In:
PLOS ONE, Public Library of Science (PLoS), Vol. 17, No. 4 ( 2022-4-7), p. e0265254-
Abstract:
Artificial intelligence and machine learning (AI/ML) is becoming increasingly more accessible to biomedical researchers with significant potential to transform biomedicine through optimization of highly-accurate predictive models and enabling better understanding of disease biology. Automated machine learning (AutoML) in particular is positioned to democratize artificial intelligence (AI) by reducing the amount of human input and ML expertise needed. However, successful translation of AI/ML in biomedicine requires moving beyond optimizing only for prediction accuracy and towards establishing reproducible clinical and biological inferences. This is especially challenging for clinical studies on rare disorders where the smaller patient cohorts and corresponding sample size is an obstacle for reproducible modeling results. Here, we present a model-agnostic framework to reinforce AutoML using strategies and tools of explainable and reproducible AI, including novel metrics to assess model reproducibility. The framework enables clinicians to interpret AutoML-generated models for clinical and biological verifiability and consequently integrate domain expertise during model development. We applied the framework towards spinal cord injury prognostication to optimize the intraoperative hemodynamic range during injury-related surgery and additionally identified a strong detrimental relationship between intraoperative hypertension and patient outcome. Furthermore, our analysis captured how evolving clinical practices such as faster time-to-surgery and blood pressure management affect clinical model development. Altogether, we illustrate how expert-augmented AutoML improves inferential reproducibility for biomedical discovery and can ultimately build trust in AI processes towards effective clinical integration.
Type of Medium:
Online Resource
ISSN:
1932-6203
DOI:
10.1371/journal.pone.0265254
DOI:
10.1371/journal.pone.0265254.g001
DOI:
10.1371/journal.pone.0265254.g002
DOI:
10.1371/journal.pone.0265254.g003
DOI:
10.1371/journal.pone.0265254.g004
DOI:
10.1371/journal.pone.0265254.g005
DOI:
10.1371/journal.pone.0265254.g006
DOI:
10.1371/journal.pone.0265254.g007
DOI:
10.1371/journal.pone.0265254.s001
DOI:
10.1371/journal.pone.0265254.s002
DOI:
10.1371/journal.pone.0265254.s003
DOI:
10.1371/journal.pone.0265254.s004
DOI:
10.1371/journal.pone.0265254.s005
DOI:
10.1371/journal.pone.0265254.s006
DOI:
10.1371/journal.pone.0265254.s007
DOI:
10.1371/journal.pone.0265254.s008
DOI:
10.1371/journal.pone.0265254.s009
DOI:
10.1371/journal.pone.0265254.s010
DOI:
10.1371/journal.pone.0265254.s011
DOI:
10.1371/journal.pone.0265254.s012
DOI:
10.1371/journal.pone.0265254.r001
DOI:
10.1371/journal.pone.0265254.r002
Language:
English
Publisher:
Public Library of Science (PLoS)
Publication Date:
2022
detail.hit.zdb_id:
2267670-3
Permalink