Test-Time Learning and Inference-Time Deliberation for Efficiency-First Offline Reinforcement Learning in Care Coordination and Population Health Management
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915504518594560 |
|---|---|
| author | Basu, Sanjay Patel, Sadiq Y. Sheth, Parth Muralidharan, Bhairavi Elamaran, Namrata Kinra, Aakriti Batniji, Rajaie |
| author_facet | Basu, Sanjay Patel, Sadiq Y. Sheth, Parth Muralidharan, Bhairavi Elamaran, Namrata Kinra, Aakriti Batniji, Rajaie |
| contents | Care coordination and population health management programs serve large Medicaid and safety-net populations and must be auditable, efficient, and adaptable. While clinical risk for outreach modalities is typically low, time and opportunity costs differ substantially across text, phone, video, and in-person visits. We propose a lightweight offline reinforcement learning (RL) approach that augments trained policies with (i) test-time learning via local neighborhood calibration, and (ii) inference-time deliberation via a small Q-ensemble that incorporates predictive uncertainty and time/effort cost. The method exposes transparent dials for neighborhood size and uncertainty/cost penalties and preserves an auditable training pipeline. Evaluated on a de-identified operational dataset, TTL+ITD achieves stable value estimates with predictable efficiency trade-offs and subgroup auditing. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_16291 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Test-Time Learning and Inference-Time Deliberation for Efficiency-First Offline Reinforcement Learning in Care Coordination and Population Health Management Basu, Sanjay Patel, Sadiq Y. Sheth, Parth Muralidharan, Bhairavi Elamaran, Namrata Kinra, Aakriti Batniji, Rajaie Computers and Society Machine Learning Care coordination and population health management programs serve large Medicaid and safety-net populations and must be auditable, efficient, and adaptable. While clinical risk for outreach modalities is typically low, time and opportunity costs differ substantially across text, phone, video, and in-person visits. We propose a lightweight offline reinforcement learning (RL) approach that augments trained policies with (i) test-time learning via local neighborhood calibration, and (ii) inference-time deliberation via a small Q-ensemble that incorporates predictive uncertainty and time/effort cost. The method exposes transparent dials for neighborhood size and uncertainty/cost penalties and preserves an auditable training pipeline. Evaluated on a de-identified operational dataset, TTL+ITD achieves stable value estimates with predictable efficiency trade-offs and subgroup auditing. |
| title | Test-Time Learning and Inference-Time Deliberation for Efficiency-First Offline Reinforcement Learning in Care Coordination and Population Health Management |
| topic | Computers and Society Machine Learning |
| url | https://arxiv.org/abs/2509.16291 |