Successful Evacuation Research Articles

Reinforcement learning-based Tsunami evacuation guidance system

Congestion and crowding are critical issues during indoor and outdoor emergency evacuations. In the 2011 Great East Japan Earthquake and Tsunami, vehicle traffic was one of the causes of the event’s casualties. After this, vehicle evacuation in tsunami events is not advised in Japan. Then, pedestrian evacuation is expected to be the primary mode of mobility in emergencies. However, crowding and congestion may affect the evacuation time of individuals and the overall outcome of the process. In addition, narrow streets and a high preference for the shortest routes may worsen the situation. This study aims to find the best evacuation route for a target population, considering less congestion in the road network and increasing the chances of reaching safe areas on time. We propose using reinforcement learning to train an intelligent network of agents, placed at the intersections, in charge of the evacuation process to fully complying evacuee agents. The model rewards decisions that lead to successful evacuation, considering the dynamics of departure times and street congestion throughout the simulation. We demonstrate the applicability of reinforcement learning to guide tsunami evacuation in a simulation and test this against a non-guided case where evacuees move following the shortest paths. Results show that the reinforcement learning model yields better outcomes than evacuations following the shortest paths.

Experimental and interpretable machine learning-based analysis of pedestrian evacuation behavior in attack situations

Previous studies have extensively examined pedestrian evacuation behavior during emergencies such as fires. However, few studies have focused on evacuation behavior during violent attacks. In this paper, we design an experiment to simulate a violent attack and study the evacuation behavior of pedestrians during such an event. A random forest model is used to predict evacuation outcomes based on experimental data. Additionally, we employ interpretable machine learning methods, specifically Partial Dependence Plots (PDPs) and Individual Conditional Expectation (ICE), to investigate the variables influencing evacuation outcomes. The results indicate that the distance variable is the key variable influencing evacuation outcomes, followed by preparation time. Generally, shorter preparation time is beneficial to a higher probability of successful evacuation. However, immediate action after identification of the attacker is instead associated with a lower probability of successful evacuation. Moreover, shorter preparation time is also related to lower probabilities of successful evacuation when approaching the attacker. The number of attackers and exits has exerted a relatively limited monotonic influence. This study contributes to the development of safety guidelines and contingency plans in the event of a violent attack.

First experience of endovascular balloon occlusion of the aorta in the wounded with hemorrhagic shock during the war in Ukraine

Background. Resuscitative endovascular balloon occlusion of the aorta (REBOA) is used worldwide to stop bleeding in trauma and wounds in patients with hemorrhagic shock. REBOA allows for the hemodynamic stabilization, patient transportation and final bleeding control. The study aims to demonstrate the capabilities of REBOA as a method of bleeding control in the wounded with hemorrhagic shock in the context of war in Ukraine. Materials and methods. Five AFU servicemen who sustained mine-blast wounds in the Eastern Ukraine as a result of shelling by Russian troops were delivered with signs of internal bleeding and hemorrhagic shock to the primary and secondary levels of medical care (Role 1, 2). The REBOA balloon catheter was inserted and inflated by surgeons working in stabilization centers or advanced surgical teams. Upon admission, all patients underwent chest and abdominal ultrasound according to the FAST protocol. We used COBRA-OS 4 Fr and ER-REBOA 7 Fr balloon catheters. The positioning of the balloon in the aorta was performed according to external anatomical landmarks (3 cases) and ultrasound (2 cases). In all clinical cases, the balloon catheter was placed in zone I. In one case, the balloon was moved from zone I to zone III (control of the source of bleeding). The duration of aortic occlusion ranged from 15 to 50 minutes. Immediately after removal of the introducer, manual compression of the puncture site was used (3 cases) or suturing of the arteriotomy (2 cases). Results. The sources of bleeding in our clinical cases were injuries of the iliac vessels (2 cases), the renal artery (1 case), and injuries of the inferior vena cava and liver (2 cases). Four patients were evacuated to a higher level of medical care after the REBOA was installed. In one case, there were complications from vascular access (femoral artery thrombosis). We were unable to save one wounded soldier, most likely due to the delay in evacuation from the previous stage, the severity of injury, and massive blood loss. Conclusions. As our observations have shown, the use of REBOA in combat conditions allows not only to stabilize hemodynamics in the wounded with severe combined trauma and bleeding but also to conduct a successful evacuation to a higher level of medical care to stop bleeding ultimately. REBOA can be successfully used at the prehospital stage. This requires clearly defined indications for the technique’s use, training of medical personnel, and provision of balloon catheters to medical units of the Armed Forces of Ukraine.

Pain Scoring in Uterine Evacuation for Incomplete Abortion Using Isolated Paracervical Block vs Combined Paracervical and Intrauterine Lignocaine Instillation: A Randomized Clinical Trial

Abstract Background Nerve block is a technique whereby local anesthetic solutions are infiltrated around a nerve (or perineurally) to provide anesthesia and analgesia. Nerve block for intraoperative and postoperative pain management is associated with improved analgesia, fewer opioid-related adverse events, earlier ambulation and shorter hospital stay when compared to intravenous opioid analgesia alone. Objective To compare efficacy of paracervical block alone versus combined paracervical block and intrauterine lidocaine installation in pain management of first trimesteric incomplete abortion. Patients and Methods A total of 80 women with first trimesteric incomplete miscarriage were admitted to the emergency department for uterine evacuation at Ain Shams University Maternity Hospital, in the period from September 2021 to September 2023 and underwent uterine evacuation using either paracervical block or combined paracervical block and intrauterine lidocaine instillation then pain score was obtained using visual analogue scale. Pain score was done 10 minutes after injection of local anaesthetic, 5 minutes after starting procedure and 1 hour postevacuation. Results It also showed that there was no statistically significant difference between both groups regarding need of opioids and time interval till opioids need. Exploring other factors that might have affected the success or failure of procedure in the study population it was found that age, parity were significant predictors such that the younger the age, the less the parity the more likely failure of procedure. Also being previous section was linked more to success than failure. Conclusion The combination of intrauterine lidocaine and paracervical block has no additive effect on conventional paracervical block in reducing the pain during uterine evacuation for incomplete abortion, but successful evacuation resulted in lower pain score and reduced needs for opioid.

A Bayesian agent-based model and software for wildfire safe evacuation planning and management

Efficient evacuation of wildfire-threatened communities is a pressing challenge. A reliable evacuation planning and execution requires a comprehensive understanding of the diverse and interdependent physical, social, and behavioral components, and advanced, yet easy to use decision support system. This paper proposes the Wildfire Safe Egress (WiSE) framework, which integrates the fire dynamics, human behavior, and traffic model to predict the chance of safe egress by any given community during a wildfire evacuation. WISE framework presents a unified dependency diagram and workflow offering consistent granularity between sub-models and creates comparable evacuation scenarios. A human behavior model is proposed to predict the community decision making and action based on their socio-demographic vulnerability profile. An agent-based stochastic approach generates evacuation departure times. The travel times are calculated through a congestion-informed traffic simulation. Finally, a Bayesian Network is used to combine the sub-models and to predict community safety (probability of successful evacuation) via probabilistic inference based on the integrated model. A proof-of-concept software implementation of the WiSE framework is also presented. To demonstrate the model and platform capabilities the evacuation of the entire city of Paradise during the California Camp Fire 2018 is simulated. The simulation results are qualitatively validated by the firefighters who served in this disaster. A sensitivity analysis of the parameters is performed to compare several evacuation scenarios and provide insights for future wildfire evacuation plannings.

Crowd navigation for dynamic hazard avoidance in evacuation using emotional reciprocal velocity obstacles

Crowd evacuation can be a challenging task, especially in emergency situations involving dynamically moving hazards. Effective obstacle avoidance is crucial for successful crowd evacuation, particularly in scenarios involving dynamic hazards such as natural or man-made disasters. In this paper, we propose a novel application of the emotional reciprocal velocity obstacles (ERVO) method for obstacle avoidance in dynamic hazard scenarios. ERVO is an established method that incorporates agent emotions and obstacle avoidance to produce more efficient and effective crowd navigation. Our approach improves on previous research by using ERVO to model the perceptive danger posed by dynamic hazards in real-time, which is crucial for rapid response in emergency situations. We conducted experiments to evaluate our approach and compared our results with other velocity obstacle methods. Our findings demonstrate that our approach is able to improve agent coordination, reduce congestion, and produce superior avoidance behavior. Our study shows that incorporating emotional reciprocity into obstacle avoidance can enhance crowd behavior in dynamic hazard scenarios.

Diagnostic value of bedside lung ultrasound and 12-zone score in the 65 cases of neonatal respiratory distress syndrome and its severity

ObjectiveTo explore the predictive value of bedside lung ultrasound score in the severity of neonatal respiratory distress syndrome (NRDS) and mechanical ventilation and extubation.MethodsThe clinical data of 65 neonates with NRDS and invasive mechanical ventilation diagnosed in the neonatal intensive care unit of our hospital from July 2021 to July 2022 were retrospectively analyzed. 65 neonates were included in the NRDS group, and 40 neonates with other common lung diseases were selected as the other lung disease groups. All neonates underwent lung ultrasound and X-ray examination. The correlation between lung ultrasound scores and arterial blood gas indexes was analyzed by Pearson. The efficacy of successful evacuation of mechanical ventilation was evaluated by lung ultrasound analysis by ROC curve analysis.ResultsThe positive rates of lung consolidation and white lung in NRDS group were higher than the other lung disease groups (P < 0.05). The positive rates of bronchial inflation sign and double lung points were lower than these in the other lung disease groups (P < 0.05). The ultrasound scores of both lungs, left lung, right lung, bilateral lung and double basal lung in the NRDS group were significantly higher than those in the other lung disease groups (P < 0.05). There was a significant positive correlation between lung ultrasound score and X-ray grade (r = 0.841, P < 0.001). The area under the curve (AUC) of lung ultrasound score for the differential diagnosis of NRDS and common lung diseases was 0.907. The AUC of lung ultrasound score in the differential diagnosis of mild and moderate, and moderate and severe NRDS were 0.914 and 0.933, respectively, which had high clinical value. The lung ultrasound score was positively correlated with the level of PaCO2 (r = 0.254, P = 0.041), and negatively correlated with the levels of SpO2 and PaO2 (r = − 0.459, − 0.362, P = 0.001, 0.003). The AUC of successful mechanical ventilation withdrawal predicted by the pulmonary ultrasound score before extubation was 0.954 (95% CI 0.907–1.000). The predictive value of successful extubation was 10 points of the pulmonary ultrasound score, with a sensitivity of 93.33% and a specificity of 88.00%.ConclusionThe bedside lung ultrasound score can intuitively reflect the respiratory status of neonates, which provides clinicians with an important basis for disease evaluation.

Untoward outcomes of successful chronic subdural hematoma evacuation, cortical blindness and brain stem stroke: A Case series

Chronic subdural hematoma (CSDH) is one of the most commonly encountered emergencies in neurosurgery practice. Burr hole with drainage of hematoma has been a time-tested standard treatment with good results and in itself a simple procedure to relieve patient clinical status. However, apparently simple surgery may at times have an unexpected surgical outcome of bilateral vision loss. All bilateral CSDHs should be treated diligently with early recognition of any visual deterioration in post-operative phase if any and due to possible interventions to be offered to the patients for prevention of permanent vision loss.

Mid-Sea Amputation of a Russian Engineer's Hand, Successful Medical Evacuation by Indian Coastguards and Replantation in Mangalore City: 19-Year Survival.

Mid-Sea Amputation of a Russian Engineer's Hand, Successful Medical Evacuation by Indian Coastguards and Replantation in Mangalore City: 19-Year Survival.

Simulated interventions based on virtual reality to improve emergency evacuation under different spatial perception models

People's emergency evacuation behavior is heavily reliant on spatial knowledge. Different spatial cognitive ways shape spatial knowledge differently. To investigate the effect of different cognitive ways on people's wayfinding performance in an indoor fire situation. The study used a virtual reality simulation of a shopping mall environment, and 128 participants were recruited for the experiment. The experiment divided the participants into six groups and placed them in two scenarios, one with and one without fire. This study also explored two other intervention behaviors to improve the participants' evacuation behaviors. The results showed that participants who used navigation had shorter walking distances and wayfinding times than those who used the You are here (YAH) map. Secondly, participants in the fire scenario walked longer distances and took longer to evacuate than those in the no-fire scenario, and they perceived successful evacuation to be more difficult. Thirdly, the intervention behavior effectively improved the participants' evacuation behavior and increased the efficiency of the evacuation. The leader's intervention was more effective in helping participants evacuate than the range intervention in this experimental setting. The findings may advance the understanding of human evacuation behavior and provide important practical implications for people's safety and emergency preparedness in shopping malls.

Explaining Factors Affecting Flood Evacuation From the Point of View of Stakeholders: A Content Analysis Study

Background: Floods are a natural hydrological hazard that causes human and environmental damage. In the response phase, evacuation is necessary to reduce deterioration. This study explains the influential factors on flood evacuation based on the opinion of the stakeholders. Materials and Methods: This is a conventional content analysis study conducted in 2021. A total of 27 participants were selected using the purposive sampling method. Data collection was performed using semi-structured interviews. Interviews continued until information saturation was reached. The recorded interviews were handwritten word by word and then analyzed. The criteria for entering the study included flood experience, the ability to communicate, and willingness to participate. The period of the interview was 40 to 70 min. Written consent was obtained from the interviewees for audio recording. The Granheim and Lundman method was used for data analysis. This study’s reliability was based on the Goba and Lincoln method. Results: Data analysis extracted four main categories with ten sub-categories, including human factors (a subcategory of individual characteristics and risk perception), social factors (a sub-category of cultural conditions and financial status), geographical factors (a sub-category of urban location and climate conditions), and infrastructure factors (a sub-category of facilities related to transportation tools and routes, urban constructions, communication infrastructure, and meteorological facilities). Conclusion: Reaching a successful evacuation requires determining the relevant factors. These factors include human, social, geographic, and infrastructure factors. The findings of this study can help managers in flood management.

Efficacy of single burr hole with irrigation and sub-dural drain in the evacuation of chronic subdural hematoma

BackgroundChronic subdural hematoma (CSDH) remains one of the most common types of traumatic and spontaneous intracranial hematomas. The optimal method of treatment has not been definitely established. Surgical treatment options includes craniotomy, trephination, burrhole drainage and twist drill perforation. This study aimed at the evaluation of the clinical and radiological outcome after the efficacy of single burr hole with irrigation and sub-dural drain in the aim of successful evacuation of CSDH.ResultsA total of 53 patients were included in this study, the mean age of patients was 61.53 + 13.81 years. Results of the paired t test showed that the Glasgow coma scale has significantly improved by 0.89 points (p < 0.001) and that the average motor power has significantly improved for all individuals by 0.4 points (p = 0.043). We found that older aged patients have significantly less improvements in the postoperative motor power (r = − 0.317, p = 0.02) and require longer hospital stay (r = 0.32, p = 0.0197).ConclusionsA single burr hole with irrigation and leaving a subdural drain is safe procedure in managing subdural hematoma. We did not experience major adverse events related to drain insertion and efficient evacuation of collection and no obvious increase in mortality or morbidity rates.

Mapping of 2021–2022 floods in North America from street photos with artificial intelligence

Successful flood response and evacuation require timely access to reliable flood depth information in urban areas. However, existing flood-depth-mapping tools do not provide real-time flood depth information in residential areas. In this paper, a deep convolutional neural network is used to determine flood depth through the analysis of crowdsourced images of submerged stop signs. Model performance in pole length estimation is tested on a test set, achieving a root mean squared error of 10.200 in. (1 in. = 1 inch = 2.54 cm) on pre-flood photographs and 6.156 in. on post-flood photographs and an average processing time of 0.05 s. The performance of the developed model is tested on two case studies: Hurricane Ian in the USA (2022) and the Pacific Northwest floods in the USA and Canada (2021), yielding mean absolute errors (MAEs) of 4.375 and 6.978 in., respectively. The overall MAE for both floods is achieved as 5.807 in., which is on par with those from previous studies. Additionally, detected flood depths are compared with readings reported by the nearest flood gauge on the same date. The outcome of this study demonstrates the applicability of this approach to low-cost, accurate, scalable and real-time flood risk mapping in most geographical locations, particularly in places where flood gauge reading is not feasible.

Endoscopic evacuation of chronic subdural hematoma with rigid and flexible endoscope: case report

Introduction: Subdural haematoma (SDH) is a common neurosurgical condition after head trauma requiring evacuation to prevent secondary brain injury. The first choice of management in these patients is a large craniotomy or burr-hole evacuation. However, sometimes due to lack vision during drain tube insertion or irrigation the authors might land up in a complication like cortical bridging vein rupture, haemorrhage etc. Also, the management of septate chronic SDH (CSDH) with multiple neo-membranes does not have a well-defined surgical approach. Recently, endoscopic evacuation has been reported to a be a feasible method for evacuation in acute, subacute and chronic SDH patients. Presentation of case: A 65-years-old male patient presented with a history of recent head injury and symptoms of headache and urinary incontinence of 7 days (Glasgow Coma Scale Score 15/15). Computed tomography scan revealed CSDH at both fronto-parietal convexity more on right side. Discussion: The authors reported our initial experience on a typical case of an older patient with chronic subdural haematoma and its evacuation with the assistance of both rigid and flexible endoscope. The authors could visualize cortical bridging veins and neo-membranes intraoperatively and guided our drainage tube accordingly to avoid inadvertent haemorrhage. There was no recurrence of symptoms postoperatively. Thus we achieved apparent successful evacuation of the CSDH in this patient in a 6-month follow-up. Conclusion: Endoscopic evacuation of CSDH proves to be an effective minimally invasive modality and more studies are required on larger patient groups with long-term follow-up imaging to confirm its superiority.

Application of 3D visualization technology based on hematoma edge key points setting for emergency hypertensive cerebral hemorrhage surgery in primary hospitals

ObjectiveThis study aims to explore the application potential of 3D visualization technology based in emergency hypertensive cerebral hemorrhage surgery in primary hospitals. The specific goal is to use 3DSlicer software to perform 3D reconstruction and body surface projection on patients with hypertensive cerebral hemorrhage, provide accurate hematoma location information, help surgeons determine the specific location of hematoma on the body surface, and reduce the expansion of surgical incisions. Methods3D reconstruction technology based on 3DSlicer software was employed to process CT images of patients with cerebral hemorrhage. By segmenting and reconstructing the images, a 3D model of the hematoma was generated and projected onto the patient's body surface. Utilizing the functionalities of 3DSlicer software in conjunction with the surgeon's anatomical knowledge, accurate hematoma positioning on the body surface was achieved. Results23 patients were enrolled in this study, and underwent successful surgical evacuation. The implementation of 3D visualization technology using 3DSlicer software is expected to provide precise hematoma localization information for emergency hypertensive intracerebral hemorrhage surgery in primary hospitals. This approach will enable surgeons to accurately determine the appropriate surgical incision, thereby minimizing unnecessary trauma and improving the overall success rate of surgery. ConclusionThis study demonstrates the potential application of 3D visualization technology based on 3DSlicer software in emergency hypertensive cerebral hemorrhage surgery within primary hospitals. By utilizing 3DSlicer software for hematoma localization, accurate information support can be provided to assist surgeons in managing patients with hypertensive cerebral hemorrhage.

Transdisciplinary Approach Toward Preparedness in a Mountainous Community in Central Taiwan and its Impact on Disaster Evacuation: A Case Study

This study examined the main factor that helped residents of Xinshan Village—which is vulnerable to landslides and debris flow hazards—to react and respond to Typhoon Morakot in such a way that no casualties were reported during the severe event in 2009. When the typhoon hit, over 20 residential houses collapsed into a river and were washed away during the night. However, the locals were evacuated before the disaster struck, which was attributed to the timely actions and cooperation that had occurred between them with their village head and the local police. Apart from them, it was also found that the central government, local government, academics, and engineering firms had played a crucial role that contributed to the preparedness of the locals to respond to the natural disaster. Specifically, assistance and resources were provided to them according to the disaster mitigation act, detailed risk reduction plans were drawn up at the town and village levels, drills and evacuation practices were held, and an early warning system was established and its robustness was tested. Prior to the 2009 typhoon, the practice of a transdisciplinary approach (TDA) toward disaster risk reduction in Xinshan Village had fostered its disaster preparedness. Consequently, TDA was identified as a key factor that had contributed to the successful evacuation of its residents before the village was hit by the typhoon.

Applications of supraorbital keyhole craniotomy in pediatric cranial trauma: illustrative series of two cases and systematic literature review.

Minimally invasive (MIS) approaches to neurosurgical diseases continue to increase in popularity due to their association with decreased infection risk, shorter recovery time, and improved cosmesis. Cosmesis and lower morbidity are especially important for pediatric patients. The supraorbital keyhole craniotomy (SOKC) is one MIS approach shown to be effective for both neoplastic and vascular pathologies in pediatric patients. However, it is limited data on its use in pediatric trauma patients. Two cases employing SOKC in pediatric trauma patients are presented here along with a systematic review of the literature. We queried PubMed, Scopus, and Web of Science databases from inception to August 2022 using the Boolean search term: (supraorbital OR eyebrow OR transeyebrow OR suprabrow OR superciliary OR supraciliary) AND (craniotomy OR approach OR keyhole OR procedure) AND (pediatric OR children OR child OR young) AND "trauma". Studies that discussed the use of an SOKC in a pediatric patient having sustained trauma to the frontal calvarium and/or anterior fossa/sellar region of the skull base were included. Details were extracted on patient demographics, trauma etiology, endoscope use, and surgical and cosmetic outcomes. We identified 89 unique studies, of which four met inclusion criteria. Thirteen total cases were represented. Age and sex were reported for 12 patients, 25% of whom were male; the mean age was 7.5years (range: 3-16). Pathologies included acute epidural hematoma (9), orbital roof fracture with dural tear (1), blowout fracture of the medial wall of the frontal sinus with supraorbital rim fracture (1), and compound skull fracture (1). Twelve patients were treated with a conventional operating microscope, while one underwent endoscope-assisted surgery. Only one significant complication (recurrent epidural hematoma) was reported. There were no reported cosmetic complications. The MIS SOKC approach is a reasonable option for select anterior skull base trauma in the pediatric population. This approach has been used previously for successful frontal epidural hematoma evacuation, which is often treated by a large craniotomy. Further study is merited.

Shelter GO: multiplayer location-based game to promote knowing shelters for emergency evacuation

In the event of a disaster, we evacuate to a shelter. However, if we do not know where to go for refuge, we consume time or end ourselves at an unknown shelter. Furthermore, we cannot decide on a suitable shelter if we do not know its capacities and features. To promote knowing shelters in advance is essential for successful emergency evacuation. A promoting approach is the use of a location-based game. Thus, a prototype of a multiplayer location-based game known as “Shelter GO” was developed to promote players to become acquainted with shelters by adopting a game element similar to Pokémon GO. The game feature allows players to not only earn points by visiting and observing shelters and collecting digital creatures at disaster-related spots but also exchange their collected digital creatures with encountered players. The digital creature exchange entails knowledge exchange. A preliminary comparative experiment demonstrated that Shelter GO can promote knowing shelters and that knowledge exchange may not be frequently done but promote knowing shelters.

Evacuation behavior under violent attacks in classrooms based on experiments and interpretable machine learning method

Extremely violent crimes seriously affect campus safety. However, there is a lack of studies on evacuation behavior in such events, and there are no effective strategies for emergency response and evacuation. To better understand evacuation behavior in campus violent attacks, this paper designs an experiment of classroom violent attacks and tries to predict the evacuation outcome with random forest algorithm based on the experimental data. Then an interpretable machine learning method named Shapley Addictive Explanations is used to study the factors affecting the evacuation outcome. The results show that the random forest model outperforms other models in prediction, with an accuracy of 96.5% on the validation set. The mean distance between participants and attacker is the most important factor with a positive effect. The second most important variable is the evacuation preparation time, with shorter preparation time being related to a higher probability of successful evacuation, except in cases where the attacker is noticed just before the attack is about to occur. Participants are more likely to successfully evacuate if they are seated in the middle row rather than in the front and back, but there exists a complex interaction between the initial location and attack route. The attack route and classroom type have a small influence, while the effect is monotonic: the attacker entering through the front door, as well as the examination classroom layout, are associated with increased chances of a successful evacuation. This study can contribute to developing security guidelines and contingency plans for campus violent attacks.

Location-Based Game for Thought-Provoking Evacuation Training

Participation in evacuation training can aid survival in the event of an unpredictable disaster, such as an earthquake. However, conventional evacuation training is not well designed for provoking critical thinking in participants regarding the processes involved in a successful evacuation. To realize thought-provoking evacuation training, we developed a location-based game that presents digital materials that express disaster situations corresponding to locations or times preset in a scenario and providing scenario-based multi-ending as the game element. The developed game motivates participants to take decisions by providing high situational and audiovisual realism. In addition, the game encourages the participants to think objectively about the evacuation process by working together with a reflection-support system. We practiced thought-provoking evacuation training with fifth-grade students, focusing on tsunami evacuation and lifesaving-related moral dilemmas. In this practice, we observed that the participants took decisions as if they were dealing with actual disaster situations and objectively thought about the evacuation process by reflecting on their decisions. Meanwhile, we found that lifesaving-related moral dilemmas are difficult to address in evacuation training.