What does this research mean for the field?

During sustained engagement with conversational AI systems, a user's within-hour pre-engagement physiological state strongly predicts their physiological state during engagement. Novelty: ClaimNovelty.METHODOLOGICAL. Consensus alignment: ConsensusAlignment.NEUTRAL.

What question did this study set out to answer?

This paper aims to explore the physiological and phenomenological aspects of sustained engagement with AI systems using a single-subject longitudinal approach.

May 21, 2026Open Access

Longitudinal Autonomic Methodology for Single-Subject Sustained-Cognitive-Work Research: A Multi-Modal Biosensing Approach

Q: What is the clinical evidence from this study?

Study design: Observational. Population: Sustained cognitive work with conversational AI systems (n=1). Intervention: Sustained engagement with conversational AI systems. Primary outcome: Correlation between pre-engagement and during-engagement physiological state (Pearson r = 0.63).

Key Result

Sustained engagement with conversational AI systems demonstrated that within-hour pre-engagement physiological state strongly predicts during-engagement state (Pearson r = 0.63).

Key Points

This paper aims to explore the physiological and phenomenological aspects of sustained engagement with AI systems using a single-subject longitudinal approach.
Conducted a 26-day longitudinal study with a single subject (N=1) using a multi-modal biosensing approach.
Collected biosignal data from a consumer-grade wearable including heart rate variability and activity, time-aligned with cognitive-interaction logs.
Developed a reproducible Python pipeline for data analysis with anonymized biosignal aggregates.
Pre-engagement physiological state predicts during-engagement state (Pearson r = 0.63, N = 273).
Sustained engagement leads to a tonic stress plateau instead of an acute spike in stress levels.
Post-engagement recovery shows a specific phenotype-dependent 4-day median time-constant.

Study Design

Type

Observational (n=1)

Multicenter

Structured PICO

Does sustained engagement with conversational AI systems affect physiological state in a single subject?

Population

Single subject (N=1) engaging with conversational AI systems

Intervention

Sustained engagement with conversational AI systems

Comparator

Pre-engagement physiological state

Outcome

Somatic and phenomenological signatures (HRV, sleep architecture, stress index, body battery, heart rate, respiration, activity recordings)surrogate

This methods paper demonstrates a reproducible pipeline for tracking physiological responses to sustained cognitive work using consumer-grade wearables in a single subject.

Main Result

Effect estimate: Pearson r = 0.63

Limitations

Raw biosignal data are not released due to GDPR Article 9 restrictions.

Abstract

Methods paper documenting a 26-day longitudinal, multi-modal, single-subject (N=1) approach to studying the somatic and phenomenological signatures of sustained engagement with conversational AI systems. Biosignal data from a consumer-grade wearable platform (HRV, sleep architecture, stress index, body battery, heart rate, respiration, activity recordings) are time-aligned with timestamped cognitive-interaction logs (475 segmented sessions, 278 bio-matched). Includes 13 ISO-704-formalized phenomenological terms (mean Aggregate Quality 0.842), a reproducible Python pipeline architecture, and anonymized day-level biosignal aggregates. Reproducible at consumer-grade hardware cost. Key findings: (a) within-hour pre-engagement physiological state strongly predicts during-engagement state (Pearson r = 0.63, N = 273); (b) sustained engagement produces a tonic stress plateau rather than acute spike; (c) post-decline recovery shows a phenotype-specific 4-day median time-constant; (d) physical activity has a chronically positive but acutely costly dual effect on autonomic recovery. Bundle V17. Access restricted; methodology is open via the Methods Paper. Raw biosignal data are not released (GDPR Article 9).