Harmonizing patient-reported outcome measures for nasal complaints using traditional and machine learning methods
Clinical Snapshot
PICO Framework
| P — Population | 1324 unique patients with nasal complaints who completed nasal obstruction measurement instruments |
| I — Intervention | Machine learning methods (linear regression, random forest regression, support vector machine regression, neural network) for harmonizing patient-reported outcome measures |
| C — Comparator | Traditional harmonization methods (linear equating and Item Response Theory) |
| O — Outcomes | Root-mean-square error (RMSE) of differences between predicted and observed scores in harmonizing NOSE, Utrecht-Q, and SCHNOS scores to ENFAS equivalents |
Bottom Line
This methodological study demonstrates that machine learning approaches outperform traditional statistical methods for harmonizing patient-reported outcome measures in nasal obstruction assessment. Using data from 1324 patients who completed four validated nasal complaint instruments (NOSE, Utrecht-Q, SCHNOS, ENFAS), the researchers found that machine learning methods achieved superior prediction accuracy compared to linear equating and Item Response Theory. While the study provides valuable methodological insights for researchers conducting meta-analyses or pooled analyses of nasal obstruction data, clinical implementation would require additional validation and consideration of practical constraints. The findings suggest potential for improved data integration in ENT research, though more detailed reporting of results and patient characteristics would strengthen the evidence base.
Key Findings
P Value: Not reported in abstract
Effect Size: Machine learning methods achieved lowest RMSE values compared to traditional methods
Primary Outcome: Root-mean-square error (RMSE) for harmonization accuracy
Nnt Or Sensitivity: 5-fold cross-validation used for model validation
Confidence Interval: Not reported in abstract
Clinical Application
Requires computational resources and expertise for implementation in clinical practice Relevant for Australian ENT practice and research; could support TGA submissions requiring PROM harmonization and facilitate multi-centre studies across Australian hospitals Patients with nasal complaints undergoing assessment with patient-reported outcome measures
Abstract
BACKGROUND: Nasal obstruction measurement instruments are widely used in the field of nasal surgery. There are various scales that measure nasal obstruction and they differ regarding the number of items, their wording, and the type of response options. In order to pool the data and analyze it together, it is necessary to harmonize it so that we can compare participants' nasal obstruction scores irrespective of instrument they filled in. Data harmonization is still not used in the field of nasal obstruction assessment. THE AIM: The aim of this study was to find the best harmonization method in terms of predicting the scores on a target instrument based on the scores from another instrument as precise as possible in the case of four different nasal complaints instruments. A method was sought to find a transformation of scores on the NOSE, Utrecht-Q and SCHNOS that makes them equivalent to ENFAS scores. METHODS: A total of 1324 unique patients completed all four measurement instruments. We tried linear equating, Item Response Theory (IRT), and the following machine learning methods: linear regression, random forest regression, support vector machine regression, and neural network. We used the root-mean-square error (RMSE) of differences between predicted and observed scores to evaluate the quality of harmonization in 5-fold cross-validation. RESULTS: The ML methods gave overall the best results (the lowest RMSEs) and outperformed IRT (which is considered as a common choice for data harmonization in psychometrics). CONCLUSION: The ML methods led to the best quality of the results, confirming their strong potential for data harmonization. This study shows that next to linear equating and IRT that are commonly used for data harmonization, we can also use ML methods for the same purpose and, by doing so, to even increase the quality of the harmonization in certain use cases.
References
- 1.Jović, M., Hof, E., Haeri, M. A., Hoorweg, J. J., & van den Berg, S. M. (2026). Harmonizing patient-reported outcome measures for nasal complaints using traditional and machine learning methods. International Journal of Medical Informatics, 106319. https://doi.org/10.1016/j.ijmedinf.2026.106319
This content is for educational purposes for healthcare professionals only and does not constitute clinical advice. Clinical decisions should be based on individual patient assessment, current guidelines, and appropriate specialist consultation. Editorial Standards · Privacy Policy · Terms of Service