Psychosis Relapse Prediction Leveraging Electronic Health Records Data and Natural Language Processing Enrichment Methods
BackgroundIdentifying patients at a high risk of psychosis relapse is crucial for early interventions. A relevant psychiatric clinical context is often recorded in clinical notes; however, the utilization of unstructured data remains limited. This study aimed to develop psychosis-relapse prediction...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2022-04-01
|
| Series: | Frontiers in Psychiatry |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fpsyt.2022.844442/full |
| _version_ | 1818670355321978880 |
|---|---|
| author | Dong Yun Lee Chungsoo Kim Seongwon Lee Seongwon Lee Sang Joon Son Sun-Mi Cho Yong Hyuk Cho Jaegyun Lim Rae Woong Park Rae Woong Park |
| author_facet | Dong Yun Lee Chungsoo Kim Seongwon Lee Seongwon Lee Sang Joon Son Sun-Mi Cho Yong Hyuk Cho Jaegyun Lim Rae Woong Park Rae Woong Park |
| author_sort | Dong Yun Lee |
| collection | DOAJ |
| description | BackgroundIdentifying patients at a high risk of psychosis relapse is crucial for early interventions. A relevant psychiatric clinical context is often recorded in clinical notes; however, the utilization of unstructured data remains limited. This study aimed to develop psychosis-relapse prediction models using various types of clinical notes and structured data.MethodsClinical data were extracted from the electronic health records of the Ajou University Medical Center in South Korea. The study population included patients with psychotic disorders, and outcome was psychosis relapse within 1 year. Using only structured data, we developed an initial prediction model, then three natural language processing (NLP)-enriched models using three types of clinical notes (psychological tests, admission notes, and initial nursing assessment) and one complete model. Latent Dirichlet Allocation was used to cluster the clinical context into similar topics. All models applied the least absolute shrinkage and selection operator logistic regression algorithm. We also performed an external validation using another hospital database.ResultsA total of 330 patients were included, and 62 (18.8%) experienced psychosis relapse. Six predictors were used in the initial model and 10 additional topics from Latent Dirichlet Allocation processing were added in the enriched models. The model derived from all notes showed the highest value of the area under the receiver operating characteristic (AUROC = 0.946) in the internal validation, followed by models based on the psychological test notes, admission notes, initial nursing assessments, and structured data only (0.902, 0.855, 0.798, and 0.784, respectively). The external validation was performed using only the initial nursing assessment note, and the AUROC was 0.616.ConclusionsWe developed prediction models for psychosis relapse using the NLP-enrichment method. Models using clinical notes were more effective than models using only structured data, suggesting the importance of unstructured data in psychosis prediction. |
| first_indexed | 2024-12-17T07:06:47Z |
| format | Article |
| id | doaj.art-66013f0b20ab48ee8496efcc27019ac4 |
| institution | Directory Open Access Journal |
| issn | 1664-0640 |
| language | English |
| last_indexed | 2024-12-17T07:06:47Z |
| publishDate | 2022-04-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Psychiatry |
| spelling | doaj.art-66013f0b20ab48ee8496efcc27019ac42022-12-21T21:59:08ZengFrontiers Media S.A.Frontiers in Psychiatry1664-06402022-04-011310.3389/fpsyt.2022.844442844442Psychosis Relapse Prediction Leveraging Electronic Health Records Data and Natural Language Processing Enrichment MethodsDong Yun Lee0Chungsoo Kim1Seongwon Lee2Seongwon Lee3Sang Joon Son4Sun-Mi Cho5Yong Hyuk Cho6Jaegyun Lim7Rae Woong Park8Rae Woong Park9Department of Biomedical Informatics, Ajou University School of Medicine, Suwon, South KoreaDepartment of Biomedical Sciences, Ajou University Graduate School of Medicine, Suwon, South KoreaDepartment of Biomedical Informatics, Ajou University School of Medicine, Suwon, South KoreaDepartment of Biomedical Sciences, Ajou University Graduate School of Medicine, Suwon, South KoreaDepartment of Psychiatry, Ajou University School of Medicine, Suwon, South KoreaDepartment of Psychiatry, Ajou University School of Medicine, Suwon, South KoreaDepartment of Psychiatry, Ajou University School of Medicine, Suwon, South KoreaDepartment of Laboratory Medicine, Myongji Hospital, Hanyang University College of Medicine, Goyang, South KoreaDepartment of Biomedical Informatics, Ajou University School of Medicine, Suwon, South KoreaDepartment of Biomedical Sciences, Ajou University Graduate School of Medicine, Suwon, South KoreaBackgroundIdentifying patients at a high risk of psychosis relapse is crucial for early interventions. A relevant psychiatric clinical context is often recorded in clinical notes; however, the utilization of unstructured data remains limited. This study aimed to develop psychosis-relapse prediction models using various types of clinical notes and structured data.MethodsClinical data were extracted from the electronic health records of the Ajou University Medical Center in South Korea. The study population included patients with psychotic disorders, and outcome was psychosis relapse within 1 year. Using only structured data, we developed an initial prediction model, then three natural language processing (NLP)-enriched models using three types of clinical notes (psychological tests, admission notes, and initial nursing assessment) and one complete model. Latent Dirichlet Allocation was used to cluster the clinical context into similar topics. All models applied the least absolute shrinkage and selection operator logistic regression algorithm. We also performed an external validation using another hospital database.ResultsA total of 330 patients were included, and 62 (18.8%) experienced psychosis relapse. Six predictors were used in the initial model and 10 additional topics from Latent Dirichlet Allocation processing were added in the enriched models. The model derived from all notes showed the highest value of the area under the receiver operating characteristic (AUROC = 0.946) in the internal validation, followed by models based on the psychological test notes, admission notes, initial nursing assessments, and structured data only (0.902, 0.855, 0.798, and 0.784, respectively). The external validation was performed using only the initial nursing assessment note, and the AUROC was 0.616.ConclusionsWe developed prediction models for psychosis relapse using the NLP-enrichment method. Models using clinical notes were more effective than models using only structured data, suggesting the importance of unstructured data in psychosis prediction.https://www.frontiersin.org/articles/10.3389/fpsyt.2022.844442/fullnatural language processingpsychotic disorderrecurrencemodelsstatisticalelectronic health records |
| spellingShingle | Dong Yun Lee Chungsoo Kim Seongwon Lee Seongwon Lee Sang Joon Son Sun-Mi Cho Yong Hyuk Cho Jaegyun Lim Rae Woong Park Rae Woong Park Psychosis Relapse Prediction Leveraging Electronic Health Records Data and Natural Language Processing Enrichment Methods Frontiers in Psychiatry natural language processing psychotic disorder recurrence models statistical electronic health records |
| title | Psychosis Relapse Prediction Leveraging Electronic Health Records Data and Natural Language Processing Enrichment Methods |
| title_full | Psychosis Relapse Prediction Leveraging Electronic Health Records Data and Natural Language Processing Enrichment Methods |
| title_fullStr | Psychosis Relapse Prediction Leveraging Electronic Health Records Data and Natural Language Processing Enrichment Methods |
| title_full_unstemmed | Psychosis Relapse Prediction Leveraging Electronic Health Records Data and Natural Language Processing Enrichment Methods |
| title_short | Psychosis Relapse Prediction Leveraging Electronic Health Records Data and Natural Language Processing Enrichment Methods |
| title_sort | psychosis relapse prediction leveraging electronic health records data and natural language processing enrichment methods |
| topic | natural language processing psychotic disorder recurrence models statistical electronic health records |
| url | https://www.frontiersin.org/articles/10.3389/fpsyt.2022.844442/full |
| work_keys_str_mv | AT dongyunlee psychosisrelapsepredictionleveragingelectronichealthrecordsdataandnaturallanguageprocessingenrichmentmethods AT chungsookim psychosisrelapsepredictionleveragingelectronichealthrecordsdataandnaturallanguageprocessingenrichmentmethods AT seongwonlee psychosisrelapsepredictionleveragingelectronichealthrecordsdataandnaturallanguageprocessingenrichmentmethods AT seongwonlee psychosisrelapsepredictionleveragingelectronichealthrecordsdataandnaturallanguageprocessingenrichmentmethods AT sangjoonson psychosisrelapsepredictionleveragingelectronichealthrecordsdataandnaturallanguageprocessingenrichmentmethods AT sunmicho psychosisrelapsepredictionleveragingelectronichealthrecordsdataandnaturallanguageprocessingenrichmentmethods AT yonghyukcho psychosisrelapsepredictionleveragingelectronichealthrecordsdataandnaturallanguageprocessingenrichmentmethods AT jaegyunlim psychosisrelapsepredictionleveragingelectronichealthrecordsdataandnaturallanguageprocessingenrichmentmethods AT raewoongpark psychosisrelapsepredictionleveragingelectronichealthrecordsdataandnaturallanguageprocessingenrichmentmethods AT raewoongpark psychosisrelapsepredictionleveragingelectronichealthrecordsdataandnaturallanguageprocessingenrichmentmethods |