Article Text

Download PDFPDF

Wisdom of patients: predicting the quality of care using aggregated patient feedback
  1. Alex Griffiths1,
  2. Meghan P Leaver2
  1. 1 Centre for Analysis of Risk and Regulation, London School of Economics and Political Science, London, UK
  2. 2 Department of Psychological and Behavioural Science, London School of Economics and Political Science, London, UK
  1. Correspondence to Dr Alex Griffiths, London School of Economics and Political Science, Centre for Analysis of Risk and Regulation, London WC2A 2AE, UK; a.griffiths{at}


Background The Care Quality Commission (CQC) is responsible for ensuring the quality of healthcare in England. To that end, CQC has developed statistical surveillance tools that periodically aggregate large numbers of quantitative performance measures to identify risks to the quality of care and prioritise its limited inspection resource. These tools have, however, failed to successfully identify poor-quality providers. Facing continued budget cuts, CQC is now further reliant on an ‘intelligence-driven’, risk-based approach to prioritising inspections and a new effective tool is required.

Objective To determine whether the near real-time, automated collection and aggregation of multiple sources of patient feedback can provide a collective judgement that effectively identifies risks to the quality of care, and hence can be used to help prioritise inspections.

Methods Our Patient Voice Tracking System combines patient feedback from NHS Choices, Patient Opinion, Facebook and Twitter to form a near real-time collective judgement score for acute hospitals and trusts on any given date. The predictive ability of the collective judgement score is evaluated through a logistic regression analysis of the relationship between the collective judgement score on the start date of 456 hospital and trust-level inspections, and the subsequent inspection outcomes.

Results Aggregating patient feedback increases the volume and diversity of patient-centred insights into the quality of care. There is a positive association between the resulting collective judgement score and subsequent inspection outcomes (OR for being rated ‘Inadequate’ compared with ‘Requires improvement’ 0.35 (95% CI 0.16 to 0.76), Requires improvement/Good OR 0.23 (95% CI 0.12 to 0.44), and Good/Outstanding OR 0.13 (95% CI 0.02 to 0.84), with p<0.05 for all).

Conclusions The collective judgement score can successfully identify a high-risk group of organisations for inspection, is available in near real time and is available at a more granular level than the majority of existing data sets. The collective judgement score could therefore be used to help prioritise inspections.

  • patient-centred care
  • patient satisfaction
  • quality measurement
  • risk management

This is an Open Access article distributed in accordance with the terms of the Creative Commons Attribution (CC BY 4.0) license, which permits others to distribute, remix, adapt and build upon this work, for commercial use, provided the original work is properly cited. See:

View Full Text

Statistics from


  • Twitter @AlexG_aca

  • Contributors AG conceived the study, gathered the data and performed the analysis. MPL led on the safety aspects of the study and devised the systematic approach for coding the Twitter data. Both authors developed the argument of the study as it progressed and cowrote the article.

  • Funding We gratefully acknowledge the financial support provided for this project by the Economic and Social Research Council (Grant Ref: ES/N018869/1) under the Open Research Area Scheme (Project Title: QUAD — Quantification, Administrative Capacity and Democracy). The QUAD project is an international project co-funded by the Agence Nationale de la Recherche (ANR, France), DeutscheForschungsgemeinschaft (DFG, Germany), Economic and Social Research Council (ESRC, UK), and the Nederlands Organisatie voor Wetenschappelijk Onderzoek (NWO, Netherlands).

  • Competing interests None declared.

  • Provenance and peer review Not commissioned; externally peer reviewed.

  • Data sharing statement The data are publicly available. Details of how to obtain the data are listed in the Technical Appendix.

Request Permissions

If you wish to reuse any or all of this article please use the link below which will take you to the Copyright Clearance Center’s RightsLink service. You will be able to get a quick price and instant permission to reuse the content in many different ways.

Linked Articles