Exploratory application of machine learning methods on patient reported data in the development of supervised models for predicting outcomes
Abstract Background Patient-reported outcome measurements (PROMs) are commonly used in clinical practice to support clinical decision making. However, few studies have investigated machine learning methods for predicting PROMs outcomes and thereby support clinical decision making. Objective This stu...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2022-09-01
|
| Series: | BMC Medical Informatics and Decision Making |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s12911-022-01973-9 |
| _version_ | 1817993949787193344 |
|---|---|
| author | Deepika Verma Duncan Jansen Kerstin Bach Mannes Poel Paul Jarle Mork Wendy Oude Nijeweme d’Hollosy |
| author_facet | Deepika Verma Duncan Jansen Kerstin Bach Mannes Poel Paul Jarle Mork Wendy Oude Nijeweme d’Hollosy |
| author_sort | Deepika Verma |
| collection | DOAJ |
| description | Abstract Background Patient-reported outcome measurements (PROMs) are commonly used in clinical practice to support clinical decision making. However, few studies have investigated machine learning methods for predicting PROMs outcomes and thereby support clinical decision making. Objective This study investigates to what extent different machine learning methods, applied to two different PROMs datasets, can predict outcomes among patients with non-specific neck and/or low back pain. Methods Using two datasets consisting of PROMs from (1) care-seeking low back pain patients in primary care who participated in a randomized controlled trial, and (2) patients with neck and/or low back pain referred to multidisciplinary biopsychosocial rehabilitation, we present data science methods for data prepossessing and evaluate selected regression and classification methods for predicting patient outcomes. Results The results show that there is a potential for machine learning to predict and classify PROMs. The prediction models based on baseline measurements perform well, and the number of predictors can be reduced, which is an advantage for implementation in decision support scenarios. The classification task shows that the dataset does not contain all necessary predictors for the care type classification. Overall, the work presents generalizable machine learning pipelines that can be adapted to other PROMs datasets. Conclusion This study demonstrates the potential of PROMs in predicting short-term patient outcomes. Our results indicate that machine learning methods can be used to exploit the predictive value of PROMs and thereby support clinical decision making, given that the PROMs hold enough predictive power |
| first_indexed | 2024-04-14T01:45:35Z |
| format | Article |
| id | doaj.art-11ddcbc6aa514f628f9fd5f4ee0294d8 |
| institution | Directory Open Access Journal |
| issn | 1472-6947 |
| language | English |
| last_indexed | 2024-04-14T01:45:35Z |
| publishDate | 2022-09-01 |
| publisher | BMC |
| record_format | Article |
| series | BMC Medical Informatics and Decision Making |
| spelling | doaj.art-11ddcbc6aa514f628f9fd5f4ee0294d82022-12-22T02:19:32ZengBMCBMC Medical Informatics and Decision Making1472-69472022-09-0122111110.1186/s12911-022-01973-9Exploratory application of machine learning methods on patient reported data in the development of supervised models for predicting outcomesDeepika Verma0Duncan Jansen1Kerstin Bach2Mannes Poel3Paul Jarle Mork4Wendy Oude Nijeweme d’Hollosy5Department of Computer Science, Norwegian University of Science and TechnologyFaculty of Electrical Engineering, Mathematics and Computer Science, University of TwenteDepartment of Computer Science, Norwegian University of Science and TechnologyFaculty of Electrical Engineering, Mathematics and Computer Science, University of TwenteDepartment of Public Health and Nursing, Norwegian University of Science and TechnologyFaculty of Electrical Engineering, Mathematics and Computer Science, University of TwenteAbstract Background Patient-reported outcome measurements (PROMs) are commonly used in clinical practice to support clinical decision making. However, few studies have investigated machine learning methods for predicting PROMs outcomes and thereby support clinical decision making. Objective This study investigates to what extent different machine learning methods, applied to two different PROMs datasets, can predict outcomes among patients with non-specific neck and/or low back pain. Methods Using two datasets consisting of PROMs from (1) care-seeking low back pain patients in primary care who participated in a randomized controlled trial, and (2) patients with neck and/or low back pain referred to multidisciplinary biopsychosocial rehabilitation, we present data science methods for data prepossessing and evaluate selected regression and classification methods for predicting patient outcomes. Results The results show that there is a potential for machine learning to predict and classify PROMs. The prediction models based on baseline measurements perform well, and the number of predictors can be reduced, which is an advantage for implementation in decision support scenarios. The classification task shows that the dataset does not contain all necessary predictors for the care type classification. Overall, the work presents generalizable machine learning pipelines that can be adapted to other PROMs datasets. Conclusion This study demonstrates the potential of PROMs in predicting short-term patient outcomes. Our results indicate that machine learning methods can be used to exploit the predictive value of PROMs and thereby support clinical decision making, given that the PROMs hold enough predictive powerhttps://doi.org/10.1186/s12911-022-01973-9Machine learningLow-back painNeck painPatient-reported outcomesSelf-reported measuresOutcome Prediction |
| spellingShingle | Deepika Verma Duncan Jansen Kerstin Bach Mannes Poel Paul Jarle Mork Wendy Oude Nijeweme d’Hollosy Exploratory application of machine learning methods on patient reported data in the development of supervised models for predicting outcomes BMC Medical Informatics and Decision Making Machine learning Low-back pain Neck pain Patient-reported outcomes Self-reported measures Outcome Prediction |
| title | Exploratory application of machine learning methods on patient reported data in the development of supervised models for predicting outcomes |
| title_full | Exploratory application of machine learning methods on patient reported data in the development of supervised models for predicting outcomes |
| title_fullStr | Exploratory application of machine learning methods on patient reported data in the development of supervised models for predicting outcomes |
| title_full_unstemmed | Exploratory application of machine learning methods on patient reported data in the development of supervised models for predicting outcomes |
| title_short | Exploratory application of machine learning methods on patient reported data in the development of supervised models for predicting outcomes |
| title_sort | exploratory application of machine learning methods on patient reported data in the development of supervised models for predicting outcomes |
| topic | Machine learning Low-back pain Neck pain Patient-reported outcomes Self-reported measures Outcome Prediction |
| url | https://doi.org/10.1186/s12911-022-01973-9 |
| work_keys_str_mv | AT deepikaverma exploratoryapplicationofmachinelearningmethodsonpatientreporteddatainthedevelopmentofsupervisedmodelsforpredictingoutcomes AT duncanjansen exploratoryapplicationofmachinelearningmethodsonpatientreporteddatainthedevelopmentofsupervisedmodelsforpredictingoutcomes AT kerstinbach exploratoryapplicationofmachinelearningmethodsonpatientreporteddatainthedevelopmentofsupervisedmodelsforpredictingoutcomes AT mannespoel exploratoryapplicationofmachinelearningmethodsonpatientreporteddatainthedevelopmentofsupervisedmodelsforpredictingoutcomes AT pauljarlemork exploratoryapplicationofmachinelearningmethodsonpatientreporteddatainthedevelopmentofsupervisedmodelsforpredictingoutcomes AT wendyoudenijewemedhollosy exploratoryapplicationofmachinelearningmethodsonpatientreporteddatainthedevelopmentofsupervisedmodelsforpredictingoutcomes |