Data Driven Classification of Opioid Patients Using Machine Learning–An Investigation
The opioid crisis has led to an increased number of drug overdoses in recent years. Several approaches have been established to predict opioid prescription by health practitioners. However, due to the complex nature of the problem, the accuracy of such methods is not yet satisfactory. Dependable and...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2023-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9991956/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841542571451482112 |
|---|---|
| author | Lisan Al Amin Md. Saddam Hossain Mukta Md. Sezan Mahmud Saikat Md. Ismail Hossain Md. Adnanul Islam Mohiuddin Ahmed Sami Azam |
| author_facet | Lisan Al Amin Md. Saddam Hossain Mukta Md. Sezan Mahmud Saikat Md. Ismail Hossain Md. Adnanul Islam Mohiuddin Ahmed Sami Azam |
| author_sort | Lisan Al Amin |
| collection | DOAJ |
| description | The opioid crisis has led to an increased number of drug overdoses in recent years. Several approaches have been established to predict opioid prescription by health practitioners. However, due to the complex nature of the problem, the accuracy of such methods is not yet satisfactory. Dependable and reliable classification of opioid dependent patients from well-grounded data sources is essential. Majority of the previous studies do not focus on the users’ mental health association for opioid intake classification. These studies do not also employ the latest deep learning based techniques such as attention and knowledge distillation mechanism to find better insights. This paper investigates the opioid classification problem by using machine learning and deep learning based techniques. We used structured and unstructured data from the MIMIC-III database to identify intentional and unintentional intake of opioid drugs. We selected 455 patient instances and used traditional machine learning and deep learning to predict intentional and accidental users. We obtained 95% and 64% test accuracy to predict the intentional and accidental users from the structured and unstructured datasets, respectively. We also achieve a distilled knowledge based test accuracy of 76.44% from the integrated above two models. Our research includes an ablation analysis and new insights related to opioid patients are extracted. |
| format | Article |
| id | doaj-art-a0d03c7dd9664debbcb39926e8c67178 |
| institution | Kabale University |
| issn | 2169-3536 |
| language | English |
| publishDate | 2023-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj-art-a0d03c7dd9664debbcb39926e8c671782025-01-14T00:00:57ZengIEEEIEEE Access2169-35362023-01-011139640910.1109/ACCESS.2022.32305969991956Data Driven Classification of Opioid Patients Using Machine Learning–An InvestigationLisan Al Amin0Md. Saddam Hossain Mukta1https://orcid.org/0000-0003-2675-5471Md. Sezan Mahmud Saikat2Md. Ismail Hossain3Md. Adnanul Islam4https://orcid.org/0000-0002-0278-7738Mohiuddin Ahmed5https://orcid.org/0000-0002-4559-4768Sami Azam6https://orcid.org/0000-0001-7572-9750Department of Computer Science and Engineering, United International University (UIU), Dhaka, BangladeshDepartment of Computer Science and Engineering, United International University (UIU), Dhaka, BangladeshDepartment of Computer Science and Engineering, United International University (UIU), Dhaka, BangladeshDepartment of Computer Science and Engineering, North South University, Dhaka, BangladeshDepartment of Human-Centered Computing (HCC), Action Lab, Monash University, Clayton, VIC, AustraliaSchool of Science, Edith Cowan University, Joondalup, WA, AustraliaCollege of Engineering and IT, Charles Darwin University, Casuarina, NT, AustraliaThe opioid crisis has led to an increased number of drug overdoses in recent years. Several approaches have been established to predict opioid prescription by health practitioners. However, due to the complex nature of the problem, the accuracy of such methods is not yet satisfactory. Dependable and reliable classification of opioid dependent patients from well-grounded data sources is essential. Majority of the previous studies do not focus on the users’ mental health association for opioid intake classification. These studies do not also employ the latest deep learning based techniques such as attention and knowledge distillation mechanism to find better insights. This paper investigates the opioid classification problem by using machine learning and deep learning based techniques. We used structured and unstructured data from the MIMIC-III database to identify intentional and unintentional intake of opioid drugs. We selected 455 patient instances and used traditional machine learning and deep learning to predict intentional and accidental users. We obtained 95% and 64% test accuracy to predict the intentional and accidental users from the structured and unstructured datasets, respectively. We also achieve a distilled knowledge based test accuracy of 76.44% from the integrated above two models. Our research includes an ablation analysis and new insights related to opioid patients are extracted.https://ieeexplore.ieee.org/document/9991956/Opioid intakemental illnessMIMIC-III databasemachine learningdeep learning |
| spellingShingle | Lisan Al Amin Md. Saddam Hossain Mukta Md. Sezan Mahmud Saikat Md. Ismail Hossain Md. Adnanul Islam Mohiuddin Ahmed Sami Azam Data Driven Classification of Opioid Patients Using Machine Learning–An Investigation IEEE Access Opioid intake mental illness MIMIC-III database machine learning deep learning |
| title | Data Driven Classification of Opioid Patients Using Machine Learning–An Investigation |
| title_full | Data Driven Classification of Opioid Patients Using Machine Learning–An Investigation |
| title_fullStr | Data Driven Classification of Opioid Patients Using Machine Learning–An Investigation |
| title_full_unstemmed | Data Driven Classification of Opioid Patients Using Machine Learning–An Investigation |
| title_short | Data Driven Classification of Opioid Patients Using Machine Learning–An Investigation |
| title_sort | data driven classification of opioid patients using machine learning x2013 an investigation |
| topic | Opioid intake mental illness MIMIC-III database machine learning deep learning |
| url | https://ieeexplore.ieee.org/document/9991956/ |
| work_keys_str_mv | AT lisanalamin datadrivenclassificationofopioidpatientsusingmachinelearningx2013aninvestigation AT mdsaddamhossainmukta datadrivenclassificationofopioidpatientsusingmachinelearningx2013aninvestigation AT mdsezanmahmudsaikat datadrivenclassificationofopioidpatientsusingmachinelearningx2013aninvestigation AT mdismailhossain datadrivenclassificationofopioidpatientsusingmachinelearningx2013aninvestigation AT mdadnanulislam datadrivenclassificationofopioidpatientsusingmachinelearningx2013aninvestigation AT mohiuddinahmed datadrivenclassificationofopioidpatientsusingmachinelearningx2013aninvestigation AT samiazam datadrivenclassificationofopioidpatientsusingmachinelearningx2013aninvestigation |