The choice of population was deliberate. Students training to become teachers occupy a unique position in the public health landscape: they are future educators who can disseminate life-saving knowledge through schools and communities, multiplying the impact of any single training program. By assessing their preparedness, the researchers hoped to gauge the potential for a self-renewing generation of first responders in a country where sudden cardiac arrest remains one of the most urgent and under-recognized public health crises. The study, published in the Journal of Emergency and Disaster Medicine, was conducted between April and May 2024 using a convenience sample with a calculated minimum requirement of 128 participants, ultimately enrolling 134 students with no missing data.

Demographically, the cohort was dominated by 23-year-olds, who made up 41 percent of respondents, followed by 22-, 24-, and 25-year-olds. Slightly more than half of the participants, 56.7 percent, were male, and nearly two-thirds were postgraduate students. Data were collected through a structured, self-administered questionnaire covering demographic variables, CPR awareness, self-rated ability, prior training, and barriers to intervention. Researchers scored five domains: confidence in performing specific skills such as checking responsiveness, assessing breathing, delivering chest compressions, using an automated external defibrillator, and providing wound care; recognition of situations indicating CPR, including unconsciousness, drowning, burns, and choking; correct response actions; symptom recognition during resuscitation; and overall perceptions of CPR’s importance.

The psychometric properties of the instrument were examined in detail. The confidence domain showed strong internal consistency, with a Cronbach’s alpha of 0.808 across its five items, while the indication, support, and symptom recognition domains demonstrated moderate reliability suitable for exploratory research, with alphas of 0.640, 0.649, and 0.630 respectively. The perception domain, by contrast, showed low internal consistency at 0.201, prompting the authors to analyze those items individually and interpret them cautiously. The overall instrument achieved an acceptable alpha of 0.645. Descriptive statistics revealed that confidence was the most variable measure, ranging from 0 to 17 with a mean of 9.22 and a standard deviation of 3.70, while perception scores were the most tightly clustered.

Attitudes toward CPR were overwhelmingly positive. A striking 70.1 percent of participants considered first aid and CPR more important in light of recent health emergencies, and 71.6 percent strongly agreed with the importance of these skills overall. Yet actual exposure was limited: 20.1 percent had never witnessed a first aid or CPR event, only 9 percent had ever provided CPR, 40.3 percent reported lacking training, and 23.9 percent cited fear of infection as a deterrent. When asked why they might hesitate, 44 percent pointed to safety protocols, 25.4 percent to needed training modifications, and only 17.9 percent reported no hesitation at all. Confidence itself was uneven, with 29.1 percent very confident in performing CPR but 11.9 percent reporting no confidence at all in basic first aid.

The statistical core of the study produced its most important insight. One-way analysis of variance showed a significant relationship between exposure to real first aid or CPR events and total preparedness scores, with F equal to 3.466 and a p-value of 0.010. Students who had actually provided CPR scored dramatically higher, averaging 27.4 points against 20.4 for those with no prior exposure, a gap that dwarfed differences attributable to perception or self-reported barriers. Neither perceived impact of CPR on health emergencies nor reasons for hesitation showed significant score differences, suggesting that nothing substitutes for hands-on experience when it comes to building genuine readiness to act.

Gender emerged as a persistent fault line. Male students scored significantly higher than female students on overall CPR preparedness, with means of 23.8 versus 20.5 and a t-statistic of 3.319 with p equal to 0.002. Chi-square analysis reinforced the pattern, showing that 56.6 percent of males fell into the high-preparedness category compared with 36.2 percent of females, a difference that was statistically significant. In univariate logistic regression, sex was a significant predictor, with female students showing odds of high preparedness less than half those of their male counterparts. However, the association lost significance in the multivariable model, hinting that the disparity may stem from differences in training exposure and experience rather than inherent capability, echoing prior research showing that women often underestimate their skills despite performing comparably.

Age and training status also mattered. Participants aged 22 showed a disproportionate concentration in the low-preparedness group, and trained students were significantly more likely to demonstrate high preparedness, at 59.4 percent versus 35.4 percent for the untrained. Formal training showed a marginal positive association with high preparedness in the multivariable logistic regression, with an odds ratio of 2.21 and p equal to 0.051, while the overall model was statistically significant and passed the Hosmer–Lemeshow goodness-of-fit test. Notably, undergraduate students scored slightly higher than postgraduates, a marginally non-significant difference suggesting that academic progression alone does not translate into emergency readiness, and that practical skill-based education must be embedded deliberately within university life.

The barriers identified by the study extend beyond knowledge. Fear of causing harm, anxiety, and uncertainty have long been documented as psychological obstacles to bystander CPR, and the COVID-19 pandemic added infection risk to the calculus, particularly around mouth-to-mouth ventilation. International resuscitation bodies responded by promoting compression-only CPR and protective equipment, and evidence has since shown that trained laypersons can use automated external defibrillators safely and effectively within structured response systems. In India, cultural discomfort with physical contact with strangers and limited public awareness of the Good Samaritan law, which legally protects emergency helpers, compound the hesitation. The authors argue that training programs must therefore address emotional preparedness and confidence-building alongside technical instruction, using simulation-based learning and periodic refresher sessions to sustain competence over time.

The study’s authors conclude that universities should implement regular, hands-on CPR and first aid programs paired with targeted interventions to dismantle psychological barriers, with particular attention to groups reporting lower confidence. They envision Varanasi, with its massive student population, becoming a model city for bystander CPR readiness, generating scalable lessons for cardiac arrest response across urban and semi-urban India. The findings come with caveats: the cross-sectional design precludes causal claims, the convenience sample of education students from a single faculty limits generalizability, and self-reported questionnaires may not reflect actual CPR competency. Still, the central message is clear and actionable, aligning with expert calls to embed CPR and defibrillator training in schools and colleges nationwide. Communities with high bystander CPR rates see substantially better survival after out-of-hospital cardiac arrest, and young people, armed with practical experience rather than theory alone, are best positioned to become the life-saving bridge between collapse and definitive care.

Subject of Research: First aid and CPR confidence, training gaps, and preparedness among university students in Varanasi, India

Article Title: The state of first aid & cardio-pulmonary resuscitation: assessment of confidence, support, and perceptions in the wake of a health emergency among students of Banaras Hindu University, Varanasi

Article References: The state of first aid & cardio-pulmonary resuscitation: assessment of confidence, support, and perceptions in the wake of a health emergency among students of Banaras Hindu University, Varanasi. (n.d.). https://doi.org/10.1007/s44467-026-00016-x

Image Credits: AI Generated

DOI: 10.1007/s44467-026-00016-x

Keywords: cardiopulmonary resuscitation, first aid, bystander CPR, cardiac arrest, health emergency preparedness, CPR training, university students, gender disparity, basic life support, COVID-19, India, Banaras Hindu University

Cardiac arrest remains one of the most time-critical emergencies in medicine. Survival depends overwhelmingly on what happens in the first minutes, and high-quality CPR, delivered with correct posture, depth and sequence, is one of the few interventions bystanders can provide before emergency services arrive. Yet training outcomes vary widely, and studies cited by the authors point to persistent challenges in nursing education and public awareness campaigns across Europe. Traditional CPR courses rely on instructors observing multiple trainees at once, which makes fine-grained, continuous correction of every compression and hand position practically impossible. The new system was designed to fill that gap by acting as a tireless, always-attentive digital assistant that evaluates every movement the moment it happens.

The technical core of the system is a two-stage pipeline. The first stage uses HRNet, a deep neural network architecture for human pose estimation that maintains high-resolution representations throughout its processing stages. Unlike architectures that downscale images and then attempt to recover spatial detail, HRNet preserves fine-grained information about body joints, which is essential for CPR, where subtle deviations in arm angle or shoulder alignment can mean the difference between effective and ineffective chest compressions. The network converts a standard camera feed into a skeletal representation of the trainee, a stick-figure abstraction that captures where the head, shoulders, elbows, wrists, hips and knees are in each frame.

The second stage takes those skeleton sequences and classifies what the trainee is actually doing. The researchers employed ST-GCN++, an improved version of the Spatio-Temporal Graph Convolutional Network, a class of models built specifically for skeleton-based action recognition. A human skeleton is naturally a graph: joints are nodes, and bones are edges. A graph convolutional network propagates information across that graph, learning patterns both in space, how the joints relate to each other in a single frame, and in time, how those relationships evolve across a sequence of frames. The “plus-plus” refinement adds improved backbone design and multi-stream inputs, boosting accuracy without requiring enormous computational resources.

To make the system work in real time, the team segmented the streaming video into short clips, classified the CPR actions on the fly, and compared the recognized action sequence against the standard CPR procedure. This is where the “process-aware” component comes in. The system does not merely ask whether a given movement resembles a chest compression; it tracks whether the actions are happening in the correct order, whether the posture matches the protocol, and whether the trainee is hesitating. When execution order or posture deviates from the standard procedure, the system immediately triggers audio-visual prompts, essentially coaching the learner in the moment rather than after the fact. The architecture is deliberately lightweight and runs on commodity hardware, a design decision that opens the door to deployment in schools, community centers, and remote or resource-constrained settings where expensive manikin sensor systems are unavailable.

The machine-learning performance figures are strong. Evaluated with randomized segment-level splits, the action classifier achieved an accuracy of 0.93 and a recall of 0.93, with a balanced accuracy of 0.91 and a macro-averaged F1-score of 0.91. The use of balanced accuracy and macro-averaged F1 indicates the team was attentive to class imbalance, ensuring the model performs well across all CPR action categories rather than excelling only on the most common ones. The researchers framed the entire work as a controlled feasibility study, and were careful to note that the model evaluation used segment-level randomization, a detail that matters because action-recognition models can sometimes exploit temporal redundancy between adjacent clips if data splitting is not handled properly.

The team then took the system out of the lab’s benchmark datasets and into a quasi-experimental training study. Sixty participants were divided into two groups of thirty. One group received traditional instructor-led CPR training; the other trained with the intelligent feedback system. The entire experiment, including participant briefing, a pre-test, instructor-led instruction, group-based practice, and post-test assessment, was completed over approximately eight hours. Performance after training was assessed by a blinded CPR instructor, who scored each participant on action sequence correctness and hesitation duration without knowing which group the participant had belonged to, a design choice that reduces evaluator bias.

The results were unambiguous. The group trained with the intelligent system significantly outperformed the traditional training group in skill execution, with a mean score of 89 versus 72, a difference that was highly statistically significant with p less than 0.001 and a large effect size, reflected in a rank-biserial correlation of 0.606. In practical terms, trainees who received instant AI feedback not only performed better but also hesitated less, suggesting the system helped them internalize the correct procedural sequence rather than forcing them to consciously recall it under pressure. The experimental group also reported lower cognitive load, measured with established psychological instruments, an outcome the authors link to the way immediate, automated feedback relieves learners of the burden of self-monitoring while performing a physically and mentally demanding task.

Usability and satisfaction metrics told a similar story. The system achieved a System Usability Scale score of 78.6, placing it in the upper range of the widely used 0-to-100 usability instrument, and participants expressed greater satisfaction with their training experience compared with the traditional group. The authors suggest that skeleton-based action recognition coupled with real-time multisensory feedback can support practical skill acquisition and learner confidence in a controlled feasibility setting, and that the reduction in cognitive load may be a key mechanism behind the improved learning outcomes, since overload during skill practice is known to impair retention.

The implications extend well beyond CPR. The study’s authors, Ming-Chuan Chiu and Zi-Heng Huang of National Tsing Hua University and Meng-Chun Kao of Yuanpei University of Medical Technology, note that the same skeleton-based approach could be extended, after further validation and runtime profiling, to other skill-based domains, from industrial assembly and physical rehabilitation to surgical technique and workplace safety training. Because the system needs only a camera and commodity computing hardware, it avoids the cost barrier of sensor-instrumented manikins, which could make high-quality, feedback-rich training accessible in low-resource environments and remote learning scenarios where certified instructors are scarce.

The research was supported by the National Science and Technology Council, Taiwan, and approved by the Research Ethics Review Committee of National Tsing Hua University. The team emphasizes that the work remains a feasibility study: larger samples, longer-term retention testing and real-world deployment studies will be needed before the system can be recommended as a replacement for, rather than a supplement to, certified CPR instruction. But the combination of near-human-level action recognition accuracy, measurable improvements in trainee performance, and a lightweight, hardware-agnostic design makes a compelling case that the next generation of life-saving training may not need a human eye on every compression, only a camera, a skeleton, and a graph neural network watching the bones move.