---
format: "aidr-story-markdown/v1"
id: "53b641f05d8b258550fdd6b9e147731f0b41d001f545fd9f47c86835211e2751"
canonical_url: "https://aidr.today/53b641f0?lang=en"
title: "Calibration-First Cross-Cohort Multimodal Temporal Learning for Transferable Asthma-Risk Forecasting"
lang: "en"
requested_lang: "en"
available_langs: ["en","vi"]
translation_fallback: null
fallback_fields: []
published_at: "2026-09-30T04:00:00.000Z"
category: "Research"
topics: ["inference"]
source_urls: ["https://arxiv.org/abs/2609.35795"]
summary: "arXiv:2609.35795v1 Announce Type: new Abstract: Asthma deterioration forecasting must remain reli- able when patient populations, sensor ecosystems, and available modalities change across cohorts. Existing models commonly optimize within-cohort discrimination and may produce poorly calibrated probabilities after transfer. We present CALIBRA, a calibration-first multimodal temporal framework for short- horizon risk prediction with incomplete data. Dedicated recurrent encoders process environmental, pulmonary, symptom, medication, wearable, and context streams; a reliability-conditioned gate suppresses stale or absent modalities, while gradient-reversal training discourages avoidable cohort signatures. A shrinkage- based hierarchical logistic layer calibrates probabilities using a patient-disjoint target subset, and split conformal prediction provides abstention-capable prediction sets. To avoid fabricating clinical evidence, we evaluate the complete implementation on a documented three-cohort semi-synthetic benchmark with controlled distribution shift, informative missingness, and sealed target patients. Across five configured seeds, CALIBRA achieved mean target-test AUPRC 0.224 ver"
---

# Calibration\-First Cross\-Cohort Multimodal Temporal Learning for Transferable Asthma\-Risk Forecasting

> [Open the canonical story](<https://aidr.today/53b641f0?lang=en>)

**Published:** 2026-09-30T04:00:00.000Z
**Category:** Research
**Topics:** inference

## Summary

arXiv:2609\.35795v1 Announce Type: new Abstract: Asthma deterioration forecasting must remain reli\- able when patient populations, sensor ecosystems, and available modalities change across cohorts\. Existing models commonly optimize within\-cohort discrimination and may produce poorly calibrated probabilities after transfer\. We present CALIBRA, a calibration\-first multimodal temporal framework for short\- horizon risk prediction with incomplete data\. Dedicated recurrent encoders process environmental, pulmonary, symptom, medication, wearable, and context streams; a reliability\-conditioned gate suppresses stale or absent modalities, while gradient\-reversal training discourages avoidable cohort signatures\. A shrinkage\- based hierarchical logistic layer calibrates probabilities using a patient\-disjoint target subset, and split conformal prediction provides abstention\-capable prediction sets\. To avoid fabricating clinical evidence, we evaluate the complete implementation on a documented three\-cohort semi\-synthetic benchmark with controlled distribution shift, informative missingness, and sealed target patients\. Across five configured seeds, CALIBRA achieved mean target\-test AUPRC 0\.224 ver

## Sources

- [Story source](<https://arxiv.org/abs/2609.35795>)