Application of machine learning techniques for warfarin dosage prediction: a case study on the MIMIC-III dataset
Warfarin, a commonly prescribed anticoagulant, poses significant dosing challenges due to its narrow therapeutic range and high variability in patient responses. This study applies advanced machine learning techniques to improve the accuracy of international normalized ratio (INR) predictions using...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
PeerJ Inc.
2025-01-01
|
| Series: | PeerJ Computer Science |
| Subjects: | |
| Online Access: | https://peerj.com/articles/cs-2612.pdf |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841560250519388160 |
|---|---|
| author | Aasim Ayaz Wani Fatima Abeer |
| author_facet | Aasim Ayaz Wani Fatima Abeer |
| author_sort | Aasim Ayaz Wani |
| collection | DOAJ |
| description | Warfarin, a commonly prescribed anticoagulant, poses significant dosing challenges due to its narrow therapeutic range and high variability in patient responses. This study applies advanced machine learning techniques to improve the accuracy of international normalized ratio (INR) predictions using the MIMIC-III dataset, addressing the critical issue of missing data. By leveraging dimensionality reduction methods such as principal component analysis (PCA) and t-distributed stochastic neighbor embedding (t-SNE), and advanced imputation techniques including denoising autoencoders (DAE) and generative adversarial networks (GAN), we achieved significant improvements in predictive accuracy. The integration of these methods substantially reduced prediction errors compared to traditional approaches. This research demonstrates the potential of machine learning (ML) models to provide more personalized and precise dosing strategies that reduce the risks of adverse drug events. Our method could integrate into clinical workflows to enhance anticoagulation therapy in cases of missing data, with potential applications in other complex medical treatments. |
| format | Article |
| id | doaj-art-099bde7b8bca46bc8140df16a062710d |
| institution | Kabale University |
| issn | 2376-5992 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | PeerJ Inc. |
| record_format | Article |
| series | PeerJ Computer Science |
| spelling | doaj-art-099bde7b8bca46bc8140df16a062710d2025-01-04T15:05:26ZengPeerJ Inc.PeerJ Computer Science2376-59922025-01-0111e261210.7717/peerj-cs.2612Application of machine learning techniques for warfarin dosage prediction: a case study on the MIMIC-III datasetAasim Ayaz Wani0Fatima Abeer1School of Engineering, Cornell University, Ithaca, New York, United StatesJahurul Islam Medical College, University of Dhaka, Bhagalpur, BangladeshWarfarin, a commonly prescribed anticoagulant, poses significant dosing challenges due to its narrow therapeutic range and high variability in patient responses. This study applies advanced machine learning techniques to improve the accuracy of international normalized ratio (INR) predictions using the MIMIC-III dataset, addressing the critical issue of missing data. By leveraging dimensionality reduction methods such as principal component analysis (PCA) and t-distributed stochastic neighbor embedding (t-SNE), and advanced imputation techniques including denoising autoencoders (DAE) and generative adversarial networks (GAN), we achieved significant improvements in predictive accuracy. The integration of these methods substantially reduced prediction errors compared to traditional approaches. This research demonstrates the potential of machine learning (ML) models to provide more personalized and precise dosing strategies that reduce the risks of adverse drug events. Our method could integrate into clinical workflows to enhance anticoagulation therapy in cases of missing data, with potential applications in other complex medical treatments.https://peerj.com/articles/cs-2612.pdfMachine learningDeep learningDimensionality reductionArtificial intelligenceMedical researchDenoising autoencoders |
| spellingShingle | Aasim Ayaz Wani Fatima Abeer Application of machine learning techniques for warfarin dosage prediction: a case study on the MIMIC-III dataset PeerJ Computer Science Machine learning Deep learning Dimensionality reduction Artificial intelligence Medical research Denoising autoencoders |
| title | Application of machine learning techniques for warfarin dosage prediction: a case study on the MIMIC-III dataset |
| title_full | Application of machine learning techniques for warfarin dosage prediction: a case study on the MIMIC-III dataset |
| title_fullStr | Application of machine learning techniques for warfarin dosage prediction: a case study on the MIMIC-III dataset |
| title_full_unstemmed | Application of machine learning techniques for warfarin dosage prediction: a case study on the MIMIC-III dataset |
| title_short | Application of machine learning techniques for warfarin dosage prediction: a case study on the MIMIC-III dataset |
| title_sort | application of machine learning techniques for warfarin dosage prediction a case study on the mimic iii dataset |
| topic | Machine learning Deep learning Dimensionality reduction Artificial intelligence Medical research Denoising autoencoders |
| url | https://peerj.com/articles/cs-2612.pdf |
| work_keys_str_mv | AT aasimayazwani applicationofmachinelearningtechniquesforwarfarindosagepredictionacasestudyonthemimiciiidataset AT fatimaabeer applicationofmachinelearningtechniquesforwarfarindosagepredictionacasestudyonthemimiciiidataset |