Wisdom of patients: predicting the quality of care using aggregated patient feedback

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.

http://ift.tt/2rztKuA