MétaCan
Menu
Back to cohort
Record W4311650614 · doi:10.1101/2022.12.02.22283021

CyclOps: Cyclical development towards operationalizing ML models for health

2022· preprint· en· W4311650614 on OpenAlexaff
Amrit Krishnan, Vallijah Subasri, Kaden McKeen, Ali Kore, Franklin Ogidi, Mahshid Alinoori, Nadim Lalani, Azra Dhalla, Amol A. Verma, Fahad Razak, Deval Pandya, Elham Dolatabadi

Bibliographic record

VenuemedRxiv · 2022
Typepreprint
Languageen
FieldComputer Science
TopicMachine Learning in Healthcare
Canadian institutionsUniversity Health NetworkHospital for Sick ChildrenSickKids FoundationVector Institute
Fundersnot available
KeywordsPython (programming language)Computer scienceCyclopsSoftwareSoftware engineeringSoftware deploymentArtificial intelligenceOperating system

Abstract

fetched live from OpenAlex

A bstract Open source software that enable research and development of machine learning (ML) models for clinical use cases are fragmented, poorly maintained and fall short in functionality. CyclOps is a software framework designed to address this gap and help accelerate the development of ML models for health. In this paper, we describe the architecture, APIs and implementation details of CyclOps, while providing benchmarks on example clinical use cases. We emphasize that CyclOps is developed to be researcher friendly, while providing APIs for building end-to-end pipelines for model development as well as deployment. We adopt software engineering and ML operations (MLOps) best practices, while providing support for handling large volumes of health data. The design of the framework is centered around the notion of iterative and cyclical development of the overall ML system, which consists of data, model development and monitoring pipelines. The core CyclOps package can be installed through the Python Package Index (PyPI) and the source code is available at https://github.com/VectorInstitute/cyclops .

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

How this classification was reachedexpand

Full frame distilled prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.

metaresearch head score (Codex)0.002
metaresearch head score (Gemma)0.000
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesMeta-epidemiology (narrow)
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: Simulation or modeling
GenreCandidate signal: Methods · Consensus signal: Methods
Teacher disagreement score0.270
Threshold uncertainty score1.000

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0020.000
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0010.000
Bibliometrics0.0000.000
Science and technology studies0.0010.000
Scholarly communication0.0000.000
Open science0.0020.004
Research integrity0.0000.001
Insufficient payload (model declined to judge)0.0000.000

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.084
GPT teacher head0.377
Teacher spread0.293 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one teacher head, not a consensus.

Study designSimulation or modeling
Domainnot available
GenreMethods

How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".

Quick stats

Citations8
Published2022
Admission routes1
Has abstractyes

Explore more

Same venuemedRxivSame topicMachine Learning in HealthcareFrench-language works237,207