Machine learning prediction of dropping out of outpatients with alcohol use disorders
<h4>Background</h4> Alcohol use disorder (AUD) is a chronic disease with a higher recurrence rate than that of other mental illnesses. Moreover, it requires continuous outpatient treatment for the patient to maintain abstinence. However, with a low probability of these patients to contin...
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Public Library of Science (PLoS)
2021-01-01
|
| Series: | PLoS ONE |
| Online Access: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8328309/?tool=EBI |
| _version_ | 1818357107963985920 |
|---|---|
| author | So Jin Park Sun Jung Lee HyungMin Kim Jae Kwon Kim Ji-Won Chun Soo-Jung Lee Hae Kook Lee Dai Jin Kim In Young Choi |
| author_facet | So Jin Park Sun Jung Lee HyungMin Kim Jae Kwon Kim Ji-Won Chun Soo-Jung Lee Hae Kook Lee Dai Jin Kim In Young Choi |
| author_sort | So Jin Park |
| collection | DOAJ |
| description | <h4>Background</h4> Alcohol use disorder (AUD) is a chronic disease with a higher recurrence rate than that of other mental illnesses. Moreover, it requires continuous outpatient treatment for the patient to maintain abstinence. However, with a low probability of these patients to continue outpatient treatment, predicting and managing patients who might discontinue treatment becomes necessary. Accordingly, we developed a machine learning (ML) algorithm to predict which the risk of patients dropping out of outpatient treatment schemes. <h4>Methods</h4> A total of 839 patients were selected out of 2,206 patients admitted for AUD in three hospitals under the Catholic Central Medical Center in Korea. We implemented six ML models—logistic regression, support vector machine, k-nearest neighbor, random forest, neural network, and AdaBoost—and compared the prediction performances thereof. <h4>Results</h4> Among the six models, AdaBoost was selected as the final model for recommended use owing to its area under the receiver operating characteristic curve (AUROC) of 0.72. The four variables affecting the prediction based on feature importance were the length of hospitalization, age, residential area, and diabetes. <h4>Conclusion</h4> An ML algorithm was developed herein to predict the risk of patients with AUD in Korea discontinuing outpatient treatment. By testing and validating various machine learning models, we determined the best performing model, AdaBoost, as the final model for recommended use. Using this model, clinicians can manage patients with high risks of discontinuing treatment and establish patient-specific treatment strategies. Therefore, our model can potentially enable patients with AUD to successfully complete their treatments by identifying them before they can drop out. |
| first_indexed | 2024-12-13T20:07:51Z |
| format | Article |
| id | doaj.art-a5dadf44c4514476a53e049ec38ab10e |
| institution | Directory Open Access Journal |
| issn | 1932-6203 |
| language | English |
| last_indexed | 2024-12-13T20:07:51Z |
| publishDate | 2021-01-01 |
| publisher | Public Library of Science (PLoS) |
| record_format | Article |
| series | PLoS ONE |
| spelling | doaj.art-a5dadf44c4514476a53e049ec38ab10e2022-12-21T23:32:58ZengPublic Library of Science (PLoS)PLoS ONE1932-62032021-01-01168Machine learning prediction of dropping out of outpatients with alcohol use disordersSo Jin ParkSun Jung LeeHyungMin KimJae Kwon KimJi-Won ChunSoo-Jung LeeHae Kook LeeDai Jin KimIn Young Choi<h4>Background</h4> Alcohol use disorder (AUD) is a chronic disease with a higher recurrence rate than that of other mental illnesses. Moreover, it requires continuous outpatient treatment for the patient to maintain abstinence. However, with a low probability of these patients to continue outpatient treatment, predicting and managing patients who might discontinue treatment becomes necessary. Accordingly, we developed a machine learning (ML) algorithm to predict which the risk of patients dropping out of outpatient treatment schemes. <h4>Methods</h4> A total of 839 patients were selected out of 2,206 patients admitted for AUD in three hospitals under the Catholic Central Medical Center in Korea. We implemented six ML models—logistic regression, support vector machine, k-nearest neighbor, random forest, neural network, and AdaBoost—and compared the prediction performances thereof. <h4>Results</h4> Among the six models, AdaBoost was selected as the final model for recommended use owing to its area under the receiver operating characteristic curve (AUROC) of 0.72. The four variables affecting the prediction based on feature importance were the length of hospitalization, age, residential area, and diabetes. <h4>Conclusion</h4> An ML algorithm was developed herein to predict the risk of patients with AUD in Korea discontinuing outpatient treatment. By testing and validating various machine learning models, we determined the best performing model, AdaBoost, as the final model for recommended use. Using this model, clinicians can manage patients with high risks of discontinuing treatment and establish patient-specific treatment strategies. Therefore, our model can potentially enable patients with AUD to successfully complete their treatments by identifying them before they can drop out.https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8328309/?tool=EBI |
| spellingShingle | So Jin Park Sun Jung Lee HyungMin Kim Jae Kwon Kim Ji-Won Chun Soo-Jung Lee Hae Kook Lee Dai Jin Kim In Young Choi Machine learning prediction of dropping out of outpatients with alcohol use disorders PLoS ONE |
| title | Machine learning prediction of dropping out of outpatients with alcohol use disorders |
| title_full | Machine learning prediction of dropping out of outpatients with alcohol use disorders |
| title_fullStr | Machine learning prediction of dropping out of outpatients with alcohol use disorders |
| title_full_unstemmed | Machine learning prediction of dropping out of outpatients with alcohol use disorders |
| title_short | Machine learning prediction of dropping out of outpatients with alcohol use disorders |
| title_sort | machine learning prediction of dropping out of outpatients with alcohol use disorders |
| url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8328309/?tool=EBI |
| work_keys_str_mv | AT sojinpark machinelearningpredictionofdroppingoutofoutpatientswithalcoholusedisorders AT sunjunglee machinelearningpredictionofdroppingoutofoutpatientswithalcoholusedisorders AT hyungminkim machinelearningpredictionofdroppingoutofoutpatientswithalcoholusedisorders AT jaekwonkim machinelearningpredictionofdroppingoutofoutpatientswithalcoholusedisorders AT jiwonchun machinelearningpredictionofdroppingoutofoutpatientswithalcoholusedisorders AT soojunglee machinelearningpredictionofdroppingoutofoutpatientswithalcoholusedisorders AT haekooklee machinelearningpredictionofdroppingoutofoutpatientswithalcoholusedisorders AT daijinkim machinelearningpredictionofdroppingoutofoutpatientswithalcoholusedisorders AT inyoungchoi machinelearningpredictionofdroppingoutofoutpatientswithalcoholusedisorders |