Toward Automated Data Extraction According to Tabular Data Structure: Cross-sectional Pilot Survey of the Comparative Clinical Literature
Bibliographic record
Abstract
BACKGROUND: Systematic reviews depend on time-consuming extraction of data from the PDFs of underlying studies. To date, automation efforts have focused on extracting data from the text, and no approach has yet succeeded in fully automating ingestion of quantitative evidence. However, the majority of relevant data is generally presented in tables, and the tabular structure is more amenable to automated extraction than free text. OBJECTIVE: The purpose of this study was to classify the structure and format of descriptive statistics reported in tables in the comparative medical literature. METHODS: We sampled 100 published randomized controlled trials from 2019 based on a search in PubMed; these results were imported to the AutoLit platform. Studies were excluded if they were nonclinical, noncomparative, not in English, protocols, or not available in full text. In AutoLit, tables reporting baseline or outcome data in all studies were characterized based on reporting practices. Measurement context, meaning the structure in which the interventions of interest, patient arm breakdown, measurement time points, and data element descriptions were presented, was classified based on the number of contextual pieces and metadata reported. The statistic formats for reported metrics (specific instances of reporting of data elements) were then classified by location and broken down into reporting strategies for continuous, dichotomous, and categorical metrics. RESULTS: We included 78 of 100 sampled studies, one of which (1.3%) did not report data elements in tables. The remaining 77 studies reported baseline and outcome data in 174 tables, and 96% (69/72) of these tables broke down reporting by patient arms. Fifteen structures were found for the reporting of measurement context, which were broadly grouped into: 1×1 contexts, where two pieces of context are reported in total (eg, arms in columns, data elements in rows); 2×1 contexts, where two pieces of context are given on row headers (eg, time points in columns, arms nested in data elements on rows); and 1×2 contexts, where two pieces of context are given on column headers. The 1×1 contexts were present in 57% of tables (99/174), compared to 20% (34/174) for 2×1 contexts and 15% (26/174) for 1×2 contexts; the remaining 8% (15/174) used unique/other stratification methods. Statistic formats were reported in the headers or descriptions of 84% (65/74) of studies. CONCLUSIONS: In this cross-sectional pilot review, we found a high density of information in tables, but with major heterogeneity in presentation of measurement context. The highest-density studies reported both baseline and outcome measures in tables, with arm-level breakout, intervention labels, and arm sizes present, and reported both the statistic formats and units. The measurement context formats presented here, broadly classified into three classes that cover 92% (71/78) of studies, form a basis for understanding the frequency of different reporting styles, supporting automated detection of the data format for extraction of metrics.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.499 | 0.757 |
| Meta-epidemiology (narrow) | 0.002 | 0.002 |
| Meta-epidemiology (broad) | 0.004 | 0.006 |
| Bibliometrics | 0.043 | 0.039 |
| Science and technology studies | 0.002 | 0.004 |
| Scholarly communication | 0.009 | 0.013 |
| Open science | 0.003 | 0.009 |
| Research integrity | 0.002 | 0.002 |
| Insufficient payload (model declined to judge) | 0.006 | 0.002 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; the direct Gemma label and the distilled Codex classifier agree on what is shown here.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".