Search

Background Although total intravenous anesthesia (TIVA) with propofol and remifentanil is frequently used to optimize intraoperative neurophysiological monitoring (IONM), the exact effect of remimazolam on IONM remains unknown. Here, we compared the effects of propofol and remimazolam along with remifentanil on IONM during TIVA. Methods In this prospective, double-blind, randomized controlled trial, 64 patients requiring IONM during cervical spine surgery were administered either propofol (Group P) or remimazolam (Group R). The preoperative latencies of the somatosensory-evoked potentials (SEP; N20 for the median nerve and P37 for the tibial nerve) were measured. SEP latencies and amplitudes and motor-evoked potential (MEP) amplitudes were measured 30 min after anesthetic induction (T1), 30 min after surgical incision (T2), after laminectomy or discectomy (T3), immediately after plate insertion or pedicle screw fixation (T4), and before surgical wound closure (T5). The primary outcome was the between-group difference in the N20 latency changes measured at T1 and preoperatively. Results The change in SEP latencies including N20 and P37 at T1 compared with preoperative time was not significantly different between Groups P and R. Except for the amplitude of the right abductor brevis, there was no significant group-by-time interaction effect for intraoperative MEP amplitudes or SEP latencies and amplitudes. Conclusions TIVA with remimazolam and remifentanil for cervical spine surgery yielded stable IONM, comparable to those observed with conventional TIVA with propofol and remifentanil. Further clinical trials are needed in other surgical contexts and with more diverse patient populations to determine the effects of remimazolam on IONM.

In this paper, we propose an option-based deep reinforcement learning (DRL) algorithm called option-critic with long short-term memory (OC-LSTM), which combines the option-critic (OC) framework containing a hierarchical policy structure with a long short-term memory (LSTM) network, which makes full use of the powerful time-series feature extraction capability of LSTM networks and uses the OC framework to learn power system topology control policy of the power system. Specifically, in a complex and variable power system, the OC-LSTM extracts key power system state information through the LSTM network and uses the OC framework to define and optimize the high-level options and low-level action policy, which effectively reduces the dimensionality of the agent’s topology control action space in the decision-making process. This combination improves the accuracy of topology control policies and effectively maintains the stability of the power system. The experimental results show that the OC-LSTM algorithm outperforms the benchmark DRL algorithm during training, with the ablation experiment further highlighting the effectiveness of LSTM in power system feature extraction. Additionally, the OC-LSTM algorithm enables stable operation of the IEEE 5-Bus, IEEE 14-Bus, and L2RPN WCCI 2020 power systems for 60 hours, all without human expert intervention.

Abstract Tissue biofabrication mimicking organ-specific architecture and function requires physiologically-relevant cell densities. Bioprinting using spheroids can achieve this, but is limited due to the lack of practical, scalable techniques. This study presents HITS-Bio (High-throughput Integrated Tissue Fabrication System for Bioprinting), a multiarray bioprinting technique for rapidly positioning multiple spheroids simultaneously using a digitally-controlled nozzle array (DCNA). HITS-Bio achieves an unprecedented speed, ten times faster compared to existing techniques while maintaining high cell viability ( > 90%). The utility of HITS-Bio was exemplified in multiple applications, including intraoperative bioprinting with microRNA transfected human adipose-derived stem cell spheroids for calvarial bone regeneration ( ~ 30 mm3) in a rat model achieving a near-complete defect closure (bone coverage area of ~ 91% in 3 weeks and ~96% in 6 weeks). Additionally, the successful fabrication of scalable cartilage constructs (1 cm3) containing ~600 chondrogenic spheroids highlights its high-throughput efficiency (under 40 min per construct) and potential for repairing volumetric defects.

A shape optimization process for a bellmouth in a gas turbine casing under high Reynolds number was conducted using computational fluid dynamics. The bellmouth connected to the nozzle guide vane was simplified assuming a cylindrically-shaped flow passage. The height of the casing entrance and the curvature of the bellmouth were selected as the geometric parameters. The curvature of the bellmouth was defined as an ellipse consisting of a major axis and a minor axis. Two hundred forty three cases were calculated with a combination of 5 parameters and 3 levels of change, and correlations for flow uniformity and pressure drop were derived. The optimized shape of the bellmouth was obtained by using the two correlations and the genetic algorithm. In addition, the optimized bellmouth was found using conditional U-Net, which predicted the flow uniformity image according to the given shape conditions. The shape of the baseline and optimized bellmouth were compared, and performances were compared in terms of flow uniformity and pressure drop. In addition, the results of the particle distribution, for particles generated after the combustion and entered the casing, were compared.

Abstract Background In common wheat (Triticum aestivum L.), allelic variations in the high-molecular-weight glutenin subunits Glu-B1 locus have important effects on grain end-use quality. The Glu-B1 locus consists of two tightly linked genes encoding x- and y-type subunits that exhibit highly variable frequencies. However, studies on the discriminating markers of the alleles that have been reported are limited. Here, we developed 11 agarose gel-based PCR markers for detecting Glu-1Bx and Glu-1By alleles. Results By integrating the newly developed markers with previously published PCR markers, nine Glu-1Bx locus alleles (Glu-1Bx6, Glu-1Bx7, Glu-1Bx7*, Glu-1Bx7 OE, Glu-1Bx13, Glu-1Bx14 (−) , Glu-1Bx14 (+)/Bx20, and Glu-1Bx17) and seven Glu-1By locus alleles (Glu-1By8, Glu-1By8*, Glu-1By9, Glu-1By15/By20, Glu-1By16, and Glu-1By18) were distinguished in 25 wheat cultivars. Glu-1Bx6, Glu-1Bx13, Glu-1Bx14 (+)/Bx20, Glu-1By16, and Glu-1By18 were distinguished using the newly developed PCR markers. Additionally, the Glu-1Bx13 and Glu-1Bx14 (+)/Bx20 were distinguished by insertions and deletions in their promoter regions. The Glu-1Bx6, Glu-1Bx7, Glu-1By9, Glu-1Bx14 (−), and Glu-1By15/By20 alleles were distinguished by using insertions and deletions in the gene-coding region. Glu-1By13, Glu-1By16, and Glu-1By18 were dominantly identified in the gene-coding region. We also developed a marker to distinguish between the two Glu-1Bx14 alleles. However, the Glu-1Bx14 (+) + Glu-1By15 and Glu-1Bx20 + Glu-1By20 allele combinations could not be distinguished using PCR markers. The high-molecular-weight glutenin subunits of wheat varieties were analyzed by ultra-performance liquid chromatography and sodium dodecyl sulfate–polyacrylamide gel electrophoresis, and the findings were compared with the results of PCR analysis. Conclusions Seven Glu-1Bx and four Glu-1By allele detection markers were developed to detect nine Glu-1Bx and seven Glu-1By locus alleles, respectively. Integrating previously reported markers and 11 newly developed PCR markers improves allelic identification of the Glu-B1 locus and facilitates more effective analysis of Glu-B1 alleles molecular variations, which may improve the end-use quality of wheat.

Abstract Background Mesenchymal stem cells (MSCs) play important roles in tissue homeostasis by providing a supportive microenvironmental niche for the hematopoietic system. Cigarette smoking induces systemic abnormalities, including an impeded recovery process after hematopoietic stem cell transplantation. However, the role of cigarette smoking-mediated alterations in MSC niche function have not been investigated. Methods In the present study, we investigated whether exposure to cigarette smoking extract (CSE) disrupts the hematopoietic niche function of MSCs, and pathways impacted. To investigate the effects on bone marrow (BM)-derived MSCs and support of hematopoietic stem and progenitor cells (HSPCs), mice were repeatedly infused with the CSE named 3R4F, and hematopoietic stem and progenitor cells (HSPCs) supporting function was determined. The impact of 3R4F on MSCs at cellular level were screened by bulk-RNA sequencing and subsequently validated through qRT-PCR. Specific inhibitors were treated to verify the ROS or NLRP3-specific effects, and the cells were then transplanted into the animal model or subjected to coculture with HSPCs. Results Both direct ex vivo and systemic in vivo MSC exposure to 3R4F resulted in impaired engraftment in a humanized mouse model. Furthermore, transcriptomic profile analysis showed significantly upregulated signaling pathways related to reactive oxygen species (ROS), inflammation, and aging in 3R4F-treated MSCs. Notably, ingenuity pathway analysis revealed the activation of NLRP3 inflammasome signaling pathway in 3R4F-treated MSCs, and pretreatment with the NLRP3 inhibitor MCC950 rescued the HSPC-supporting ability of 3R4F-treated MSCs. Conclusion In conclusion, these findings indicate that exposure to CSE reduces HSPCs supportive function of MSCs by inducing robust ROS production and subsequent NLRP3 activation.

It has been known for some time that many tumors have a significantly different conductivity and permittivity from surrounding normal tissue. This high 'contrast' in tissue electrical properties, occurring between a few kilohertz and several megahertz, may permit differentiating malignant from benign tissues. Here we show the ability of electrical impedance spectroscopy (EIS) to roughly localize and clearly distinguish cancers from normal tissues and benign lesions. Localization of these lesions is confirmed by simultaneous, in register digital breast tomosynthesis (DBT) mammography or 3-D mammograms. Index Terms--Breast cancer detection, digital breast tomosynthesis (DBT) mammography, electrical impedance spectroscopy (EIS), electrical impedance tomography (EIT).

Objectives To construct a new scoring system utilizing biomarkers, vitals, and imaging data to predict 30-day mortality in acute pulmonary embolism (PE). Background Acute PE, a well-known manifestation of venous thromboembolic disease, is responsible for over 100,000 deaths worldwide yearly. Contemporary management algorithms rely on a multidisciplinary approach to care via PE response teams (PERT) in the identification of low, intermediate, and high-risk patients. The PESI and sPESI scores have been used as cornerstones of the triage process in assigning risk of 30-day mortality for patients presenting with acute PE; however, the specificity of these scoring systems has often come into question. Methods This study retrospectively analyzed 488 patients with acute PE who were managed at a tertiary care institution with either conservative therapy consisting of low molecular weight or unfractionated heparin, advanced therapies consisting of catheter directed therapies, aspiration thrombectomy, or a combination of these therapies, or surgical embolectomy. The CLOT-5 score was designed to include vital signs, biomarkers, and imaging data to predict 30-day mortality in patients presenting with acute PE. Results The CLOT-5 score had an area under the curve (AUC) of 0.901 with a standard error of 0.29, while the PESI and sPESI scores had an AUC and standard errors of 0.793 ±­ 0.43 and 0.728 ± 0.55, respectively. Conclusions When incorporated into the management algorithms of national PERT programs, the CLOT-5 score may allow for rapid and comprehensive assessment of patients with acute PE at high risk for clinical decompensation, leading to early escalation of care where appropriate.

Rehabilitation training is essential for a successful recovery of upper extremity function after stroke. Training programs are typically conducted in hospitals or rehabilitation centers, supervised by specialized medical professionals. However, frequent visits to hospitals can be burdensome for stroke patients with limited mobility. We consider a self-administered rehabilitation system based on a mobile application in which patients can periodically upload videos of themselves performing reach-to-grasp tasks to receive recommendations for self-managed exercises or progress reports. Sensing equipment aside from cameras is typically unavailable in the home environment. A key contribution of our work is to propose a deep learning-based assessment model trained only with video data. As all patients carry out identical tasks, a fine-grained assessment of task execution is required. Our model addresses this difficulty by learning RGB and optical flow data in a complementary manner. The correlation between the RGB and optical flow data is captured by a novel module for modality fusion using cross-attention with Transformers. Experiments showed that our model achieved higher accuracy in movement assessment than existing methods for action recognition. Based on the assessment model, we developed a patient-centered, solution-based mobile application for upper extremity exercises for hemiplegia, which can recommend 57 exercises with three levels of difficulty. A prototype of our application was evaluated by potential end-users and achieved a good quality score on the Mobile Application Rating Scale (MARS).

It is well known that identification of the complete system dynamics is challenging, especially in noisy environments. The Koopman operator theory provides a linear representation of a nonlinear system using only the input/output data acquired from the system, which does not need the exact model dynamics. Since the data is collected from the real-world, noise is inherent in that collected data. Therefore, the identified model with the Koopman operator can consider noise appeared in the real-world. In this paper, we propose the Koopman-based control system for quadrotors with the environment selector under varying noisy environments. We consider varying noisy environments of the quadrotor changing from nominal to windy, and construct two different quadrotor dynamics depending on the environment by using the Koopman operator theory. Then the proposed environment selector identifies whether the current environment is nominal or windy, by which an appropriate quadrotor dynamics obtained by the Koopman operator is determined. The selected Koopman dynamics is used in the Model Predictive Control (MPC) to obtain the optimal control input for the quadrotor. Note that by the proposed environment selector and the MPC-based control input, the quadrotor is able to follow the optimal reference trajectory generated by the Soft Actor-Critic (SAC) algorithm even in suddenly varying noisy environments. To verify the effectiveness of the proposed control system, we provide the simulation and experiment results of the quadrotor under various environment situations. In particular, we verify that by the proposed method, the quadrotor is able to follow the optimal reference trajectory even under varying noisy environments.

Objective Although adult spinal deformity (ASD) surgery aims to restore and maintain alignment, proximal junctional kyphosis (PJK) may occur. While existing scoring systems predict PJK, they predominantly offer a generalized 3-tier risk classification, limiting their utility for nuanced treatment decisions. This study seeks to establish a personalized risk calculator for PJK, aiming to enhance treatment planning precision. Methods Patient data for ASD were sourced from the Korean spinal deformity database. PJK was defined a proximal junctional angle (PJA) of ≥ 20° at the final follow-up, or an increase in PJA of ≥ 10° compared to the preoperative values. Multivariable analysis was performed to identify independent variables. Subsequently, 5 machine learning models were created to predict individualized PJK risk post-ASD surgery. The most efficacious model was deployed as an online and interactive calculator. Results From a pool of 201 patients, 49 (24.4%) exhibited PJK during the follow-up period. Through multivariable analysis, postoperative PJA, body mass index, and deformity type emerged as independent predictors for PJK. When testing machine learning models using study results and previously reported variables as hyperparameters, the random forest model exhibited the highest accuracy, reaching 83%, with an area under the receiver operating characteristics curve of 0.76. This model has been launched as a freely accessible tool at: (https://snuspine.shinyapps.io/PJKafterASD/). Conclusion An online calculator, founded on the random forest model, has been developed to gauge the risk of PJK following ASD surgery. This may be a useful clinical tool for surgeons, allowing them to better predict PJK probabilities and refine subsequent therapeutic strategies.

Abstract Background Although the prognostic value of the Controlling Nutritional Status (CONUT) score in diffuse large B-cell lymphoma (DLBCL) has been reported in several previous studies, its clinical relevance for the presence of sarcopenia has not been assessed. Methods In this study, 305 DLBCL patients were reviewed. They were categorized into normal/mild (n = 219) and moderate/severe (n = 86) CONUT groups. Sarcopenia was assessed using the L3-skeletal muscle index measured by baseline computed tomography imaging. Based on CONUT score and sarcopenia, patients were grouped: A (normal/mild CONUT and no sarcopenia), B (either moderate/severe CONUT or sarcopenia, but not both), and C (both moderate/severe CONUT and sarcopenia). Results The moderate/severe CONUT group showed higher rates of ≥ grade 3 febrile neutropenia, thrombocytopenia, non-hematologic toxicities, and early treatment discontinuation not related to disease progression, compared to the normal/mild CONUT group. The moderate/severe CONUT group had a lower complete response rate (58.1% vs. 80.8%) and shorter median overall survival (18.5 vs. 162.6 months) than the normal/mild group. Group C had the poorest prognosis with a median survival of 8.6 months, while groups A and B showed better outcomes (not reached and 60.1 months, respectively). Combining CONUT score and sarcopenia improved the predictive accuracy of the Cox regression model (C-index: 0.763), compared to the performance of using either CONUT score (C-index: 0.754) or sarcopenia alone (C-index: 0.755). Conclusions In conclusion, the moderate/severe CONUT group exhibited treatment intolerance, lower response, and poor prognosis. Additionally, combining CONUT score and sarcopenia enhanced predictive accuracy for survival outcomes compared to individual variables.

Background Semi-rigid neck collars to protect the cervical spine can limit the extent of neck movement and mouth opening; this may further complicate orotracheal intubation. We aimed to compare intubation environments obtained with videolaryngoscopy using the technique of gliding a blade under the epiglottis and that obtained using the conventional Macintosh blade technique of blade tip placement on the vallecula. Methods This prospective randomized study included patients aged ≥ 20 years with American Society of Anesthesiologists physical status I–III scheduled for cervical spine surgery between October 2020 and August 2021. Patients were divided into two groups according to the placement of the blade of the McGrathTM videolaryngoscope: the gliding and conventional groups. The percentage of glottic opening (POGO) score was the primary endpoint. We also recorded the time to obtain the optimal laryngoscopic view, intubation duration, and ease and satisfaction of the researcher performing intubation. Results Among 176 patients, the POGO scores were significantly higher in the gliding group than in the conventional group (88.9 ± 14.7 vs. 63.8 ± 27.4, P < 0.001). The time to achieve the optimal glottic view for intubation and duration of intubation were also shorter, and ease and satisfaction in performing intubation were better in the gliding group than in the conventional group. Conclusion Our findings demonstrated a superior glottic view and more favorable intubation environments when the blade tip was placed under the epiglottis than using the conventional Macintosh technique in patients with immobilized cervical spine.

Abstract Both the uterus and breasts have sex hormone dependence, yet there are few studies on the association between breast disease and uterine fibroids (UFs). The purpose of this study was to investigate the incidence of benign breast disease (BBD), carcinoma in situ (CIS), and breast cancer (BC) in women treated for UFs compared to women who were not treated for UFs. This retrospective cohort study used national health insurance data from January 1st, 2011, to December 31st, 2020. We selected women between 20 and 50 years old who (1) were treated for UFs (UF group) or (2) visited medical institutions for personal health screening tests without UFs (control group). We analyzed independent variables such as age, socioeconomic status (SES), region, Charlson comorbidity index (CCI), delivery status, menopausal status, menopausal hormone therapy (MHT), endometriosis, hypertension (HTN), diabetes mellitus (DM), and dyslipidemia based on the first date of uterine myomectomy in the UF group and the first visiting date for health screening in the non-UF group. There were 190,583 and 439,940 participants in the UF and control groups, respectively. Compared with those of the control group, the RRs of BBD, CIS, and BC were increased in the UF group. The hazard ratios (HRs) of BBD, CIS, and BC in the UF group were 1.335 (95% confidence interval (CI) 1.299–1.372), 1.796 (95% CI 1.542–2.092), and 1.3 (95% CI 1.198–1.41), respectively. When we analyzed the risk of BC according to age at inclusion, UFs group had the increased risk of BCs in all age groups in comparison with control group. Women with low SES (HR 0.514, 95% CI 0.36–0.734) and living in rural areas (HR 0.889, 95% CI 0.822–0.962) had a lower risk of BC. Our study showed that women with UFs had a higher risk of BBD, CIS, and BC than those without UFs. This result suggests that women with UFs should be more conscious of BC than those without UFs. Therefore, doctors should consider recommending regular breast self-exams, mammography, or ultrasound for the early detection of BC in women with UFs.

Abstract Background Nowadays bleaching procedures have gained popularity in orthodontic patients. Peroxide and Carbamide acids are the common agents which are used in in-office and at home bleaching techniques. Consequently, the Bonding adhesion to the enamel can be influenced by the orthodontic phase and the residual peroxide might interfere with the polymerization and the adhesion of the brackets. Frequent debonding of the brackets from teeth after the bleaching procedure could cause the lengthening of the therapy and promote irregularities on enamel surface derived from an additional bonding phase of the brackets. The aim of this systematic review is to appraise the influence regarding the effect of the bleaching procedure on the bond strength of orthodontic brackets. Methods An electronic database search was performed. Search terms included: bleaching, brackets, adhesion; data were extracted and summarized. Risk of bias was assessed using the Chocrane risk of bias tool, adapted for in vitro studies. Results A total of 8689 articles were screened and 11 studies met the inclusion criteria of this systematic review. 1000 teeth of human and bovine origin were analyzed for the shear bond strength (SBS) of stainless and ceramic brackets after the bleaching treatments. All the authors divided the groups in different subgroups with different bleaching agents and in different concentration. The SBS value allowed to demonstrate the necessity to delay the bonding of the brackets for two weeks after a bleaching treatment and its improvement when tooth mousse or antioxidants agents are used. Conclusions The SBS values and the delay of the bonding procedure must be considered in dental practice and clinical strategies are necessary in order to avoid drawbacks which could cause the debonding of the brackets after bleaching due to the alterations of the dental substrate, thus interfering with the orthodontic treatments.

Abstract Background Sexual dimorphism in placental physiology affects the functionality of placental adaptation during adverse pregnancy. Defects of placental function compromise fetal programming, affecting the offspring’s adult life. However, studies focusing on the relationship between sex-specific placental adaptation and consequent fetal maldevelopment under sub-optimal uterus milieu are still elusive. Methods Here, we investigated the effects of maternal lipopolysaccharide (LPS) exposure between placental sex. Pregnant ICR mice received intraperitoneal injection of phosphate-buffered saline or 100, 200, and 400 µg/kg LPS on the gestational day (GD) 15.5. To determine whether prenatal maternal LPS exposure resulted in complicated pregnancy outcomes, survival rate of embryos was calculated and the growth of embryos and placentas was examined. To elucidate global transcriptomic changes occurring in the placenta, total RNA-sequencing (RNA-seq) was performed in female and male placentas. Results LPS administration induced placental inflammation in both sexes at GD 17.5. Prenatal infection resulted in growth retardation in both sexes of embryos, and especially more prevalently in male. Impaired placental development was observed in a sex-specific manner. LPS 400 µg/kg reduced the percentage area of the labyrinth in females and junctional zone in males, respectively. RNA-sequencing revealed widespread sexually dimorphic transcriptional changes in placenta. In particular, representative changes were involved in biological processes such as trophoblast differentiation, nutrient/ion transporter, pregnancy, and immune system. Conclusions Our results present the sexually dimorphic responses of placental physiology in intrauterine growth restriction model and provide tentative relationship further to be elucidated between sex-biased placental functional change and long-term effects on the offspring’s later life.

Abstract Background Several population-based studies and observational studies have shown that oophorectomy is associated with an increased risk of colorectal cancer (CRC), and hormone replacement therapy has been associated with a reduction in the risk of colorectal cancer. This study was carried out to investigate whether hysterectomy, which may affect the levels of female hormones, is associated with a risk of cancer of the specific gastrointestinal tract. Methods This population-based retrospective cohort study was conducted using insurance data provided by the Health Insurance Review and Assessment Service (HIRA) from January 1, 2007, to December 31, 2020. The hysterectomy group included 40- to 59-year-old women who underwent hysterectomy with uterine leiomyoma or uterine endometriosis from January 1, 2011, to December 31, 2014. The control group included women aged 40 to 59 years who visited medical institutions for medical examination from January 1, 2011 to December 31, 2014. Results The hysterectomy and non-hysterectomhy groups comprised 66,204 and 89,768 subjects, respectively. The median ages in the non-hysterectomy group and hysterectomy group were 48 (range: 43–53) and 46 (range: 44–49) years, respectively. In the unadjusted results of the analysis, all colorectal cancer (CRC) increased in the hysterectomy alone group (HR 1.222, 95% confidence interval (CI) 1.016–1.47, p = 0.033), sigmoid colon cancer increased in the hysterectomy alone group (HR 1.71, 95% CI 1.073–2.724, p = 0.024), and rectal cancer increased in the hysterectomy with adnexal surgery group (HR 1.924, 95% CI 1.073–2.724, p = 0.002). The adjusted results showed that all CRC increased in the hysterectomy alone group (HR 1.406, 95% CI 1.057–1.871, p = 0.019), colon cancer increased in the hysterectomy alone group (HR 1.523, 95% CI 1.068–2.17, p = 0.02), and rectal cancer increased in the hysterectomy with adnexal surgery group (HR 1.933, 95% CI 1.131–3.302, p = 0.016). The all-cause mortality of GI cancer increased in the hysterectomy alone group (HR 3.495, 95% CI 1.347–9.07, p = 0.001). Conclusions This study showed that the risk of all CRC increased in women who underwent hysterectomy compared with women who did not. In particular, the risk of rectal cancer was significantly higher in the women who underwent hysterectomy with adnexal surgery than in the controls. There was no association between hysterectomy and other GI cancers.

In this paper, we propose a soft actor–critic (SAC) algorithm with hindsight experience replay (HER), called SACHER, which is a class of deep reinforcement learning (DRL) algorithm. SAC is an off-policy model-free DRL algorithm that outperforms earlier DRL algorithms in terms of exploration and robustness. However, in SAC, maximizing the entropy-augmented objective degrades the optimality of learning outcomes. We propose SACHER to improve the learning performance of SAC. We apply SACHER to the path planning and collision avoidance control of unmanned aerial vehicles (UAVs). We demonstrate the effectiveness of SACHER in terms of the success rate, learning speed, and collision avoidance performance of UAV operation.