EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Beyond ratings: a condition-aware natural language processing framework for drug effectiveness decomposition, regulatory benchmarking, safety signal detection, and adversarial robustness assessment using patient-generated reviews

Doaa Al-Turkey, Rasheed Mohammad iD, Tatiana Grieshofer

Naunyn-Schmiedeberg's Archives of Pharmacology · 12.11.2026

DOI: 10.1007/s00210-026-06080-4 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Naunyn-Schmiedeberg's Archives of Pharmacology, online erschienen am 12.11.2026. Verfasst von Doaa Al-Turkey und 2 weiteren Autor:innen. Beteiligte Einrichtung: Computing, Engineering and the Built Environment, Birmingham City University, Birmingham, UK. Die Arbeit nennt 49 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Patient-generated drug reviews offer a large source of real-world evidence on perceived medication effectiveness, yet existing computational analyses predominantly model effectiveness as a single drug-level estimate, ignoring variation across therapeutic indications. This study introduces an integrated four-module natural language processing (NLP) framework that extends patient review analytics from aggregate rating prediction toward condition-aware pharmacovigilance support. Module 1 decomposes drug effectiveness across 1880 drug–condition pairs (623 drugs; 131 conditions), showing that the same medication can differ by up to 4.18 rating points across indications (mean cross-condition range = 0.98 rating points on a 1–10 scale among the 533 drugs observed in at least two conditions). A condition-aware model combining term frequency–inverse document frequency (TF-IDF) features with linear support vector regression (SVR) achieves a coefficient of determination ( R 2 ) of 0.749 (95% confidence interval (CI) 0.731–0.767), comparable to a drug-level model ( R 2 = 0.744), while providing indication-specific estimates. Item-based collaborative filtering imputes unobserved drug–condition pairs with a hold-out root mean squared error (RMSE) of 0.716, no better than a simple additive drug + condition baseline. Module 2 benchmarks patient-derived scores against documented U.S. Food and Drug Administration (FDA) safety actions for 230 matched drugs. FDA-actioned drugs were rated slightly higher (Cohen’s d = − 0.297, 95% CI − 0.431 to − 0.163; area under the receiver operating characteristic curve (AUC) = 0.592), but this difference was largely explained by their much higher review volume: it disappeared with unshrunk ratings ( d = − 0.045) and was attenuated after covariate adjustment (odds ratio 1.12, 95% CI 0.95–1.31), although a small difference persisted among drugs with at least 50 reviews ( d = − 0.285). Module 3 constructs a composite safety concern score from four lexicon-based dimensions. The score discriminated FDA-actioned drugs modestly (AUC = 0.568, 95% CI 0.516–0.619), including among drugs with at least 50 reviews (AUC = 0.593) and with corrected lexicon matching (AUC = 0.574); discontinuation language was the most consistent discriminating feature. The module flags 141 “blind-spot” drugs combining high ratings with high safety-concern language; many flags reflected lexicon terms that name the treated condition, so blind spots are hypothesis-generating only. Module 4 evaluates robustness to simple text perturbations and template-based fake review injection. TF-IDF with SVR and TF-IDF with Ridge regression yield robustness indices of 0.991 and 0.994, respectively; approximately 50 (SVR) and 61 (Ridge; extrapolated) injected reviews were required to shift a prediction by one rating point for sparsely reviewed target drugs. Condition-aware effectiveness estimates and linguistic safety signals can complement, but not replace, established pharmacovigilance sources.

Schlagwörter

Stichwörter der Autor:innen

Adversarial robustnessCollaborative filteringCondition-aware effectiveness predictionDrug–condition decompositionFDA safety actionsNatural language processingPatient-generated drug reviewsPharmacovigilanceTerm frequency–inverse document frequency

Autor:innen und Institutionen

  • Computing, Engineering and the Built Environment, Birmingham City University, Birmingham, UK.
  • Computing, Engineering and the Built Environment, Birmingham City University, Birmingham, UK. rasheed.mohammad@bcu.ac.uk.
  • School of English, Birmingham City University, Birmingham, UK.

ORCID-Profile: Rasheed Mohammad

Zitieren

APA

Al-Turkey, D., Mohammad, R., & Grieshofer, T. (2026). Beyond ratings: a condition-aware natural language processing framework for drug effectiveness decomposition, regulatory benchmarking, safety signal detection, and adversarial robustness assessment using patient-generated reviews. Naunyn-Schmiedeberg's Archives of Pharmacology. https://doi.org/10.1007/s00210-026-06080-4

Vancouver

Al-Turkey D, Mohammad R, Grieshofer T. Beyond ratings: a condition-aware natural language processing framework for drug effectiveness decomposition, regulatory benchmarking, safety signal detection, and adversarial robustness assessment using patient-generated reviews. Naunyn-Schmiedeberg's Archives of Pharmacology. 2026. doi:10.1007/s00210-026-06080-4

BibTeX
@article{AlTurkey2026,
  author = {Al-Turkey, Doaa and Mohammad, Rasheed and Grieshofer, Tatiana},
  title = {Beyond ratings: a condition-aware natural language processing framework for drug effectiveness decomposition, regulatory benchmarking, safety signal detection, and adversarial robustness assessment using patient-generated reviews},
  journal = {Naunyn-Schmiedeberg's Archives of Pharmacology},
  year = {2026},
  doi = {10.1007/s00210-026-06080-4}
}
Kostenlos starten →