hedging of claims.

Methods

Using software that automatically detects limitation-acknowledging sentences and calculates the level of hedging in sentences, we compared the submitted manuscripts and their ultimate publications of all randomized trials published in 2015 in 27 BioMed Central (BMC) journals and BMJ Open. We used mixed linear and logistic regression models, accounting for clustering of manuscript-publication pairs within journals, to quantify before-after changes in the mean numbers of limitation-acknowledging sentences, in the probability that a manuscript with zero self-acknowledged limitations ended up as a publication with at least one and in hedging scores.

Results

Four hundred forty-six manuscript-publication pairs were analyzed. The median number of manuscripts per journal was 10.5 (interquartile range 6–18). The average number of distinct limitation sentences increased by 1.39 (95% CI 1.09–1.76), from 2.48 in manuscripts to 3.87 in publications. Two hundred two manuscripts (45.3%) did not mention any limitations. Sixty-three (31%, 95% CI 25–38) of these mentioned at least one after peer review. Changes in mean hedging scores were negligible.

Conclusions

Our findings support the idea that editorial handling and peer review lead to more self-acknowledgment of study limitations, but not to changes in linguistic nuance.