MétaCan
Menu
Back to cohort
Record W4406187159 · doi:10.1101/2025.01.06.25320076

From Patient Voices to Policy: Data Analytics Reveals Patterns in Ontario’s Hospital Feedback

2025· preprint· en· W4406187159 on OpenAlexafffundabout
Pourya Momtaz, Mohammad Noaeen, Konrad Samsel, Neil Seeman, Robert Cribb, Syed Ishtiaque Ahmed, Amol A. Verma, Dionne M. Aleman, Zahra Shakeri

Bibliographic record

VenuemedRxiv · 2025
Typepreprint
Languageen
FieldHealth Professions
TopicPatient Satisfaction in Healthcare
Canadian institutionsSchwartz/Reisman Emergency Medicine InstituteSt. Michael's HospitalPublic Health OntarioUniversity of Toronto
FundersNatural Sciences and Engineering Research Council of CanadaUniversity of Toronto
KeywordsAnalyticsData scienceBusinessPolitical sciencePsychologyComputer science

Abstract

fetched live from OpenAlex

Abstract Patient satisfaction is a central measure of high-performing healthcare systems, yet real-world evaluations at scale remain challenging. In this study, we analyzed over 120,000 de-identified patient reviews from 45 Ontario hospitals between 2015 and 2022. We applied natural language processing (NLP), including named entity recognition (NER), to extract insights on hospital wards, patient health outcomes, and medical conditions. We also examined regional demographic data to identify potential disparities emerging during the COVID-19 pandemic. Our findings show that nearly 80% of the hospitals studied had fewer than 50% positive reviews, exposing systemic gaps in meeting patient needs. In particular, negative reviews decreased during COVID-19, suggesting possible shifts in patient expectations or increased appreciation for strained healthcare workers; however, certain units, such as intensive care and cardiology, experienced fewer positive ratings, reflecting pandemic and related pressures on critical care services. ‘Anxiety’ emerged as a recurrent concern in negative reviews, pointing to the growing awareness of mental health needs. Furthermore, hospitals located in regions with higher percentages of visible minority and low-income populations initially saw higher positive review rates before COVID-19, but this trend reversed after 2020. Collectively, these results demonstrate how large-scale unstructured data can identify fundamental drivers of patient satisfaction, while underscoring the urgent need for adaptive strategies to address anxiety and combat systemic inequalities. Author Summary Understanding what patients think and feel about hospital care can lead to better health services and outcomes. We analyzed more than 120,000 patient reviews from 45 Ontario hospitals between 2015 and 2022. Our study combined natural language processing techniques to identify key concerns, including anxiety, billing difficulties, and interactions with staff. We also compared patient experiences before and during the COVID-19 pandemic, uncovering a drop in negative reviews and a rise in positive reviews, though certain units—such as intensive care—faced growing pressure. A particularly revealing finding was that hospitals located in regions with higher numbers of visible minority and low-income groups received more positive feedback before the pandemic, but this reversed after 2020. These patterns hint at deeper systemic issues, especially during times of crisis. By pinpointing the main drivers of satisfaction and dissatisfaction, our work highlights the need for healthcare services that prioritize kindness, clear communication, efficient operations, and equitable access for all. Lessons from this research could guide targeted improvements, ensuring that every patient, regardless of background or income, receives the compassionate and timely care they deserve. Our hope is that policymakers, hospital administrators, and community advocates will use these findings to shape policies that improve patient trust and well-being.

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 imitation

Not 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.

metaresearch head score (Codex)0.008
metaresearch head score (Gemma)0.075
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Observational · Consensus signal: Observational
GenreCandidate signal: Empirical · Consensus signal: Empirical
Teacher disagreement score0.462
Threshold uncertainty score0.930

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0080.075
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0040.009
Science and technology studies0.0010.001
Scholarly communication0.0030.001
Open science0.0010.002
Research integrity0.0010.001
Insufficient payload (model declined to judge)0.0010.000

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 head0.145
GPT teacher head0.439
Teacher spread0.294 · 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 source (direct Gemma or distilled Codex), not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designObservational
Domainnot available
GenreEmpirical

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
Published2025
Admission routes3
Has abstractyes

Explore more

Same venuemedRxivSame topicPatient Satisfaction in HealthcareFrench-language works237,207