An exploratory deep learning approach to investigate tuberculosis pathogenesis in nonhuman primate model: Combining automated radiological analysis with clinical and biomarkers data.

BACKGROUND: Tuberculosis (TB) kills approximately 1.6 million people yearly despite the fact anti-TB drugs are generally curative. Therefore, TB-case detection and monitoring of therapy, need a comprehensive approach. Automated radiological analysis, combined with clinical, microbiological, and immunological data, by machine learning (ML), can help achieve it. METHODS: Six rhesus macaques were experimentally inoculated with pathogenic Mycobacterium tuberculosis in the lung. Data, including Computed Tomography (CT), were collected at 0, 2, 4, 8, 12, 16, and 20 weeks. RESULTS: Our ML-based CT analysis (TB-Net) efficiently and accurately analyzed disease progression, performing better than standard deep learning model (LLM OpenAI's CLIP Vi4). TB-Net based results were more consistent than, and confirmed independently by, blinded manual disease scoring by two radiologists and exhibited strong correlations with blood biomarkers, TB-lesion volumes, and disease-signs during disease pathogenesis. CONCLUSION: The proposed approach is valuable in early disease detection, monitoring efficacy of therapy, and clinical decision making.

Frontiers in Acute Pain Management: Emerging Concepts in Pain Pathways and the Role of VX-548 as a Novel NaV1.8 Inhibitor: A Narrative Review.

PURPOSE OF REVIEW: Despite ongoing research into alternative postsurgical pain treatments, opioids remain widely used analgesics regardless of associated adverse effects, including dependence and overdose, as demonstrated throughout the current opioid crisis. This is likely related to a failure in proving the efficacy of alternative analgesics in clinical trials, despite strong evidence supporting the potential for effective analgesia through in vitro studies. While NaV1.7 and NaV1.8 channels have shown to be key components of pain perception, studies regarding pharmacological agents utilizing these channels as targets have largely failed to demonstrate the efficacy of these proposed analgesics when compared to current multimodal pain treatment regimens. RECENT FINDINGS: However, the novel NaV1.8 channel inhibitor, VX-548 has surpassed previously studied NaV1.8 inhibitors in clinical trials and continues to hold promise of a novel efficacious analgesic to potentially be utilized in multimodal pain treatment on postsurgical patients. Additionally, NaV1.8 is encoded by the SCN10A, which has been shown to be minimally expressed in the brain, suggesting a lower likelihood of adverse effects in the CNS, including dependence and abuse. Novel pharmacologic analgesics that are efficacious without the significant side effects associated with opioids have lacked meaningful development. However, recent clinical trials have shown promising results in the safety and efficacy of the pharmacological agent VX-548. Still, more clinical trials directly comparing the efficacy of VX-548 to standard of care post-surgical drugs, including opioids like morphine and hydromorphone are needed to demonstrate the long-term viability of the agent replacing current opioids with an unfavorable side effect profile.

Nutrition guidance within a multimodal intervention improves diet quality in prodromal Alzheimer's disease: Multimodal Preventive Trial for Alzheimer's Disease (MIND-ADmini).

BACKGROUND: Multimodal lifestyle interventions can benefit overall health, including cognition, in populations at-risk for dementia. However, little is known about the effect of lifestyle interventions in patients with prodromal Alzheimer's disease (AD). Even less is known about dietary intake and adherence to dietary recommendations within this population making it difficult to design tailored interventions for them. METHOD: A 6-month MIND-ADmini pilot randomized controlled trial (RCT) was conducted among 93 participants with prodromal AD in Sweden, Finland, Germany, and France. Three arms were included in the RCT: 1) multimodal lifestyle intervention (nutritional guidance, exercise, cognitive training, vascular/metabolic risk management, and social stimulation); 2) multimodal lifestyle intervention + medical food product; and 3) regular health advice (control group). Adherence to dietary advice was assessed with a brief food intake questionnaire by using the Healthy Diet Index (HDI) and Mediterranean Diet Adherence Screener (MEDAS). The intake of macro- and micronutrients were analyzed on a subsample using 3-day food records. RESULTS: The dietary quality in the intervention groups, pooled together, improved compared to that of the control group at the end of the study, as measured with by HDI (p = 0.026) and MEDAS (p = 0.008). The lifestyle-only group improved significantly more in MEDAS (p = 0.046) and almost significantly in HDI (p = 0.052) compared to the control group, while the lifestyle + medical food group improved in both HDI (p = 0.042) and MEDAS (p = 0.007) during the study. There were no changes in macro- or micronutrient intake for the intervention groups at follow-up; however, the intakes in the control group declined in several vitamins and minerals when adjusted for energy intake. CONCLUSION: These results suggest that dietary intervention as part of multimodal lifestyle interventions is feasible and results in improved dietary quality in a population with prodromal AD. Nutrient intakes remained unchanged in the intervention groups while the control group showed a decreasing nutrient density. TRIAL REGISTRATION: ClinicalTrials.gov NCT03249688, 2017-07-08.

Predicting conversion from mild cognitive impairment to Alzheimer's disease: a multimodal approach.

Successively predicting whether mild cognitive impairment patients will progress to Alzheimer's disease is of significant clinical relevance. This ability may provide information that can be leveraged by emerging intervention approaches and thus mitigate some of the negative effects of the disease. Neuroimaging biomarkers have gained some attention in recent years and may be useful in predicting the conversion of mild cognitive impairment to Alzheimer's disease. We implemented a novel multi-modal approach that allowed us to evaluate the potential of different imaging modalities, both alone and in different degrees of combinations, in predicting the conversion to Alzheimer's disease of mild cognitive impairment patients. We applied this approach to the imaging data from the Alzheimer's Disease Neuroimaging Initiative that is a multi-modal imaging dataset comprised of MRI, Fluorodeoxyglucose PET, Florbetapir PET and diffusion tensor imaging. We included a total of 480 mild cognitive impairment patients that were split into two groups: converted and stable. Imaging data were segmented into atlas-based regions of interest, from which relevant features were extracted for the different imaging modalities and used to construct machine-learning models to classify mild cognitive impairment patients into converted or stable, using each of the different imaging modalities independently. The models were then combined, using a simple weight fusion ensemble strategy, to evaluate the complementarity of different imaging modalities and their contribution to the prediction accuracy of the models. The single-modality findings revealed that the model, utilizing features extracted from Florbetapir PET, demonstrated the highest performance with a balanced accuracy of 83.51%. Concerning multi-modality models, not all combinations enhanced mild cognitive impairment conversion prediction. Notably, the combination of MRI with Fluorodeoxyglucose PET emerged as the most promising, exhibiting an overall improvement in predictive capabilities, achieving a balanced accuracy of 78.43%. This indicates synergy and complementarity between the two imaging modalities in predicting mild cognitive impairment conversion. These findings suggest that ß-amyloid accumulation provides robust predictive capabilities, while the combination of multiple imaging modalities has the potential to surpass certain single-modality approaches. Exploring modality-specific biomarkers, we identified the brainstem as a sensitive biomarker for both MRI and Fluorodeoxyglucose PET modalities, implicating its involvement in early Alzheimer's pathology. Notably, the corpus callosum and adjacent cortical regions emerged as potential biomarkers, warranting further study into their role in the early stages of Alzheimer's disease.

A multimodal dataset for investigating working memory in presence of music: a pilot study.

Introduction: Decoding an individual's hidden brain states in responses to musical stimuli under various cognitive loads can unleash the potential of developing a non-invasive closed-loop brain-machine interface (CLBMI). To perform a pilot study and investigate the brain response in the context of CLBMI, we collect multimodal physiological signals and behavioral data within the working memory experiment in the presence of personalized musical stimuli. Methods: Participants perform a working memory experiment called the n-back task in the presence of calming music and exciting music. Utilizing the skin conductance signal and behavioral data, we decode the brain's cognitive arousal and performance states, respectively. We determine the association of oxygenated hemoglobin (HbO) data with performance state. Furthermore, we evaluate the total hemoglobin (HbT) signal energy over each music session. Results: A relatively low arousal variation was observed with respect to task difficulty, while the arousal baseline changes considerably with respect to the type of music. Overall, the performance index is enhanced within the exciting session. The highest positive correlation between the HbO concentration and performance was observed within the higher cognitive loads (3-back task) for all of the participants. Also, the HbT signal energy peak occurs within the exciting session. Discussion: Findings may underline the potential of using music as an intervention to regulate the brain cognitive states. Additionally, the experiment provides a diverse array of data encompassing multiple physiological signals that can be used in the brain state decoder paradigm to shed light on the human-in-the-loop experiments and understand the network-level mechanisms of auditory stimulation.

Simultaneous grading diagnosis of liver fibrosis, inflammation, and steatosis using multimodal quantitative ultrasound and artificial intelligence framework.

Noninvasive, accurate, and simultaneous grading of liver fibrosis, inflammation, and steatosis is valuable for reversing the progression and improving the prognosis quality of chronic liver diseases (CLDs). In this study, we established an artificial intelligence framework for simultaneous grading diagnosis of these three pathological types through fusing multimodal tissue characterization parameters dug by quantitative ultrasound methods derived from ultrasound radiofrequency signals, B-mode images, shear wave elastography images, and clinical ultrasound systems, using the liver biopsy results as the classification criteria. One hundred forty-two patients diagnosed with CLD were enrolled in this study. The results show that for the classification of fibrosis grade ≥ F1, ≥ F2, ≥ F3, and F4, the highest AUCs were respectively 0.69, 0.82, 0.84, and 0.88 with single clinical indicator alone, and were 0.81, 0.83, 0.89, and 0.91 with the proposed method. For the classification of inflammation grade ≥ A2 and A3, the highest AUCs were respectively 0.66 and 0.76 with single clinical indicator alone and were 0.80 and 0.93 with the proposed method. For the classification of steatosis grade ≥ S1 and ≥ S2, the highest AUCs were respectively 0.71 and 0.90 with single clinical indicator alone and were 0.75 and 0.92 with the proposed method. The proposed method can effectively improve the grading diagnosis performance compared with the present clinical indicators and has potential applications for noninvasive, accurate, and simultaneous diagnosis of CLDs.

An injectable hydrogel based on sodium alginate and gelatin treats bacterial keratitis through multimodal antibacterial strategy.

Bacterial keratitis is among the most prevalent causes of blindness. Currently, the abuse of antibiotics in clinical settings not only lacks bactericidal effects but also readily induces bacterial resistance, making the clinical treatment of bacterial keratitis a significant challenge. In this study, we present an injectable hydrogel (GS-PNH-FF@CuS/MnS) containing self-assembled diphenylalanine dipeptide (FF) and CuS/MnS nanocomposites (CuS/MnS NCs) that destroy bacterial cell walls through a synergistic combination of mild photothermal therapy (PTT), chemodynamic therapy (CDT), ion release chemotherapy, and self-assembled dipeptide contact, thereby eliminating Pseudomonas aeruginosa. Under 808 nm laser irradiation, the bactericidal efficiency of GS-PNH-FF@CuS/MnS hydrogel against P. aeruginosa in vitro reach up to 96.97 %. Furthermore, GS-PNH-FF@CuS/MnS hydrogel is applied topically to kill bacteria, reduce inflammation, and promote wound healing. Hematoxylin-eosin (H&E) staining, Masson staining, immunohistochemistry and immunofluorescence staining are used to evaluate the therapeutic effect on infected rabbit cornea models in vivo. The GS-PNH-FF@CuS/MnS demonstrate good biocompatibility with human corneal epithelial cells and exhibit no obvious eyes side effects. In conclusion, the GS-PNH-FF@CuS/MnS hydrogel in this study provides an effective and safe treatment strategy for bacterial keratitis through a multimodal approach.

Nefopam as a multimodal analgesia in thoracoscopic surgery: a randomized controlled trial.

Background: Video-assisted thoracoscopic surgery (VATS) is a minimally invasive procedure. However, some patients still experience severe pain after VATS. Pain after VATS can disturb deep breathing and coughing, and can increase postoperative pulmonary complications. Therefore, multidisciplinary pain management is emphasized for enhanced recovery after VATS. Nefopam is a centrally-acting, non-opioid, non-steroidal analgesic drug, and its pain reduction effect in many surgeries has been reported. We sought to determine whether administration of nefopam is effective as multimodal analgesia in VATS. Methods: This study enrolled patients aged 19 years or older, and scheduled for elective VATS lobectomy with American Society of Anesthesiologists (ASA) physical class I-III. Forty-six participants were randomly divided into a group receiving nefopam (group N), and a control group (group O) in a 1:1 ratio. The study participants, and the researcher collecting the data were blinded to the group allocation. For the group N, nefopam 20 mg was administered before surgical incision and also at the end of surgery while chest tube was inserted. For the group O, normal saline 100 mL was administered. The primary outcome of this study was the pain score, by verbal numerical rating scale, at rest and upon coughing. Results: Forty-five participants (group N =22, group O =23) were involved in the statistical analysis. Nefopam reduced pain at rest at 0 h [8 (IQR, 5-10) vs. 4 (IQR, 2-7), P=0.01], and at 0-1 h [5 (IQR, 5-8) vs. 3 (IQR, 2-5), P=0.001]. Pain upon coughing decreased with nefopam at 0 h [9 (IQR, 6-10) vs. 6 (IQR, 2-8), P=0.009], 0-1 h [6 (IQR, 5-8) vs. 5 (IQR, 2-6), P=0.001], and at 12-24 h [4 (IQR, 3-7) vs. 3 (IQR, 1-4), P=0.03]. Injection of 20 mg of nefopam before incision and at the end of surgery relieved postoperative pain at 0 h, 1 h at rest and at 0 h, 1 h, 12-24 h with coughing after VATS. Conclusions: Therefore, nefopam can serve as a useful component of multimodal analgesia for pain management after VATS. Trial Registration: ClinicalTrials.gov (NCT05173337).

Knowledge enhanced bottom-up affordance grounding for robotic interaction.

With the rapid advancement of robotics technology, an increasing number of researchers are exploring the use of natural language as a communication channel between humans and robots. In scenarios where language conditioned manipulation grounding, prevailing methods rely heavily on supervised multimodal deep learning. In this paradigm, robots assimilate knowledge from both language instructions and visual input. However, these approaches lack external knowledge for comprehending natural language instructions and are hindered by the substantial demand for a large amount of paired data, where vision and language are usually linked through manual annotation for the creation of realistic datasets. To address the above problems, we propose the knowledge enhanced bottom-up affordance grounding network (KBAG-Net), which enhances natural language understanding through external knowledge, improving accuracy in object grasping affordance segmentation. In addition, we introduce a semi-automatic data generation method aimed at facilitating the quick establishment of the language following manipulation grounding dataset. The experimental results on two standard dataset demonstrate that our method outperforms existing methods with the external knowledge. Specifically, our method outperforms the two-stage method by 12.98% and 1.22% of mIoU on the two dataset, respectively. For broader community engagement, we will make the semi-automatic data construction method publicly available at https://github.com/wmqu/Automated-Dataset-Construction4LGM.

Application of multimodal ultrasonography to predicting the acute kidney injury risk of patients with sepsis: artificial intelligence approach.

The occurrence of acute kidney injury in sepsis represents a common complication in hospitalized and critically injured patients, which is usually associated with an inauspicious prognosis. Thus, additional consequences, for instance, the risk of developing chronic kidney disease, can be coupled with significantly higher mortality. To intervene in advance in high-risk patients, improve poor prognosis, and further enhance the success rate of resuscitation, a diagnostic grading standard of acute kidney injury is employed to quantify. In the article, an artificial intelligence-based multimodal ultrasound imaging technique is conceived by incorporating conventional ultrasound, ultrasonography, and shear wave elastography examination approaches. The acquired focal lesion images in the kidney lumen are mapped into a knowledge map and then injected into feature mining of a multicenter clinical dataset to accomplish risk prediction for the occurrence of acute kidney injury. The clinical decision curve demonstrated that applying the constructed model can help patients whose threshold values range between 0.017 and 0.89 probabilities. Additionally, the metrics of model sensitivity, specificity, accuracy, and area under the curve (AUC) are computed as 67.9%, 82.48%, 76.86%, and 0.692%, respectively, which confirms that multimodal ultrasonography not only improves the diagnostic sensitivity of the constructed model but also dramatically raises the risk prediction capability, thus illustrating that the predictive model possesses promising validity and accuracy metrics.

Multimodal pretraining for unsupervised protein representation learning.

Proteins are complex biomolecules essential for numerous biological processes, making them crucial targets for advancements in molecular biology, medical research, and drug design. Understanding their intricate, hierarchical structures, and functions is vital for progress in these fields. To capture this complexity, we introduce Multimodal Protein Representation Learning (MPRL), a novel framework for symmetry-preserving multimodal pretraining that learns unified, unsupervised protein representations by integrating primary and tertiary structures. MPRL employs Evolutionary Scale Modeling (ESM-2) for sequence analysis, Variational Graph Auto-Encoders (VGAE) for residue-level graphs, and PointNet Autoencoder (PAE) for 3D point clouds of atoms, each designed to capture the spatial and evolutionary intricacies of proteins while preserving critical symmetries. By leveraging Auto-Fusion to synthesize joint representations from these pretrained models, MPRL ensures robust and comprehensive protein representations. Our extensive evaluation demonstrates that MPRL significantly enhances performance in various tasks such as protein-ligand binding affinity prediction, protein fold classification, enzyme activity identification, and mutation stability prediction. This framework advances the understanding of protein dynamics and facilitates future research in the field. Our source code is publicly available at https://github.com/HySonLab/Protein_Pretrain.

Multimodal in-vivo maps as a tool to characterize retinal structural biomarkers for progression in adult-onset Stargardt disease.

Purpose: To characterize retinal structural biomarkers for progression in adult-onset Stargardt disease from multimodal retinal imaging in-vivo maps. Methods: Seven adult patients (29-69 years; 3 males) with genetically-confirmed and clinically diagnosed adult-onset Stargardt disease and age-matched healthy controls were imaged with confocal and non-confocal Adaptive Optics Scanning Light Ophthalmoscopy (AOSLO), optical coherence tomography (OCT), fundus infrared (FIR), short wavelength-autofluorescence (FAF) and color fundus photography (CFP). Images from each modality were scaled for differences in lateral magnification before montages of AOSLO images were aligned with en-face FIR, FAF and OCT scans to explore changes in retinal structure across imaging modalities. Photoreceptors, retinal pigment epithelium (RPE) cells, flecks, and other retinal alterations in macular regions were identified, delineated, and correlated across imaging modalities. Retinal layer-thicknesses were extracted from segmented OCT images in areas of normal appearance on clinical imaging and intact outer retinal structure on OCT. Eccentricity dependency in cell density was compared with retinal thickness and outer retinal layer thickness, evaluated across patients, and compared with data from healthy controls. Results: In patients with Stargardt disease, alterations in retinal structure were visible in different image modalities depending on layer location and structural properties. The patients had highly variable foveal structure, associated with equally variable visual acuity (-0.02 to 0.98 logMAR). Cone and rod photoreceptors, as well as RPE-like structures in some areas, could be quantified on non-confocal split-detection AOSLO images. RPE cells were also visible on dark field AOSLO images close to the foveal center. Hypo-reflective gaps of non-waveguiding cones (dark cones) were seen on confocal AOSLO in regions with clinically normal CFP, FIR, FAF and OCT appearance and an intact cone inner segment mosaic in three patients. Conclusion: Dark cones were identified as a possible first sign of retinal disease progression in adult-onset Stargardt disease as these are observed in retinal locations with otherwise normal appearance and outer retinal thickness. This corroborates a previous report where dark cones were proposed as a first sign of progression in childhood-onset Stargardt disease. This also supports the hypothesis that, in Stargardt disease, photoreceptor degeneration occurs before RPE cell death.

Adaptive optics retinal imaging in patients with usher syndrome.

Purpose: To determine the structure of the cone photoreceptor mosaic in the macula in eyes with retinitis pigmentosa related to Usher syndrome using adaptive optics fundus (AO) imaging and to correlate these findings with those of the standard clinical diagnostics. Methods: Ten patients with a genetically confirmed retinitis pigmentosa in Usher syndrome due to biallelic variants in MYO7A or USH2A were enrolled in the study. All patients underwent a complete ophthalmological examination including best corrected visual acuity (BCVA), spectral-domain optical coherence tomography (SD-OCT) with fundus autofluorescence photography (FAF), full-field (ffERG) and multifocal electroretinography (mfERG) and Adaptive Optics Flood Illuminated Ophthalmoscopy (AO, rtx1™, Imagine Eyes, Orsay, France). The cone density was assessed centrally and at each 0.5 degree horizontally and vertically from 1-4 degree of eccentricity. Results: In the AO images, photoreceptor cell death was visualized as a disruption of the cone mosaic and low cone density. In the early stage of the disease, cones were still visible in the fovea, whereas outside the fovea a loss of cones was recognizable by blurry, dark patches. The blurry patches corresponded to the parafoveal hypofluorescent ring in the FAF images and the beginning loss of the IS/OS line and external limiting membrane in the SD-OCT images. FfERGs were non-recordable in 7 patients and reduced in 3. The mfERG was reduced in all patients and correlated significantly (p <0.001) with the cone density. The kinetic visual field area, measured with III4e and I4e, did not correlate with the cone density. Conclusion: The structure of the photoreceptors in Usher syndrome patients were detectable by AO fundus imaging. The approach of using high-resolution technique to assess the photoreceptor structure complements the established clinical examinations and allows a more sensitive monitoring of early stages of retinitis pigmentosa in Usher syndrome.

Multi-Modal Melt-Processing of Birefringent Cellulosic Materials for Eco-Friendly Anti-Counterfeiting.

Ubiquitous anti-counterfeiting materials with a rapidly rising annual consumption (over 1010 m2) can pose a serious environmental burden. Biobased cellulosic materials with birefringence offer attractive sustainable alternatives, but their scalable solvent-free processing remain challenging. Here, a dynamic chemical modification strategy is proposed for multi-modal melt-processing of birefringent cellulosic materials for eco-friendly anti-counterfeiting. Relying on the thermal-activated dynamic covalent-locking of the spatial topological structure of preferred oriented cellulose, the strategy balances the contradiction between the strong confinement of long-range ordered structures and the molecular motility required for entropically-driven reconstruction. Equipped with customizable processing forms including mold-pressing, spinning, direct-ink-writing, and blade-coating, the materials exhibit a wide color gamut, self-healing efficiency (94.5%), recyclability, and biodegradability. Moreover, the diversified flexible elements facilitate scalable fabrication and compatibility with universal processing techniques, thereby enabling versatile and programmable anti-counterfeiting. The strategy is expected to provide references for multi-modal melt-processing of cellulose and promote sustainable innovation in the anti-counterfeiting industry.

Cross-attention enables deep learning on limited omics-imaging-clinical data of 130 lung cancer patients.

Deep-learning tools that extract prognostic factors derived from multi-omics data have recently contributed to individualized predictions of survival outcomes. However, the limited size of integrated omics-imaging-clinical datasets poses challenges. Here, we propose two biologically interpretable and robust deep-learning architectures for survival prediction of non-small cell lung cancer (NSCLC) patients, learning simultaneously from computed tomography (CT) scan images, gene expression data, and clinical information. The proposed models integrate patient-specific clinical, transcriptomic, and imaging data and incorporate Kyoto Encyclopedia of Genes and Genomes (KEGG) and Reactome pathway information, adding biological knowledge within the learning process to extract prognostic gene biomarkers and molecular pathways. While both models accurately stratify patients in high- and low-risk groups when trained on a dataset of only 130 patients, introducing a cross-attention mechanism in a sparse autoencoder significantly improves the performance, highlighting tumor regions and NSCLC-related genes as potential biomarkers and thus offering a significant methodological advancement when learning from small imaging-omics-clinical samples.

Radiomics Based on Multimodal magnetic resonance imaging for the Differential Diagnosis of Benign and Malignant Vertebral Compression Fractures.

OBJECTIVES: Recent studies have indicated that radiomics may have excellent performance and clinical application prospects in the differential diagnosis of benign and malignant vertebral compression fractures (VCFs). However, multimodal magnetic resonance imaging (MRI)-based radiomics model is rarely used in the differential diagnosis of benign and malignant VCFs, and is limited to lumbar. Herein, this study intends to develop and validate MRI radiomics models for differential diagnoses of benign and malignant VCFs in patients. METHODS: This cross-sectional study involved 151 adult patients diagnosed with VCF in The First Affiliated Hospital of Soochow University in 2016-2021. The study was conducted in three steps: (i) the original MRI images were segmented, and the region of interest (ROI) was marked out; (ii) among the extracted features, those features with Pearson's correlation coefficient lower than 0.9 and the top 15 with the highest variance and Lasso regression coefficient less than and more than 0 were selected; (iii) MRI images and combined data were studied by logistic regression, decision tree, random forest and extreme gradient boosting (XGBoost) models in training set and the test set (ratio of 8:2), respectively; and the models were further verified and evaluated for the differential diagnosis performance. The evaluated indexes included area under receiver (AUC) of operating characteristic curve, accuracy, sensitivity, specificity, negative predictive value (NPV), positive predictive value (PPV), and 95% confidence intervals (CIs). The AUCs were used to assess the predictive performance of different machine learning modes for benign and malignant VCFs. RESULTS: A total of 1144 radiomics features, and 14 clinical features were extracted. Finally, 12 radiomics features were included in the radiomics model, and 12 radiomics features with 14 clinical features were included in the combined model. In the radiomics model, the differential diagnosis performance in the logistic regression model with the AUC of 0.905 ± 0.026, accuracy of 0.817 ± 0.057, sensitivity of 0.831 ± 0.065, and negative predictive value of 0.813 ± 0.042, was superior to the other three. In the combined model, XGBoost model had the superior differential diagnosis performance with specificity (0.979 ± 0.026) and positive predictive value (0.971 ± 0.035). CONCLUSION: The multimodal MRI-based radiomics model performed well in the differential diagnosis of benign and malignant VCFs, which may provide a tool for clinicians to differentially diagnose VCFs.

Acute Pain Management in a Multi-site Trauma Patient.

Pain management is often difficult in the setting of multi-site trauma such as that caused by motor vehicle accidents (MVA), which is especially compounded in the setting of polysubstance abuse. This often results in patients with poor pain tolerance requiring escalating doses of opioid therapy, which creates a vicious cycle. The use of peripheral nerve blocks (PNB) has been shown to decrease overall opioid consumption and can be used effectively to manage postoperative pain in this patient population. Our case report aims to highlight the importance of PNBs as part of a multimodal approach to pain management in patients with polytrauma in the setting of polysubstance abuse.