ABSTRACT
The inherent ambiguity in reconstructed images from coherent diffraction imaging (CDI) poses an intrinsic challenge, as images derived from the same dataset under varying initial conditions often display inconsistencies. This study introduces a method that employs the Noise2Noise approach combined with neural networks to effectively mitigate these ambiguities. We applied this methodology to hundreds of ambiguous reconstructed images retrieved from a single diffraction pattern using a conventional retrieval algorithm. Our results demonstrate that ambiguous features in these reconstructions are effectively treated as inter-reconstruction noise and are significantly reduced. The post-Noise2Noise treated images closely approximate the average and singular value decomposition analysis of various reconstructions, providing consistent and reliable reconstructions.
ABSTRACT
Movement sonification has emerged as a promising approach for rehabilitation and motion control. Despite significant advancements in sensor technologies, challenges remain in developing cost-effective, user-friendly, and reliable systems for gait detection and sonification. This study introduces a novel wearable personalised sonification and biofeedback device to enhance movement awareness for individuals with irregular gait and posture. Through the integration of inertial measurement units (IMUs), MATLAB, and sophisticated audio feedback mechanisms, the device offers real-time, intuitive cues to facilitate gait correction and improve functional mobility. Utilising a single wearable sensor attached to the L4 vertebrae, the system captures kinematic parameters to generate auditory feedback through discrete and continuous tones corresponding to heel strike events and sagittal plane rotations. A preliminary test that involved 20 participants under various audio feedback conditions was conducted to assess the system's accuracy, reliability, and user synchronisation. The results indicate a promising improvement in movement awareness facilitated by auditory cues. This suggests a potential for enhancing gait and balance, particularly beneficial for individuals with compromised gait or those undergoing a rehabilitation process. This paper details the development process, experimental setup, and initial findings, discussing the integration challenges and future research directions. It also presents a novel approach to providing real-time feedback to participants about their balance, potentially enabling them to make immediate adjustments to their posture and movement. Future research should evaluate this method in varied real-world settings and populations, including the elderly and individuals with Parkinson's disease.
Subject(s)
Biofeedback, Psychology , Gait , Movement , Wearable Electronic Devices , Humans , Movement/physiology , Biofeedback, Psychology/instrumentation , Gait/physiology , Male , Female , Adult , Biomechanical Phenomena , Postural Balance/physiology , Posture/physiology , Young AdultABSTRACT
Background: Resuscitative endovascular balloon occlusion of the aorta (REBOA) has been an established life-saving procedure for adult trauma patients, but the evidence for its use in pediatric patients is still under question. The purpose of this study was to examine the outcome of REBOA in pediatric patients. Methods: We retrospectively analyzed observational cohort data from the American College of Surgeons-Trauma Quality Improvement Program from 2017 to 2019. We analyzed 183 506 trauma patients aged 7-18, and 111 patients were matched by propensity score analysis. Basic demographics, injury severity, trauma type, and clinical outcomes of the patients receiving REBOA and those not receiving REBOA were compared. In the REBOA patients, a subgroup analysis was performed to evaluate the potential influence of age and body weight on the outcomes of REBOA. Results: After the pretreatment factors were balanced for the REBOA and no-REBOA groups, the patients in the REBOA group had more transfused packed red blood cells within the first 4 hours (3250 mL vs. 600 mL, p<0.001), and the mortality rate was higher in the REBOA group, but it did not reach statistical significance (56.8% vs. 36.5%, p=0.067). No significant difference was detected regarding in-hospital complications. In the subgroup analysis of the patients who received REBOA, we discovered no significant difference in mortality and complications between the subgroups when compared by age (>15 years old/≤15 years old) or weight (>58 kg or ≤58 kg). Conclusions: Pediatric trauma patients who received REBOA were not significantly associated with an increased risk of mortality when compared with no-REBOA patients with matched basic demographics and pretreatment factors. Younger age and lighter body weight did not seem to influence the outcomes of REBOA regarding survival and complications. Level of evidence: Level III.
ABSTRACT
PURPOSE: This research aimed to identify the function of fat mass- and obesity-associated protein (FTO), an eraser of N6-methyladenosine (m6A), and explore its possible mechanisms in uveal melanoma (UVM). METHODS: We performed quantitative real-time PCR (qPCR), Western blotting and gene correlation analysis with GEPIA2 to assess FTO expression and identify its potential targets in UVM. CCK-8, colony formation, cell cycle, cell apoptosis, wound healing and Transwell invasion assays were utilized to assess cell viability, cell cycle distribution, apoptosis, migration and invasion. Western blotting, qPCR and methylated RNA immunoprecipitation-qPCR (MeRIP-qPCR) were carried out to explore the underlying mechanism of FTO in 2 UVM cell lines. RESULTS: FTO, a key m6A demethylase, was found to be upregulated in human UVM tissues compared with normal choroid tissues. Knockdown of FTO in Mel270 and OMM2.3 cells significantly promoted proliferation and migration and suppressed apoptosis. Mechanistically, knockdown of FTO decreased the expression of ATG5, an autophagy-related gene, leading to attenuation of autophagosome formation, thereby inhibiting autophagy. Upon FTO knockdown, increased levels of methylated ATG5 and decreased ATG5 stability were detected. Furthermore, ATG5 dramatically alleviated FTO downregulation-induced tumor growth and metastasis. CONCLUSIONS: Our research highlights the importance of the m6A demethylase FTO in UVM by demonstrating that it direct regulates ATG5-induced autophagy in an m6A-dependent manner. These findings suggest that FTO may serve as a potential therapeutic target for UVM.
ABSTRACT
Fibrinogen-fibrin degradation products (DR-70) are derived from tumor cells or metastases. Our previous study reported the diagnostic values in dogs with tumors, but no research has yet to be conducted to establish DR-70 as a prognostic marker. Herein, we investigated changes in DR-70 concentrations and disease courses in dogs with tumors. Overall survival time (OST) analysis was performed in 195 dogs with tumors, stratified with a recommended cut-off (1.514 µg/mL). Continual DR-70 measurements were performed during the medical interventions of 27 dogs with neoplasms. Clinical conditions and medical records were retrospectively reviewed. According to a cut-off value, dogs with plasma DR-70 concentrations above 1.514 µg/mL had shorter survival rates than those with concentrations below this threshold. In cases with complete or partial remission in response to treatment, the DR-70 concentration was decreased compared with that at the first visit, whereas it was increased in patients with disease progression. Our study suggested that changes in DR-70 concentration can be used as a prognostic biomarker for canine neoplasms. Furthermore, increased plasma DR-70 levels might be associated with shorter survival, and DR-70 concentrations may reflect responses to medical intervention.
Subject(s)
Biomarkers, Tumor , Dog Diseases , Fibrin Fibrinogen Degradation Products , Neoplasms , Dogs , Animals , Dog Diseases/blood , Dog Diseases/mortality , Dog Diseases/diagnosis , Neoplasms/veterinary , Neoplasms/blood , Neoplasms/mortality , Neoplasms/diagnosis , Prognosis , Retrospective Studies , Male , Female , Biomarkers, Tumor/blood , Fibrin Fibrinogen Degradation Products/analysis , Fibrin Fibrinogen Degradation Products/metabolism , Survival Analysis , Fibrinogen/analysisABSTRACT
BACKGROUND AND AIM: Primary liver cancer, particularly hepatocellular carcinoma (HCC), represents a substantial global health challenge. Although immune checkpoint inhibitors are effective in HCC treatment, several patients still experience disease progression. Interleukin-1 (IL-1) regulates immunity and inflammation. We investigate the role of IL-1 in HCC development and progression and determine the potential therapeutic impact of gemcitabine in treating HCC. METHODS: Hydrodynamics-based transfection, employing the sleeping beauty transposase system, delivered surrogate tumor antigens, NRAS (NRAS proto-oncogene, GTPase), ShP53, and SB100 to C57BL/6 mice. A basic HCC mouse model was established. Pathogen-free animals were tested for serum and hepatotoxicity. The HCC prognosis was monitored using alanine aminotransferase and aspartate aminotransferase levels. Liver histology immunohistochemistry and mouse splenocyte/intra-hepatic immune cell flow cytometry were conducted. IL-1ß levels in human and mouse serum were assessed. RESULTS: Interleukin-1ß levels were elevated in patients with HCC compared with those in non-HCC controls. Hepatic IL-1ß levels were higher in HCC mouse models than those in non-HCC mice, suggesting localized hepatic inflammation. IL-1 receptor type 1 (IL-1R1) knockout (IL-1R1-/-) mice exhibited less severe HCC progression than that in wild-type mice, despite the high intra-hepatic IL-1ß concentration. IL-1R1-/- mice exhibited increased hepatic levels of myeloid-derived suppressor cells and regulatory T cells, which may exacerbate HCC. Gemcitabine significantly reduced the HCC tumor burden, improved liver conditions, and increased survival rates in HCC mouse models. Gemcitabine reduced the hepatic levels of myeloid-derived suppressor cells and regulatory T cells, potentially alleviating immune suppression in the liver. CONCLUSIONS: Targeting IL-1 or combining gemcitabine with immunotherapy is a promising approach for treating advanced-stage HCC.
ABSTRACT
This study aimed to clarify how microclimate diversity altered volatilomics in Cabernet Sauvignon grapes and wines. Four row-oriented vineyards were selected, and metabolites of grapes and wines were determined from separate canopy sides. Results showed that shaded sides received 59% of the solar radiation and experienced 55% of the high-temperature days compared to the exposed sides on average. Grape primary metabolites were slightly affected by the canopy side. Herbaceous aromas were consistently more abundant in grapes and wines from shaded clusters. Heat-stressed canopy sides accelerated terpenoid loss and increased norisoprenoid levels in grapes, while ß-damascenone in north-side wines was 13%-32% higher than that in south-side wines of the east-west vineyard. The northeast-southwest vineyard showed the most notable variation in taste and aroma sensory scores, with four parameters significantly different. There were 32 aroma series identified in wines, and banana, pineapple, and strawberry odors were highly correlated with aroma sensory score.
ABSTRACT
Tissue-resident memory T cells (TRM) are a specialized subset of long-lived memory T cells that reside in peripheral tissues. However, the impact of TRM-related immunosurveillance on the tumor-immune microenvironment (TIME) and tumor progression across various non-small-cell lung cancer (NSCLC) patient populations is yet to be elucidated. Our comprehensive analysis of multiple independent single-cell and bulk RNA-seq datasets of patient NSCLC samples generated reliable, unique TRM signatures, through which we inferred the abundance of TRM in NSCLC. We discovered that TRM abundance is consistently positively correlated with CD4+ T helper 1 cells, M1 macrophages, and resting dendritic cells in the TIME. In addition, TRM signatures are strongly associated with immune checkpoint and stimulatory genes and the prognosis of NSCLC patients. A TRM-based machine learning model to predict patient survival was validated and an 18-gene risk score was further developed to effectively stratify patients into low-risk and high-risk categories, wherein patients with high-risk scores had significantly lower overall survival than patients with low-risk. The prognostic value of the risk score was independently validated by the Cancer Genome Atlas Program (TCGA) dataset and multiple independent NSCLC patient datasets. Notably, low-risk NSCLC patients with higher TRM infiltration exhibited enhanced T-cell immunity, nature killer cell activation, and other TIME immune responses related pathways, indicating a more active immune profile benefitting from immunotherapy. However, the TRM signature revealed low TRM abundance and a lack of prognostic association among lung squamous cell carcinoma patients in contrast to adenocarcinoma, indicating that the two NSCLC subtypes are driven by distinct TIMEs. Altogether, this study provides valuable insights into the complex interactions between TRM and TIME and their impact on NSCLC patient prognosis. The development of a simplified 18-gene risk score provides a practical prognostic marker for risk stratification.
Subject(s)
Carcinoma, Non-Small-Cell Lung , Lung Neoplasms , Memory T Cells , Tumor Microenvironment , Humans , Carcinoma, Non-Small-Cell Lung/immunology , Carcinoma, Non-Small-Cell Lung/mortality , Carcinoma, Non-Small-Cell Lung/genetics , Tumor Microenvironment/immunology , Tumor Microenvironment/genetics , Lung Neoplasms/immunology , Lung Neoplasms/mortality , Lung Neoplasms/genetics , Lung Neoplasms/pathology , Prognosis , Memory T Cells/immunology , Immunologic Memory , Lymphocytes, Tumor-Infiltrating/immunologyABSTRACT
Cancer has become a primary global health concern, which has prompted increased attention towards targeted therapeutic approaches like photothermal therapy (PTT). The unique optical and magnetic properties of nanodiamonds (NDs) have made them versatile nanomaterials with promising applications in biomedicine. This comprehensive review focuses on the potential of NDs as a multifaceted platform for anticancer therapy, mainly focusing on their dual functionality in PTT and temperature sensing. The review highlighted NDs' ability to enhance PTT through hybridization or modification, underscoring their adaptability in delivering small molecule reagents effectively. Furthermore, NDs, particularly fluorescent nanodiamonds (FNDs) with negatively charged nitrogen-vacancy centers, enable precise temperature monitoring, enhancing PTT efficacy in anticancer treatment. Integrating FNDs into PTT holds promise for advancing therapeutic efficacy by providing valuable insights into localized temperature variations and cell death mechanisms. This review highlights new insights into cancer treatment strategies, showcasing the potential of NDs to revolutionize targeted therapeutics and improve patient outcomes.
Subject(s)
Nanodiamonds , Neoplasms , Photothermal Therapy , Nanodiamonds/chemistry , Nanodiamonds/therapeutic use , Humans , Neoplasms/therapy , Neoplasms/drug therapy , Neoplasms/pathology , Temperature , Animals , Antineoplastic Agents/chemistry , Antineoplastic Agents/pharmacology , Antineoplastic Agents/therapeutic useABSTRACT
Barium titanate (BaTiO3, BTO), conventionally used for dielectric and ferroelectric applications, has been assessed for biomedical applications, such as its utilization as a radiopacifier in mineral trioxide aggregates (MTA) for endodontic treatment. In the present study, BTO powders were prepared using the sol-gel process, followed by calcination at 400-1100 °C. The X-ray diffraction technique was then used to examine the as-prepared powders to elucidate the effect of calcination on the phase composition and crystalline size of BTO. Calcined BTO powders were then used as radiopacifiers for MTA. MTA-like cements were investigated to determine the optimal calcination temperature based on the radiopacity and diametral tensile strength (DTS). The experimental results showed that the formation of BTO phase was observed after calcination at temperatures of 600 °C and above. The calcined powders were a mixture of BaTiO3 phase with residual BaCO3 and/or Ba2TiO4 phases. The performance of MTA-like cements with BTO addition increased with increasing calcination temperature up to 1000 °C. The radiopacity, however, decreased after 7 days of simulated oral environmental storage, whereas an increase in DTS was observed. Optimal MTA-like cement was obtained by adding 40 wt.% 1000 °C-calcined BTO powder, with its resulting radiopacity and DTS at 4.83 ± 0.61 mmAl and 2.86 ± 0.33 MPa, respectively. After 7 days, the radiopacity decreased slightly to 4.69 ± 0.51 mmAl, accompanied by an increase in DTS to 3.13 ± 0.70 MPa. The optimal cement was biocompatible and verified using MG 63 and L929 cell lines, which exhibited cell viability higher than 95%.
ABSTRACT
Cancer immunotherapy represents a paradigm shift in oncology, offering a superior anti-tumor efficacy and the potential for durable remission. The success of personalized vaccines and cell therapies hinges on the identification of immunogenic epitopes capable of eliciting an effective immune response. Current limitations in the availability of immunogenic epitopes restrict the broader application of such therapies. A critical criterion for serving as potential cancer antigens is their ability to stably bind to the major histocompatibility complex (MHC) for presentation on the surface of tumor cells. To address this, we have developed a comprehensive database of MHC epitopes, experimentally validated for their MHC binding and cell surface presentation. Our database catalogs 451 065 MHC peptide epitopes, each with experimental evidence for MHC binding, along with detailed information on human leukocyte antigen allele specificity, source peptides, and references to original studies. We also provide the grand average of hydropathy scores and predicted immunogenicity for the epitopes. The database (MHCepitopes) has been made available on the web and can be accessed at https://github.com/jcm1201/MHCepitopes.git. By consolidating empirical data from various sources coupled with calculated immunogenicity and hydropathy values, our database offers a robust resource for selecting actionable tumor antigens and advancing the design of antigen-specific cancer immunotherapies. It streamlines the process of identifying promising immunotherapeutic targets, potentially expediting the development of effective antigen-based cancer immunotherapies.
ABSTRACT
BACKGROUND: Monitoring Intraabdominal Pressure (IAP) is essential in critical care, as elevated IAP can lead to severe complications, including Abdominal Compartment Syndrome (ACS). Advances in technology, such as digital capsules, have opened new avenues for measuring IAP non-invasively. This study assesses the feasibility and effectiveness of using a capsular device for IAP measurement in an animal model. METHOD: In our controlled experiment, we anesthetized pigs and simulated elevated IAP conditions by infusing CO2 into the peritoneal cavity. We compared IAP measurements obtained from three different methods: an intravesical catheter (IAPivp), a capsular device (IAPdot), and a direct peritoneal catheter (IAPdir). The data from these methods were analyzed to evaluate agreement and accuracy. RESULTS: The capsular sensor (IAPdot) provided continuous and accurate detection of IAP over 144 h, with a total of 53,065,487 measurement triplets recorded. The correlation coefficient (R²) between IAPdot and IAPdir was excellent at 0.9241, demonstrating high agreement. Similarly, IAPivp and IAPdir showed strong correlation with an R² of 0.9168. CONCLUSION: The use of capsular sensors for continuous and accurate assessment of IAP marks a significant advancement in the field of critical care monitoring. The high correlation between measurements from different locations and methods underscores the potential of capsular devices to transform clinical practices by providing reliable, non-invasive IAP monitoring.
Subject(s)
Feasibility Studies , Intra-Abdominal Hypertension , Animals , Swine , Intra-Abdominal Hypertension/diagnosis , Intra-Abdominal Hypertension/physiopathology , Monitoring, Physiologic/methods , Monitoring, Physiologic/instrumentation , Pressure , Abdominal Cavity/physiology , Abdominal Cavity/physiopathology , Reproducibility of Results , Disease Models, AnimalABSTRACT
BACKGROUND: The impact of resuscitative endovascular balloon occlusion of the aorta (REBOA) on traumatic brain injuries remains uncertain, with potential outcomes ranging from neuroprotection to exacerbation of the injury. The study aimed to evaluate consciousness recovery in patients with blunt trauma with shock and traumatic brain injuries. MATERIAL AND METHODS: Data were obtained from the American College of Surgeons Trauma Quality Improvement Program from 2017-2019. During the study period, 3,138,896 trauma registries were examined, and 16,016 adult patients with blunt trauma, shock, and traumatic brain injuries were included. Among these, 172 (1.1%) underwent REBOA. Comparisons were conducted between patients with and without REBOA after implementing 1:3 propensity score matching to mitigate disparities. The primary outcome was the highest Glasgow Coma Scale score during admission. The secondary outcomes encompassed the volume of blood transfusion, the necessity for hemostatic interventions and therapeutic neurosurgery, and mortality rate. RESULTS: Through well-balanced propensity score matching, a notable difference in mortality rate was observed, with 59.7% in the REBOA group and 48.7% in the non-REBOA group (P=0.015). In the REBOA group, the median 4-hour red blood cell transfusion was significantly higher (2800 mL [1500, 4908] vs. 1300 mL [600, 2500], P<0.001). The REBOA group required lesser hemorrhagic control surgeries (31.8% vs. 47.7%, P<0.001) but needed more transarterial embolization interventions (22.2% vs 15.9%, P=0.076). The incidence of therapeutic neurosurgery was 5.1% in the REBOA group and 8.7% in the non-REBOA group (P=0.168). Among survivors in the REBOA group, the median highest Glasgow Coma Scale score during admission was significantly greater for both total (11 [8, 14] vs. 9 [6, 12], P=0.036) and motor components (6 [4, 6] vs. 5 [3, 6], P=0.037). The highest GCS score among the survivors with predominant pelvic injuries was not different between the two groups (11 [8, 13] vs. 11 [7, 14], P=0.750). CONCLUSIONS: Patients experiencing shock and traumatic brain injury have high mortality rates, necessitating swift resuscitation and prompt hemorrhagic control. The use of REBOA as an adjunct for bridging definitive hemorrhagic control may correlate with enhanced consciousness recovery.
ABSTRACT
Background: The global aging population presents a significant challenge, with older adults experiencing declining physical and cognitive abilities and increased vulnerability to chronic diseases and adverse health outcomes. This study aims to develop an interpretable deep learning (DL) model to predict adverse events in geriatric patients within 72 hours of hospitalization. Methods: The study used retrospective data (2017-2020) from a major medical center in Taiwan. It included non-trauma geriatric patients who visited the emergency department and were admitted to the general ward. Data preprocessing involved collecting prognostic factors like vital signs, lab results, medical history, and clinical management. A deep feedforward neural network was developed, and performance was evaluated using accuracy, sensitivity, specificity, positive predictive value (PPV), and area under the receiver operating characteristic curve (AUC). Model interpretation utilized the Shapley Additive Explanation (SHAP) technique. Results: The analysis included 127,268 patients, with 2.6% experiencing imminent intensive care unit transfer, respiratory failure, or death during hospitalization. The DL model achieved AUCs of 0.86 and 0.84 in the validation and test sets, respectively, outperforming the Sequential Organ Failure Assessment (SOFA) score. Sensitivity and specificity values ranged from 0.79 to 0.81. The SHAP technique provided insights into feature importance and interactions. Conclusion: The developed DL model demonstrated high accuracy in predicting serious adverse events in geriatric patients within 72 hours of hospitalization. It outperformed the SOFA score and provided valuable insights into the model's decision-making process.
Subject(s)
Deep Learning , Hospitalization , Humans , Aged , Female , Male , Retrospective Studies , Hospitalization/statistics & numerical data , Aged, 80 and over , Taiwan , ROC Curve , Geriatric Assessment/methods , Prognosis , Intensive Care Units , Organ Dysfunction Scores , Area Under Curve , Emergency Service, Hospital , Risk AssessmentSubject(s)
Biomarkers , Humans , Biomarkers/analysis , History, 21st Century , History, 20th CenturyABSTRACT
Phytochemical investigation of the bark of Cryptomeria japonica led to the isolation of five new abietane diterpenoids, 5-epi-12-hydroxy-6-nor-5,6-secoabieta-8,11,13-trien-7,5-olide (1), 12-hydroxy-6ß-methoxy-6,7-secoabieta-8,11,13-trien-7,6-olide (2), 6ß,12-dihydroxy-7,8-secoabieta-8,11,13-trien-7,8-olide (4), 5,12-dihydroxy-7,8-secoabieta-8,11,13-trien-7,8-olide (5), and 5α,8-epoxy-12-hydroxy-7,8-secoabieta-8,11,13-trien-7-al (6), together with one known abietane diterpenoid, obtuanhydride (3). Their structures were elucidated by analysis of spectroscopic data and comparison with the spectral data of known analogs. At the concentration of 100 µg/mL, compounds 4, 5, and 6 inhibited antifungal activities against wood decay fungi activity by 18.7, 37.2, and 46.7%, respectively.
ABSTRACT
Extracellular vesicle (EV) research is rapidly advancing from fundamental science to translational applications in EV-based personalized therapeutics and diagnostics. Yet, fundamental questions persist regarding EV biology and mechanisms, particularly concerning the heterogeneous interactions between EVs and cells. While we have made strides in understanding virus delivery and intracellular vesicle transport, our comprehension of EV trafficking remains limited. EVs are believed to mediate intercellular communication through cargo transfer, but uncertainties persist regarding the occurrence and quantification of EV-cargo delivery within acceptor cells. This ambiguity is crucial to address, given the significant translational impact of EVs on therapeutics and diagnostics. This perspective article does not seek to provide exhaustive recommendations and guidance on EV-related studies, as these are well-articulated in position papers and statements by the International Society for Extracellular Vesicles (ISEV), including the 'Minimum Information for Studies of Extracellular Vesicles' (MISEV) 2014, MISEV2018, and the recent MISEV2023. Instead, recognizing the multilayered heterogeneity of EVs as both a challenge and an opportunity, this perspective emphasizes novel approaches to facilitate our understanding of diverse EV biology, address uncertainties, and leverage this knowledge to advance EV-based personalized diagnostics and therapeutics. Specifically, this perspective synthesizes current insights, identifies opportunities, and highlights exciting technological advancements in ultrasensitive single EV or "digital" profiling developed within the author's multidisciplinary group. These newly developed technologies address technical gaps in dissecting the molecular contents of EV subsets, contributing to the evolution of EVs as next-generation liquid biopsies for diagnostics and providing better quality control for EV-based therapeutics.
Subject(s)
Extracellular Vesicles , Precision Medicine , Extracellular Vesicles/metabolism , Humans , Precision Medicine/methods , Cell Communication , AnimalsABSTRACT
Purpose: To develop a rib and clavicle fracture detection model for chest radiographs in trauma patients using a deep learning (DL) algorithm. Materials and methods: We retrospectively collected 56 145 chest X-rays (CXRs) from trauma patients in a trauma center between August 2008 and December 2016. A rib/clavicle fracture detection DL algorithm was trained using this data set with 991 (1.8%) images labeled by experts with fracture site locations. The algorithm was tested on independently collected 300 CXRs in 2017. An external test set was also collected from hospitalized trauma patients in a regional hospital for evaluation. The receiver operating characteristic curve with area under the curve (AUC), accuracy, sensitivity, specificity, precision, and negative predictive value of the model on each test set was evaluated. The prediction probability on the images was visualized as heatmaps. Results: The trained DL model achieved an AUC of 0.912 (95% CI 87.8 to 94.7) on the independent test set. The accuracy, sensitivity, and specificity on the given cut-off value are 83.7, 86.8, and 80.4, respectively. On the external test set, the model had a sensitivity of 88.0 and an accuracy of 72.5. While the model exhibited a slight decrease in accuracy on the external test set, it maintained its sensitivity in detecting fractures. Conclusion: The algorithm detects rib and clavicle fractures concomitantly in the CXR of trauma patients with high accuracy in locating lesions through heatmap visualization.
ABSTRACT
Diagnostic imaging is essential in modern trauma care for initial evaluation and identifying injuries requiring intervention. Deep learning (DL) has become mainstream in medical image analysis and has shown promising efficacy for classification, segmentation, and lesion detection. This narrative review provides the fundamental concepts for developing DL algorithms in trauma imaging and presents an overview of current progress in each modality. DL has been applied to detect free fluid on Focused Assessment with Sonography for Trauma (FAST), traumatic findings on chest and pelvic X-rays, and computed tomography (CT) scans, identify intracranial hemorrhage on head CT, detect vertebral fractures, and identify injuries to organs like the spleen, liver, and lungs on abdominal and chest CT. Future directions involve expanding dataset size and diversity through federated learning, enhancing model explainability and transparency to build clinician trust, and integrating multimodal data to provide more meaningful insights into traumatic injuries. Though some commercial artificial intelligence products are Food and Drug Administration-approved for clinical use in the trauma field, adoption remains limited, highlighting the need for multi-disciplinary teams to engineer practical, real-world solutions. Overall, DL shows immense potential to improve the efficiency and accuracy of trauma imaging, but thoughtful development and validation are critical to ensure these technologies positively impact patient care.
ABSTRACT
BACKGROUND: Low back pain (LBP) is a leading cause of disability worldwide and has posed numerous health and socioeconomic challenges. This study compared whether nonsteroidal anti-inflammatory drugs (NSAIDs) in combination with tramadol, tizanidine or placebo would be the best treatment regime to improve the Roland Morris Disability Questionnaire (RMDQ) scores at 1 week. METHODS: This was a multi-center, double-blind, randomized, and placebo-controlled trial including adult patients with acute LBP and sciatica in three emergency departments in Hong Kong. Patients were randomized to the receive tramadol 50 mg, tizanidine 2 mg, or placebo every 6 hours for 2 weeks in a 1:1:1 ratio. The RMDQ and other secondary outcomes were measured at baseline, Day 2, 7, 14, 21, and 28. Data were analyzed on an intention to treat basis. Crude and adjusted mean differences in the changes of RMDQ and NRS scores from baseline to Day 7 between tizanidine/tramadol and placebo were determined with 95% confidence intervals. RESULTS: Two hundred and ninety-one patients were analyzed with the mean age of 47.4 years and 57.7% were male. The primary outcome of mean difference in RMDQs on Day 7 (compared with baseline) was non-significant for tizanidine compared with placebo (adjusted mean difference - 0.56, 95% CI -2.48 to 1.37) and tramadol compared with placebo (adjusted mean difference - 0.85, 95% CI -2.80 to 1.10). Only 23.7% were fully compliant to the treatment allocated. Complier Average Causal Effect analysis also showed no difference in the primary outcome for the tizanidine and tramadol versus placebo. CONCLUSION: Among patients with acute LBP and sciatica presenting to the ED, adding tramadol or tizanidine to diclofenac did not improve functional recovery.