# Patterns of smartphone typing performance by time awake: implications for unobtrusive ambulatory mental fatigue assessment

**Authors:** Yu Fang, Peter Yang, Elena Frank, Cathy Goldstein, Aidan G. C. Wright, Amy S. B. Bohnert, Vik Kheterpal, Srijan Sen, Zhenke Wu, Tianzhen Chen, Louise Millard

PMC · DOI: 10.1371/journal.pdig.0001281 · PLOS Digital Health · 2026-03-26

## TL;DR

Smartphone typing speed changes predict mental fatigue, offering a real-time, unobtrusive way to monitor alertness in high-risk jobs.

## Contribution

Using smartphone typing data to detect mental fatigue in real-world settings, without lab equipment.

## Key findings

- Typing speed peaks around 7.5 hours after waking and declines significantly after 15.3 hours awake.
- The decline in typing speed aligns with lab-based tests showing lapses in attention after prolonged wakefulness.
- Smartphone typing metrics can serve as a scalable, continuous tool for mental fatigue assessment.

## Abstract

Mental fatigue undermines workplace safety and productivity. Early detection of subtle declines in objective alertness and cognitive performance in workers can enable timely interventions to prevent costly errors and safeguard employee health. However, conventional assessments often require controlled laboratory conditions and prolonged testing, limiting their real-world applicability. Here, we demonstrate an approach that utilizes smartphone keyboard metrics in everyday use to provide a more scalable, continuous, and ambulatory method for evaluating mental fatigue. We examined the adjusted association between novel yet widely available SensorKit typing performance metrics and wearable-derived time since waking from a most recent major sleep episode or napping among 366 first-year training physicians in the United States who generated 45,042 typing sessions over a two-month period. Typing performance, especially typing speed, has a significant non-linear adjusted relationship with time awake. At the population-level, typing speed increases and peaks around 7.5 hours since awake and has a substantial decrease around 15.3 hours of time awake, highly consistent with classical lab-based active task Psychomotor Vigilance Test findings that showed increased response lapses beyond 15.8 hours of wake period. Our findings are relevant for developing a ubiquitous and unobtrusive tool to assess, monitor, and manage mental fatigue on a continuous basis in everyday life, especially for populations in high-risk and high-stake settings.

Mental fatigue can impact people’s safety and performance at work, especially in demanding jobs like medicine or shift work. We wanted to find an easy and effective way to measure when people start feeling mentally tired, without interrupting their regular work and life. In this study, we followed 366 new doctors across the United States as they typed on their iPhones as they did their usual daily activities. By collecting data from over 45,000 typing sessions through the native keyboard sensor, and combining it with information about their sleep, we noticed clear changes in how fast people typed as they became more tired. Typing speed increased over the first several hours after waking up, but then showed a clear slowdown as people stayed awake longer, closely matching results from special attention tests done in special labs. Our work shows that everyday smartphone typing could reveal early signs of mental fatigue in real time. This approach could help people in high-stress jobs track their own alertness and take steps to prevent mistakes, ultimately supporting safer and healthier workplaces.

## Full-text entities

- **Diseases:** impairment of (MESH:D060825), sleep (MESH:D012893), sleep deprivation (MESH:D012892), fatigue (MESH:D005221), Mental fatigue (MESH:D005222)
- **Chemicals:** PDIG-D-25-00755R1 (-), nicotine (MESH:D009538), caffeine (MESH:D002110)
- **Species:** Mus musculus (house mouse, species) [taxon 10090], Homo sapiens (human, species) [taxon 9606]

## Full text

_Full body text omitted from this summary view._ Fetch the complete paper as Markdown: https://tomesphere.com/paper/PMC13020785/full.md

## Figures

5 figures with captions in the complete paper: https://tomesphere.com/paper/PMC13020785/full.md

## References

31 references — full list in the complete paper: https://tomesphere.com/paper/PMC13020785/full.md

---
Source: https://tomesphere.com/paper/PMC13020785