Stress induces behavioral abnormalities by increasing expression of phagocytic receptor MERTK in astrocytes to promote synapse phagocytosis.

Childhood neglect and/or abuse can induce mental health conditions with unknown mechanisms. Here, we identified stress hormones as strong inducers of astrocyte-mediated synapse phagocytosis. Using in vitro, in vivo, and human brain organoid experiments, we showed that stress hormones increased the expression of the Mertk phagocytic receptor in astrocytes through glucocorticoid receptor (GR). In post-natal mice, exposure to early social deprivation (ESD) specifically activated the GR-MERTK pathway in astrocytes, but not in microglia. The excitatory post-synaptic density in cortical regions was reduced in ESD mice, and there was an increase in the astrocytic engulfment of these synapses. The loss of excitatory synapses, abnormal neuronal network activities, and behavioral abnormalities in ESD mice were largely prevented by ablating GR or MERTK in astrocytes. Our work reveals the critical roles of astrocytic GR-MERTK activation in evoking stress-induced abnormal behaviors in mice, suggesting GR-MERTK signaling as a therapeutic target for stress-induced mental health conditions.

Microglial MERTK eliminates phosphatidylserine-displaying inhibitory post-synapses.

Glia contribute to synapse elimination through phagocytosis in the central nervous system. Despite the important roles of this process in development and neurological disorders, the identity and regulation of the "eat-me" signal that initiates glia-mediated phagocytosis of synapses has remained incompletely understood. Here, we generated conditional knockout mice with neuronal-specific deletion of the flippase chaperone Cdc50a, to induce stable exposure of phosphatidylserine, a well-known "eat-me" signal for apoptotic cells, on the neuronal outer membrane. Surprisingly, acute Cdc50a deletion in mature neurons causes preferential phosphatidylserine exposure in neuronal somas and specific loss of inhibitory post-synapses without effects on other synapses, resulting in abnormal excitability and seizures. Ablation of microglia or the deletion of microglial phagocytic receptor Mertk prevents the loss of inhibitory post-synapses and the seizure phenotype, indicating that microglial phagocytosis is responsible for inhibitory post-synapse elimination. Moreover, we found that phosphatidylserine is used for microglia-mediated pruning of inhibitory post-synapses in normal brains, suggesting that phosphatidylserine serves as a general "eat-me" signal for inhibitory post-synapse elimination.

Adolescent Parvalbumin Expression in the Left Orbitofrontal Cortex Shapes Sociability in Female Mice.

The adolescent social experience is essential for the maturation of the prefrontal cortex in mammalian species. However, it still needs to be determined which cortical circuits mature with such experience and how it shapes adult social behaviors in a sex-specific manner. Here, we examined social-approaching behaviors in male and female mice after postweaning social isolation (PWSI), which deprives social experience during adolescence. We found that the PWSI, particularly isolation during late adolescence, caused an abnormal increase in social approaches (hypersociability) only in female mice. We further found that the PWSI female mice showed reduced parvalbumin (PV) expression in the left orbitofrontal cortex (OFCL). When we measured neural activity in the female OFCL, a substantial number of neurons showed higher activity when mice sniffed other mice (social sniffing) than when they sniffed an object (object sniffing). Interestingly, the PWSI significantly reduced both the number of activated neurons and the activity level during social sniffing in female mice. Similarly, the CRISPR/Cas9-mediated knockdown of PV in the OFCL during late adolescence enhanced sociability and reduced the social sniffing-induced activity in adult female mice via decreased excitability of PV+ neurons and reduced synaptic inhibition in the OFCL Moreover, optogenetic activation of excitatory neurons or optogenetic inhibition of PV+ neurons in the OFCL enhanced sociability in female mice. Our data demonstrate that the adolescent social experience is critical for the maturation of PV+ inhibitory circuits in the OFCL; this maturation shapes female social behavior via enhancing social representation in the OFCL SIGNIFICANCE STATEMENT Adolescent social isolation often changes adult social behaviors in mammals. Yet, we do not fully understand the sex-specific effects of social isolation and the brain areas and circuits that mediate such changes. Here, we found that adolescent social isolation causes three abnormal phenotypes in female but not male mice: hypersociability, decreased PV+ neurons in the left orbitofrontal cortex (OFCL), and decreased socially evoked activity in the OFCL Moreover, parvalbumin (PV) deletion in the OFCL in vivo caused the same phenotypes in female mice by increasing excitation compared with inhibition within the OFCL Our data suggest that adolescent social experience is required for PV maturation in the OFCL, which is critical for evoking OFCL activity that shapes social behaviors in female mice.

Abnormal Lymphatic Sphingosine-1-Phosphate Signaling Aggravates Lymphatic Dysfunction and Tissue Inflammation.

BACKGROUND: Lymphedema is a global health problem with no effective drug treatment. Enhanced T-cell immunity and abnormal lymphatic endothelial cell (LEC) signaling are promising therapeutic targets for this condition. Sphingosine-1-phosphate (S1P) mediates a key signaling pathway required for normal LEC function, and altered S1P signaling in LECs could lead to lymphatic disease and pathogenic T-cell activation. Characterizing this biology is relevant for developing much needed therapies. METHODS: Human and mouse lymphedema was studied. Lymphedema was induced in mice by surgically ligating the tail lymphatics. Lymphedematous dermal tissue was assessed for S1P signaling. To verify the role of altered S1P signaling effects in lymphatic cells, LEC-specific S1pr1-deficient (S1pr1LECKO) mice were generated. Disease progression was quantified by tail-volumetric and -histopathologic measurements over time. LECs from mice and humans, with S1P signaling inhibition, were then cocultured with CD4 T cells, followed by an analysis of CD4 T-cell activation and pathway signaling. Last, animals were treated with a monoclonal antibody specific to P-selectin to assess its efficacy in reducing lymphedema and T-cell activation. RESULTS: Human and experimental lymphedema tissues exhibited decreased LEC S1P signaling through S1P receptor 1 (S1PR1). LEC S1pr1 loss-of-function exacerbated lymphatic vascular insufficiency, tail swelling, and increased CD4 T-cell infiltration in mouse lymphedema. LECs, isolated from S1pr1LECKO mice and cocultured with CD4 T cells, resulted in augmented lymphocyte differentiation. Inhibiting S1PR1 signaling in human dermal LECs promoted T-helper type 1 and 2 (Th1 and Th2) cell differentiation through direct cell contact with lymphocytes. Human dermal LECs with dampened S1P signaling exhibited enhanced P-selectin, an important cell adhesion molecule expressed on activated vascular cells. In vitro, P-selectin blockade reduced the activation and differentiation of Th cells cocultured with shS1PR1-treated human dermal LECs. P-selectin-directed antibody treatment improved tail swelling and reduced Th1/Th2 immune responses in mouse lymphedema. CONCLUSIONS: This study suggests that reduction of the LEC S1P signaling aggravates lymphedema by enhancing LEC adhesion and amplifying pathogenic CD4 T-cell responses. P-selectin inhibitors are suggested as a possible treatment for this pervasive condition.

Stepwise development and expansion of an abdominal normothermic regional perfusion program for donation after circulatory determination of death organ procurement.

INTRODUCTION: Normothermic regional perfusion (NRP) represents an innovative technology that improves the outcomes for liver and kidney recipients of donation after circulatory determination of death (DCD) organs but protocols for abdominal-only NRP (A-NRP) DCD are lacking in the US. METHODS: We describe the implementation and expansion strategies of a transplant-center-based A-NRP DCD program that has grown in volume, geographical reach, and donor acceptance parameters, presented as four eras. RESULTS: In the implementation era, two donors were attempted, and one liver graft was transplanted. In the local expansion era, 33% of attempted donors resulted in transplantation and 42% of liver grafts from donors who died within the functional warm ischemic time (fWIT) limit were transplanted. In the Regional Expansion era, 25% of attempted donors resulted in transplantation and 50% of liver grafts from donors who died within the fWIT limit were transplanted. In the Donor Acceptance Expansion era, 46% of attempted donors resulted in transplantation and 72% of liver grafts from donors who died within the fWIT limit were transplanted. Eight discarded grafts demonstrated a potential opportunity for utilization. CONCLUSION: The stepwise approach to building an A-NRP program described here can serve as a model for other transplant centers.

Genomic variation in 3,010 diverse accessions of Asian cultivated rice.

Here we analyse genetic variation, population structure and diversity among 3,010 diverse Asian cultivated rice (Oryza sativa L.) genomes from the 3,000 Rice Genomes Project. Our results are consistent with the five major groups previously recognized, but also suggest several unreported subpopulations that correlate with geographic location. We identified 29 million single nucleotide polymorphisms, 2.4 million small indels and over 90,000 structural variations that contribute to within- and between-population variation. Using pan-genome analyses, we identified more than 10,000 novel full-length protein-coding genes and a high number of presence-absence variations. The complex patterns of introgression observed in domestication genes are consistent with multiple independent rice domestication events. The public availability of data from the 3,000 Rice Genomes Project provides a resource for rice genomics research and breeding.

Determination of Gait Events and Temporal Gait Parameters for Persons with a Knee-Ankle-Foot Orthosis.

Gait event detection is essential for controlling an orthosis and assessing the patient's gait. In this study, patients wearing an electromechanical (EM) knee-ankle-foot orthosis (KAFO) with a single IMU embedded in the thigh were subjected to gait event detection. The algorithm detected four essential gait events (initial contact (IC), toe off (TO), opposite initial contact (OIC), and opposite toe off (OTO)) and determined important temporal gait parameters such as stance/swing time, symmetry, and single/double limb support. These gait events were evaluated through gait experiments using four force plates on healthy adults and a hemiplegic patient who wore a one-way clutch KAFO and a pneumatic cylinder KAFO. Results showed that the smallest error in gait event detection was found at IC, and the largest error rate was observed at opposite toe off (OTO) with an error rate of -2.8 ± 1.5% in the patient group. Errors in OTO detection resulted in the largest error in determining the single limb support of the patient with an error of 5.0 ± 1.5%. The present study would be beneficial for the real-time continuous monitoring of gait events and temporal gait parameters for persons with an EM KAFO.

Measurements of Electrodermal Activity, Tissue Oxygen Saturation, and Visual Analog Scale for Different Cuff Pressures.

The quantification of comfort in binding parts, essential human-machine interfaces (HMI) for the functioning of rehabilitation robots, is necessary to reduce physical strain on the user despite great achievements in their structure and control. This study aims to investigate the physiological impacts of binding parts by measuring electrodermal activity (EDA) and tissue oxygen saturation (StO2). In Experiment 1, EDA was measured from 13 healthy subjects under three different pressure conditions (10, 20, and 30 kPa) for 1 min using a pneumatic cuff on the right thigh. In Experiment 2, EDA and StO2 were measured from 10 healthy subjects for 5 min. To analyze the correlation between EDA parameters and the decrease in StO2, a survey using the visual analog scale (VAS) was conducted to assess the level of discomfort at each pressure. The EDA signal was decomposed into phasic and tonic components, and the EDA parameters were extracted from these two components. RM ANOVA and a post hoc paired t-test were used to determine significant differences in parameters as the pressure increased. The results showed that EDA parameters and the decrease in StO2 significantly increased with the pressure increase. Among the extracted parameters, the decrease in StO2 and the mean SCL proved to be effective indicators. Such analysis outcomes would be highly beneficial for studies focusing on the comfort assessment of the binding parts of rehabilitation robots.

Relationship matters: a qualitative study of medical students' experiences in a learner-driven research program in South Korea.

BACKGROUND: Although research experience is important for medical students, it is difficult to develop research skills only through a formal curriculum. To develop research programs that address the authentic needs of students and align with the entirety of the medical school curriculum, a learner-centered approach may be more effective than an instructor-centered approach. This study investigates medical student perspectives on factors that help them develop research competency. METHODS: Hanyang University College of Medicine in South Korea operates the Medical Scientist Training Program (MSTP) as a supplement to its formal curriculum. Semi-structured interviews were held with 18 students (20 cases) in the program, and qualitative content analysis was performed using the software tool MAXQDA20. RESULTS: The findings are discussed in relation to three domains: learner engagement, instructional design, and program development. The students were more engaged when they perceived the program as a new experience, had prior research experience, wanted to make a good impression, and felt a sense of contribution. In terms of instructional design, they positively participated in research when their supervisors respected them, set clear tasks, provided constructive feedback, and invited them into the research community. In particular, the students highly valued relationships with their professors, and these relationships served not only as a main motivating factor in their research participation but also affected their college lives and careers. CONCLUSIONS: The longitudinal relationship between students and professors has newly emerged in the Korean context as a factor that strengthens student engagement in research and the complementary relationship between formal curriculum and MSTP was highlighted to encourage student engagement in research.

TinyFallNet: A Lightweight Pre-Impact Fall Detection Model.

Falls represent a significant health concern for the elderly. While studies on deep learning-based preimpact fall detection have been conducted to mitigate fall-related injuries, additional efforts are needed for embedding in microcomputer units (MCUs). In this study, ConvLSTM, the state-of-the-art model, was benchmarked, and we attempted to lightweight it by leveraging features from image-classification models VGGNet and ResNet while maintaining performance for wearable airbags. The models were developed and evaluated using data from young subjects in the KFall public dataset based on an inertial measurement unit (IMU), leading to the proposal of TinyFallNet based on ResNet. Despite exhibiting higher accuracy (97.37% < 98.00%) than the benchmarked ConvLSTM, the proposed model requires lower memory (1.58 MB > 0.70 MB). Additionally, data on the elderly from the fall data of the FARSEEING dataset and activities of daily living (ADLs) data of the KFall dataset were analyzed for algorithm validation. This study demonstrated the applicability of image-classification models to preimpact fall detection using IMU and showed that additional tuning for lightweighting is possible due to the different data types. This research is expected to contribute to the lightweighting of deep learning models based on IMU and the development of applications based on IMU data.

The Illustration of Altered Glucose Dependency in Drug-Resistant Cancer Cells.

A chemotherapeutic approach is crucial in malignancy management, which is often challenging due to the development of chemoresistance. Over time, chemo-resistant cancer cells rapidly repopulate and metastasize, increasing the recurrence rate in cancer patients. Targeting these destined cancer cells is more troublesome for clinicians, as they share biology and molecular cross-talks with normal cells. However, the recent insights into the metabolic profiles of chemo-resistant cancer cells surprisingly illustrated the activation of distinct pathways compared with chemo-sensitive or primary cancer cells. These distinct metabolic dynamics are vital and contribute to the shift from chemo-sensitivity to chemo-resistance in cancer. This review will discuss the important metabolic alterations in cancer cells that lead to drug resistance.

A Cross-Sectional Investigation of the Association between Arterial Stiffness and Depressive Symptoms, Anxiety Symptoms, and Quality of Life.

Background and Objectives: Previous studies have assessed the association between arterial stiffness and depressive and anxiety symptoms, but the results were inconsistent. We aimed to conduct a cross-sectional study to assess the relationship between arterial stiffness, depressive and anxiety symptoms, and quality of life. Materials and Methods: We analyzed the 2014-2015 Korea Institute of Sport Science Fitness Standards project data. Brachial-ankle pulse wave velocity (baPWV) was measured to assess arterial stiffness. High baPWV was defined as a baPWV higher than 1400 cm/s. Participants completed Beck's depressive symptoms inventory (BDI), Beck's anxiety symptoms inventory (BAI), and the World Health Organization's Quality of Life Questionnaire (WHOQOL-Bref). We performed a logistic regression analysis by adjusting confounding factors and used the inverse probability of treatment weighting (IPTW) method. Results: 1936 participants were included in the analysis (men 43.9%, median age 47). Participants with a high baPWV had higher odds of depressive symptoms compared to those with a normal baPWV (aOR 1.920, 95% CI 1.062-3.472, p = 0.031; IPTW OR 2.637, 95% CI 1.219-5.704, p = 0.014). In addition, baPWV was significantly associated with depressive symptoms in the IPTW model in men but not in women (OR 2.497, 95% CI 1.004-6.207, p = 0.049). High baPWV was not associated with anxiety symptoms in all models, but it was associated with poor QOL in women (OR 4.561, 95% CI 1.465-14.199, p = 0.009). Conclusions: High baPWV was associated with higher odds of depressive symptoms, especially in men. Our study suggests a modest association between arterial stiffness and depressive symptoms in Korean adults.

3D Ultrastructure of Synaptic Inputs to Distinct GABAergic Neurons in the Mouse Primary Visual Cortex.

Synapses are the fundamental elements of the brain's complicated neural networks. Although the ultrastructure of synapses has been extensively studied, the difference in how synaptic inputs are organized onto distinct neuronal types is not yet fully understood. Here, we examined the cell-type-specific ultrastructure of proximal processes from the soma of parvalbumin-positive (PV+) and somatostatin-positive (SST+) GABAergic neurons in comparison with a pyramidal neuron in the mouse primary visual cortex (V1), using serial block-face scanning electron microscopy. Interestingly, each type of neuron organizes excitatory and inhibitory synapses in a unique way. First, we found that a subset of SST+ neurons are spiny, having spines on both soma and dendrites. Each of those spines has a highly complicated structure that has up to eight synaptic inputs. Next, the PV+ and SST+ neurons receive more robust excitatory inputs to their perisoma than does the pyramidal neuron. Notably, excitatory synapses on GABAergic neurons were often multiple-synapse boutons, making another synapse on distal dendrites. On the other hand, inhibitory synapses near the soma were often single-targeting multiple boutons. Collectively, our data demonstrate that synaptic inputs near the soma are differentially organized across cell types and form a network that balances inhibition and excitation in the V1.

The effect of deliberative process on the self-sacrificial decisions of utilitarian healthcare students.

BACKGROUND: The COVID-19 pandemic has highlighted prosocial behavior as a professional healthcare core competency. Although medical students are expected to work in the best interests of their patients, in the pandemic context, there is a greater need for ethical attention to be paid to the way medical students deal with moral dilemmas that may conflict with their obligations. METHODS: This study was conducted in the spring semester of 2019 on 271 students majoring in health professions: medicine, dentistry, and veterinary medicine. All participants provided informed consent and completed measures that assessed utilitarian moral views, cognitive reflections, cognitive reappraisal, and moral judgment. RESULTS: The healthcare-affiliated students who scored higher on the instrumental harm subscale in the measurement of utilitarian moral views were more likely to endorse not only other-sacrificial actions but also self-sacrificial ones for the greater good in moral dilemma scenarios. In particular, those engaged in deliberative processes tended to make more self-sacrificial judgments. The mediation analysis also revealed that the effect of deliberative processes on self-sacrificial judgments was mediated by cognitive reappraisal. CONCLUSIONS: These findings suggested that cognitive reappraisal through deliberative processes is involved when the students with utilitarian inclination make prosocial decisions, that it is necessary to consider both moral views and emotional regulation when admitting candidates, and that moral education programs are needed in the healthcare field.

Analysis on Students' Career Preparation in One Korean Medical School: Based on the Relationship and Trend Between Career Maturity and Specialty Indecision.

BACKGROUND: For medical school students, specialty choice after graduation significantly impacts their future doctor life. Several Korean medical schools have made efforts to prepare career development programs. However, career support programs based on the systematic analysis of medical school students' first to the final year are still lacking. Therefore, this study aims to analyze the students' career preparation of one medical school in Korea using the Career Maturity Inventory (CMI) and Specialty Indecision Scale (SIS) and to explore the relationship between CMI and SIS variables. METHODS: From December 2020 to July 2021, we conducted an online survey of 600 students in years 1 to 4 at Seoul National University College of Medicine. We analyzed the differences between the years of the students through one-way analysis of variance of the CMI and SIS and the relationship between the two instruments by correlation analysis and multiple regression analysis. RESULTS: A total of 198 students completed the survey. The average scores of the CMI variables tended to increase as the year of study went up, and the confidence score of the 1st year students was significantly lower than that of the 2nd and 4th year students. Although there was almost no consistent decrease by year in the SIS variables, 3rd and 4th year students showed significantly lower readiness scores than 1st year students. Additionally, we found that the CMI variables mostly had a negative effect on the SIS variables. CONCLUSION: There is an increasing tendency for career maturity by year of study in Korean medical school students. However, looking at the SIS results, the career concerns vary among the students. Therefore, medical schools can effectively use the SIS to identify the career concerns of students.

Validity of OSCE Evaluation Using the FLEX Model of Blended Learning.

BACKGROUND: For OSCE (Objective Structured Clinical Examination) scoring, medical schools must bring together many clinical experts at the same place, which is very risky in the context of the coronavirus pandemic. However, if the FLEX model with the properties of self-directed learning and offline feedback is applied to OSCE, it is possible to provide a safe and effective evaluation environment for both universities and students through experts' evaluation of self-video clips of medical students. The present study investigated validity of the FLEX model to evaluate OSCE in a small group of medical students. METHODS: Sixteen 3rd grade medical students who failed on OSCE were required to take a make-up examination by videotaping the failed items and submitting them online. The scores between original examination and make-up examination were compared using Paired Wilcoxon Signed Rank Test, and a post-hoc questionnaire was conducted. RESULTS: The score for make-up examination was significantly higher than those for original examination. The significance was maintained even when the score was compared by individual domains of skills and proficiency. In terms of preference, students were largely in favor of self-videotaped examination primarily due to the availability of self-practice. CONCLUSION: The FLEX model can be effectively applied to medical education, especially for evaluation of OSCE.

Time to surgery and survival in breast cancer.

BACKGROUND: This study aimed to investigate the effect of the time from diagnosis to breast cancer surgery on breast cancer patients' prognosis. METHODS: Of the 1900 patients diagnosed with invasive (stage 1-3) breast cancer who underwent surgery in KUH between 2012 and 2019, 279 patients were enrolled in this study. All patients, including those who received neoadjuvant chemotherapy, were classified as Model 1 subjects, and those who received immediate surgical treatment were classified as Model 2 subjects. We conducted a Cox regression analysis to identify prognostic factors of breast cancer associated with the time from diagnosis to surgery. RESULTS: The univariate results indicated a sharp drop in both groups' survival rates when the time to surgery was delayed for more than 8 weeks (Model 1 p = 0.000; Model 2 p = 0.001). In the multivariate analysis, the hazard ratio (HR) of Model 1increased (HR = 6.84, 95% CI 1.06-44.25) in response to a delay in surgery of more than 8 weeks. Smoking and the American Joint Committee on Cancer (AJCC) staging system had a negative effect on breast cancer prognosis, while hormone therapy had a positive effect. CONCLUSION: For all patients, a delay in breast cancer surgery of more than 8 weeks was inversely associated with survival.

Developing a best practice framework for clinical competency education in the traditional East-Asian medicine curriculum.

BACKGROUND: While clinical competency is crucial for traditional East-Asian medical education, available studies on the educational system for fostering clinical performance are scarce. This study aimed to review the educational system, curriculum, facilities, and management of current traditional East-Asian medicine in a well-established university of Korea and develop a Best Practice Framework (BPF) of clinical competency education. METHODS: The clinical competency education system in Pusan National University School of Korean Medicine was systematically described through 5 steps of governance of the educational system, competency of the graduates, educational resources, assessment strategies and tools, and gaps in the curriculum. We also reviewed the experiences in education and the points to be improved. RESULTS: The Office of Traditional Korean Medicine Education governs the development, implementation, and evaluation of the educational curriculum for cultivating students' clinical competency. Medical students have undertaken 39 modules of clinical biomedicine and 21 of traditional medicine during the clinical clerkship courses in an affiliated hospital, Clinical Skill Practice Center, clinical research center, practice lab for medical herb, and other locations. After training, 15 modules of simulated clinical training using standardized patients, students' clinical competency are evaluated by a Clinical Performance Test using a Clinical Performance Examination (CPX) and an Objective Structured Clinical Examination (OSCE) for biomedical and traditional medical skills. CONCLUSIONS: A clinical competency framework is required for a qualified physician of traditional East-Asian medicine. This study reviewed the current well-organized educational system of Korean traditional medicine in detail, which can be used for the BPF of competency-based clinical education. We expect the current study to be a representative reference for establishing an educational system of traditional medicine such as acupuncture and medical herbs in other countries.

Fall-from-Height Detection Using Deep Learning Based on IMU Sensor Data for Accident Prevention at Construction Sites.

Workers at construction sites are prone to fall-from-height (FFH) accidents. The severity of injury can be represented by the acceleration peak value. In the study, a risk prediction against FFH was made using IMU sensor data for accident prevention at construction sites. Fifteen general working movements (NF: non-fall), five low-hazard-fall movements, (LF), and five high-hazard-FFH movements (HF) were performed by twenty male subjects and a dummy. An IMU sensor was attached to the T7 position of the subject to measure the three-axis acceleration and angular velocity. The peak acceleration value, calculated from the IMU data, was 4 g or less in general work movements and 9 g or more in FFHs. Regression analysis was performed by applying various deep learning models, including 1D-CNN, 2D-CNN, LSTM, and Conv-LSTM, to the risk prediction, and then comparing them in terms of their mean absolute error (MAE) and mean squared error (MSE). The FFH risk level was estimated based on the predicted peak acceleration. The Conv-LSTM model trained by MAE showed the smallest error (MAE: 1.36 g), and the classification with the predicted peak acceleration showed the best accuracy (97.6%). This study successfully predicted the FFH risk levels and could be helpful to reduce fatal injuries at construction sites.