MLHOps: Machine Learning Health Operations
Machine Learning Health Operations (MLHOps) is the combination of processes for reliable, efficient, usable, and ethical deployment and maintenance of machine learning models in healthcare settings. This paper provides both a survey of work in this area and guidelines for developers and clinicians t...
Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10811924/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832575613041377280 |
|---|---|
| author | Faiza Khan Khattak Vallijah Subasri Amrit Krishnan Chloe Pou-Prom Sedef Akinli-Kocak Elham Dolatabadi Deval Pandya Laleh Seyyed-Kalantari Frank Rudzicz |
| author_facet | Faiza Khan Khattak Vallijah Subasri Amrit Krishnan Chloe Pou-Prom Sedef Akinli-Kocak Elham Dolatabadi Deval Pandya Laleh Seyyed-Kalantari Frank Rudzicz |
| author_sort | Faiza Khan Khattak |
| collection | DOAJ |
| description | Machine Learning Health Operations (MLHOps) is the combination of processes for reliable, efficient, usable, and ethical deployment and maintenance of machine learning models in healthcare settings. This paper provides both a survey of work in this area and guidelines for developers and clinicians to deploy and maintain their own models in clinical practice. We cover the foundational concepts of general machine learning operations and describe the initial setup of MLHOps pipelines (including data sources, preparation, engineering, and tools). We then describe long-term monitoring and updating (including data distribution shifts and model updating) and ethical considerations (including bias, fairness, interpretability, and privacy). This work therefore provides guidance across the full pipeline of MLHOps from conception to initial and ongoing deployment. We also include a checklist to ensure thorough verification of each step in the process. |
| format | Article |
| id | doaj-art-bcb7a133fe164ed1b1802e9f986e7595 |
| institution | Kabale University |
| issn | 2169-3536 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj-art-bcb7a133fe164ed1b1802e9f986e75952025-01-31T23:04:29ZengIEEEIEEE Access2169-35362025-01-0113203742041210.1109/ACCESS.2024.352127910811924MLHOps: Machine Learning Health OperationsFaiza Khan Khattak0https://orcid.org/0000-0002-9902-0583Vallijah Subasri1Amrit Krishnan2Chloe Pou-Prom3Sedef Akinli-Kocak4Elham Dolatabadi5https://orcid.org/0000-0003-2236-2611Deval Pandya6Laleh Seyyed-Kalantari7https://orcid.org/0000-0002-1059-7125Frank Rudzicz8https://orcid.org/0000-0002-1139-3423Vector Institute, Toronto, ON, CanadaVector Institute for Artificial Intelligence, Toronto, ON, CanadaVector Institute for Artificial Intelligence, Toronto, ON, CanadaSt. Michael’s Hospital, Toronto, ON, CanadaVector Institute for Artificial Intelligence, Toronto, ON, CanadaVector Institute for Artificial Intelligence, Toronto, ON, CanadaVector Institute for Artificial Intelligence, Toronto, ON, CanadaVector Institute for Artificial Intelligence, Toronto, ON, CanadaVector Institute for Artificial Intelligence, Toronto, ON, CanadaMachine Learning Health Operations (MLHOps) is the combination of processes for reliable, efficient, usable, and ethical deployment and maintenance of machine learning models in healthcare settings. This paper provides both a survey of work in this area and guidelines for developers and clinicians to deploy and maintain their own models in clinical practice. We cover the foundational concepts of general machine learning operations and describe the initial setup of MLHOps pipelines (including data sources, preparation, engineering, and tools). We then describe long-term monitoring and updating (including data distribution shifts and model updating) and ethical considerations (including bias, fairness, interpretability, and privacy). This work therefore provides guidance across the full pipeline of MLHOps from conception to initial and ongoing deployment. We also include a checklist to ensure thorough verification of each step in the process.https://ieeexplore.ieee.org/document/10811924/Computational and artificial intelligencemachine learningengineering in medicine and biologyelectronic healthcarehealth information managementhospitals |
| spellingShingle | Faiza Khan Khattak Vallijah Subasri Amrit Krishnan Chloe Pou-Prom Sedef Akinli-Kocak Elham Dolatabadi Deval Pandya Laleh Seyyed-Kalantari Frank Rudzicz MLHOps: Machine Learning Health Operations IEEE Access Computational and artificial intelligence machine learning engineering in medicine and biology electronic healthcare health information management hospitals |
| title | MLHOps: Machine Learning Health Operations |
| title_full | MLHOps: Machine Learning Health Operations |
| title_fullStr | MLHOps: Machine Learning Health Operations |
| title_full_unstemmed | MLHOps: Machine Learning Health Operations |
| title_short | MLHOps: Machine Learning Health Operations |
| title_sort | mlhops machine learning health operations |
| topic | Computational and artificial intelligence machine learning engineering in medicine and biology electronic healthcare health information management hospitals |
| url | https://ieeexplore.ieee.org/document/10811924/ |
| work_keys_str_mv | AT faizakhankhattak mlhopsmachinelearninghealthoperations AT vallijahsubasri mlhopsmachinelearninghealthoperations AT amritkrishnan mlhopsmachinelearninghealthoperations AT chloepouprom mlhopsmachinelearninghealthoperations AT sedefakinlikocak mlhopsmachinelearninghealthoperations AT elhamdolatabadi mlhopsmachinelearninghealthoperations AT devalpandya mlhopsmachinelearninghealthoperations AT lalehseyyedkalantari mlhopsmachinelearninghealthoperations AT frankrudzicz mlhopsmachinelearninghealthoperations |