The DOI matches its Crossref record; 26 of the 26 references it cites were found in a registry or an index; 15 of the 50 sources its claims cite were checked for support.
Automated Mass Extraction of Over 680,000 PICOs from Clinical Study Abstracts Using Generative AI: A Proof-of-Concept Study.
Open accessAbstract
Generative artificial intelligence (GenAI) shows promise in automating key tasks involved in conducting systematic literature reviews (SLRs), including screening, bias assessment and data extraction. This potential automation is increasingly relevant as pharmaceutical developers face challenging requirements for timely and precise SLRs using the population, intervention, comparator and outcome (PICO) framework, such as those under the impending European Union (EU) Health Technology Assessment Regulation 2021/2282 (HTAR). This proof-of-concept study aimed to evaluate the feasibility, accuracy and efficiency of using GenAI for mass extraction of PICOs from PubMed abstracts. Abstracts were retrieved from PubMed using a search string targeting randomised controlled trials. A PubMed clinical study ‘specific/narrow’ filter was also applied. Retrieved abstracts were processed using the OpenAI Batch application programming interface (API), which allowed parallel processing and interaction with Generative Pre-trained Transformer 4 Omni (GPT-4o) via custom Python scripts. PICO elements were extracted using a zero-shot prompting strategy. Results were stored in CSV files and subsequently imported into a PostgreSQL database. The PubMed search returned 682,667 abstracts. PICOs from all abstracts were extracted in < 3 h, with an average processing time of 200 s per 1000 abstracts. A total of 395,992,770 tokens were processed, with an average of 580 tokens per abstract. The total cost was $3390. On the basis of a random sample of 350 abstracts, human verification confirmed that GPT-4o accurately and comprehensively extracted 342 (98%) of all PICOs, with only outcome elements rarely missed. Using GenAI to extract PICOs from clinical study abstracts could fundamentally transform the way SLRs are conducted. By enabling pharmaceutical developers to anticipate PICO requirements, this approach allows for proactive preparation for the EU HTAR process, or other health technology assessments (HTAs), streamlining efficiency and reducing the burden of meeting these requirements. This study explored how artificial intelligence (AI) can help automate a key part of systematic literature reviews (SLRs), which are used to summarise research in healthcare. AI was used to extract specific information referred to as population, intervention, comparator and outcome (PICOs) from nearly 700,000 abstracts of clinical studies from the PubMed database. AI extracted the PICO information from all the abstracts in under 3 h, which is significantly faster than a human could do. This demonstrates that AI could save a lot of time and effort compared with using human reviewers to do the same task. The study also found that AI performed accurately in identifying the PICO elements in the abstracts, although further human verification is still required. The use of AI in this way could help pharmaceutical developers meet upcoming requirements from the European Union, which require timely and thorough reviews of clinical evidence. AI can speed up the process, reducing the burden on pharmaceutical developers and allowing them to prepare more efficiently for these assessments. However, further testing and validation is needed before using AI in this way becomes common.
Overview
CoChat Summary
TL;DR
This proof-of-concept study used GPT-4o via the OpenAI Batch API to extract PICO elements from 682,667 PubMed randomised controlled trial abstracts in under 3 h at a total cost of $3390, with 98% accuracy in a 350-abstract human-verified sample. It suggests GenAI could streamline PICO scoping for systematic literature reviews and EU HTAR/JCA preparation, though validation is limited to PubMed abstracts and English-language records.
Key findings
- The PubMed search returned 682,667 abstracts; PICOs from all abstracts were extracted in < 3 h, with an average processing time of 200 s per 1000 abstracts. A total of 395,992,770 tokens were processed, averaging 580 tokens per abstract, at a total cost of $3390, representing a 50% cost reduction versus processing abstracts individually.
- On the basis of a random sample of 350 abstracts, human verification confirmed GPT-4o accurately and comprehensively extracted 342 (98%) of all PICOs; population, intervention and comparator were consistently extracted correctly, while some outcome elements were rarely missed.
- One human reviewer required approximately 8 h to review and compare PICO data for 274 abstracts; at that rate, one reviewer would need approximately 2492 working days, or at least 10 working years, to review the total number of abstracts.
- The authors state that, to their knowledge, this is the first instance of PICO extraction achieved with this level of speed, scale and accuracy.
Methods
- Proof-of-concept study: abstracts were retrieved from PubMed on 11 June 2024 using a search string targeting randomised controlled trials plus the PubMed clinical study ‘specific/narrow’ filter; 682,667 abstracts were retrieved and all were included, with no further filters.
- PICO extraction used GPT-4o through the OpenAI Batch API, custom Python scripts, and a zero-shot input/output prompting strategy; prompts were iteratively refined until no further improvements were identified. Results were stored in CSV files and imported into a PostgreSQL database.
- Accuracy was assessed by human verification of a random subsample of 350 abstracts (0.05% of the total dataset); time and cost were tracked, with cost calculated from aggregated token counts and a 50% batch API discount.
Limitations
- The paper states that only PubMed abstracts were used because of its freely available API, limiting generalisability; abstracts are often limited to around 300 words, so PICO elements for HTA analyses may have been missed, and further testing is needed for full texts.
- The paper states that effectiveness in specific research areas remains unclear, validation with narrower searches is necessary, and an English-language-only filter means performance on non-English-language abstracts is unknown.
- Evident from the text: accuracy was verified in only 350 of 682,667 abstracts (0.05%), and missed outcome elements were not verified against full publications; the authors note that further large-scale verification will be essential for regulatory and HTA settings.
Model-written summary. Check it against the paper before relying on it.
Integrity signals
Registry
Cites
Statistics
Figures


Verification
Claims the paper makes
7 Valid · 0 Not valid · 18 Not checked · 28 Own results and interpretations
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“Recent advancements in generative artificial intelligence (GenAI), particularly large language models (LLMs), have demonstrated the potential of this technology to automate key tasks involved in conducting systematic literature reviews (SLRs)”
§ Automated Mass Extraction of Over 680,000 PICOs from Clinical Study Abstracts Using Generative AI: A Proof-of-Concept Study > Introduction
What the sources say
- Could not verifycites [1] Murad MH, Asi N, Alsawas M, Alahdab F. New evidence pyramid. Evid Based Med. 2016;21:125–7. https://doi.org/10.1136/ebmed-2016-110401. sourceExperimental — accuracy not yet measured
Our copy of Murad et al. (2016) 'New evidence pyramid' is a perspective on the EBM hierarchy: the Abstract and 'Rationale for modification 1/2' sections discuss GRADE, heterogeneity and systematic reviews as a 'lens' for consuming evidence, and 'Implications and limitations' covers teaching use. No passage mentions generative AI, large language models, machine learning or automation of review tasks (searched: 'artificial intelligence large language models automate systematic review screening'; 'automation of literature search and study selection in systematic reviews'). The full text is complete (not truncated), but the claim's point simply is not addressed by this paper, so it can be neither confirmed nor contradicted here. (LLM, conf=0.75)
- Supportedcites [2] Fleurence RL, Bian J, Wang X, Xu H, Dawoud D, Fakhouri T, et al. Generative AI for health technology assessment: opportunities, challenges, and policy considerations. 2024. Available from: https://www.researchgate.net/publication/382302525_Generative_AI_for_Health_Technology_Assessment_Opportunities_Challenges_and_Policy_Considerations. Accessed 23 Aug 2024. source
The Results section of the ISPOR report states that 'generative AI has the potential to assist in automating aspects of systematic literature reviews by proposing search terms, screening abstracts, extracting data, and generating code for meta-analyses,' which matches the claim's attribution of potential automation of key SLR tasks to GenAI/LLMs. The Introduction's section 'Applications of Generative AI in Literature Reviews and Evidence Synthesis' elaborates the same tasks (search-strategy/Mesh term generation, abstract screening, data extraction, report drafting), and its summary reiterates 'there is promise in using foundation models to support a range of tasks required in SLRs.' The source couples this with limits (inaccuracies, hallucinations, need for human oversight), but the citing sentence is hedged to 'potential,' so it does not overstate the source. (LLM, conf=0.87)
- Partly supportedcites [3] Page MJ, Moher D, Bossuyt PM, Boutron I, Hoffmann TC, Mulrow CD, et al. PRISMA 2020 explanation and elaboration: updated guidance and exemplars for reporting systematic reviews. BMJ. 2021;372: n160. https://doi.org/10.1136/bmj.n160. sourceExperimental — accuracy not yet measured
Our copy of the PRISMA 2020 explanation and elaboration supports only the generic automation half of the claim: Item 8 (Selection process) states that 'Increasingly, a mix of screening approaches might be applied (such as automation to eliminate records before screening or prioritise records during screening)' and that machine learning classifiers 'can increase review efficiency', and Item 9 (Data collection process) refers to 'machine learning models to extract sentences from articles relevant to the PICO characteristics'. Nothing in our copy mentions generative artificial intelligence, large language models, or any demonstrated potential of such systems to automate SLR tasks (searched: 'large language model', 'generative AI', 'natural language processing', 'text mining'); the highest-ranked passages are all about conventional ML classifiers, crowdsourcing and prior 'known' assessments, and the paper predates GenAI advances. The GenAI/LLM-specific attribution therefore rests on other work, not this source. (LLM, conf=0.70)
boostedstates a possible cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Could not verify
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“Prior work in this area has explored the feasibility of using natural language processing (NLP) to automate PICO extraction from biomedical abstracts with limited success [5, 27, 28].”
§ Automated Mass Extraction of Over 680,000 PICOs from Clinical Study Abstracts Using Generative AI: A Proof-of-Concept Study > Discussion
What the sources say
- Partly supportedcites [5] Khraisha Q, Put S, Kappenberg J, Warraitch A, Hadfield K. Can large language models replace humans in systematic reviews? Evaluating GPT-4’s efficacy in screening and extracting data from peer-reviewed and grey literature in multiple languages. Res Synth Methods. 2024;15:616–26. https://doi.org/10.1002/jrsm.1715. sourceExperimental — accuracy not yet measured
The Discussion (p. 6) does characterise prior automated-extraction work as limited: previous AI endeavours faced 'the incapability to either review full-texts (Clark et al., 2020; Nye et al., 2018) or to extract data deviating from a predetermined structure (Summerscales et al., 2011; Wallace et al., 2016)', and Wallace et al. (2016) is listed in the References (p. 10) as 'Extracting PICO sentences from clinical trial reports using supervised distant supervision' — so the 'prior NLP work on PICO extraction, with limited success' part is supported. However, the source's account attaches that work to clinical trial reports / full texts, not to biomedical abstracts, and its stated limitation is rigidity of a predetermined data structure rather than overall lack of success; the abstract-specific scope of the citing sentence is not in our copy. The Introduction (p. 2) likewise discusses AI tools' deterioration without a human in the loop for screening and extraction from full-text articles, not abstract-level PICO extraction. (LLM, conf=0.70)
- Not checked yetcites [27] Nye B, Jessy Li J, Patel R, Yang Y, Marshall IJ, Nenkova A, et al. A corpus with multi-level annotations of patients, interventions and outcomes to support language processing for medical literature. Proc Conf Assoc Comput Linguist Meet. 2018;2018:197–207.
- Supportedcites [28] Hu Y, Keloth VK, Raja K, Chen Y, Xu H. Towards precise PICO extraction from abstracts of randomized controlled trials using a section-specific learning approach. Bioinformatics. 2023. https://doi.org/10.1093/bioinformatics/btad542. source
The Introduction (p.1) and Related work sections 2.1-2.2 of our copy lay out prior NLP/ML/DL efforts to automate PICO extraction from PubMed/RCT abstracts (Demner-Fushman and Lin 2007, Kim et al. 2011, Nye et al. 2018, Kang et al. 2019/2021, Zhang et al. 2020, Liu et al. 2021b), i.e. the feasibility of the task was explored. The 'limited success' part is carried by the same passages: prior models 'rely heavily on hand-crafted features' and on scarce annotated corpora, the EBM-NLP baseline NER performance is 'not satisfying (a token-level F1 score of 68% on the span-level and 48% on the hierarchical labels)' with enumerated 'probable reasons for low performance', and a cited sentence classifier reached 'the least performance of 0.31 F1-score on the Intervention class' (3.3). Only nuance: our copy's scope is RCT/PubMed abstracts rather than biomedical abstracts generally, which is a subset and does not undercut the attributed point. (LLM, conf=0.85)
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Partly supported
The sources with a verdict support this claim; the rest weren’t checked yet, have no full text we could read, or their verdicts aren’t rated yet.
In the paper
“With only around 100 days to submit a JCA dossier after the PICO scope is confirmed, pharmaceutical developers face significant pressure to meet stringent deadlines, potentially impacting the quality and comprehensiveness of the submissions [8, 10].”
§ Automated Mass Extraction of Over 680,000 PICOs from Clinical Study Abstracts Using Generative AI: A Proof-of-Concept Study > Introduction
What the sources say
- Supportedcites [8] Schuster V. EU HTA regulation and joint clinical assessment—threat or opportunity? J Mark Access Health Policy. 2024;12:100–4. https://doi.org/10.3390/jmahp12020008. source
Section 2 says manufacturers must prepare the JCA dossier after PICO consolidation and submit it roughly 100 days later. The Conclusions describe writing a dossier within 100 days as unrealistic and warn that some manufacturers may miss the deadline, supporting the claim of significant pressure. (LLM, conf=0.94)
- Not checked yetcites [10] European Commission. Commission Implementing Regulation (EU) 2024/1381 of 23 May 2024 laying down, pursuant to Regulation (EU) 2021/2282 on health technology assessment, procedural rules for the interaction during, exchange of information on, and participation in, the preparation and update of joint clinical assessments of medicinal products for human use at Union level, as well as templates for those joint clinical assessments. 2024. https://eur-lex.europa.eu/legal-content/EN/TXT/?uri=OJ%3AL_202401381. Accessed 22 Jul 2024.
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Supported
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“On the basis of a random sample of 350 abstracts, human verification confirmed that GPT-4o accurately and comprehensively extracted 342 (98%) of all PICOs”
- Also stated in: § Accuracy of the PICO Extractions · plain
“On the basis of the random sample of 350 abstracts, human verification confirmed that GPT-4o accurately and comprehensively extracted 342 (98%) of all PICOs.”
- Also stated in: § Discussion · hedged
“Our LLM-based process extracted PICO data from approximately 683,000 abstracts with up to 98% accuracy, on the basis of a random sample of 350 abstracts.”
§ Automated Mass Extraction of Over 680,000 PICOs from Clinical Study Abstracts Using Generative AI: A Proof-of-Concept Study > Abstract > Results
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Also stated in: § Accuracy of the PICO Extractions · plain
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“The PubMed search returned 682,667 abstracts.”
- Also stated in: § Results · plain
“The PubMed search returned 682,667 abstracts.”
§ Automated Mass Extraction of Over 680,000 PICOs from Clinical Study Abstracts Using Generative AI: A Proof-of-Concept Study > Abstract > Results
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Also stated in: § Results · plain
13 more claims
Create a free account to see all 53 claims and to verify the 35 references still open.
- It may state two separate claims as one. 21
- Probably not a substantial claim. 25
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“In some instances, however, this evaluation was qualitative where the models were applied to large unlabelled, real-life datasets. 46,58,69,48,95,101,102,164”
From Data extraction methods for systematic review (semi)automation: Update of a living systematic review (2025) · cites this paper as [164]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“Finally, different names for the same entity within an abstract are a potential source of problems, 84 which for example makes the extraction of outcomes challenging.”
From Data extraction methods for systematic review (semi)automation: Update of a living systematic review (2025) · cites this paper as [164]
Experimental — accuracy not yet measured
Citations
Cites
Page, M. J., Moher, D., Bossuyt, P. M., Boutron, I., Hoffmann, T. C., Mulrow, C. D., Shamseer, L., Tetzlaff, J. M., Akl, E. A., Brennan, S. E., et al. (2021) · BMJ · doi:10.1136/bmj.n160 · Cited by 13,262 · cited 4×
“…artificial intelligence (GenAI), particularly large language models (LLMs), have demonstrated the potential of this technology to automate key tasks involved in conducting systematic literature reviews (SLRs), widely regarded as the gold standard for synthesizing evidence in healthcare [1–3].”
BackgroundInfluentialMurad, M. H., Asi, N., Alsawas, M., & Alahdab, F. (2016) · Evidence Based Medicine · doi:10.1136/ebmed-2016-110401 · Cited by 1,388
Plan-and-Solve Prompting: Improving Zero-Shot Chain-of-Thought Reasoning by Large Language ModelsPreprint
Wang, L., Xu, W., Lan, Y.-H., Hu, Z.-Q., Lan, Y.-S., Lee, R. K.-W., & Lim, E.-P. (2023) · Annual Meeting of the Association for Computational Linguistics · doi:10.48550/arxiv.2305.04091 · Cited by 946
Prompt Engineering with ChatGPT: A Guide for Academic Writers
Giray, L. (2023) · Annals of Biomedical Engineering · doi:10.1007/s10439-023-03272-4 · Cited by 776 · cited 1×
“The process began with simple input/output (I/O) zero-shot prompting [23], where the LLM was provided with an abstract and asked to extract each PICO element.”
MethodBorah, R., Brown, A. W., Capers, P. L., & Kaiser, K. A. (2017) · BMJ Open · doi:10.1136/bmjopen-2016-012545 · Cited by 737 · cited 2×
“However, traditional SLRs are both time-consuming and costly to complete [4, 11, 32].”
BackgroundMethodPlan-and-Solve Prompting: Improving Zero-Shot Chain-of-Thought Reasoning by Large Language Models
Wang, L., Xu, W., Lan, Y., Hu, Z., Lan, Y., Lee, R. K.-W., & Lim, E.-P. (2023) · Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.18653/v1/2023.acl-long.147 · Cited by 344
Khraisha, Q., Put, S., Kappenberg, J., Warraitch, A., & Hadfield, K. (2024) · Research Synthesis Methods · doi:10.1002/jrsm.1715 · Cited by 269
Khraisha, Q., Put, S., Kappenberg, J., Warraitch, A., & Hadfield, K. (2023) · arXiv · doi:10.48550/arxiv.2310.17526 · Cited by 268
Mathes, T., Klaßen, P., & Pieper, D. (2017) · BMC Medical Research Methodology · doi:10.1186/s12874-017-0431-4 · Cited by 240 · cited 1×
“It is important to note, however, that human data extraction is also not error-free; several studies have reported high error rates, often involving misidentification or placing correct data in the wrong fields [29–31].”
BackgroundAutomated Paper Screening for Clinical Reviews Using Large Language Models
Guo, E., Gupta, M., Deng, J., Park, Y.-J., Paget, M., & Naugler, C. (2023) · arXiv · doi:10.48550/arxiv.2305.00844 · Cited by 230
Research works printed but not linked: 1
- PubMed. PubMed user guide: clinical study categories. 2024. https://pubmed.ncbi.nlm.nih.gov/help/#clinical-study-category-filters. Accessed 27 Aug 2024.
Cited by
Data extraction methods for systematic review (semi)automation: a living systematic review
Schmidt, L., Olorisade, B. K., McGuinness, L. A., Thomas, J., & Higgins, J. P. T. (2021) · F1000Research · doi:10.12688/f1000research.51117.1 · Cited by 106
Data extraction methods for systematic review (semi)automation: Update of a living systematic review
Schmidt, L., Finnerty Mutlu, A. N., Elmore, R., Olorisade, B. K., Thomas, J., & Higgins, J. P. T. (2025) · F1000Research · doi:10.12688/f1000research.51117.3 · Cited by 27
Reason, T., Klijn, S. L., Rawlinson, W. D., Benbow, E., Langham, J., Teitsson, S., Johannesen, K. M., & Malcolm, B. (2025) · PharmacoEconomics - Open · doi:10.1007/s41669-025-00580-4 · Cited by 26
Self-citationSchmidt, L., Campbell, F., Craig, D., Walker, V. R., Rooney, A. A., Schmitt, C., Härtung, T., & Thomas, J. (2025) · Evidence-Based Toxicology · doi:10.1080/2833373x.2025.2546791 · Cited by 13
Use of Large Language Models to Extract Cost-Effectiveness Analysis Data: A Case Study
Gu, X., Zhang, H., Patil, D., Zafarí, Z., Slejko, J. F., & Onukwugha, E. (2025) · Value in Health · doi:10.1016/j.jval.2025.05.008 · Cited by 11
Metadata
- Authors
- Reason, T., Langham, J., & Gimblett, A.
- Corresponding author
- Reason, Tim
- ORCID
- Langham, Julia
- Venue
- Pharmaceutical Medicine
- Published
- 2024-09
- Volume
- 38
- Issue
- 5
- Pages
- 365-372
- ISSN
- 0265-0673 (ISSN-L)
- 1178-2595
- 1179-1993
- PMC
- PMC11473607
- OpenAlex
- W4402858850
- Semantic Scholar
- 74e8265cd1a6230f855b08da22bb932d751493ed
- Cited by
- 16
- References
- 23
- Citations by year
- 2026: 7 · 2025: 9
- FWCI
- 4.47
- Type
- journal article
- Language
- en
- Open access
- hybrid
- doi.org
- Licence
- cc-by-nc
- creativecommons.org/licenses/by-nc/4.0 (tdm)
- creativecommons.org/licenses/by-nc/4.0 (vor, 25 d)
- Locations
- Pharmaceutical Medicine (publishedVersion, cc-by-nc)
- PubMed Central (publishedVersion, cc-by-nc)
- PubMed (publishedVersion)
- Topics
- Social Sciences › Decision Sciences › Statistics, Probability and Uncertainty › Meta-analysis and systematic reviews
- Health Sciences › Medicine › Health Informatics › Artificial Intelligence in Healthcare and Education
- Health Sciences › Medicine › Health Informatics › Biomedical Text Mining and Ontologies
- Keywords
- generative AI, GPT-4o, automated data extraction, systematic reviews, clinical trial abstracts, PubMed, health technology assessment, zero-shot prompting, drug development, OpenAI API, token cost, randomized controlled trials
- MeSH terms
- Abstracting and Indexing, Proof of Concept Study, Systematic Reviews as Topic, Artificial Intelligence, Humans, Technology Assessment, Biomedical, Randomized Controlled Trials as Topic, PubMed
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
The claim verdicts this report counts are experimental: their accuracy is not yet measured.
A language model drew the claims from the paper on 2026-10-04, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).
A second model labelled each claim on 2026-10-04 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).
Cited sources are checked with a language model’s help (qwen3.8-omni-flash and gpt-6-sol).
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Automated Mass Extraction of Over 680,000 PICOs from Clinical Study Abstracts Using Generative AI: A Proof-of-Concept Study. https://app.cochat.ai/papers/10.1007/s40290-024-00539-6
- The paper
- Reason, T., Langham, J., & Gimblett, A. (2024). Automated Mass Extraction of Over 680,000 PICOs from Clinical Study Abstracts Using Generative AI: A Proof-of-Concept Study. Pharmaceutical Medicine. https://doi.org/10.1007/s40290-024-00539-6
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.