Generating actionable evidence from free-text feedback to improve maternity and acute hospital experiences: A computational text analytics & predictive modelling approach
Bibliographic record
Abstract
Abstract Background Patient experience surveys are a key source of evidence for supporting decision-making and quality improvement in healthcare services. These surveys contain two main types of questions: closed and open-ended, asking about patients’ care experiences. Apart from the knowledge obtained from analysing closed-ended questions, invaluable insights can be gleaned from free-text data. Advanced analytics techniques are increasingly used to harness free-text data, yet existing approaches do not offer the rigour required to support formal decision-making through free-text. Methods This study addresses the challenge of effectively and rigorously analysing patients’ free-text feedback to improve maternity and acute hospital services in Ireland. Aspects of healthcare services (i.e. themes) that could be improved were determined using computational text analytics and predictive modelling. Themes extracted from comments were prioritised based on volume, the intensity of negative affect expressed in the texts, and the estimated influence of the themes on overall patient satisfaction. Results Results demonstrate the viability of producing rigorous evidence for prioritising interventions to improve healthcare services based on free-text feedback. Specifically, consistency in advice and support in breastfeeding were among the most important issues for maternity services. For acute hospital services, meals quality and access, A&E waiting time, ward hygiene and communication at discharge were among the most important issues. Women also wanted more emphasis on prior birth experience and complications in future maternity care surveys. Conclusions Advances in computational text modelling enable the extraction of concrete and actionable insights from the analysis of free-text data. This approach also allows decision-makers to prioritise emergent themes and inform actions that will positively impact overall patient satisfaction.
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 imitationNot 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.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.061 | 0.259 |
| Meta-epidemiology (narrow) | 0.002 | 0.001 |
| Meta-epidemiology (broad) | 0.002 | 0.003 |
| Bibliometrics | 0.012 | 0.008 |
| Science and technology studies | 0.001 | 0.003 |
| Scholarly communication | 0.008 | 0.005 |
| Open science | 0.004 | 0.005 |
| Research integrity | 0.003 | 0.003 |
| Insufficient payload (model declined to judge) | 0.007 | 0.001 |
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.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
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".