Outcome Prediction for Patients with Bipolar Disorder Using Prodromal and Onset Data
Background: Predicting the outcomes of serious mental illnesses including bipolar disorder (BD) is clinically beneficial, yet difficult. Objectives: This study aimed to predict hospitalization and mortality for patients with incident BD using a deep neural network approach. Methods: We randomly samp...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-01-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/13/3/1552 |
| _version_ | 1797625201452646400 |
|---|---|
| author | Yijun Shao Yan Cheng Srikanth Gottipati Qing Zeng-Treitler |
| author_facet | Yijun Shao Yan Cheng Srikanth Gottipati Qing Zeng-Treitler |
| author_sort | Yijun Shao |
| collection | DOAJ |
| description | Background: Predicting the outcomes of serious mental illnesses including bipolar disorder (BD) is clinically beneficial, yet difficult. Objectives: This study aimed to predict hospitalization and mortality for patients with incident BD using a deep neural network approach. Methods: We randomly sampled 20,000 US Veterans with BD. Data on patients’ prior hospitalizations, diagnoses, procedures, medications, note types, vital signs, lab results, and BD symptoms that occurred within 1 year before and at the onset of the incident BD were extracted as features. We then created novel temporal images of patient clinical features both during the prodromal period and at the time of the disease onset. Using each temporal image as a feature, we trained and tested deep neural network learning models to predict the 1-year combined outcome of hospitalization and mortality. Results: The models achieved accuracies of 0.766–0.949 and AUCs of 0.745–0.806 for the combined outcomes. The AUC for predicting mortality was 0.814, while its highest and lowest values for predicting different types of hospitalization were 90.4% and 70.1%, suggesting that some outcomes were more difficult to predict than others. Conclusion: Deep learning using temporal graphics of clinical history is a new and promising analytical approach for mental health outcome prediction. |
| first_indexed | 2024-03-11T09:53:12Z |
| format | Article |
| id | doaj.art-a6239b4812fe4b028a77fc0fedfd6024 |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-11T09:53:12Z |
| publishDate | 2023-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-a6239b4812fe4b028a77fc0fedfd60242023-11-16T16:07:07ZengMDPI AGApplied Sciences2076-34172023-01-01133155210.3390/app13031552Outcome Prediction for Patients with Bipolar Disorder Using Prodromal and Onset DataYijun Shao0Yan Cheng1Srikanth Gottipati2Qing Zeng-Treitler3Biomedical Informatics Center, George Washington University, Washington, DC 20037, USABiomedical Informatics Center, George Washington University, Washington, DC 20037, USABiomedical Informatics Center, George Washington University, Washington, DC 20037, USABiomedical Informatics Center, George Washington University, Washington, DC 20037, USABackground: Predicting the outcomes of serious mental illnesses including bipolar disorder (BD) is clinically beneficial, yet difficult. Objectives: This study aimed to predict hospitalization and mortality for patients with incident BD using a deep neural network approach. Methods: We randomly sampled 20,000 US Veterans with BD. Data on patients’ prior hospitalizations, diagnoses, procedures, medications, note types, vital signs, lab results, and BD symptoms that occurred within 1 year before and at the onset of the incident BD were extracted as features. We then created novel temporal images of patient clinical features both during the prodromal period and at the time of the disease onset. Using each temporal image as a feature, we trained and tested deep neural network learning models to predict the 1-year combined outcome of hospitalization and mortality. Results: The models achieved accuracies of 0.766–0.949 and AUCs of 0.745–0.806 for the combined outcomes. The AUC for predicting mortality was 0.814, while its highest and lowest values for predicting different types of hospitalization were 90.4% and 70.1%, suggesting that some outcomes were more difficult to predict than others. Conclusion: Deep learning using temporal graphics of clinical history is a new and promising analytical approach for mental health outcome prediction.https://www.mdpi.com/2076-3417/13/3/1552predictionbipolar disorderdeep neural networksupport vector machine |
| spellingShingle | Yijun Shao Yan Cheng Srikanth Gottipati Qing Zeng-Treitler Outcome Prediction for Patients with Bipolar Disorder Using Prodromal and Onset Data Applied Sciences prediction bipolar disorder deep neural network support vector machine |
| title | Outcome Prediction for Patients with Bipolar Disorder Using Prodromal and Onset Data |
| title_full | Outcome Prediction for Patients with Bipolar Disorder Using Prodromal and Onset Data |
| title_fullStr | Outcome Prediction for Patients with Bipolar Disorder Using Prodromal and Onset Data |
| title_full_unstemmed | Outcome Prediction for Patients with Bipolar Disorder Using Prodromal and Onset Data |
| title_short | Outcome Prediction for Patients with Bipolar Disorder Using Prodromal and Onset Data |
| title_sort | outcome prediction for patients with bipolar disorder using prodromal and onset data |
| topic | prediction bipolar disorder deep neural network support vector machine |
| url | https://www.mdpi.com/2076-3417/13/3/1552 |
| work_keys_str_mv | AT yijunshao outcomepredictionforpatientswithbipolardisorderusingprodromalandonsetdata AT yancheng outcomepredictionforpatientswithbipolardisorderusingprodromalandonsetdata AT srikanthgottipati outcomepredictionforpatientswithbipolardisorderusingprodromalandonsetdata AT qingzengtreitler outcomepredictionforpatientswithbipolardisorderusingprodromalandonsetdata |