Saved in:
| Main Author: | |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2510.15943 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908600461426688 |
|---|---|
| author | Joseph, Jimmy |
| author_facet | Joseph, Jimmy |
| contents | We offer a pragmatic model to operationalize responsible, secure, and sustainable healthcare AI, aligning world-class technical excellence with organizational readiness. The framework includes five key pillars - Leadership & Strategy, MLOps & Technical Infrastructure, Governance & Ethics, Education & Workforce Development, and Change Management & Adoption - and is intended to operationalize 'compliance-by-design' while delivering measurable impact. We demonstrate its utility through two deployments. (A) An inpatient length of stay (LOS) prediction service had R^2=0.41-0.58 with validation cohorts in an observational pilot (n = 3,184 encounters, 4 units, June-August 2025). Adoption was 78 percent by week 6, and target units saw 5-10 percent relative declines in mean LOS for complex cases vs. pre-pilot baselines. (B) An AI-augmented radiology second-reader for lung nodules (PACS-integrated with thresholding and explanation overlays) achieved high sensitivity (95 percent) and provided a +8.0 percentage-point lift in detection of sub-centimeter actionable findings, without slowing workflow (median report TAT 23 min, p = 0.64). Both services executed in monitored, auditable pipelines with well-defined rollback, bias checks, and no evidence of security incidents. These findings indicate that by combining strong MLOps and AI security with governance, education, and human-centric change, we can accelerate adoption of AI while improving security and outcomes. We end with limitations, generalization considerations, and a roadmap for scaling across varied clinical and operational use cases. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_15943 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Enabling Responsible, Secure and Sustainable Healthcare AI - A Strategic Framework for Clinical and Operational Impact Joseph, Jimmy Computers and Society We offer a pragmatic model to operationalize responsible, secure, and sustainable healthcare AI, aligning world-class technical excellence with organizational readiness. The framework includes five key pillars - Leadership & Strategy, MLOps & Technical Infrastructure, Governance & Ethics, Education & Workforce Development, and Change Management & Adoption - and is intended to operationalize 'compliance-by-design' while delivering measurable impact. We demonstrate its utility through two deployments. (A) An inpatient length of stay (LOS) prediction service had R^2=0.41-0.58 with validation cohorts in an observational pilot (n = 3,184 encounters, 4 units, June-August 2025). Adoption was 78 percent by week 6, and target units saw 5-10 percent relative declines in mean LOS for complex cases vs. pre-pilot baselines. (B) An AI-augmented radiology second-reader for lung nodules (PACS-integrated with thresholding and explanation overlays) achieved high sensitivity (95 percent) and provided a +8.0 percentage-point lift in detection of sub-centimeter actionable findings, without slowing workflow (median report TAT 23 min, p = 0.64). Both services executed in monitored, auditable pipelines with well-defined rollback, bias checks, and no evidence of security incidents. These findings indicate that by combining strong MLOps and AI security with governance, education, and human-centric change, we can accelerate adoption of AI while improving security and outcomes. We end with limitations, generalization considerations, and a roadmap for scaling across varied clinical and operational use cases. |
| title | Enabling Responsible, Secure and Sustainable Healthcare AI - A Strategic Framework for Clinical and Operational Impact |
| topic | Computers and Society |
| url | https://arxiv.org/abs/2510.15943 |