The exact text we saved

This is the version exactly as it was saved, character for character. The SHA-256 hash below is a 64-character code worked out from that text. Run the same text through SHA-256 and you get the same code; change a single letter and the code comes out completely different. Each version also stores the previous version’s hash, which chains them together so no version can be swapped out quietly.

TRUVACE RECORD VERSION
record: TRV-2026-2856
version: 1
kind: certified
reason: Certified into the record
timestamp: 2026-11-12T17:35:36.253970Z
status: published
lens: p_space
sector: health
headline: The Performance of Wearable AI in Detecting Stress Among Students: Systematic Review and Meta-Analysis
dek: Background Students usually encounter stress throughout their academic path. Ongoing stressors may lead to chronic stress, adversely affecting their physical and mental well-being. Thus, early detection and monitoring of stress among students are crucial. Wearable artificial intelligence (AI) has emerged as a valuable tool for this purpose. It offers an objective, noninvasive, nonobtrusive, automated approach to continuously monitor biomarkers in real time, thereby addressing the limitations of traditional appro…
gain_title: (none)
problem_title: A systematic review of 19 studies of students found wearable AI stress detection reached 85.6% pooled accuracy but averaged only 75.5% sensitivity and 74.4% specificity, which the authors called suboptimal and not ready to use without questionnaires.
trace_subject: (none)
gain_reading: (none)
gain_evidence: (none)
problem_reading: A systematic review of 19 studies of students found wearable AI stress detection reached 85.6% pooled accuracy but averaged only 75.5% sensitivity and 74.4% specificity, which the authors called suboptimal and not ready to use without questionnaires.
problem_evidence: Wearable AI shows promise in detecting student stress but currently has suboptimal performance. | The average estimates of sensitivity, specificity, and F1-score were 0.755 (SD 0.181), 0.744 (SD 0.147), and 0.759 (SD 0.139), respectively.
quick_read: A systematic review and meta-analysis in the Journal of Medical Internet Research pooled 19 studies on wearable AI that tries to detect stress in students from heart rate, skin conductance and activity data. Meta-analysing 37 accuracy estimates from 6 of those studies gave a pooled mean accuracy of 0.856 (95% CI 0.70-0.93).

Accuracy alone flattered the tools. Average sensitivity was 0.755, specificity 0.744 and F1-score 0.759, and the authors judged performance suboptimal, noting that AI has scored higher for cancers, heart disease and eye disorders in earlier reviews. They advise using wearable AI alongside clinical questionnaires.

The evidence base is thin: most included studies were small, results varied enormously between studies, and none tried to predict future stress or tell stress apart from depression or anxiety.
limitation: Accuracy estimates in the meta-analyses came from only six studies, many studies were small, and the review excluded non-English, pre-2015 and public-dataset studies, so conclusions are not definitive.
tag: Evidence-backed problem
key_points: The review searched 7 databases on June 12, 2023, screened 327 retrieved records and included 19 studies published between 2015 and 2023. | Only 6 of the 19 studies gave enough data for meta-analysis; their 37 accuracy estimates pooled to 0.856, with considerable heterogeneity (I2 = 98.8%). | Average sensitivity was 0.755 across 27 estimates from 6 studies, and average specificity was 0.744 across 8 estimates from 2 studies. | Accuracy differed by device: electrodes reached 94.4%, smartwatches 83.6% and smart bands 69.5%; wrist-worn devices scored 77.3% versus 94.4% for other body locations. | Accuracy was 93.3% when stress was labelled by experimental context versus 70.6% when it relied on self-reported questionnaires; the authors say confounding may explain several subgroup differences. | Participants in the included studies ranged from 5 to 652, 74% of studies had 50 or fewer participants, and 17 of 19 studies focused on undergraduates. | All 19 studies detected current stress; none tried to predict future stress or separate stress from conditions such as depression and anxiety. | Only 4 of 19 studies (21%) were judged low risk of bias in all domains.
rundown: Two reviewers independently selected studies, extracted data and assessed bias with an adapted QUADAS-2 tool, with high agreement (kappa 0.87 for titles and abstracts, 0.92 for full texts). The review was registered with PROSPERO and followed PRISMA-DTA reporting guidance. Studies that used public datasets such as WESAD were excluded.

The included studies used 16 different wearable devices, most often Empatica E4 and Samsung Galaxy watches, worn mostly on the wrist (16 of 19). They tested 22 algorithms, most commonly support vector machines (14 of 19) and k-nearest neighbour (13 of 19). Most studies sorted students into two classes, stressed or not stressed (15 of 19).

Subgroup analyses found accuracy varied significantly with number of stress classes (P=.02), device type (P=.049), device location (P=.02), dataset size (P=.009) and ground truth (P=.001). The authors note that these factors overlap: the studies using electrodes, multiple body sites and objective labels were largely the same ones, so the groupings should be read with caution.

The authors say they cannot endorse immediate use in clinical or academic settings, citing suboptimal performance, small samples, few studies feeding the meta-analyses and high risk of bias in many studies. They call for studies of postgraduate and high school students, future stress prediction, and gold-standard cortisol-based ground truth.
sources:
- peer_reviewed | Journal of Medical Internet Research | https://doi.org/10.2196/52622 | 2023-12-19
prev: 0000000000000000000000000000000000000000000000000000000000000000

SHA-256 hash

2f431fee905a62eaf67dd1b52b3cfd4f3fe7df3fdd42b48a7be5740d33df4796

Previous version’s hash

0000000000000000000000000000000000000000000000000000000000000000