Intimate Partner Violence and Injury Prediction From Radiology Reports
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2020
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866910744018157568 |
|---|---|
| author | Chen, Irene Y. Alsentzer, Emily Park, Hyesun Thomas, Richard Gosangi, Babina Gujrathi, Rahul Khurana, Bharti |
| author_facet | Chen, Irene Y. Alsentzer, Emily Park, Hyesun Thomas, Richard Gosangi, Babina Gujrathi, Rahul Khurana, Bharti |
| contents | Intimate partner violence (IPV) is an urgent, prevalent, and under-detected public health issue. We present machine learning models to assess patients for IPV and injury. We train the predictive algorithms on radiology reports with 1) IPV labels based on entry to a violence prevention program and 2) injury labels provided by emergency radiology fellowship-trained physicians. Our dataset includes 34,642 radiology reports and 1479 patients of IPV victims and control patients. Our best model predicts IPV a median of 3.08 years before violence prevention program entry with a sensitivity of 64% and a specificity of 95%. We conduct error analysis to determine for which patients our model has especially high or low performance and discuss next steps for a deployed clinical risk model. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2009_09084 |
| institution | arXiv |
| publishDate | 2020 |
| record_format | arxiv |
| spellingShingle | Intimate Partner Violence and Injury Prediction From Radiology Reports Chen, Irene Y. Alsentzer, Emily Park, Hyesun Thomas, Richard Gosangi, Babina Gujrathi, Rahul Khurana, Bharti Computers and Society Computation and Language Machine Learning Intimate partner violence (IPV) is an urgent, prevalent, and under-detected public health issue. We present machine learning models to assess patients for IPV and injury. We train the predictive algorithms on radiology reports with 1) IPV labels based on entry to a violence prevention program and 2) injury labels provided by emergency radiology fellowship-trained physicians. Our dataset includes 34,642 radiology reports and 1479 patients of IPV victims and control patients. Our best model predicts IPV a median of 3.08 years before violence prevention program entry with a sensitivity of 64% and a specificity of 95%. We conduct error analysis to determine for which patients our model has especially high or low performance and discuss next steps for a deployed clinical risk model. |
| title | Intimate Partner Violence and Injury Prediction From Radiology Reports |
| topic | Computers and Society Computation and Language Machine Learning |
| url | https://arxiv.org/abs/2009.09084 |