Stress remains a key issue in long-distance driving, where prolonged periods behind the wheel can lead to fatigue, reduced attention, and increased risk of accidents. This study explores an approach for detecting potentially stressful situations using pulse rate variability (PRV) metrics extracted from photoplethysmography (PPG) signals. Data gathering involved PPG signals with video recordings for validation. After applying a Min–Max standardization to align individual differences, a Z-score method flagged outliers whenever the values of the PRV parameters deviated more than three standard deviations from the mean. Events were only considered if these outliers persisted for at least one second, reducing the impact of brief fluctuations not related to genuine stress. To make the results more interpretable, outliers occurring within three seconds of each other were merged into single episodes. This process provided a clearer picture of sustained stress, rather than isolated spikes. A final comparison with video footage confirmed that many flagged intervals corresponded to visibly tense driver reactions or challenging driving conditions, suggesting a reasonable alignment between physiological data and observable stress cues. In general, the findings highlight the importance of combining PPG-based PRV measurements, time-based outlier clustering, and video validation to detect moments of elevated stress. This integrated methodology has potential in applications such as advanced driver assistance systems, driver training programs, and other interventions aimed at improving safety and reducing risk on long journeys.