Early identification of autism spectrum disorder based on machine learning with eye-tracking data.

BACKGROUND: Early identification of autism spectrum disorder (ASD) improves long-term outcomes, yet significant diagnostic delays persist. METHODS: A retrospective cohort of 449 children (ASD: 246, typically developing [TD]: 203) was used for model development. Eye-movement data were collected from the participants watching videos that featured eye-tracking paradigms for assessing social and non-social cognition. Five machine learning algorithms, namely random forest, support vector machine, logistic regression, artificial neural network, and extreme gradient boosting, were trained to classify children with ASD and TD. The best-performing algorithm was selected to build the final model which was further evaluated in a prospective cohort of 80 children. The Shapley values interpreted important eye-tracking features. RESULTS: Random forest outperformed other algorithms during model development and achieved an area under the curve of 0.849 (< 3 years: 0.832, ≥ 3 years: 0.868) on the external validation set. Of the ten most important eye-tracking features, three measured social cognition, and the rest were related to non-social cognition. A deterioration in model performance was observed using only the social or non-social cognition-related eye-tracking features. LIMITATIONS: The sample size of this study, although larger than that of existing studies of ASD based on eye-tracking data, was still relatively small compared to the number of features. CONCLUSIONS: Machine learning models based on eye-tracking data have the potential to be cost- and time-efficient digital tools for the early identification of ASD. Eye-tracking phenotypes related to social and non-social cognition play an important role in distinguishing children with ASD from TD children.

Preparation, characterisation, and pharmacodynamic study of myricetin pH-sensitive liposomes.

AIMS: Myricetin (MYR) was incorporated into pH-sensitive liposomes in order to improve its bioavailability and anti-hyperuricemic activity. METHODS: The MYR pH-sensitive liposomes (MYR liposomes) were prepared using thin film dispersion method, and assessed by particle size (PS), polydispersed index (PDI), zeta potential (ZP), encapsulation efficiency, drug loading, and in vitro release rate. Pharmacokinetics and anti-hyperuricemic activities were also evaluated. RESULTS: The PS, PDI, ZP, encapsulation efficiency, and drug loading of MYR liposomes were 184.34 ± 1.05 nm, 0.215 ± 0.005, -38.46 ± 0.30 mV, 83.42 ± 1.07%w/w, and 6.20 ± 0.31%w/w, respectively. The release rate of MYR liposomes was higher than free MYR, wherein the cumulative value responded to pH. Besides, the Cmax of MYR liposomes was 4.92 ± 0.20 µg/mL. The level of uric acid in the M-L-H group (200 mg/kg) was reduced by 54.74%w/v in comparison with the model group. CONCLUSION: MYR liposomes exhibited pH sensitivity and could potentially enhance the oral bioavailability and anti-hyperuricemic efficacy of MYR.

FraHMT: A Fragment-Oriented Heterogeneous Graph Molecular Generation Model for Target Proteins.

The molecular generation task stands as a pivotal step in the domains of computational chemistry and drug discovery, aiming to computationally generate molecular structures for specific properties. In contrast to previous models that focused primarily on SMILES strings or molecular graphs, our model placed a special emphasis on the substructure information on molecules, enabling the model to learn richer chemical rules and structure features from fragments and chemical reaction information on molecules. To accomplish this, we fragmented the molecules to construct heterogeneous graph representations based on atom and fragment information. Then our model mapped the heterogeneous graph data into a latent vector space by using an encoder and employed a self-regressive generative model as a decoder for molecular generation. Additionally, we performed transfer learning on the model using a small set of ligand molecules known to be active against the target protein to generate molecules that bind better to the target protein. Experimental results demonstrate that our model is highly competitive with state-of-the-art models. It can generate valid and diverse molecules with favorable physicochemical properties and drug-likeness. Importantly, they produce novel molecules with high docking scores against the target proteins.

Prediction of tumor lysis syndrome in childhood acute lymphoblastic leukemia based on machine learning models: a retrospective study.

Background: Tumor lysis syndrome (TLS) often occurs early after induction chemotherapy for acute lymphoblastic leukemia (ALL) and can rapidly progress. This study aimed to construct a machine learning model to predict the risk of TLS using clinical indicators at the time of ALL diagnosis. Methods: This observational cohort study was conducted at the National Clinical Research Center for Child Health and Disease. Data were collected from pediatric ALL patients diagnosed between December 2008 and December 2021. Four machine learning models were constructed using the Least Absolute Shrinkage and Selection Operator (LASSO) to select key clinical indicators for model construction. Results: The study included 2,243 pediatric ALL patients, and the occurrence of TLS was 8.87%. A total of 33 indicators with missing values ≤30% were collected, and 12 risk factors were selected through LASSO regression analysis. The CatBoost model with the best performance after feature screening was selected to predict the TLS of ALL patients. The CatBoost model had an AUC of 0.832 and an accuracy of 0.758. The risk factors most associated with TLS were the absence of potassium, phosphorus, aspartate transaminase (AST), white blood cell count (WBC), and urea levels. Conclusion: We developed the first TLS prediction model for pediatric ALL to assist clinicians in risk stratification at diagnosis and in developing personalized treatment protocols. This study is registered on the China Clinical Trials Registry platform (ChiCTR2200060616). Clinical trial registration: https://www.chictr.org.cn/, identifier ChiCTR2200060616.

Virtual screening and biological evaluation of natural products as urate transporter 1 (URAT1) inhibitors.

Hyperuricemia is mainly caused by insufficient renal urate excretion. Urate transporter 1 (URAT1), an organic anion transporter, is the main protein responsible for urate reabsorption. In this study, we utilized artificial intelligence-based AlphaFold2 program to construct URAT1 structural model. After molecular docking and conformational evaluation, four e-pharmacophoric models were constructed based on the complex structures of probenecid-URAT1, benzbromarone-URAT1, lesinurad-URAT1, and verinurad-URAT1. Combining pharmacophore modeling, molecular docking, MM/GBSA calculation and ADME prediction, 25 flavonoids were selected from the natural products database containing 10,968 molecules. Then, a model of HEK-293T cells overexpressing URAT1 was constructed, and the inhibitory activity to URAT1 of 25 flavonoids was evaluated by measuring their effect on cellular uptake of 6-carboxyfluorescein (6-CFL). Fisetin, baicalein, and acacetin showed the best activity with IC50 values of 12.77, 26.71, and 57.30 µM, respectively. Finally, the structure-activity relationship of these three flavonoids was analyzed by molecular docking and molecular dynamics simulations. The results showed that the carbonyl group on C-4 and hydroxyl group on C-7, C-4', and C-5' in flavonoids were conducive for URAT1 inhibitory effects. This study facilitates the application of flavonoids in the development of URAT1 inhibitors.Communicated by Ramaswamy H. Sarma.

Evaluation of ChatGPT-generated medical responses: A systematic review and meta-analysis.

OBJECTIVE: Large language models (LLMs) such as ChatGPT are increasingly explored in medical domains. However, the absence of standard guidelines for performance evaluation has led to methodological inconsistencies. This study aims to summarize the available evidence on evaluating ChatGPT's performance in answering medical questions and provide direction for future research. METHODS: An extensive literature search was conducted on June 15, 2023, across ten medical databases. The keyword used was "ChatGPT," without restrictions on publication type, language, or date. Studies evaluating ChatGPT's performance in answering medical questions were included. Exclusions comprised review articles, comments, patents, non-medical evaluations of ChatGPT, and preprint studies. Data was extracted on general study characteristics, question sources, conversation processes, assessment metrics, and performance of ChatGPT. An evaluation framework for LLM in medical inquiries was proposed by integrating insights from selected literature. This study is registered with PROSPERO, CRD42023456327. RESULTS: A total of 3520 articles were identified, of which 60 were reviewed and summarized in this paper and 17 were included in the meta-analysis. ChatGPT displayed an overall integrated accuracy of 56 % (95 % CI: 51 %-60 %, I2 = 87 %) in addressing medical queries. However, the studies varied in question resource, question-asking process, and evaluation metrics. As per our proposed evaluation framework, many studies failed to report methodological details, such as the date of inquiry, version of ChatGPT, and inter-rater consistency. CONCLUSION: This review reveals ChatGPT's potential in addressing medical inquiries, but the heterogeneity of the study design and insufficient reporting might affect the results' reliability. Our proposed evaluation framework provides insights for the future study design and transparent reporting of LLM in responding to medical questions.

Predicting autism spectrum disorder using maternal risk factors: A multi-center machine learning study.

Autism spectrum disorder (ASD) is a neurodevelopmental disorder with a complex environmental etiology involving maternal risk factors, which have been combined with machine learning to predict ASD. However, limited studies have considered the factors throughout preconception, perinatal, and postnatal periods, and even fewer have been conducted in multi-center. In this study, five predictive models were developed using 57 maternal risk factors from a cohort across ten cities (ASD:1232, typically developing[TD]: 1090). The extreme gradient boosting model performed best, achieving an accuracy of 66.2 % on the external cohort from three cities (ASD:266, TD:353). The most important risk factors were identified as unstable emotions and lack of multivitamin supplementation using Shapley values. ASD risk scores were calculated based on predicted probabilities from the optimal model and divided into low, medium, and high-risk groups. The logistic analysis indicated that the high-risk group had a significantly increased risk of ASD compared to the low-risk group. Our study demonstrated the potential of machine learning models in predicting the risk for ASD based on maternal factors. The developed model provided insights into the maternal emotion and nutrition factors associated with ASD and highlighted the potential clinical applicability of the developed model in identifying high-risk populations.

Radiation reduction for interventional radiology imaging: a video frame interpolation solution.

PURPOSE: The aim of this study was to diminish radiation exposure in interventional radiology (IR) imaging while maintaining image quality. This was achieved by decreasing the acquisition frame rate and employing a deep neural network to interpolate the reduced frames. METHODS: This retrospective study involved the analysis of 1634 IR sequences from 167 pediatric patients (March 2014 to January 2022). The dataset underwent a random split into training and validation subsets (at a 9:1 ratio) for model training and evaluation. Our approach proficiently synthesized absent frames in simulated low-frame-rate sequences by excluding intermediate frames from the validation subset. Accuracy assessments encompassed both objective experiments and subjective evaluations conducted by nine radiologists. RESULTS: The deep learning model adeptly interpolated the eliminated frames within IR sequences, demonstrating encouraging peak signal-to-noise ratio (PSNR) and structural similarity index (SSIM) results. The average PSNR values for angiographic, subtraction, and fluoroscopic modes were 44.94 dB, 34.84 dB, and 33.82 dB, respectively, while the corresponding SSIM values were 0.9840, 0.9194, and 0.7752. Subjective experiments conducted with experienced interventional radiologists revealed minimal discernible differences between interpolated and authentic sequences. CONCLUSION: Our method, which interpolates low-frame-rate IR sequences, has shown the capability to produce high-quality IR images. Additionally, the model exhibits potential for reducing the frame rate during IR image acquisition, consequently mitigating radiation exposure. CRITICAL RELEVANCE STATEMENT: This study presents a critical advancement in clinical radiology by demonstrating the effectiveness of a deep neural network in reducing radiation exposure during pediatric interventional radiology while maintaining image quality, offering a potential solution to enhance patient safety. KEY POINTS: • Reducing radiation: cutting IR image to reduce radiation. • Accurate frame interpolation: our model effectively interpolates missing frames. • High visual quality in terms of PSNR and SSIM, making IR procedures safer without sacrificing quality.

Virtual screening of natural products targeting ubiquitin-specific protease 7.

Ubiquitin-specific protease 7 (USP7) is a promising prognostic and druggable target for cancer therapy. Inhibition of USP7 can activate the MDM2-P53 signaling pathway, thereby promoting cancer cell apoptosis. This study based on watvina molecular docking of virtual screening method and biological evaluation found the new USP7 inhibitors targeting catalytic active site. Three hits were screened from 3760 natural products and validated as USP7 inhibitors by enzymatic and kinetic assays. The IC50 values of scutellarein (Scu), semethylzeylastera (DML) and salvianolic acid C (SAC) were 3.017, 6.865 and 8.495 µM, respectively. Further, we reported that the hits could downregulate MDM2 and activate p53 signal pathway in HCT116 cells. Molecular dynamics simulation was used to investigate the binding mechanism of USP7 to Scu, the compound with the best performance, which formed stable contact with Val296, Gln297, Phe409, Tyr465 and Tyr514. These interactions are essential for maintaining the biological activity of Scu. Three natural products are suitable as lead compounds for the development of novel USP7 inhibitors, especially anti-colon cancer drugs.Communicated by Ramaswamy H. Sarma.

Fluorescence detecting glycopeptide antibiotics via a dynamic molecular switch.

BACKGROUND: Glycopeptide antibiotics (GPAs) represented by vancomycin (VAN) are clinically used as a first-line treatment for serious infections caused by Gram-positive pathogens. The use and dosing methods of GPAs are rigorously managed for safety considerations, which calls for fast and accurate quantification approaches. RESULT: A new sort of fluorescent probes for GPAs has been proposed, each of which was integrated by a fluorescein-based reporter and a GPAs' recognition peptide D-alanyl-D-alanine (D-Ala-D-Ala). These probes work as dynamic molecular switches, which mainly exist as non-fluorescent spirolactam forms in the absence of GPAs. GPAs binding with the dipeptide regulates the dynamic balance between fluorescence OFF lactam form and fluorescence ON ring-opened form, rendering these probes capable of GPAs detecting. The most promising one P1 exhibits excellent sensitivity and selectivity towards GPAs detection. SIGNIFICANCE: Different to previous developments, P1 consists of a single fluorophore without the need of a fluorescence-quenching group or a secondary dye, which is the smallest fluorescent probe for GPAs up to now. P1 realizes direct VAN quantification from complex biological samples including real serums, dispensing with additional drug extraction. More interestingly, both P1 and P6 can distinguish GPAs with different peptide backbones, which has not been achieved previously.

Structural basis for sugar perception by Drosophila gustatory receptors.

Insects rely on a family of seven transmembrane proteins called gustatory receptors (GRs) to encode different taste modalities, such as sweet and bitter. We report structures of Drosophila sweet taste receptors GR43a and GR64a in the apo and sugar-bound states. Both GRs form tetrameric sugar-gated cation channels composed of one central pore domain (PD) and four peripheral ligand-binding domains (LBDs). Whereas GR43a is specifically activated by the monosaccharide fructose that binds to a narrow pocket in LBDs, disaccharides sucrose and maltose selectively activate GR64a by binding to a larger and flatter pocket in LBDs. Sugar binding to LBDs induces local conformational changes, which are subsequently transferred to the PD to cause channel opening. Our studies reveal a structural basis for sugar recognition and activation of GRs.

Three Licorice Extracts' Impact on the Quality of Fresh-Cut Sweet Potato (Ipomoea batatas (L.) Lam) Slices.

The quality of fresh-cut produce, particularly sweet potatoes, is crucial for their value. Licorice extract is an optional additive in fresh-cut sweet potatoes. This study examined the impact of three licorice extracts (licorice acid, LA; licorice flavonoids, LF; and licorice polysaccharides, LP) on the quality of fresh-cut sweet potato slices (FCSPSs) for one week of storage. After one week of storage, the extracts showed varying effects on FCSPSs. LA and LF treatments reduced the area proportion of browning (APB), while LP treatments increased APB and decreased L* values. Antioxidant experiments revealed that LP treatments increased PPO and POD activity while reducing SOD activity. The concentrations of the three licorice extracts showed a strong negative correlation with SOD activity. In conclusion, LP harmed the appearance and antioxidant qualities of FCSPSs. LA and LF may be suitable additive components for FCSPSs, and 30 mg/mL LA and LF treatments were found to maintain the appearance and texture quality of FCSPSs during storage. Therefore, careful consideration should be given when using LP as a food additive for FCSPSs.

Comparative analysis of upper aerodigestive tract and non-upper aerodigestive tract in NK/T-cell lymphoma

Objective Nasal or extranasal natural killer/T-cell lymphoma (NKTCL) is a very rare aggressive lymphoma, but it is increasingly diagnosed. To evaluate some specificity by comparative analysis between primary upper aerodigestive tract (UAT) and non-upper aerodigestive tract (NUAT)NKTCL. Methods A retrospective analysis was performed on NKTCL patients from January 2013 to November 2022 in our cancer center. Results The majority of the lesions were UAT-NKTCL 70 cases (92.1%), the primary NUAT occurred in 6 cases. Patients in the UAT group were mainly in the early stage and in the low and medium risk, while those in the NUAT group were late stage and in high risk (p = 0.000). The expressions of CD3 and TIA-1 in UAT group were higher than those in NUAT group (p = 0.031, p = 0.003), while CD7 was dominant in NUAT group (p = 0.009). For early stage NKTCL, multivariate analysis suggested that gender and PINK score were independent factors affecting PFS and OS (p < 0.05). The 3 year OS rate in initial CR group was 90.1% versus 46.4% in non-CR group (p = 0.000). In advanced stage, KI67% and bone marrow involvement were independent factors affecting OS (p = 0.022, p = 0.038). Conclusion It was difficult to distinguish between UAT and NUAT-NKTCL from histopathology. NUAT-NKTCL patients did have advanced stage and poor outcome. The prognostic value of PINK score and bone marrow involvement was proposed. We aimed to improve initial CR rates, as well as to find new predictive models to predict the whole population (AU)

A Clinical Classification of Cervical Ossification of the Posterior Longitudinal Ligament to Guide Surgical Strategy.

STUDY DESIGN: A clinical classification of cervical ossification of the posterior longitudinal ligament (COPLL) was developed based on imaging findings. OBJECTIVE: This study aimed to establish a clinical classification for COPLL and provide corresponding surgery strategies for each subtype. SUMMARY OF BACKGROUND DATA: A practical and reliable classification is needed to guide the treatment of COPLL. MATERIALS AND METHODS: This study retrospectively reviewed plain radiographs, computed tomography scans, and magnetic resonance images of patients diagnosed with COPLL between 2018 and 2022 at Shanghai Changzheng Hospital. The types of COPLL were classified according to the location, morphology, and canal-occupying ratio (OR) of the ossification mass. Interobserver and intraobserver reliability were evaluated using Cohen's kappa. RESULTS: A total of 1000 cases were included, which were classified into five types: focal type (F type), short-sequential type (S type), long-sequential type (L type), high type (H type), and mixed type (M type). In addition, each type could be classified into subtype 1 or subtype 2 according to the canal-OR. Then each type could be further classified into other subtypes according to location and morphology. The interobserver reliabilities in the first and second rounds were 0.853 and 0.887, respectively. The intraobserver reliability was 0.888. CONCLUSION: The authors classified COPLL into a system comprised of five types and several subtypes according to canal-OR, location, and morphology. Surgical strategies for each subtype are also suggested. This provides a theoretical guide for the description and surgical management of COPLL.

Preparation of astaxanthin-loaded composite micelles with coaxial electrospray technology for enhanced oral bioavailability and improved antioxidation capability.

BACKGROUND: Astaxanthin (AST) is approved by the US Food and Drug Administration (FDA) as a safe dietary supplement for humans. As a potent lipid-soluble keto-carotenoid, it is widely used in food, cosmetics, and the pharmaceutical industry. However, its low solubility limits its powerful biological activity and its application in these fields. This study aims to develop a delivery system to address the low solubility and bioavailability of AST and to enhance its antioxidant capacity. RESULTS: Astaxanthin-loaded composite micelles were successfully prepared via coaxial electrospray technology. Astaxanthin existed in the amorphous state in the electro-sprayed formulation with an approximate particle size of 186.28 nm and with a polydispersity index of 0.243. In this delivery system, Soluplus and copovidone (PVPVA 64) were the main polymeric matrix for AST, which then released the drug upon contact with aqueous media, resulting in an overall increase in drug solubility and a release rate of 94.08%. Meanwhile, lecithin, and Polyethylene glycol-grafted Chitosan (PEG-g-CS) could support the absorption of AST in the gastrointestinal tract, assisting transmembrane transport. The relative bioavailability reached about 308.33% and the reactive oxygen species (ROS) scavenging efficiency of the formulation was 44.10%, which was 1.57 times higher than that of free astaxanthin (28.10%) when both were at the same concentration level based on astaxanthin. CONCLUSION: Coaxial electrospray could be applied to prepare a composite micelles system for the delivery of poorly water-soluble active ingredients in functional food, cosmetics, and medicine. © 2023 Society of Chemical Industry.

Comparative analysis of upper aerodigestive tract and non-upper aerodigestive tract in NK/T-cell lymphoma.

OBJECTIVE: Nasal or extranasal natural killer/T-cell lymphoma (NKTCL) is a very rare aggressive lymphoma, but it is increasingly diagnosed. To evaluate some specificity by comparative analysis between primary upper aerodigestive tract (UAT) and non-upper aerodigestive tract (NUAT)NKTCL. METHODS: A retrospective analysis was performed on NKTCL patients from January 2013 to November 2022 in our cancer center. RESULTS: The majority of the lesions were UAT-NKTCL 70 cases (92.1%), the primary NUAT occurred in 6 cases. Patients in the UAT group were mainly in the early stage and in the low and medium risk, while those in the NUAT group were late stage and in high risk (p = 0.000). The expressions of CD3 and TIA-1 in UAT group were higher than those in NUAT group (p = 0.031, p = 0.003), while CD7 was dominant in NUAT group (p = 0.009). For early stage NKTCL, multivariate analysis suggested that gender and PINK score were independent factors affecting PFS and OS (p < 0.05). The 3 year OS rate in initial CR group was 90.1% versus 46.4% in non-CR group (p = 0.000). In advanced stage, KI67% and bone marrow involvement were independent factors affecting OS (p = 0.022, p = 0.038). CONCLUSION: It was difficult to distinguish between UAT and NUAT-NKTCL from histopathology. NUAT-NKTCL patients did have advanced stage and poor outcome. The prognostic value of PINK score and bone marrow involvement was proposed. We aimed to improve initial CR rates, as well as to find new predictive models to predict the whole population.

Clinical Features, Diagnosis, and Treatment of Congenital and Neonatal Tuberculosis: A Retrospective Study.

INTRODUCTION: Limited studies have explored the clinical features, treatment, and prognosis of neonatal tuberculosis (TB). Here, we attempted to delineate the clinical characteristics of neonatal TB, which may help clinicians further understand this disease. METHODS: A retrospective analysis of neonates diagnosed with congenital and/or neonatal TB disease from January 2010 to December 2020 was performed. Information on the demographic and epidemiological features, clinical symptoms, laboratory and imaging examinations, therapeutic regimens, and outcomes was collected. Kaplan-Meier analysis was used to present the time to disease onset, time to diagnosis, etc. Results: Forty-eight cases of neonatal TB were classified into congenital (n = 33) and postnatal (n = 15). The median time to disease onset in postnatal group was significantly longer than that in congenital group. Positive results for gastric fluid acid-fast bacilli, TB culture, Xpert MTB/RIF, interferon-γ release assay (IGRA), and tuberculin skin test were detected in 26/48 (54.2%), 14/34 (41.2%), 11/18 (61.1%), 19/29 (65.5%), and 8/24 (33.3%) patients, respectively. For lymphadenopathy, computed tomography (CT) scans showed a higher detection rate than did X-ray (80.0% vs. 0). Of the 48 infants, 44/48 (91.7%) received anti-TB therapy, and 33/44 (75%) were clinically improved or cured after 22.1 months (interquartile range: 12.4-27.7) of follow-up. Drug-induced liver injury occurred in 14/44 (31.8%) patients. DISCUSSION/CONCLUSION: IGRA and Xpert MTB/RIF showed good positive rate in neonatal TB infection/disease. In cases where TB is presumed but etiological evidence is lacking, low-dose CT could be considered. Prompt treatment under careful surveillance is important for preventing mortality and avoiding severe adverse effects.

Predictive model for early death risk in pediatric hemophagocytic lymphohistiocytosis patients based on machine learning.

Background: Hemophagocytic Lymphohistiocytosis (HLH) is a rare and life-threatening disease in children, with a high early mortality rate. This study aimed to construct machine learning model to predict the risk of early death using clinical indicators at the time of HLH diagnosis. Methods: This observational cohort study was conducted at the National Clinical Research Center for Child Health and Disease. Data was collected from pediatric HLH patients diagnosed by the HLH-2004 protocol between January 2006 and December 2022. Six machine learning models were constructed using the Least Absolute Shrinkage and Selection Operator (LASSO) to select key clinical indicators for model construction. Results: The study included 587 pediatric HLH patients, and the early mortality rate was 28.45 %. The logistic and XGBoost model with the best performance after feature screening were selected to predict early death of HLH patients. The logistic model had an AUC of 0.915 and an accuracy of 0.863, while the XGBoost model had an AUC of 0.889 and an accuracy of 0.829. The risk factors most associated with early death were the absence of immunochemotherapy, decreased TC levels, increased BUN and total bilirubin, and prolonged TT. We developed an online calculator tool for predicting the probability of early death in children with HLH. Conclusions: We developed the first web-based early mortality prediction tool for pediatric HLH to assist clinicians in risk stratification at diagnosis and in developing personalized treatment protocols. This study is registered on the China Clinical Trials Registry platform (ChiCTR2200061315).

Sympathetic Neurotransmitter, VIP, Delays Intervertebral Disc Degeneration via FGF18/FGFR2-Mediated Activation of Akt Signaling Pathway.

Neuromodulation-related intervertebral disc degeneration (IVDD) is a novel IVDD pattern and are proposed recently. However, the mechanistic basis of neuromodulation and intervertebral disc (IVD) homeostasis remains unclear. Here, this study aimed to investigate the expression of postganglionic sympathetic nerve fiber-derived vasoactive intestinal peptide (VIP) system in human IVD tissue, and to assess the role of VIP-related neuromodulation in IVDD. Patient samples and in vitro cell experiments showed that the expression of receptors for VIP is negatively correlated with the severity of IVDD, and the administration of exogenous VIP can ameliorate interleukin 1ß-induced nucleus pulposus (NP) cell apoptosis and inflammation. Further mRNA-seq analysis revealed that fibroblast growth factor 18- (FGF18)-mediated activation of V-akt murine thymoma viral oncogene homolog signaling pathway is involved in the protective effects of VIP on inflammation-induced NP cell degeneration. Further analysis identified VIP via its receptor vasoactive intestinal peptide receptor 2 can directly result in decreased expression of miR-15a-5p, which targeted FGF18. Finally, in vivo mice lumbar IVDD model confirmed that focally exogenous administration of VIP can effectively ameliorated the progression of IVDD, as shown by the radiological and histological analysis. In conclusion, these results indicated that sympathetic neurotransmitter, VIP, delayed IVDD via FGF18/FGFR2-mediated activation of V-akt murine thymoma viral oncogene homolog signaling pathway, which will broaden the horizon concerning how the neuromodulation correlates with IVDD and shed new light on novel therapeutical alternatives to IVDD.

A hybrid model for hand-foot-mouth disease prediction based on ARIMA-EEMD-LSTM.

BACKGROUND: Hand, foot, and mouth disease (HFMD) is a common infectious disease that poses a serious threat to children all over the world. However, the current prediction models for HFMD still require improvement in accuracy. In this study, we proposed a hybrid model based on autoregressive integrated moving average (ARIMA), ensemble empirical mode decomposition (EEMD) and long short-term memory (LSTM) to predict the trend of HFMD. METHODS: The data used in this study was sourced from the National Clinical Research Center for Child Health and Disorders, Chongqing, China. The daily reported incidence of HFMD from 1 January 2015 to 27 July 2023 was collected to develop an ARIMA-EEMD-LSTM hybrid model. ARIMA, LSTM, ARIMA-LSTM and EEMD-LSTM models were developed to compare with the proposed hybrid model. Root mean square error (RMSE), mean absolute error (MAE) and coefficient of determination (R2) were adopted to evaluate the performances of the prediction models. RESULTS: Overall, ARIMA-EEMD-LSTM model achieved the most accurate prediction for HFMD, with RMSE, MAPE and R2 of 4.37, 2.94 and 0.996, respectively. Performing EEMD on the residual sequence yields 11 intrinsic mode functions. EEMD-LSTM model is the second best, with RMSE, MAPE and R2 of 6.20, 3.98 and 0.996. CONCLUSION: Results showed the advantage of ARIMA-EEMD-LSTM model over the ARIMA model, the LSTM model, the ARIMA-LSTM model and the EEMD-LSTM model. For the prevention and control of epidemics, the proposed hybrid model may provide a more powerful help. Compared with other three models, the two integrated with EEMD method showed significant improvement in predictive capability, offering novel insights for modeling of disease time series.