Predicting Anti-inflammatory Peptides by Ensemble Machine Learning and Deep Learning.

Inflammation is a biological response to harmful stimuli, aiding in the maintenance of tissue homeostasis. However, excessive or persistent inflammation can precipitate a myriad of pathological conditions. Although current treatments such as NSAIDs, corticosteroids, and immunosuppressants are effective, they can have side effects and resistance issues. In this backdrop, anti-inflammatory peptides (AIPs) have emerged as a promising therapeutic approach against inflammation. Leveraging machine learning methods, we have the opportunity to accelerate the discovery and investigation of these AIPs more effectively. In this study, we proposed an advanced framework by ensemble machine learning and deep learning for AIP prediction. Initially, we constructed three individual models with extremely randomized trees (ET), gated recurrent unit (GRU), and convolutional neural networks (CNNs) with attention mechanism and then used stacking architecture to build the final predictor. By utilizing various sequence encodings and combining the strengths of different algorithms, our predictor demonstrated exemplary performance. On our independent test set, our model achieved an accuracy, MCC, and F1-score of 0.757, 0.500, and 0.707, respectively, clearly outperforming other contemporary AIP prediction methods. Additionally, our model offers profound insights into the feature interpretation of AIPs, establishing a valuable knowledge foundation for the design and development of future anti-inflammatory strategies.

Co-exposure to nanoplastics and acetaminophen causes skeletal dysplasia and behavioral abnormalities in zebrafish.

Nanoplastics (NPs) and acetaminophen (APAP) are thought to be common contaminants and are invariably detected in the environment. Despite the increasing awareness of their toxicity to humans and animals, the embryonic toxicity, skeletal development toxicity, and mechanism of action of their combined exposure have not been clarified. This study was performed to investigate whether combined exposure to NPs and APAP induces abnormal embryonic and skeletal development in zebrafish and to explore the potential toxicological mechanisms. All zebrafish juveniles in the high-concentration compound exposure group showed some abnormal phenomena such as pericardial edema, spinal curvature, cartilage developmental abnormality and melanin inhibition together with a significant downward trend in body length. Behavioral data also implicated that the exposure of APAP alone, as well as the co-exposure of NPs and APAP, caused a depression in the total distance, swimming speed and the maximum acceleration. Furthermore, real-time polymerase chain reaction analysis showed that compared with exposure alone, the expression level of genes related to osteogenesis, runx2a, runx2b, Sp7, bmp2b and shh was significantly reduced with compound exposure. These results suggest that the compound exposure of NPs and APAP has adverse impacts on zebrafish embryonic development and skeletal growth.

The Majority of Patients Aged 40 and Older Having Allograft Anterior Cruciate Ligament Reconstruction Achieve a Patient Acceptable Symptomatic State.

PURPOSE: To evaluate patient satisfaction, retear rates, and patient-reported outcomes (PROs) in patients aged 40 and older undergoing allograft anterior cruciate ligament reconstruction (ACLR). The secondary goal was to compare these parameters between groups of patients with intact versus failed grafts, and to evaluate these in relation to a historically reported International Knee Documentation Committee (IKDC) patient-acceptable symptoms state (PASS) score. METHODS: Records of patients aged 40 and older who underwent ACLR between 2005 and 2016 at a single institution with a minimum 2-year follow-up were retrospectively reviewed. Patient-reported satisfaction, outcome scores, and failure rates were analyzed. The rate of achieving a previously defined IKDC PASS score based on younger cohorts was reported, and an updated PASS threshold for older patients was calculated. RESULTS: 201 patients were included with a mean age of 48.6 years (range: 40-68) and mean follow-up of 6.2 years (range: 2.8-11.2). 182 (90.5%) patients reported satisfaction following surgery. 16 (8.0%) patients experienced failure of their ACLR, 10 of which underwent revision ACLR. The median IKDC score in the intact ACLR group was 86.2, compared to 66.7 in the failure group (P < .001). In total, 134 (72.4%) patients in the intact group achieved the historical PASS score of 75.9 on IKDC compared to only 4 (25%) in the failure group (χ2 = 15.396, P < .001). An updated IKDC PASS threshold for older cohorts was calculated to be 66.7. CONCLUSION: Patients aged 40 and older who underwent allograft ACLR had an 8.0% failure rate at a mean follow-up of 6 years. Graft failure in patients aged 40 and older was associated with worse PROs. The majority of patients achieved the historically reported IKDC PASS threshold. Additionally, an updated age-appropriate IKDC PASS score of 66.7 was calculated to aid in future ACLR studies assessing older patients. STUDY DESIGN: Level IV.

Dual-color meta-image display with a silver nanopolarizer based metasurface.

Plasmonic metallic nanostructures with anisotropic design have unusual polarization-selective characteristic which can be utilized to build nanopolarizers at the nanoscale. Herein, we propose a dual-color image display platform by reconfiguring two types of silver nanoblocks in a single-celled metasurface. Governed by Malus's law, the two types of silver nanoblocks both acting as nanopolarizers with different orientations can continuously modulate the intensity of incident linearly polarized red and green light pixel-by-pixel, respectively. As a result, an ultra-compact, high-resolution, and continuous-greyscale dual-color image can be recorded right at the surface of the meta-device. We demonstrate the dual-color Malus metasurface by successfully encoding and decoding a red-green continuously-grayscale image into a metasurface sample. The experimentally captured meta-image with high-fidelity and resolution as high as 63500 dots per inch (dpi) has verified our proposal. With the advantages such as continuous grayscale modulation, ultrathin, high stability and high density, the proposed dual-color encoded metasurfaces can be readily used in ultra-compact image displays, high-end anti-counterfeiting, high-density optical information storage and information encryption, etc.

Development and validation of a custom panel including 183 Y-SNPs for Chinese Y-chromosomal haplogroups dissection using a MALDI-TOF MS system.

Y-chromosome SNP haplogroups exhibit geographic structuring in many populations around the world. Therefore, Y-chromosome haplogroups have been widely used to infer paternal biogeographical ancestry and high-resolution paternal lineage classification. In the present study, we designed a customized panel containing 183 Y-SNPs based on previous studies and evaluated the genotyping performance and repeatability, concordance, sensitivity, and ability of analysing case-type samples using a MALDI-TOF MS platform. The average call rate for duplicate typing of any one SNP in the panel was 97.0%. In the concordance and accuracy study, the results of haplogroup designation obtained from MALDI-TOF MS platform were fully consistent with those obtained from the next-generation sequencing (NGS) platform. The optimal amount of template DNA in the PCR seemed to be 10 ng. However, if less DNA (≥156.25 pg) was available, it was still possible to obtain meaningful haplogroup information. For the application part, this panel could be applied for the detection of blood, semen, and buccal swabs samples. Particularly, blood stain on FTA card samples could be dissected by direct PCR amplification on the MALDI-TOF MS platform. Besides, 371 unrelated male individuals from four Chinese ethnic groups (Han, Hui, Mongolian, and Kazak) were detected using this panel. Total 78 terminal haplogroups were found and the haplogroup diversity was 0.933576. The results demonstrate that this panel could be an accurate, fast, and cost-effective method for database construction where the amount of sample material is less of a concern and when the cost of the assay is taken into consideration.

Positive Effects of Heme Oxygenase Upregulation on Adiposity and Vascular Dysfunction: Gene Targeting vs. Pharmacologic Therapy.

OBJECTIVE: Heme oxygenase (HO-1) plays a critical role in adipogenesis and it is important to understand its function in obesity. Many studies have shown that upregulation of HO-1 can affect the biologic parameters in obesity-mediated diabetes, hypertension and vascular endothelial cell function. Thus, we aimed to explore the hypothesis that upregulation of HO-1, using a pharmacologic approach as well as gene targeting, would improve both adiposity and endothelial cell dysfunction by direct targeting of endothelial cells. Our second aim was to compare the short-term effect of a HO-1 inducer, cobalt-protoporphrin IX (CoPP), with the long-term effects of gene targeted therapy on vascular and adipocyte stem cells in obese mice. METHOD: We examined the effect of CoPP on fat pre-adipocytes and mesenchymal stem cells (MSC) in mice fed a high-fat diet (HFD). We also used a lentiviral construct that expressed heme oxygenase (HO-1) that was under the control of an endothelium specific promoter, vascular endothelium cadherin (VECAD) heme oxygenase (VECAD-HO-1). We targeted endothelial cells using vascular endothelium cadherin/green fluorescent protein fusion construct (VECAD-GFP) as the control. Conditioned media (CM) from endothelial cells (EC) was added to fat derived adipocytes. Additionally, we treated renal interlobar arteries with phenylephrine and dosed cumulative increments of acetylcholine both with and without exposure to CoPP. We did the same vascular reactivity experiments with VECAD-HO-1 lentiviral construct compared to the control. RESULTS: CoPP improved vascular reactivity and decreased adipogenesis compared to the control. MSCs exposed to CM from EC transfected with VECAD-HO-1 showed decreased adipogenesis, smaller lipid droplet size and decreased PPAR-γ, C/EBP and increased Wnt 10b compared to the control. HO-1 upregulation had a direct effect on reducing adipogenesis. This effect was blocked by tin mesoporphrin (SnMP). EC treated with VECAD-HO-1 expressed lower levels of ICAM and VCAM compared to the control, suggesting improved EC function. This also improved ACH induced vascular reactivity. These effects were also reversed by SnMP. The effect of viral transfection was much more specific and sustained than the effects of pharmacologic therapy, CoPP. CONCLUSION: This study demonstrates that a pharmacological inducer of HO-1 such as CoPP improves endothelial cell function while dampening adipogenesis, but long-term HO-1 expression by direct targeting of endothelial cells by gene transfer therapy may offer a more specific and ideal solution. This was evidenced by smaller healthier adipocytes that had improved insulin sensitivity, suggesting increased adiponectin levels. HO-1 upregulation reestablished the "crosstalk" between perivascular adipose tissue and the vascular system that was lost in the chronic inflammatory state of obesity. This study demonstrates that gene targeting of EC may well be the future direction in treating obesity induced EC dysfunction, with the finding that targeting the vasculature had a direct and sustained effect on adipogenesis.

A Robust Feedforward Model of the Olfactory System.

Most natural odors have sparse molecular composition. This makes the principles of compressed sensing potentially relevant to the structure of the olfactory code. Yet, the largely feedforward organization of the olfactory system precludes reconstruction using standard compressed sensing algorithms. To resolve this problem, recent theoretical work has shown that signal reconstruction could take place as a result of a low dimensional dynamical system converging to one of its attractor states. However, the dynamical aspects of optimization slowed down odor recognition and were also found to be susceptible to noise. Here we describe a feedforward model of the olfactory system that achieves both strong compression and fast reconstruction that is also robust to noise. A key feature of the proposed model is a specific relationship between how odors are represented at the glomeruli stage, which corresponds to a compression, and the connections from glomeruli to third-order neurons (neurons in the olfactory cortex of vertebrates or Kenyon cells in the mushroom body of insects), which in the model corresponds to reconstruction. We show that should this specific relationship hold true, the reconstruction will be both fast and robust to noise, and in particular to the false activation of glomeruli. The predicted connectivity rate from glomeruli to third-order neurons can be tested experimentally.

Accelerating drug discovery, development, and clinical trials by artificial intelligence.

Artificial intelligence (AI) has profoundly advanced the field of biomedical research, which also demonstrates transformative capacity for innovation in drug development. This paper aims to deliver a comprehensive analysis of the progress in AI-assisted drug development, particularly focusing on small molecules, RNA, and antibodies. Moreover, this paper elucidates the current integration of AI methodologies within the industrial drug development framework. This encompasses a detailed examination of the industry-standard drug development process, supplemented by a review of medications presently undergoing clinical trials. Conclusively, the paper tackles a predominant obstacle within the AI pharmaceutical sector: the absence of AI-conceived drugs receiving approval. This paper also advocates for the adoption of large language models and diffusion models as a viable strategy to surmount this challenge. This review not only underscores the significant potential of AI in drug discovery but also deliberates on the challenges and prospects within this dynamically progressing field.

Effects of attentional instructions on the behavioral and neural mechanisms of speech auditory feedback control.

The present study investigated how instructions for paying attention to auditory feedback may affect speech error detection and sensorimotor control. Electroencephalography (EEG) and speech signals were recorded from 21 neurologically intact adult subjects while they produced the speech vowel sound /a/ and received randomized ±100 cents pitch-shift alterations in their real-time auditory feedback. Subjects were instructed to pay attention to their auditory feedback and press a button to indicate whether they detected a pitch-shift stimulus during trials. Data for this group was compared with 22 matched subjects who completed the same speech task under altered auditory feedback condition without attentional instructions. Results revealed a significantly smaller magnitude of speech compensations in the attentional-instruction vs. no-instruction group and a positive linear association between the magnitude of compensations and P2 event-related potential (ERP) amplitudes. In addition, we found that the amplitude of P2 ERP component was significantly larger in the attentional-instruction vs. no-instruction group. Source localization analysis showed that this effect was accounted for by significantly stronger neural activities in the right hemisphere insula, precentral gyrus, postcentral gyrus, transverse temporal gyrus, and superior temporal gyrus in the attentional-instruction group. These findings suggest that attentional instructions may enhance speech auditory feedback error detection, and subsequently improve sensorimotor control via generating more stable speech outputs (i.e., smaller compensations) in response to pitch-shift alterations. Our data are informative for advancing theoretical models and motivating targeted interventions with a focus on the role of attentional instructions for improving treatment outcomes in patients with motor speech disorders.

Insights into Antisite Defect Complex Induced High Ferro-Piezoelectric Properties in KNbO3 Perovskite: First-Principles Study.

Improving ferro-piezoelectric properties of niobate-based perovskites is highly desirable for developing eco-friendly high-performance sensors and actuators. Although electro-strain coupling is usually obtained by constructing multiphase boundaries via complex chemical compositions, defect engineering can also create opportunities for novel property and functionality advancements. In this work, a representative tetragonal niobate-based perovskite, i.e., KNbO3, is studied by using first-principles calculations. Two intrinsic types of Nb antisite defect complexes are selected to mimic alkali-deficiency induced excess Nb antisites in experiments. The formation energy, electronic profiles, polarization, and piezoelectric constants are systematically analyzed. It is shown that the structural distortion and chemical heterogeneity around the energetically favorable antisite pair defects, i.e., (NbK4·+KNb4'), lower the crystal symmetry of KNbO3 from tetragonal to triclinic phase, and facilitate polarization emergence and reorientation to substantially enhance intrinsic ferro-piezoelectricity (i.e., spontaneous polarization Ps of 68.2 µC/cm2 and piezoelectric strain constant d33 of 228.3 pC/N) without complicated doping and alloying.

Numerical simulation of autoclaved aerated concrete masonry wall subjected to close-in explosion and the structural damage assessment.

In this study, we investigated the destructive effect of autoclaved aerated concrete (AAC) masonry walls subjected to close-in explosions. First, full-size refined finite-element models of the AAC masonry wall were established, and the accuracy of the models was verified by comparison with the test results. The destruction pattern and damage characteristics of the AAC wall were studied, and the effects of block size, wall thickness, mortar compressive strength, and explosion distance on the destruction degree of the AAC masonry walls were analyzed. The results showed that the destruction pattern of the AAC masonry wall subjected to close-in explosion manifested as punching damage in the middle of the wall. When the scaled distance remained unchanged, the punching damage area of the AAC masonry wall was positively correlated with the block size and negatively correlated with the wall thickness and mortar compressive strength. When the explosive equivalent remained unchanged and the explosion distance increased, the punching damage area first increased and then decreased. According to the damage mechanism of the AAC masonry wall, a calculation method for predicting the punching damage area of the AAC masonry wall was established, and the accuracy of this method was verified by comparing it with the numerical results. In addition, the damage criterion based on the punching damage area was established to determine the destruction levels of AAC masonry walls.

Analyzing Surgical Technique in Diverse Open Surgical Videos With Multitask Machine Learning.

Objective: To overcome limitations of open surgery artificial intelligence (AI) models by curating the largest collection of annotated videos and to leverage this AI-ready data set to develop a generalizable multitask AI model capable of real-time understanding of clinically significant surgical behaviors in prospectively collected real-world surgical videos. Design, Setting, and Participants: The study team programmatically queried open surgery procedures on YouTube and manually annotated selected videos to create the AI-ready data set used to train a multitask AI model for 2 proof-of-concept studies, one generating surgical signatures that define the patterns of a given procedure and the other identifying kinematics of hand motion that correlate with surgeon skill level and experience. The Annotated Videos of Open Surgery (AVOS) data set includes 1997 videos from 23 open-surgical procedure types uploaded to YouTube from 50 countries over the last 15 years. Prospectively recorded surgical videos were collected from a single tertiary care academic medical center. Deidentified videos were recorded of surgeons performing open surgical procedures and analyzed for correlation with surgical training. Exposures: The multitask AI model was trained on the AI-ready video data set and then retrospectively applied to the prospectively collected video data set. Main Outcomes and Measures: Analysis of open surgical videos in near real-time, performance on AI-ready and prospectively collected videos, and quantification of surgeon skill. Results: Using the AI-ready data set, the study team developed a multitask AI model capable of real-time understanding of surgical behaviors-the building blocks of procedural flow and surgeon skill-across space and time. Through principal component analysis, a single compound skill feature was identified, composed of a linear combination of kinematic hand attributes. This feature was a significant discriminator between experienced surgeons and surgical trainees across 101 prospectively collected surgical videos of 14 operators. For each unit increase in the compound feature value, the odds of the operator being an experienced surgeon were 3.6 times higher (95% CI, 1.67-7.62; P = .001). Conclusions and Relevance: In this observational study, the AVOS-trained model was applied to analyze prospectively collected open surgical videos and identify kinematic descriptors of surgical skill related to efficiency of hand motion. The ability to provide AI-deduced insights into surgical structure and skill is valuable in optimizing surgical skill acquisition and ultimately improving surgical care.

Membrane Fusion-Mediated Loading of Therapeutic siRNA into Exosome for Tissue-Specific Application.

Tissue-specific delivery of oligonucleotide therapeutics beyond the liver remains a key challenge in nucleic acid drug development. To address this issue, exploiting exosomes as a novel carrier has emerged as a promising approach for efficient nucleic acid drug delivery. However, current exosome-based delivery systems still face multiple hurdles in their clinical applications. Herein, this work presents a strategy for constructing a hybrid exosome vehicle (HEV) through a DNA zipper-mediated membrane fusion approach for tissue-specific siRNA delivery. As a proof-of-concept, this work successfully fuses a liposome encapsulating anti-NFKBIZ siRNAs with corneal epithelium cell (CEC)-derived exosomes to form a HEV construct for the treatment of dry eye disease (DED). With homing characteristics inherited from exosomes, the siRNA-bearing HEV can target its parent cells and efficiently deliver the siRNA payloads to the cornea. Subsequently, the NFKBIZ gene silencing significantly reduces pro-inflammatory cytokine secretions from the ocular surface, reshapes its inflammatory microenvironment, and ultimately achieves an excellent therapeutic outcome in a DED mouse model. As a versatile platform, this hybrid exosome with targeting capability and designed therapeutic siRNAs may hold great potential in various disease treatments.

Cholesterol efflux from C1QB-expressing macrophages is associated with resistance to chimeric antigen receptor T cell therapy in primary refractory diffuse large B cell lymphoma.

Chimeric antigen receptor T (CAR-T) cell therapy has demonstrated promising efficacy in early trials for relapsed/refractory diffuse large B cell lymphoma (DLBCL). However, its efficacy in treating primary refractory DLBCL has not been comprehensively investigated, and the underlying resistance mechanisms remain unclear. Here, we report the outcomes of a phase I, open-label, single-arm clinical trial of relmacabtagene autoleucel (relma-cel), a CD19-targeted CAR-T cell product, with safety and efficacy as primary endpoints. Among the 12 enrolled patients, 8 experienced grade 4 hematologic toxicity of treatment-emergent adverse event. No grade ≥3 cytokine release syndrome or neurotoxicity occurred. Single-cell RNA sequencing revealed an increase proportion of C1QB-expressing macrophages in patients with progressive disease before CAR-T cell therapy. Cholesterol efflux from M2 macrophages was found to inhibit CAR-T cells cytotoxicity by inducing an immunosuppressive state in CD8+ T cells, leading to their exhaustion. Possible interactions between macrophages and CD8+ T cells, mediating lipid metabolism (AFR1-FAS), immune checkpoint activation, and T cell exhaustion (LGALS9-HAVCR2, CD86-CTLA4, and NECTIN2-TIGIT) were enhanced during disease progression. These findings suggest that cholesterol efflux from macrophages may trigger CD8+ T cell exhaustion, providing a rationale for metabolic reprogramming to counteract CAR-T treatment failure. Chinadrugtrials.org.cn identifier: CTR20200376.

Mechanism of dioscin ameliorating renal fibrosis through NF­κB signaling pathway­mediated inflammatory response.

Dioscin (DIS) is a natural compound derived from Chinese herbal medicine. In recent years, multiple studies have reported that DIS has immunoregulation, anti­fibrosis, anti­inflammation, anti­viral and anti­tumor effects. However, the mechanism by which DIS ameliorates renal fibrosis and inflammation remains to be elucidated. The aim of the present study was to investigate the role of DIS in renal fibrosis and inflammation and to explore its underlying mechanism. It used network pharmacology to predict the targets of DIS for the treatment of renal interstitial fibrosis. The present study was performed using unilateral ureteral obstruction mice and HK­2 cells in vivo and in vitro. The mice were treated with different doses of DIS. Kidney tissues were collected for histopathology staining, western blotting, immunohistochemistry staining and reverse transcription­quantitative (RT­q) PCR. TGF­ß1 (2 ng/ml) was used to induce renal fibrosis in the cells. Then, cells were respectively treated with DIS (3.125, 6.25, 12.5 µM) and Bay11­7082 (an inhibitor of NF­κB p65 nuclear transcription, 1 µM) for another 24 h. The expressions of inflammatory factors and NF­κB pathway proteins were detected by immunofluorescence, ELISA, western blotting and RT­qPCR. DIS alleviated renal injury in the UUO mice. Mechanistically, DIS not only decreased the expressions of inflammatory factors including IL­1ß, NOD­like receptor thermal protein domain associated protein 3, monocyte chemotactic protein 1, IL­6, TNF­α and IL­18 but also reduced the level of phosphorylation of NF­κB p65 in vivo and in vitro, which was similar to the impact of Bay11­7082. DIS ameliorated renal fibrosis by inhibiting the NF­κB signaling pathway­mediated inflammatory response, which may be a therapeutic pathway for delaying chronic kidney disease.

Concurrent remission of lymphoma and Sjögren's disease following anti-CD19 chimeric antigen receptor-T cell therapy for diffuse large B-cell lymphoma: a case report.

Anti-CD19 chimeric antigen receptor (CAR)-T cells not only target CD19-positive malignant lymphoma cells but also normal B cells. The utility of CAR-T cell therapy has been reported in rheumatoid arthritis and systemic lupus erythematosus; however, its use in Sjögren's disease (SjD) remains unknown. In this study, we describe the case of a 76-year-old woman with active SjD for 10 years who was diagnosed with diffuse large B-cell lymphoma. After receiving anti-CD19 CAR-T cell therapy, she achieved complete remission (CR) on day 28. Since the onset of her 10-year history with SjD, she was negative for antinuclear antibodies and anti-Ro-52 for the first time on day 90 after CAR-T cell therapy. Six months after CAR-T cell therapy, the CR status was maintained, serum cytokine levels returned to their normal levels, and dry mouth symptoms improved. The EULAR Sjögren's Syndrome Disease Activity Index score decreased from 5 to 2, indicating a partial remission of SjD activity compared with that before CAR-T cell treatment. In the early stage of treatment, she presented with grade 2 cytokine release syndrome and grade 1 neurotoxicity, which were completely controlled after an active intervention. This case highlights the potential application of CAR-T cells in treating autoimmune diseases, such as SjD.

Boosting Delirium Identification Accuracy With Sentiment-Based Natural Language Processing: Mixed Methods Study.

BACKGROUND: Delirium is an acute neurocognitive disorder that affects up to half of older hospitalized medical patients and can lead to dementia, longer hospital stays, increased health costs, and death. Although delirium can be prevented and treated, it is difficult to identify and predict. OBJECTIVE: This study aimed to improve machine learning models that retrospectively identify the presence of delirium during hospital stays (eg, to measure the effectiveness of delirium prevention interventions) by using the natural language processing (NLP) technique of sentiment analysis (in this case a feature that identifies sentiment toward, or away from, a delirium diagnosis). METHODS: Using data from the General Medicine Inpatient Initiative, a Canadian hospital data and analytics network, a detailed manual review of medical records was conducted from nearly 4000 admissions at 6 Toronto area hospitals. Furthermore, 25.74% (994/3862) of the eligible hospital admissions were labeled as having delirium. Using the data set collected from this study, we developed machine learning models with, and without, the benefit of NLP methods applied to diagnostic imaging reports, and we asked the question "can NLP improve machine learning identification of delirium?" RESULTS: Among the eligible 3862 hospital admissions, 994 (25.74%) admissions were labeled as having delirium. Identification and calibration of the models were satisfactory. The accuracy and area under the receiver operating characteristic curve of the main model with NLP in the independent testing data set were 0.807 and 0.930, respectively. The accuracy and area under the receiver operating characteristic curve of the main model without NLP in the independent testing data set were 0.811 and 0.869, respectively. Model performance was also found to be stable over the 5-year period used in the experiment, with identification for a likely future holdout test set being no worse than identification for retrospective holdout test sets. CONCLUSIONS: Our machine learning model that included NLP (ie, sentiment analysis in medical image description text mining) produced valid identification of delirium with the sentiment analysis, providing significant additional benefit over the model without NLP.

Physician Experience Design (PXD): More Usable Machine Learning Prediction for Clinical Decision Making.

Delirium is an acute neurocognitive disorder, which is difficult to identify and predict. Using GEMINI, Canada's largest hospital data and analytics study, we had a labeled sample of around 4,000 cases with approximately 25% of cases being labeled as having delirium. Based on this labeled data, we developed machine learning (ML) models and interacted with physicians to interpret the ML models and their predictions. We developed a preliminary Explainable Artificial Intelligence (XAI) framework for physician experience design (PXD) to improve the uptake of ML models by improving the transparency of model results, thereby increasing physician trust in models as well as the uptake of model results for clinical decision making. We developed our PXD approach first with Conceptual Investigation to collect and extract physicians' feedback on ML models and their evaluation requirements. We carried out a case study, working closely with the physicians in a participatory design process to develop a dashboard that presents ML delirium identification results interactively based on physician selections and inputs. In this approach a physician-preferred ML model for clinical decision making is selected through PXD evaluation.

Urine protein in patients with type I hypersensitivity is indicative of reversible renal tube injury.

AIMS: In our clinical work, some patients with type I hypersensitivity could be detected protein in their urine. This study focused on the early renal injury in patients with type I hypersensitivity. MAIN METHODS: From 43 type I hypersensitivity patients with proteinuria, 10 patients were randomly selected for mass spectrometry analysis of 24-h urine together with 5 healthy volunteers. Mice were vaccinated with Dermatophagoides farina (Der f) and ovalbumin (OVA) were used as antigen to establish the type I hypersensitivity animal models. KEY FINDINGS: The urine protein of hypersensitivity patients was significantly increased in the alpha-1-microglobulin/ bikunin precursor (Protein AMBP) (t = 3.140, P = 0.008), retinol binding protein 4 (RBP4) (t = 2.426, P = 0.031), kininogen-1 (t = 2.501, P = 0.027), and transferrin appeared only in patients' urine. After immunizing mice with antigens, significant increases of the total serum immunoglobulin E (IgE) were observed in both Der f (86.92 ± 36.01 U/mL, t = 5.231, P = 0.0004) and OVA group (34.65 ± 24.72 U/mL, t = 2.891, P = 0.0161) compared with the negative control group (2.68 ± 0.47 U/mL). Meanwhile, definite eosinophil infiltration around the impaired renal tubules as well as the bronchus in Der f mice were observed, and urine protein appeared. After stopping the allergen stimulation, proteinuria disappeared. Instead, when the mice were treated with the antigen again, proteinuria reappeared. SIGNIFICANCE: Our findings suggest that renal tubular damage in patients with type I hypersensitivity is reversible, and proteinuria disappears with allergy symptoms remission.

Overview of Rapid Detection Methods for Salmonella in Foods: Progress and Challenges.

Salmonella contamination in food production and processing is a serious threat to consumer health. More and more rapid detection methods have been proposed to compensate for the inefficiency of traditional bacterial cultures to suppress the high prevalence of Salmonella more efficiently. The contamination of Salmonella in foods can be identified by recognition elements and screened using rapid detection methods with different measurable signals (optical, electrical, etc.). Therefore, the different signal transduction mechanisms and Salmonella recognition elements are the key of the sensitivity, accuracy and specificity for the rapid detection methods. In this review, the bioreceptors for Salmonella were firstly summarized and described, then the current promising Salmonella rapid detection methods in foodstuffs with different signal transduction were objectively summarized and evaluated. Moreover, the challenges faced by these methods in practical monitoring and the development prospect were also emphasized to shed light on a new perspective for the Salmonella rapid detection methods applications.