RESUMO
AIM OF THE STUDY: We evaluated whether an artificial intelligence (AI)-driven robot cardiopulmonary resuscitation (CPR) could improve hemodynamic parameters and clinical outcomes. METHODS: We developed an AI-driven CPR robot which utilizes an integrated feedback system with an AI model predicting carotid blood flow (CBF). Twelve pigs were assigned to the AI robot group (n = 6) and the LUCAS 3 group (n = 6). They underwent 6 min of CPR after 7 min of ventricular fibrillation. In the AI robot group, the robot explored for the optimal compression position, depth and rate during the first 270-second period, and continued CPR with the optimal setup during the next 90-second period and beyond. The primary outcome was CBF during the last 90-second period. The secondary outcomes were coronary perfusion pressure (CPP), end-tidal carbon dioxide level (ETCO2) and return of spontaneous circulation (ROSC). RESULTS: The AI model's prediction performance was excellent (Pearson correlation coefficient = 0.98). CBF did not differ between the two groups [estimate and standard error (SE), -23.210 ± 20.193, P = 0.250]. CPP, ETCO2 level and rate of ROSC also did not show difference [estimate and SE, -0.214 ± 7.245, P = 0.976 for CPP; estimate and SE, 1.745 ± 3.199, P = 0.585 for ETCO2; 5/6 (83.3%) vs. 4/6 (66.7%), P = 1.000 for ROSC). CONCLUSION: This study provides proof of concept that an AI-driven CPR robot in porcine cardiac arrest is feasible. Compared to a LUCAS 3, an AI-driven CPR robot produced comparable hemodynamic and clinical outcomes.
RESUMO
Background/Aims: We investigated how interactions between humans and computer-aided detection (CADe) systems are influenced by the user's experience and polyp characteristics. Methods: We developed a CADe system using YOLOv4, trained on 16,996 polyp images from 1,914 patients and 1,800 synthesized sessile serrated lesion (SSL) images. The performance of polyp detection with CADe assistance was evaluated using a computerized test module. Eighteen participants were grouped by colonoscopy experience (nurses, fellows, and experts). The value added by CADe based on the histopathology and detection difficulty of polyps were analyzed. Results: The area under the curve for CADe was 0.87 (95% confidence interval [CI], 0.83 to 0.91). CADe assistance increased overall polyp detection accuracy from 69.7% to 77.7% (odds ratio [OR], 1.88; 95% CI, 1.69 to 2.09). However, accuracy decreased when CADe inaccurately detected a polyp (OR, 0.72; 95% CI, 0.58 to 0.87). The impact of CADe assistance was most and least prominent in the nurses (OR, 1.97; 95% CI, 1.71 to 2.27) and the experts (OR, 1.42; 95% CI, 1.15 to 1.74), respectively. Participants demonstrated better sensitivity with CADe assistance, achieving 81.7% for adenomas and 92.4% for easy-to-detect polyps, surpassing the standalone CADe performance of 79.7% and 89.8%, respectively. For SSLs and difficult-to-detect polyps, participants' sensitivities with CADe assistance (66.5% and 71.5%, respectively) were below those of standalone CADe (81.1% and 74.4%). Compared to the other two groups (56.1% and 61.7%), the expert group showed sensitivity closest to that of standalone CADe in detecting SSLs (79.7% vs 81.1%, respectively). Conclusions: CADe assistance boosts polyp detection significantly, but its effectiveness depends on the user's experience, particularly for challenging lesions.
RESUMO
Recognizing anatomical sections during colonoscopy is crucial for diagnosing colonic diseases and generating accurate reports. While recent studies have endeavored to identify anatomical regions of the colon using deep learning, the deformable anatomical characteristics of the colon pose challenges for establishing a reliable localization system. This study presents a system utilizing 100 colonoscopy videos, combining density clustering and deep learning. Cascaded CNN models are employed to estimate the appendix orifice (AO), flexures, and "outside of the body," sequentially. Subsequently, DBSCAN algorithm is applied to identify anatomical sections. Clustering-based analysis integrates clinical knowledge and context based on the anatomical section within the model. We address challenges posed by colonoscopy images through non-informative removal preprocessing. The image data is labeled by clinicians, and the system deduces section correspondence stochastically. The model categorizes the colon into three sections: right (cecum and ascending colon), middle (transverse colon), and left (descending colon, sigmoid colon, rectum). We estimated the appearance time of anatomical boundaries with an average error of 6.31 s for AO, 9.79 s for HF, 27.69 s for SF, and 3.26 s for outside of the body. The proposed method can facilitate future advancements towards AI-based automatic reporting, offering time-saving efficacy and standardization.
Assuntos
Doenças do Colo , Aprendizado Profundo , Humanos , Colonoscopia , Algoritmos , Análise por ConglomeradosRESUMO
BACKGROUND: Recently, we developed a chest compression device that can move the chest compression position without interruption during CPR and be remotely controlled to minimize rescuer exposure to infectious diseases. The purpose of this study was to compare its performance with conventional mechanical CPR device in a mannequin and a swine model of cardiac arrest. MATERIALS AND METHODS: A prototype of a remote-controlled automatic chest compression device (ROSCER) that can change the chest compression position without interruption during CPR was developed, and its performance was compared with LUCAS 3 in a mannequin and a swine model of cardiac arrest. In a swine model of cardiac arrest, 16 male pigs were randomly assigned into the two groups, ROSCER CPR (n = 8) and LUCAS 3 CPR (n = 8), respectively. During 5 minutes of CPR, hemodynamic parameters including aortic pressure, right atrial pressure, coronary perfusion pressure, common carotid blood flow, and end-tidal carbon dioxide partial pressure were measured. RESULTS: In the compression performance test using a mannequin, compression depth, compression time, decompression time, and plateau time were almost equal between ROSCER and LUCAS 3. In a swine model of cardiac arrest, coronary perfusion pressure showed no difference between the two groups (p = 0.409). Systolic aortic pressure and carotid blood flow were higher in the LUCAS 3 group than in the ROSCER group during 5 minutes of CPR (p < 0.001, p = 0.008, respectively). End-tidal CO2 level of the ROSCER group was initially lower than that of the LUCAS 3 group, but was higher over time (p = 0.022). A Kaplan-Meier survival analysis for ROSC also showed no difference between the two groups (p = 0.46). CONCLUSION: The prototype of a remote-controlled automated chest compression device can move the chest compression position without interruption during CPR. In a mannequin and a swine model of cardiac arrest, the device showed no inferior performance to a conventional mechanical CPR device.
Assuntos
Reanimação Cardiopulmonar , Parada Cardíaca , Masculino , Animais , Suínos , Projetos Piloto , Manequins , Parada Cardíaca/terapia , Pressão , HemodinâmicaRESUMO
Computer-aided detection (CADe) systems have been actively researched for polyp detection in colonoscopy. To be an effective system, it is important to detect additional polyps that may be easily missed by endoscopists. Sessile serrated lesions (SSLs) are a precursor to colorectal cancer with a relatively higher miss rate, owing to their flat and subtle morphology. Colonoscopy CADe systems could help endoscopists; however, the current systems exhibit a very low performance for detecting SSLs. We propose a polyp detection system that reflects the morphological characteristics of SSLs to detect unrecognized or easily missed polyps. To develop a well-trained system with imbalanced polyp data, a generative adversarial network (GAN) was used to synthesize high-resolution whole endoscopic images, including SSL. Quantitative and qualitative evaluations on GAN-synthesized images ensure that synthetic images are realistic and include SSL endoscopic features. Moreover, traditional augmentation methods were used to compare the efficacy of the GAN augmentation method. The CADe system augmented with GAN synthesized images showed a 17.5% improvement in sensitivity on SSLs. Consequently, we verified the potential of the GAN to synthesize high-resolution images with endoscopic features and the proposed system was found to be effective in detecting easily missed polyps during a colonoscopy.
Assuntos
Pólipos do Colo/patologia , Colonoscopia , Neoplasias Colorretais/patologia , Detecção Precoce de Câncer , Interpretação de Imagem Assistida por Computador , Redes Neurais de Computação , Bases de Dados Factuais , Humanos , Valor Preditivo dos Testes , Estudos Prospectivos , Reprodutibilidade dos Testes , Estudos RetrospectivosRESUMO
BACKGROUND: Beta-blockers blunt the stress response to hemorrhage. Our aim was to investigate the feasibility of noninvasive pulse oximeter plethysmographic waveform variation (PoPV) for predicting blood volume loss in an esmolol-treated swine hemorrhagic shock model. MATERIALS AND METHODS: Controlled hemorrhage was induced in eight male domestic pigs. In four pigs, a total of 15% and 30% blood volume was drawn step-by-step over 10 min in each step (controlled hemorrhage-only pigs). In the other four pigs, the heart rate (HR) was reduced and maintained by 30% from baseline by esmolol infusion before controlled hemorrhage (esmolol-treated pigs). Diagnostic abilities of HR, pulse pressure variation (PPV), PoPV, and mean arterial pressure for 15% and 30% blood volume loss were determined by the area under the receiver operating characteristic curve (AUC). RESULTS: PoPV was well correlated with PPV in controlled hemorrhage-only pigs (r = 0.717) and esmolol-treated pigs (r = 0.532). In controlled hemorrhage-only pigs, HR (AUC = 0.841 and 0.864), PPV (0.878 and 0.843), and PoPV (0.779 and 0.793) accurately predicted 15% and 30% of blood volume loss. In esmolol-treated pigs, the diagnostic ability of HR was decreased (AUC = 0.766 and 0.733). However, diagnostic abilities of PPV (0.848 and 0.804) and PoPV (0.808 and 0.842) were not deteriorated. CONCLUSIONS: The diagnostic ability of HR for blood volume loss was blunted by esmolol. However, those of PPV and PoPV were not altered. PoPV may be considered to be a useful noninvasive tool to predict blood volume loss in injured patients taking beta-blockers.
Assuntos
Pressão Sanguínea/efeitos dos fármacos , Oximetria/métodos , Propanolaminas/administração & dosagem , Choque Hemorrágico/diagnóstico , Animais , Pressão Sanguínea/fisiologia , Modelos Animais de Doenças , Relação Dose-Resposta a Droga , Estudos de Viabilidade , Frequência Cardíaca/efeitos dos fármacos , Frequência Cardíaca/fisiologia , Humanos , Masculino , Oximetria/instrumentação , Oxigênio/sangue , Pletismografia/instrumentação , Pletismografia/métodos , Choque Hemorrágico/tratamento farmacológico , Choque Hemorrágico/fisiopatologia , Sus scrofaRESUMO
OBJECTIVES: To evaluate the deep learning models for differentiating invasive pulmonary adenocarcinomas (IACs) among subsolid nodules (SSNs) considered for resection in a retrospective diagnostic cohort in comparison with a size-based logistic model and expert radiologists. METHODS: This study included 525 patients (309 women; median, 62 years) to develop models, and an independent cohort of 101 patients (57 women; median, 66 years) was used for validation. A size-based logistic model and deep learning models using 2.5-dimension (2.5D) and three-dimension (3D) CT images were developed to discriminate IAC from less invasive pathologies. Overall performance, discrimination, and calibration were assessed. Diagnostic performances of the three thoracic radiologists were compared with those of the deep learning model. RESULTS: The overall performances of the deep learning models (Brier score, 0.122 for the 2.5D DenseNet and 0.121 for the 3D DenseNet) were superior to those of the size-based logistic model (Brier score, 0.198). The area under the receiver operating characteristic curve (AUC) of the 2.5D DenseNet (0.921) was significantly higher than that of the 3D DenseNet (0.835; p = 0.037) and the size-based logistic model (0.836; p = 0.009). At equally high sensitivities of 90%, the 2.5D DenseNet showed significantly higher specificity (88.2%; all p < 0.05) and positive predictive value (97.4%; all p < 0.05) than other models. Model calibration was poor for all models (all p < 0.05). The 2.5D DenseNet had a comparable performance with the radiologists (AUC, 0.848-0.910). CONCLUSION: The 2.5D DenseNet model could be used as a highly sensitive and specific diagnostic tool to differentiate IACs among SSNs for surgical candidates. KEY POINTS: ⢠The deep learning model developed using 2.5D DenseNet showed higher overall performance and discrimination than the size-based logistic model for the differentiation of invasive adenocarcinomas among subsolid nodules for surgical candidates. ⢠The 2.5D DenseNet demonstrated a thoracic radiologist-level diagnostic performance and had higher specificity (88.2%) at equal sensitivities (90%) than the size-based logistic model (specificity, 52.9%). ⢠The 2.5D DenseNet could be used to reduce potential overtreatment for the indolent subsolid nodules or to select candidates for sublobar resection instead of the standard lobectomy.
Assuntos
Adenocarcinoma de Pulmão/diagnóstico , Aprendizado Profundo , Neoplasias Pulmonares/diagnóstico , Radiografia Torácica/métodos , Radiologistas , Tomografia Computadorizada por Raios X/métodos , Idoso , Feminino , Humanos , Modelos Logísticos , Masculino , Pessoa de Meia-Idade , Curva ROC , Estudos RetrospectivosRESUMO
Objective: We evaluated the validity of a newly developed mobile application (i.e. the Weighing Cam) for pediatric weight estimation compared with that of the Broselow tape. Methods: We developed an application that estimates the weight of pediatric patients using a smartphone camera and displays the drug dosage, device size, and defibrillation energy on the screen of the smartphone. We enrolled a convenience sample of pediatric patients aged <16 years who presented at two pediatric emergency departments of two tertiary academic hospitals in South Korea. The pediatric patients' heights and weights were measured; then, one researcher estimated the weights using the application. Using the measured height, we determined the weight estimated by the Broselow tape. We compared the estimated measurements by determining the mean percentage error (MPE), mean absolute percentage error, root mean square percentage error, and percentages predicted within 10% and 20% of the actual. Results: In total, 480 patients were enrolled in 16 age categories, each with 15 males and 15 females of different ages. The Weighing Cam demonstrated a lower bias (mean difference: -1.98% [95% confidence interval -2.91% to -1.05%] for MPE) and a higher proportion of estimated weights within 10% of the actual weights than the Broselow tape (mean difference: 9.1% [95% confidence interval 3.0% to 15.1%]). The Weighing Cam showed better performance in terms of accuracy and precision than the Broselow tape in all subgroups stratified by age or body mass index percentile. Conclusions: The Weighing Cam may estimate pediatric patients' weights more accurately than the Broselow tape. The Weighing Cam may be useful for pediatric resuscitation in both prehospital and hospital settings.