MétaCan
Menu
Back to cohort
Record W4396901591 · doi:10.1016/j.esmoop.2024.103007

Perception of cure in prostate cancer: human-led and artificial intelligence-assisted landscape review and linguistic analysis of literature, social media and policy documents

2024· review· en· W4396901591 on OpenAlexaff
Eleni Efstathiou, Axel S. Merseburger, Andrea Liew, K. Kurtyka, Oishika Panda, Danielle E. Dalechek, Anne Christine Stender Heerdegen, Rishi Jain, Francesco De Solda, Shane McCarthy, Sabine Brookman‐May, Suneel Mundle, Wellam F. Yu Ko, Laura Krabbe

Bibliographic record

VenueESMO Open · 2024
Typereview
Languageen
FieldMedicine
TopicProstate Cancer Diagnosis and Treatment
Canadian institutionsUniversity of British Columbia
FundersJohnson and Johnson
KeywordsContext (archaeology)Social mediaKey (lock)PsychologyMedicineComputer scienceWorld Wide Web

Abstract

fetched live from OpenAlex

•AI can be used successfully in qualitative research involving large language-based databases.•Academic researchers, clinicians, policymakers and the general public actively discuss cure in early-stage PC.•Stakeholders use different definitions of and context for cure in their communications about cure.•Cure and cure-related key words are positively perceived by all stakeholders. BackgroundUnderstanding stakeholders’ perception of cure in prostate cancer (PC) is essential to preparing for effective communication about emerging treatments with curative intent. This study used artificial intelligence (AI) for landscape review and linguistic analysis of definition, context and value of cure among stakeholders in PC.Materials and methodsSubject-matter experts (SMEs) selected cure-related key words using Elicit, a semantic literature search engine, and extracted hits containing the key words from Medline, Sermo and Overton, representing academic researchers, health care providers (HCPs) and policymakers, respectively. NetBase Quid, a social media analytics and natural language processing tool, was used to carry out key word searches in social media (representing the general public). NetBase Quid analysed linguistics of key word-specific hit sets for key word count, geolocation and sentiments. SMEs qualitatively summarised key word-specific insights. Contextual terms frequently occurring with key words were identified and quantified.ResultsSMEs identified seven key words applicable to PC (number of acquired hits) across four platforms: Cure (12429), Survivor (6063), Remission (1904), Survivorship (1179), Curative intent (432), No evidence of disease (381) and Complete remission (83). Most commonly used key words were Cure by the general public and HCPs (11815 and 224 hits), Survivorship by academic researchers and Survivor by policymakers (378 hits each). All stakeholders discussed Cure and cure-related key words primarily in early-stage PC and associated them with positive sentiments. All stakeholders defined cure differently but communicated about it in relation to disease measurements (e.g. prostate-specific antigen) or surgery. Stakeholders preferred different terms when discussing cure in PC: Cure (academic researchers), Cure rates (HCPs), Potential cure and Survivor/Survivorship (policymakers) and Cure and Survivor (general public).ConclusionThis human-led, AI-assisted large-scale qualitative language-based research revealed that cure was commonly discussed by academic researchers, HCPs, policymakers and the general public, especially in early-stage PC. Stakeholders defined and contextualised cure in their communications differently and associated it with positive value. Understanding stakeholders’ perception of cure in prostate cancer (PC) is essential to preparing for effective communication about emerging treatments with curative intent. This study used artificial intelligence (AI) for landscape review and linguistic analysis of definition, context and value of cure among stakeholders in PC. Subject-matter experts (SMEs) selected cure-related key words using Elicit, a semantic literature search engine, and extracted hits containing the key words from Medline, Sermo and Overton, representing academic researchers, health care providers (HCPs) and policymakers, respectively. NetBase Quid, a social media analytics and natural language processing tool, was used to carry out key word searches in social media (representing the general public). NetBase Quid analysed linguistics of key word-specific hit sets for key word count, geolocation and sentiments. SMEs qualitatively summarised key word-specific insights. Contextual terms frequently occurring with key words were identified and quantified. SMEs identified seven key words applicable to PC (number of acquired hits) across four platforms: Cure (12429), Survivor (6063), Remission (1904), Survivorship (1179), Curative intent (432), No evidence of disease (381) and Complete remission (83). Most commonly used key words were Cure by the general public and HCPs (11815 and 224 hits), Survivorship by academic researchers and Survivor by policymakers (378 hits each). All stakeholders discussed Cure and cure-related key words primarily in early-stage PC and associated them with positive sentiments. All stakeholders defined cure differently but communicated about it in relation to disease measurements (e.g. prostate-specific antigen) or surgery. Stakeholders preferred different terms when discussing cure in PC: Cure (academic researchers), Cure rates (HCPs), Potential cure and Survivor/Survivorship (policymakers) and Cure and Survivor (general public). This human-led, AI-assisted large-scale qualitative language-based research revealed that cure was commonly discussed by academic researchers, HCPs, policymakers and the general public, especially in early-stage PC. Stakeholders defined and contextualised cure in their communications differently and associated it with positive value.

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 distilled prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.

metaresearch head score (Codex)0.000
metaresearch head score (Gemma)0.000
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Other design · Consensus signal: none
GenreCandidate signal: Review · Consensus signal: Review
Teacher disagreement score0.917
Threshold uncertainty score0.890

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0000.000
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0030.000
Bibliometrics0.0010.001
Science and technology studies0.0000.000
Scholarly communication0.0000.000
Open science0.0000.000
Research integrity0.0000.000
Insufficient payload (model declined to judge)0.0000.000

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.

Opus teacher head0.071
GPT teacher head0.451
Teacher spread0.380 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one teacher head, not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designOther design
Domainnot available
GenreReview

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".

Quick stats

Citations1
Published2024
Admission routes1
Has abstractyes

Explore more

Same venueESMO OpenSame topicProstate Cancer Diagnosis and TreatmentFrench-language works237,207