Uveal melanoma distant metastasis prediction system: A retrospective observational study based on machine learning.

Uveal melanoma (UM) patients face a significant risk of distant metastasis, closely tied to a poor prognosis. Despite this, there is a dearth of research utilizing big data to predict UM distant metastasis. This study leveraged machine learning methods on the Surveillance, Epidemiology, and End Results (SEER) database to forecast the risk probability of distant metastasis. Therefore, the information on UM patients from the SEER database (2000-2020) was split into a 7:3 ratio training set and an internal test set based on distant metastasis presence. Univariate and multivariate logistic regression analyses assessed distant metastasis risk factors. Six machine learning methods constructed a predictive model post-feature variable selection. The model evaluation identified the multilayer perceptron (MLP) as optimal. Shapley additive explanations (SHAP) interpreted the chosen model. A web-based calculator personalized risk probabilities for UM patients. The results show that nine feature variables contributed to the machine learning model. The MLP model demonstrated superior predictive accuracy (Precision = 0.788; ROC AUC = 0.876; PR AUC = 0.788). Grade recode, age, primary site, time from diagnosis to treatment initiation, and total number of malignant tumors were identified as distant metastasis risk factors. Diagnostic method, laterality, rural-urban continuum code, and radiation recode emerged as protective factors. The developed web calculator utilizes the MLP model for personalized risk assessments. In conclusion, the MLP machine learning model emerges as the optimal tool for predicting distant metastasis in UM patients. This model facilitates personalized risk assessments, empowering early and tailored treatment strategies.

Anti-phasic oscillatory development for speech and noise processing in cochlear implanted toddlers.

Human brain demonstrates amazing readiness for speech and language learning at birth, but the auditory development preceding such readiness remains unknown. Cochlear implanted (CI) children (n = 67; mean age 2.77 year ± 1.31 SD; 28 females) with prelingual deafness provide a unique opportunity to study this stage. Using functional near-infrared spectroscopy, it was revealed that the brain of CI children was irresponsive to sounds at CI hearing onset. With increasing CI experiences up to 32 months, the brain demonstrated function, region and hemisphere specific development. Most strikingly, the left anterior temporal lobe showed an oscillatory trajectory, changing in opposite phases for speech and noise. The study provides the first longitudinal brain imaging evidence for early auditory development preceding speech acquisition.

Differential auditory cortical development in left and right cochlear implanted children.

Unilateral aural stimulation has been shown to cause massive cortical reorganization in brain with congenital deafness, particularly during the sensitive period of brain development. However, it is unclear which side of stimulation provides most advantages for auditory development. The left hemisphere dominance of speech and linguistic processing in normal hearing adult brain has led to the assumption of functional and developmental advantages of right over left implantation, but existing evidence is controversial. To test this assumption and provide evidence for clinical choice, we examined 34 prelingually deaf children with unilateral cochlear implants using near-infrared spectroscopy. While controlling for age of implantation, residual hearing, and dominant hand, cortical processing of speech showed neither developmental progress nor influence of implantation side weeks to months after implant activation. In sharp contrast, for nonspeech (music signal vs. noise) processing, left implantation showed functional advantages over right implantation that were not yet discernable using clinical, questionnaire-based outcome measures. These findings support the notion that the right hemisphere develops earlier and is better preserved from adverse environmental influences than its left counterpart. This study thus provides, to our knowledge, the first evidence for differential influences of left and right auditory peripheral stimulation on early cortical development of the human brain.

Application and interpretation of machine learning models in predicting the risk of severe obstructive sleep apnea in adults.

BACKGROUND: Obstructive sleep apnea (OSA) is a globally prevalent disease with a complex diagnostic method. Severe OSA is associated with multi-system dysfunction. We aimed to develop an interpretable machine learning (ML) model for predicting the risk of severe OSA and analyzing the risk factors based on clinical characteristics and questionnaires. METHODS: This was a retrospective study comprising 1656 subjects who presented and underwent polysomnography (PSG) between 2018 and 2021. A total of 23 variables were included, and after univariate analysis, 15 variables were selected for further preprocessing. Six types of classification models were used to evaluate the ability to predict severe OSA, namely logistic regression (LR), gradient boosting machine (GBM), extreme gradient boosting (XGBoost), adaptive boosting (AdaBoost), bootstrapped aggregating (Bagging), and multilayer perceptron (MLP). All models used the area under the receiver operating characteristic curve (AUC) was calculated as the performance metric. We also drew SHapley Additive exPlanations (SHAP) plots to interpret predictive results and to analyze the relative importance of risk factors. An online calculator was developed to estimate the risk of severe OSA in individuals. RESULTS: Among the enrolled subjects, 61.47% (1018/1656) were diagnosed with severe OSA. Multivariate LR analysis showed that 10 of 23 variables were independent risk factors for severe OSA. The GBM model showed the best performance (AUC = 0.857, accuracy = 0.766, sensitivity = 0.798, specificity = 0.734). An online calculator was developed to estimate the risk of severe OSA based on the GBM model. Finally, waist circumference, neck circumference, the Epworth Sleepiness Scale, age, and the Berlin questionnaire were revealed by the SHAP plot as the top five critical variables contributing to the diagnosis of severe OSA. Additionally, two typical cases were analyzed to interpret the contribution of each variable to the outcome prediction in a single patient. CONCLUSIONS: We established six risk prediction models for severe OSA using ML algorithms. Among them, the GBM model performed best. The model facilitates individualized assessment and further clinical strategies for patients with suspected severe OSA. This will help to identify patients with severe OSA as early as possible and ensure their timely treatment. TRIAL REGISTRATION: Retrospectively registered.

Altered functional connectivity of primary visual cortex in adults with strabismus and amblyopia: a resting-state fMRI study.

Functional connectivity of the primary visual cortex was explored with resting functional magnetic resonance imaging among adults with strabismus and amblyopia and healthy controls. We used the two-sample test and receiver operating characteristic curves to investigate the differences in mean functional connectivity values between the groups with strabismus and amblyopia and healthy controls. Compared with healthy controls, functional connectivity values in the left Brodmann areas 17, including bilateral lingual/angular gyri, were reduced in groups with strabismus and amblyopia. Moreover, functional connectivity values in the right Brodmann area 17, including left cuneus, right inferior occipital gyrus, and left inferior parietal lobule, were reduced in adults with strabismus and amblyopia. Our findings indicate that functional connectivity abnormalities exist between the primary visual cortex and other regions. This may be the basis of the pathological mechanism of visual dysfunction and stereovision disorders in adults with strabismus and amblyopia.

Oxidative stress induced by NOX2 contributes to neuropathic pain via plasma membrane translocation of PKCε in rat dorsal root ganglion neurons.

BACKGROUND: Nicotinamide adenine dinucleotide phosphate oxidase 2 (NOX2)-induced oxidative stress, including the production of reactive oxygen species (ROS) and hydrogen peroxide, plays a pivotal role in neuropathic pain. Although the activation and plasma membrane translocation of protein kinase C (PKC) isoforms in dorsal root ganglion (DRG) neurons have been implicated in multiple pain models, the interactions between NOX2-induced oxidative stress and PKC remain unknown. METHODS: A spared nerve injury (SNI) model was established in adult male rats. Pharmacologic intervention and AAV-shRNA were applied locally to DRGs. Pain behavior was evaluated by Von Frey tests. Western blotting and immunohistochemistry were performed to examine the underlying mechanisms. The excitability of DRG neurons was recorded by whole-cell patch clamping. RESULTS: SNI induced persistent NOX2 upregulation in DRGs for up to 2 weeks and increased the excitability of DRG neurons, and these effects were suppressed by local application of gp91-tat (a NOX2-blocking peptide) or NOX2-shRNA to DRGs. Of note, the SNI-induced upregulated expression of PKCε but not PKC was decreased by gp91-tat in DRGs. Mechanical allodynia and DRG excitability were increased by ψεRACK (a PKCε activator) and reduced by εV1-2 (a PKCε-specific inhibitor). Importantly, εV1-2 failed to inhibit SNI-induced NOX2 upregulation. Moreover, the SNI-induced increase in PKCε protein expression in both the plasma membrane and cytosol in DRGs was attenuated by gp91-tat pretreatment, and the enhanced translocation of PKCε was recapitulated by H2O2 administration. SNI-induced upregulation of PKCε was blunted by phenyl-N-tert-butylnitrone (PBN, an ROS scavenger) and the hydrogen peroxide catalyst catalase. Furthermore, εV1-2 attenuated the mechanical allodynia induced by H2O2 CONCLUSIONS: NOX2-induced oxidative stress promotes the sensitization of DRGs and persistent pain by increasing the plasma membrane translocation of PKCε.

Video display terminal use and other risk factors for abnormal blinking in children: gender differences.

OBJECTIVE: To explore the risk factors for abnormal blinking in children and compare these between boys and girls. METHODS: Children attending the Children's Optometry Clinic between June 2019 and June 2020 were recruited for the study. The time they had spent viewing video displays (VDTt) over the past 6 months was recorded. Incomplete blinking (IB) and blinking rate were measured and all participants were allocated to groups based on their blink rate (<20 times/min = normal blinking group, NBG; ≥20 times/min = abnormal blinking group, ABG). Tear film (TF) stability was also evaluated. The corresponding statistical methods are used to analyze the data. RESULTS: A total of 87 boys and 80 girls were enrolled in the study. No significant difference in age was found between the 2 groups. There was a significant difference in TF stability between the two groups (P<0.05). According to binary logistic analysis, VDTt and ocular protection index (OPI) are important risk factors for abnormal blinking, with cut-off values of 1.75 hours and 1.014 respectively in boys; and 1.25 hours and 1.770 respectively in girls. The average of lipid layer thickness was an important protective factor for children using VDT for long periods, with a cut-off value of 58.5 nm in boys and 53.5nm in girls. CONCLUSION: Risk factors for abnormal blinking in both boys and girls include VDTt and OPI.

Abnormal Fractional Amplitude of Low-Frequency Fluctuation Changes in Patients with Monocular Blindness: A Functional Magnetic Resonance Imaging (MRI) Study.

BACKGROUND We used fractional amplitude of low-frequency fluctuation (fALFF) technology to investigate spontaneous cerebral activity in patients with monocular blindness (MB) and in healthy controls (HCs). MATERIAL AND METHODS Thirty MB patient and 15 HCs were included in this study. All subjects were scanned by resting-state functional magnetic resonance imaging (rs-fMRI). The independent sample t test and chi-squared test were applied to analyze demographics of MB patients and HCs. The 2-sample t test and receiver operating characteristic (ROC) curves were applied to identify the difference in average fALFF values between MB patients and HCs. Pearson's correlation analysis was applied to explore the relationship between the average fALFF values of brain areas and clinical behavior in the MB group. RESULTS MB patients had lower fALFF values in the left anterior cingulate and higher fALFF values in the left precuneus and right and left inferior parietal lobes than in HCs. Moreover, the mean fALFF values of MB patients in the left anterior cingulate had negative correlations with the anxiety scale score (r=-0.825, P<0.001) and the depression scale score (r=-0.871, P<0.001). CONCLUSIONS Our study found that MB patients had abnormal spontaneous activities in the visual and vision-related regions. The finding of abnormal neuronal activity helps to reveal the underlying neuropathologic mechanisms of vision loss.

Altered Brain Network Centrality in Patients with Adult Strabismus with Amblyopia: A Resting-State Functional Magnetic Resonance Imaging (fMRI) Study.

BACKGROUND The aim of this study was to explore potential changes in brain function network activity in patients with adult strabismus with amblyopia (SA) using the voxel-wise degree centrality (DC) method. MATERIAL AND METHODS We enrolled 15 patients with SA (6 males, 9 females) and 15 sex-matched healthy controls (HCs). All subjects completed resting functional magnetic resonance imaging scans. Independent-sample t tests and receiver operating characteristic (ROC) curves were used to assess DC value differences between groups, and Pearson correlation analysis was performed to evaluate correlations between DC-changed brain regions and clinical data of patients with SA. RESULTS Compared with the HC group, DC values that were lower in patients with SA included the left middle frontal gyrus and bilateral angular gyri. Increases were observed in the left fusiform gyrus, right lingual gyrus, right middle occipital gyrus, right postcentral gyrus, and left paracentral lobule. However, DC values were not correlated with clinical manifestations. ROC curve analysis showed high accuracy. CONCLUSIONS We found abnormal neural activity in specific brain regions in patients with SA. Specifically, we observed significant changes in DC values compared to HCs. These changes may be useful to identify the specific mechanisms involved in brain dysfunction in SA.

Genetic association between PAX2 and mullerian duct anomalies in Han Chinese females.

PURPOSE: The study aims to investigate the genetic association between paired box gene 2 (PAX2) and mullerian duct anomalies (MDA) in Chinese Han females. METHODS: Matrix-assisted laser desorption/ionization time-of-flight mass spectrometry (MALDI-TOF MS) was used to identify the genotypes of three tag single nucleotide polymorphisms (SNPs) in PAX2 in 362 MDA cases and 406 controls. RESULTS: We found that one tag SNP (rs12266644) of PAX2 was associated with susceptibility to MDA. The genotype distributions of the SNP rs12266644 have a statistically significant difference in the MDA patients and controls with a p value = 0.008. In the dominant model, we also observed that the GT + TT genotype increased the risk for MDA (p = 0.015, OR = 1.637, 95 % CI = 1.096-2.443). CONCLUSION: The polymorphism rs12266644 of PAX2 might be a risk factor for MDA in Chinese Han females.

Analysis of the Association between Catechol-O-Methyltransferase Val158Met and Male Sexual Orientation.

INTRODUCTION: Male sexual orientation is thought to have a genetic component. However, previous studies have failed to generate positive results from among candidate genes. Catechol-O-methyltransferase (COMT), located on chromosome 22, has six exons, spans 27 kb, and encodes a protein of 271 amino acids. COMT has an important role in regulating the embryonic levels of catecholamine neurotransmitters (such as dopamine, norepinephrine, and epinephrine) and estrogens. COMT is also thought to be related to sexual orientation. AIMS: This study aimed to investigate the relationship between the COMT Val158Met variant and male sexual orientation. We performed association analysis of the COMT gene single nucleotide polymorphism, Val158Met, in 409 homosexual cases and 387 heterosexual control Chinese men. COMT polymorphism status was determined using a polymerase chain reaction-based assay. METHODS: Polymerase chain reaction was performed to genotype the COMT Val158Met polymorphism. MAIN OUTCOME MEASURES: The frequency differences of the genotype and alleles distribution between the male homosexual and control groups. RESULTS: Significant differences, both in genotype and alleles, between male homosexual individuals and controls indicated a genetic component related to male homosexuality. The Val allele recessive model could be an interrelated genetic model of the cause of male homosexuality. CONCLUSION: The COMT Val158Met variant might be associated with male sexual orientation and a recessive model was suggested.

[Protective effect of astragalus saponin extracts on kidneys of diabetic rats].

To study the protective effect of astragalus saponin extracts (AS) on kidneys of diabetic rats. Totally 32 diabetic rats induced by streptozotocin (STZ) were divided into AS high and low dose groups, the positive control group and the model group (DM group) and orally administered with 50 mg x- kg(-1) x d(-1) AS 200, 25 mg x kg(-1) x d(-1) valsartan, 10 mL x kg(-1) x d(1) physiological saline, respectively. Another 8 healthy rats were collected in the normal control group (NC group, physiological saline 10 mL x kg(-1). d(-1)). All rats were treated for consecutively 6 weeks. After the administration, the body weight was measured every week, the concentration of blood glucose was monitored on week 2, 4 and 6. The total urine and total urinary protein (U-TP) in 24 h were measured by the metabolic cage method on week 6; At the end of week 6, blood samples were collected from hearts to detect blood urea nitrogen (BUN), serum creatinine (Scr), uric acid (UA) , total cholesterol (CH) triglyceride (TG) by biochemical methods. Kidneys were collect to calculate the kidney hypertrophy index and observe the pathological sections. The laboratory results show that in the DM group, the blood glucose, metabolic cost in 24 h, kidney hypertrophy index, U-TP, BUN, Scr, UA, TG were significantly higher than that in the NC group (P < 0.01, P < 0.05) , with significant pathological changes; After the intervention with AS, the metabolic value in 24 h, kidney hypertrophy index, U-TP, BUN, Scr, UA, TG were significantly lower in the high dose group (P < 0.01, P < 0.05), and the kidney hypertrophy index, BUN, Scr, UA, TG in the low dose group were also significantly lower (P < 0.05), with slight reduction in renal pathological changes in both groups. In conclusion, Astragalus saponin extracts have a certain protective effect on kidneys of diabetic rats.

Machine learning predictors of risk of death within 7 days in patients with non-traumatic subarachnoid hemorrhage in the intensive care unit: A multicenter retrospective study.

Non-traumatic subarachnoid hemorrhage (SAH) is a critical neurosurgical emergency with a high mortality rate, imposing a significant burden on both society and families. Accurate prediction of the risk of death within 7 days in SAH patients can provide valuable information for clinicians, enabling them to make better-informed medical decisions. In this study, we developed six machine learning models using the MIMIC III database and data collected at our institution. These models include Logistic Regression (LR), AdaBoosting (AB), Multilayer Perceptron (MLP), Bagging (BAG), Gradient Boosting Machines (GBM), and Extreme Gradient Boosting (XGB). The primary objective was to identify predictors of death within 7 days in SAH patients admitted to intensive care units. We employed univariate and multivariate logistic regression as well as Pearson correlation analysis to screen the clinical variables of the patients. The initially screened variables were then incorporated into the machine learning models, and the performance of these models was evaluated. Furthermore, we compared the performance differences among the six models and found that the MLP model exhibited the highest performance with an AUC of 0.913. In this study, we conducted risk factor analysis using Shapley values to identify the factors associated with death within 7 days in patients with SAH. The risk factors we identified include Gcsmotor, bicarbonate, wbc, spo2, heartrate, age, nely, glucose, aniongap, GCS, rbc, sysbp, sodium, and gcseys. To provide clinicians with a useful tool for assessing the risk of death within 7 days in SAH patients, we developed a web calculator based on the MLP machine learning model.

Prediction Model of Ocular Metastases in Gastric Adenocarcinoma: Machine Learning-Based Development and Interpretation Study.

Background: Although gastric adenocarcinoma (GA) related ocular metastasis (OM) is rare, its occurrence indicates a more severe disease. We aimed to utilize machine learning (ML) to analyze the risk factors of GA-related OM and predict its risks. Methods: This is a retrospective cohort study. The clinical data of 3532 GA patients were collected and randomly classified into training and validation sets in a ratio of 7:3. Those with or without OM were classified into OM and non-OM (NOM) groups. Univariate and multivariate logistic regression analyses and least absolute shrinkage and selection operator were conducted. We integrated the variables identified through feature importance ranking and further refined the selection process using forward sequential feature selection based on random forest (RF) algorithm before incorporating them into the ML model. We applied six ML algorithms to construct the predictive GA model. The area under the receiver operating characteristic (ROC) curve indicated the model's predictive ability. Also, we established a network risk calculator based on the best performance model. We used Shapley additive interpretation (SHAP) to identify risk factors and to confirm the interpretability of the black box model. We have de-identified all patient details. Results: The ML model, consisting of 13 variables, achieved an optimal predictive performance using the gradient boosting machine (GBM) model, with an impressive area under the curve (AUC) of 0.997 in the test set. Utilizing the SHAP method, we identified crucial factors for OM in GA patients, including LDL, CA724, CEA, AFP, CA125, Hb, CA153, and Ca2+. Additionally, we validated the model's reliability through an analysis of two patient cases and developed a functional online web prediction calculator based on the GBM model. Conclusion: We used the ML method to establish a risk prediction model for GA-related OM and showed that GBM performed best among the six ML models. The model may identify patients with GA-related OM to provide early and timely treatment.

Ensemble learning-assisted prediction of prolonged hospital length of stay after spine correction surgery: a multi-center cohort study.

PURPOSE: This research aimed to develop a machine learning model to predict the potential risk of prolonged length of stay in hospital before operation, which can be used to strengthen patient management. METHODS: Patients who underwent posterior spinal deformity surgery (PSDS) from eleven medical institutions in China between 2015 and 2022 were included. Detailed preoperative patient data, including demographics, medical history, comorbidities, preoperative laboratory results, and surgery details, were collected from their electronic medical records. The cohort was randomly divided into a training dataset and a validation dataset with a ratio of 70:30. Based on Boruta algorithm, nine different machine learning algorithms and a stack ensemble model were trained after hyperparameters tuning visualization and evaluated on the area under the receiver operating characteristic curve (AUROC), precision-recall curve, calibration, and decision curve analysis. Visualization of Shapley Additive exPlanations method finally contributed to explaining model prediction. RESULTS: Of the 162 included patients, the K Nearest Neighbors algorithm performed the best in the validation group compared with other machine learning models (yielding an AUROC of 0.8191 and PRAUC of 0.6175). The top five contributing variables were the preoperative hemoglobin, height, body mass index, age, and preoperative white blood cells. A web-based calculator was further developed to improve the predictive model's clinical operability. CONCLUSIONS: Our study established and validated a clinical predictive model for prolonged postoperative hospitalization duration in patients who underwent PSDS, which offered valuable prognostic information for preoperative planning and postoperative care for clinicians. Trial registration ClinicalTrials.gov identifier NCT05867732, retrospectively registered May 22, 2023, https://classic. CLINICALTRIALS: gov/ct2/show/NCT05867732 .

TIPE2 Inhibits MGD Inflammation by Regulating Macrophage Polarization.

BACKGROUND: The aim of this study was to decide the role of the polarization of macrophages regulated by tumor necrosis factor-α (TNF-α)-induced protein 8-like 2 (TIPE2) in meibomian gland dysfunction (MGD). METHODS: Firstly, the secretory function of the meibomian gland (MG) in apolipoprotein E knockout (ApoE-/-) MGD mice and normal mice was detected by oil red staining. Then, the expression levels of markers of M1 and M2 macrophages were detected by immunofluorescence staining in MGD, normal mice, and mild and severe MGD corpses to decide the role of M1 and M2 macrophages in MGD inflammation. Meanwhile, the expression levels of TIPE2 in MGD mice and MGD patients were detected by immunofluorescence staining, and the correlations among TIPE2, M1 and M2 macrophages were analyzed by immunofluorescence double staining in MGD mice and MGD patients. Furthermore, lipopolysaccharide (LPS) and interleulkin-4 (IL-4) were used to induce M1 and M2 polarization of macrophages, and the mRNA level of TIPE2 was detected in M1 and M2 macrophages. RESULTS: Oil red staining showed that eyelid fat congestion was more severe in (ApoE-/-) MGD mice than in normal mice, and the M1 macrophage was the primary inflammatory cell infiltrated in (ApoE-/-) MGD mice (p < 0.05). The results of the immunofluorescence staining showed that the infiltration of macrophages in MGD mice was more obvious than that in the normal group, and M1 macrophage was the dominant group (p < 0.05). Similar to the results of the MGD mouse model, more macrophage infiltration was observed in MGD patients' MG tissues, and there were more M1 cells in the severe group than in the mild group (p < 0.05). Moreover, the expression of TIPE2 was positively correlated with the expression of M2 macrophages in MGD patients and mice MG tissues (p < 0.05). The expression of TIPE2 mRNA in LPS-induced M1 macrophages declined, while the expression of TIPE2 mRNA in IL-4-induced M2 macrophages increased (p < 0.05). CONCLUSION: M1 macrophage was the dominant group infiltrated in the MG tissue of MGD, and TIPE2 is a potential anti-inflammatory target for preventing the development of MGD by promoting the M2 polarization of macrophages.

Development and validation of a machine learning-based prognostic risk stratification model for acute ischemic stroke.

Acute ischemic stroke (AIS) is a most prevalent cause of serious long-term disability worldwide. Accurate prediction of stroke prognosis is highly valuable for effective intervention and treatment. As such, the present retrospective study aims to provide a reliable machine learning-based model for prognosis prediction in AIS patients. Data from AIS patients were collected retrospectively from the Second Affiliated Hospital of Xuzhou Medical University between August 2017 and July 2019. Independent prognostic factors were identified by univariate and multivariate logistic analysis and used to develop machine learning (ML) models. The ML model performance was assessed by area under the receiver operating characteristic curve (AUC) and radar plot. Shapley Additive explanations (SHAP) values were used to interpret the importance of all features included in the predictive model. A total of 677 AIS patients were included in the present study. Poor prognosis was observed in 209 patients (30.9%). Six variables, including neuron specific enolase (NSE), homocysteine (HCY), S-100ß, dysphagia, C-reactive protein (CRP), and anticoagulation were included to establish ML models. Six different ML algorithms were tested, and Random Forest model was selected as the final predictive model with the greatest AUC of 0.908. Moreover, according to SHAP results, NSE impacted the predictive model the most, followed by HCY, S-100ß, dysphagia, CRP and anticoagulation. Based on the RF model, an online tool was constructed to predict the prognosis of AIS patients and assist clinicians in optimizing patient treatment. The present study revealed that NSE, HCY, CRP, S-100ß, anticoagulation, and dysphagia were important factors for poor prognosis in AIS patients. ML algorithms were used to develop predictive models for predicting the prognosis of AIS patients, with the RF model presenting the optimal performance.

MLN4924 Promotes Self-Renewal of Limbal Stem Cells and Ocular Surface Restoration.

OBJECTIVE: To study the role of MLN4924 in corneal stem cell maintenance and corneal injury repair. METHODS: In cell experiments, the Sprague-Dawley (SD) rat corneal epithelial cells were co-cultured with mitomycin C-inactivated mouse feeder cells in a supplemental hormonal epithelial medium (SHEM) with or without MLN4924. Cells were photographed using an optical microscope. Furthermore, we performed crystal violet, polymerase chain reaction (PCR), and immunofluorescence staining on limbal stem cells (LSCs). In animal experiments, we scraped the corneal epithelium with a central corneal diameter of 4 mm in SD rats. The area of the corneal epithelial defect was calculated by fluorescein sodium staining. RESULTS: LSCs in the MLN4924 group had significantly proliferated. The MLN4924 treatment evidently enhanced the clone formation rate and clone area of LSCs. The expression levels of Ki67, p63, ABCG2, Bmi1, and C/EBPδ increased in LSCs after MLN4924 treatment, whereas the expression of K12 decreased. At 12 and 24 h after scraping, the corneal epithelium recovery rate in the eyes of the MLN4924-treated rats was accelerated. CONCLUSIONS: MLN4924 can maintain stemness, reduce differentiation, promote the proliferative capacity of rat LSCs, and accelerate corneal epithelial wound healing in SD rats.

Prediction model for hepatocellular carcinoma recurrence after hepatectomy: Machine learning-based development and interpretation study.

Background: Identifying patients with hepatocellular carcinoma (HCC) at high risk of recurrence after hepatectomy can help to implement timely interventional treatment. This study aimed to develop a machine learning (ML) model to predict the recurrence risk of HCC patients after hepatectomy. Methods: We retrospectively collected 315 HCC patients who underwent radical hepatectomy at the Third Affiliated Hospital of Sun Yat-sen University from April 2013 to October 2017, and randomly divided them into the training and validation sets at a ratio of 7:3. According to the postoperative recurrence of HCC patients, the patients were divided into recurrence group and non-recurrence group, and univariate and multivariate logistic regression were performed for the two groups. We applied six machine learning algorithms to construct the prediction models and performed internal validation by 10-fold cross-validation. Shapley additive explanations (SHAP) method was applied to interpret the machine learning model. We also built a web calculator based on the best machine learning model to personalize the assessment of the recurrence risk of HCC patients after hepatectomy. Results: A total of 13 variables were included in the machine learning models. The multilayer perceptron (MLP) machine learning model was proved to achieve optimal predictive value in test set (AUC = 0.680). The SHAP method displayed that γ-glutamyl transpeptidase (GGT), fibrinogen, neutrophil, aspartate aminotransferase (AST) and total bilirubin (TB) were the top 5 important factors for recurrence risk of HCC patients after hepatectomy. In addition, we further demonstrated the reliability of the model by analyzing two patients. Finally, we successfully constructed an online web prediction calculator based on the MLP machine learning model. Conclusion: MLP was an optimal machine learning model for predicting the recurrence risk of HCC patients after hepatectomy. This predictive model can help identify HCC patients at high recurrence risk after hepatectomy to provide early and personalized treatment.

Prediction model of ocular metastasis from primary liver cancer: Machine learning-based development and interpretation study.

BACKGROUND: Ocular metastasis (OM) is a rare metastatic site of primary liver cancer (PLC). The purpose of this study was to establish a clinical predictive model of OM in PLC patients based on machine learning (ML). METHODS: We retrospectively collected the clinical data of 1540 PLC patients and divided it into a training set and an internal test set in a 7:3 proportion. PLC patients were divided into OM and non-ocular metastasis (NOM) groups, and univariate logistic regression analysis was performed between the two groups. The variables with univariate logistic analysis p < 0.05 were selected for the ML model. We constructed six ML models, which were internally verified by 10-fold cross-validation. The prediction performance of each ML model was evaluated by receiver operating characteristic curves (ROCs). We also constructed a web calculator based on the optimal performance ML model to personalize the risk probability for OM. RESULTS: Six variables were selected for the ML model. The extreme gradient boost (XGB) ML model achieved the optimal differential diagnosis ability, with an area under the curve (AUC) = 0.993, accuracy = 0.992, sensitivity = 0.998, and specificity = 0.984. Based on these results, an online web calculator was constructed by using the XGB ML model to help clinicians diagnose and treat the risk probability of OM in PLC patients. Finally, the Shapley additive explanations (SHAP) library was used to obtain the six most important risk factors for OM in PLC patients: CA125, ALP, AFP, TG, CA199, and CEA. CONCLUSION: We used the XGB model to establish a risk prediction model of OM in PLC patients. The predictive model can help identify PLC patients with a high risk of OM, provide early and personalized diagnosis and treatment, reduce the poor prognosis of OM patients, and improve the quality of life of PLC patients.