Back to AI Research

AI Research

AI-driven Optimisation of Quality of Recovery (QoR)... | AI Research

Key Takeaways

  • AI-driven Optimisation of Quality of Recovery (QoR) in Remote Patient Monitoring Remote patient monitoring (RPM) allows healthcare providers to track a patie...
  • Remote patient monitoring depends on patient-reported data to capture the subjective dimension of recovery that devices cannot measure.
  • The Quality of Recovery (QoR-15) survey is the gold-standard instrument for this purpose.
  • It was designed and validated for occasional in-hospital assessment, yet remote monitoring now administers it to patients daily.
  • In our own post-surgical deployment, only 55% of patients submitted the survey more than 14 days of 30 monitoring days.
Paper AbstractExpand

Remote patient monitoring depends on patient-reported data to capture the subjective dimension of recovery that devices cannot measure. The Quality of Recovery (QoR-15) survey is the gold-standard instrument for this purpose. It was designed and validated for occasional in-hospital assessment, yet remote monitoring now administers it to patients daily. In our own post-surgical deployment, only 55% of patients submitted the survey more than 14 days of 30 monitoring days. We developed QoR-compact, a five-item daily input for the RPM prediction pathway. Setting a deployment-driven target of one-third of the daily items, we exhaustively evaluated all 3,003 five-question subsets of the QoR-15 and tested whether the best of them matches the full instrument in predicting near-term postoperative recovery severity. QoR-compact achieves a mean AUC-ROC of 0.968 (95% CI 0.915-0.988), statistically comparable to the 0.964 baseline obtained with one-third of the items. Patient-level backtesting indicates that it tracks readmission events as faithfully as the full form. Its five items span the physical and psychological axes of recovery: Q3 (feeling rested), Q9 (feeling comfortable and in control), Q10 (general well-being), Q12 (severe pain), and Q14 (feeling worried or anxious). The QoR-15 remains the gold-standard measure of recovery; QoR-compact complements it as a shorter daily input designed for prediction. This parity provides the basis for a prospective study of whether a lighter daily input is, in turn, completed more consistently. External validation on larger cohorts is required before clinical use.

AI-driven Optimisation of Quality of Recovery (QoR) in Remote Patient Monitoring
Remote patient monitoring (RPM) allows healthcare providers to track a patient’s recovery at home using wearable devices and daily surveys. The gold-standard survey for this is the 15-item Quality of Recovery (QoR-15) questionnaire. However, because this survey was originally designed for occasional use in a hospital, asking patients to complete all 15 questions every day at home creates a significant burden, often leading to low completion rates. This paper explores whether a shorter, five-item version of the survey—called "QoR-compact"—can provide the same predictive accuracy as the full 15-item version, potentially improving patient engagement and data quality.

Developing a Smarter, Shorter Survey

To create the compact version, the researchers analyzed data from the HALO-Surgery study, which tracked patients recovering from abdominal or thoracic cancer surgery. They identified that the 15 questions in the original survey often overlap in the information they provide—for example, questions about pain or well-being are often closely related. By exhaustively testing all 3,003 possible five-question combinations, the team identified the subset that most effectively predicted a patient's recovery status.

The Five Key Indicators

The final QoR-compact selection consists of five specific questions that capture both the physical and psychological aspects of recovery:

  • Q3: Feeling rested
  • Q9: Feeling comfortable and in control
  • Q10: General well-being
  • Q12: Severe pain
  • Q14: Feeling worried or anxious
    These items were chosen because they consistently appeared in the highest-performing predictive models and proved to be the most sensitive indicators of a patient's health trajectory.

Performance and Clinical Impact

The researchers found that the five-item QoR-compact performed just as well as the full 15-item survey, achieving a mean AUC-ROC of 0.968 compared to the 0.964 baseline. When tested against real-world data, the compact survey successfully tracked patient recovery and even signaled potential issues, such as hospital readmissions, as effectively as the full version. This suggests that for the purpose of daily monitoring and predicting recovery, a shorter survey can be just as reliable as a longer one.

Important Considerations

While these results are promising, the authors emphasize that the QoR-15 remains the gold standard for comprehensive recovery measurement. The QoR-compact is intended to serve as a complementary tool specifically for daily, AI-driven remote monitoring. Because this study was conducted on a specific cohort of cancer surgery patients, the authors note that external validation on larger, more diverse groups is necessary before the tool is ready for widespread clinical use. Future research will focus on whether this reduced survey length actually leads to higher patient compliance and how it can be integrated with data from wearable devices.

Comments (0)

No comments yet

Be the first to share your thoughts!