Machine learning-based model development for predicting risk factors of prolonged intra-aortic balloon pump therapy in patients with coronary artery bypass grafting.

Machine learning algorithms are frequently used to clinical risk prediction. Our study was designed to predict risk factors of prolonged intra-aortic balloon pump (IABP) use in patients with coronary artery bypass grafting (CABG) through developing machine learning-based models. Patients who received perioperative IABP therapy were divided into two groups based on their length of IABP implantation longer than the 75th percentile for the whole cohort: normal (≤ 10 days) and prolonged (> 10 days) groups. Seven machine learning-based models were created and evaluated, and then the Shapley Additive exPlanations (SHAP) method was employed to further illustrate the influence of the features on model. In our study, a total of 143 patients were included, comprising 56 cases (38.16%) in the prolonged group. The logistic regression model was considered the final prediction model according to its most excellent performance. Furthermore, feature important analysis identified left ventricular end-systolic or diastolic diameter, preoperative IABP use, diabetes, and cardiac troponin T as the top five risk variables for prolonged IABP implantation in patients. The SHAP analysis further explained the features attributed to the model. Machine learning models were successfully developed and used to predict risk variables of prolonged IABP implantation in patients with CABG. This may help early identification for prolonged IABP use and initiate clinical interventions.

Immune Checkpoint Inhibitors-Associated Diabetes and Ketoacidosis Were Found in FDA Adverse Event Reporting System: A Real-World Evidence Database Study.

OBJECTIVE: To investigate the risk of developing diabetes and ketoacidosis in clinical patients with immune checkpoint inhibitors (ICIs). METHODS: We looked in the FDA Adverse Event Reporting System for reports of ICIs-associated diabetes mellitus (DM) and ketoacidosis between January 2004 and March 2022. We explored the signals using fourfold table-based proportional imbalance algorithms. Patient characteristics, country distribution, and outcomes of adverse reactions were described. Kruskal-Wallis test was used to compare the time of onset and prognosis of adverse reactions. RESULTS: A total of 2110 reports of ICIs-related DM were included in the study. The largest number of reports was from Japan (752, 35.64%), followed by the United States and France (624, 29.57%; 183, 8.67%). Seven drugs detected signals of DM and ketoacidosis according to 4 proportional imbalance algorithms: nivolumab, pembrolizumab, cemiplimab, dostarlimab, atezolizumab, avelumab, and durvalumab. Diabetes and ketoacidosis generally occurred early in the course of ICIs treatment, the median time to event onset was 144.5 (interquartile range 27-199) days. ICIs-related diabetes and ketoacidosis events resulted in 934 major medical events (44.3%), 524 hospitalizations (24.8%), 60 life-threatening events (2.8%), 42 deaths (2.0%), and 39 disability events (1.8%). CONCLUSION: The study reveals the risk and characteristics of diabetes and ketoacidosis associated with ICIs, which may provide evidence for postmarketing evaluation. Careful consideration should be given to the possibility of an increased risk of diabetes and ketoacidosis after using ICIs, and careful monitoring for diabetes and ketoacidosis is recommended.

Derivatives of Br-doped metal-organic framework for improved acetaldehyde adsorption-photocatalytic oxidation.

Different Br-doped metal-organic frameworks (MOFs) derived (Brx@UiO-66) have been prepared by heat treatment using UiO-66 as the precursor. The experimental results showed that Br0.2@UiO-66 exhibited the best photocatalytic oxidation and adsorption performances toward acetaldehyde. In the dynamic system, the acetaldehyde removal rate and adsorption capacity of Br0.2@UiO-66 were 93.2 % and 230.59 mg/g, respectively. The improvement of the photocatalytic performance can be attributed to the presence of Br ions and CBr bonds, which facilitated the rapid separation of electrons and holes and the production of •O2-. In addition, Br0.2@UiO-66 had a better adsorption performance than 300UiO-66, mainly because of the increased Lewis acidity of the metal active sites due to Br doping. Radical capture experiments indicated that •O2- and e- were the primary active substances in acetaldehyde oxidation, and allowed establishing the possible mechanism of acetaldehyde oxidation. This work shows that MOFs can have high catalytic oxidation performances toward volatile organic compounds (VOCs) while retaining their adsorption capacity, and can be used for practical applications in the adsorption-catalytic integrated degradation of VOCs.

Myeloid-Mas Signaling Modulates Pathogenic Crosstalk among MYC+CD63+ Endothelial Cells, MMP12+ Macrophages, and Monocytes in Acetaminophen-Induced Liver Injury.

Acetaminophen overdose is a leading cause of acute liver failure (ALF). Despite the pivotal role of the inflammatory microenvironment in the progression of advanced acetaminophen-induced liver injury (AILI), a comprehensive understanding of the underlying cellular interactions and molecular mechanisms remains elusive. Mas is a G protein-coupled receptor highly expressed by myeloid cells; however, its role in the AILI microenvironment remains to be elucidated. A multidimensional approach, including single-cell RNA sequencing, spatial transcriptomics, and hour-long intravital imaging, is employed to characterize the microenvironment in Mas1 deficient mice at the systemic and cell-specific levels. The characteristic landscape of mouse AILI models involves reciprocal cellular communication among MYC+CD63+ endothelial cells, MMP12+ macrophages, and monocytes, which is maintained by enhanced glycolysis and the NF-κB/TNF-α signaling pathway due to myeloid-Mas deficiency. Importantly, the pathogenic microenvironment is delineated in samples obtained from patients with ALF, demonstrating its clinical relevance. In summary, these findings greatly enhance the understanding of the microenvironment in advanced AILI and offer potential avenues for patient stratification and identification of novel therapeutic targets.

Correction: MiR-4458-loaded gelatin nanospheres target COL11A1 for DDR2/SRC signaling pathway inactivation to suppress the progression of estrogen receptor-positive breast cancer.

Correction for 'MiR-4458-loaded gelatin nanospheres target COL11A1 for DDR2/SRC signaling pathway inactivation to suppress the progression of estrogen receptor-positive breast cancer' by Jie Liu et al., Biomater. Sci., 2022, 10, 4596-4611, https://doi.org/10.1039/D2BM00543C.

Neoadjuvant versus adjuvant radiotherapy for resectable locally advanced gastric cancer: A SEER population analysis.

Background: There is a lack of evidence on whether resectable locally advanced gastric cancer (LAGC) patients could benefit from neoadjuvant or adjuvant radiotherapy (RT). Methods: Patients with surgically diagnosed LAGC from 2004 to 2015 were retrieved from the SEER database. Kaplan-Meier method and the log-rank test were used to evaluate survival analysis between neoadjuvant and adjuvant RT. Univariate Cox regression was used to evaluate the hazard ratio (HR) and 95 % confidence interval (CI). Results: A total of 4790 LAGC patients who treated with surgery and RT were identified, including 3187 patients with intestinal subtype and 1603 patients with diffuse subtype. For patients with both intestinal and diffuse subtypes, median cancer-specific survival (mCSS) was better with adjuvant RT or neoadjuvant RT. Moreover, patients benefited more from adjuvant RT than neoadjuvant RT (intestinal subtype: mCSS 49 vs. 36 months, P < 0.001; diffuse subtype: mCSS 32 vs. 26 months, P = 0.050). Further analyses showed that patients with intestinal subtype and T1-2N+, T3N-, T3N+ subgroups, as well as patients with diffuse subtype and T1-2N+ and T3N+ subgroups benefited more from adjuvant RT than those with neoadjuvant RT. Patients in the diffuse subtype and T3N- subgroups also tended benifit from adjuvant RT and survive. There was no difference in survival between the T4N- and T4N + subgroups of the two subtypes. After propensity score matching, subgroup analysis identified an improved survival in favor of adjuvant RT in the age ≥65 years and female subgroups in diffuse subtypes and T4N+ patients. Conclusions: For patients with resectable LAGC in the T1-2N+, T3N-, T3N+ clinical subgroups, adjuvant RT yields more benefits than neoadjuvant RT or no RT, which is worthy of prospective clinical trial.

The efficacy and safety of fexuprazan in treating erosive esophagitis: a phase III, randomized, double-blind, multicenter study.

BACKGROUND AND AIM: Fexuprazan is a novel potassium-competitive acid blocker (P-CAB). This study aimed to explore the noninferior efficacy and safety of fexuprazan to esomeprazole in treating erosive esophagitis (EE). METHODS: This was a phase III, randomized, double-blind multicenter study. Patients with endoscopically confirmed EE were randomized to receive fexuprazan 40 mg or esomeprazole 40 mg once a daily for 4-8 weeks. The healing rates of EE, symptom response, GERD-health-related quality life (GERD-HRQL), and treatment-emergent adverse events (TEAEs) were compared between fexuprazan group and esomeprazole group. RESULTS: A total of 332 subjects were included in full analysis set (FAS) and 311 in per-protocol set (PPS). The healing rates of fexuprazan and esomeprazole groups at 8 weeks were 88.5% (146/165) and 89.0% (145/163), respectively, in FAS and 97.3% (145/149) and 97.9% (143/146), respectively, in PPS. Noninferiority of fexuprazan compared with esomeprazole according to EE healing rates at 8 weeks was demonstrated in both FAS and PPS analysis. No significant difference was found between groups in EE healing rates at 4 weeks, symptom responses, and changes of GERD-HRQL. The incidence of drug-related AEs was 19.4% (32/165) in fexuprazan arm and 19.6% (32/163) in esomeprazole arm. CONCLUSION: This study demonstrated noninferior efficacy of fexuprazan to esomeprazole in treating EE. The incidence of TEAEs was similar between fexuprazan and esomeprazole. Trial registration number NCT05813561.

Combined impact of hypoalbuminemia and pharmacogenomic variants on voriconazole trough concentration: data from a real-life clinical setting in the Chinese population.

Voriconazole (VRC) displays highly variable pharmacokinetics impacting treatment efficacy and safety. To provide evidence for optimizing VRC therapy regimens, the authors set out to determine the factors impacting VRC steady-state trough concentration (Cmin) in patients with various albumin (Alb) level. A total of 275 blood samples of 120 patients and their clinical characteristics and genotypes of CYP2C19, CYP3A4, CYP3A5, CYP2C9, FMO3, ABCB1, POR, NR1I2 and NR1I3 were included in this study. Results of multivariate linear regression analysis demonstrated that C-reactive protein (CRP) and total bilirubin (T-Bil) were predictors of the VRC Cmin adjusted for dose in patients with hypoalbuminemia (Alb < 35 g/L) (R2 = 0.16, P < 0.001). Additionally, in patients with normal albumin level (Alb ≥ 35 g/L), it resulted in a significant model containing factors of the poor metabolizer (PM) CYP2C19 genotype and CRP level (R2 = 0.26, P < 0.001). Therefore, CRP and T-Bil levels ought to receive greater consideration than genetic factors in patients with hypoalbuminemia.

Prognostic value of virtual portal pressure gradient response in compensated cirrhotic patients treated with carvedilol.

AIM: This study aimed to assess the prognostic significance of virtual portal pressure gradient (vPPG) response to carvedilol in patients with compensated cirrhosis (CC). METHODS: Compensated cirrhosis patients with high-risk varices were prospectively enrolled to receive carvedilol for prevention of first variceal hemorrhage (VH) and followed up for 1 year. The vPPG response was defined as a reduction of vPPG >10% from baseline after 1-month therapy. Logistic and Cox regression analyses were performed to identify independent predictors for vPPG response and first decompensation, respectively. Competitive risk models were constructed to predict disease progression, and validated using the C-index, Kaplan-Meier analysis, competitive risk analysis, and calibration curves. RESULTS: A total of 129 patients completed this study, of whom 56 (43.4%) achieved vPPG response and were referred as vPPG responders. Baseline vPPG, red color sign, Model for End-stage Liver Disease score, serum monocyte chemoattractant protein-1 (MCP-1), and laminin levels significantly correlated with vPPG response, which itself was further documented as an independent predictor of VH, ascites, and overall decompensation events in CC. Moreover, the red color sign or Child-Turcotte-Pugh score effectively predicted VH, while ascites correlated well with portal flow velocity or MCP-1. The predictive models for VH and ascites showed a good discrimination with C-index values of 0.747 and 0.689 respectively, and the high consistency on calibration curves. CONCLUSION: The vPPG response could be used as a noninvasive tool for prediction of disease progression in patients with CC.

Individualized treatment with voriconazole in the Chinese population: Inflammation level as a novel marker for dose optimization.

AIMS: The aim of this study was to explore the influence and possible mechanisms of pharmacokinetics-related gene polymorphisms, especially CYP2C19 polymorphisms, and non-genetic factors combined with the inflammatory status on the voriconazole (VRC) metabolism of the Chinese population. METHODS: Clinical studies were performed by collecting more than one VRC trough concentration and C-reactive protein (CRP) level. A total of 265 blood samples were collected from 120 patients. RESULTS: Results of multiple regression analyses demonstrated that CYP2C19 genotypes and albumin (Alb) level remained predictors of Cmin ss/D in patients with no to mild inflammation (R2 = 0.12, P < .001). In addition, in patients with moderate to severe inflammation, it resulted in a significant model containing factors of CRP and total bilirubin (T-Bil) levels (R2 = 0.19, P < .001). In non-clinical studies, 32 rats were divided into control and inflammatory groups, and it was found that the mean residence time (MRT(0-t) ) of VRC in the inflammatory group was significantly longer than that in the control group (P < .001), which may be due to down-regulation of mRNA and protein expression of CYP2C19 (CYP2C6 in rats) through interleukin (IL)-6/signal transducer and activator of transcription (STAT) 3 pathway. CONCLUSIONS: Therefore, the effect of CYP2C19 polymorphisms on VRC metabolism may be masked by inflammatory status, which should be of more concern than CYP2C19 polymorphisms in patients with moderate to severe inflammation. Additionally, the impact of Alb and T-Bil on VRC metabolism should not be disregarded.

Lower circulating irisin levels in type 2 diabetes mellitus patients with chronic complications: A meta-analysis.

Purpose: The aim of this study was to provide evidence of the differences in circulating irisin levels between type 2 diabetes mellitus (T2DM) patients with and without chronic complications. Methods: We performed a meta-analysis to compare circulating irisin levels between different groups. Literature search was conducted in PubMed, Cochrane Library, Embase, WanFang, and China National Knowledge Infrastructure databases from inception through December 2022. Random effects model and standard mean difference (SMD) was used to calculate the pooled outcomes with 95 % confidence intervals (CIs). Results: Forty-two studies that matched the inclusion criteria were analyzed. Circulating irisin levels were significantly lower in T2DM patients with chronic complications than those in T2DM patients without chronic complications (SMD: -1.43; 95 % CI: -1.76 to -1.09; p < 0.00001) and healthy control group (SMD: -2.40; 95 % CI: -3.02 to -1.77; p < 0.00001). Moreover, irisin levels further decrease with the aggravation of complications in T2DM patients with diabetic nephropathy or diabetic retinopathy. Conclusion: Compared with T2DM patients without chronic complications, T2DM patients with chronic complications had lower circulating irisin levels. In addition, irisin levels were negatively correlated with the severity of chronic complications.

Pharmacokinetics of cyanidin-3-O-galactoside and cyanidin-3-O-arabinoside after intravenous administration in rats.

Cyanidin-3-O-galactoside and cyanidin-3-O-arabinoside (purity >98%) were isolated from black chokeberry by preparative high-performance liquid chromatography, and an animal experiment was conducted to investigate the pharmacokinetics of two anthocyanin monomers after intravenous administration. The results showed that cyanidin-3-O-galactoside has preferable druggability than cyanidin-3-O-arabinoside in pharmacokinetic area.

FBXL5 promotes lipid accumulation in alcoholic fatty liver disease by promoting the ubiquitination and degradation of TFEB.

BACKGROUND: Alcoholic fatty liver disease (AFLD) is characterized by abnormal lipid droplet accumulation in liver. Epigenetic regulation plays an important role in the pathogenesis of AFLD. Comprehensive bioinformatics analysis revealed that an E3 ubiquitin ligase, F-box and leucine-rich repeats protein 5 (FBXL5), was significantly upregulated in AFLD mice. METHODS: The mouse model of AFLD was established by feeding Lieber-DeCarli liquid diet containing ethanol. An in vitro model of AFLD was established by treating HepG2 cells with ethanol (EtOH). The FBXL5 expression was assessed by quantitative real-time PCR (qRT-PCR) and western blotting assays. The levels of triglyceride (TG), alanine aminotransferase (ALT), aspartate aminotransferase (AST), and lipid accumulation were analyzed by enzyme-linked immunosorbent assay (ELISA) and Nile red staining. RESULTS: The FBXL5 expression was markedly up-regulated in in vivo and in vitro models of AFLD compared with controls. Functionally, FBXL5 knockdown alleviated lipid accumulation in EtOH-treated HepG2 cells. Mechanistically, FBXL5 directly interacted with transcription factor EB (TFEB) and accelerated its ubiquitination-mediated degradation. TFEB knockdown reversed the effect of FBXL5 inhibition on decreasing EtOH-induced lipid accumulation. CONCLUSION: Our data suggest that FBXL5 promotes lipid accumulation in AFLD by promoting the ubiquitination and degradation of TFEB.

Subcellular compartmentalization in the biosynthesis and engineering of plant natural products.

Plant natural products (PNPs) are specialized metabolites with diverse bioactivities. They are extensively used in the pharmaceutical, cosmeceutical and food industries. PNPs are synthesized in plant cells by enzymes that are distributed in different subcellular compartments with unique microenvironments, such as ions, co-factors and substrates. Plant metabolic engineering is an emerging and promising approach for the sustainable production of PNPs, for which the knowledge of the subcellular compartmentalization of their biosynthesis is instrumental. In this review we describe the state of the art on the role of subcellular compartments in the biosynthesis of major types of PNPs, including terpenoids, phenylpropanoids, alkaloids and glucosinolates, and highlight the efforts to target biosynthetic pathways to subcellular compartments in plants. In addition, we will discuss the challenges and strategies in the field of plant synthetic biology and subcellular engineering. We expect that newly developed methods and tools, together with the knowledge gained from the microbial chassis, will greatly advance plant metabolic engineering.

Effect of ligand substitution in UiO-66 metal-organic frameworks on the photocatalytic oxidation of acetaldehyde.

A series of functionalized X-UiO-66 (X = NH2, H, Br and NO2) materials were prepared using a hydrothermal method and modified with various ligands. Their photocatalytic activity was evaluated by the oxidation of acetaldehyde. Experimental results show that the introduction of different ligands significantly influences the physicochemical properties of UiO-66. Br-UiO-66 exhibited the highest photocatalytic activity and CO2 selectivity of 85.6% and 85.7%, respectively. Photochemical properties reveal that -Br functional group facilitate the separation of photogenerated electrons and holes, significantly improving their transfer and oxygen reduction. As a result, an increased number of hydroxyl and superoxide radicals can form, improving the efficiency of the photocatalytic reaction. Br-UiO-66 accumulates fewer intermediates on its surface and still shows excellent photocatalytic activity and structural stability after 24 h of dynamic reaction. This work demonstrates the excellent adsorption and catalytic oxidation performance of Br-UiO-66 towards acetaldehyde and may provide new ideas for researching catalysts in the photocatalytic degradation of pollutants.

Estimation of Wind Speed Based on Schlieren Machine Vision System Inspired by Greenhouse Top Vent.

Greenhouse ventilation has always been an important concern for agricultural workers. This paper aims to introduce a low-cost wind speed estimating method based on SURF (Speeded Up Robust Feature) feature matching and the schlieren technique for airflow mixing with large temperature differences and density differences like conditions on the vent of the greenhouse. The fluid motion is directly described by the pixel displacement through the fluid kinematics analysis. Combining the algorithm with the corresponding image morphology analysis and SURF feature matching algorithm, the schlieren image with feature points is used to match the changes in air flow images in adjacent frames to estimate the velocity from pixel change. Through experiments, this method is suitable for the speed estimation of turbulent or disturbed fluid images. When the supply air speed remains constant, the method in this article obtains 760 sets of effective feature matching point groups from 150 frames of video, and approximately 500 sets of effective feature matching point groups are within 0.1 difference of the theoretical dimensionless speed. Under the supply conditions of high-frequency wind speed changes and compared with the digital signal of fan speed and data from wind speed sensors, the trend of wind speed changes is basically in line with the actual changes. The estimation error of wind speed is basically within 10%, except when the wind speed supply suddenly stops or the wind speed is 0 m/s. This method involves the ability to estimate the wind speed of air mixing with different densities, but further research is still needed in terms of statistical methods and experimental equipment.

PIF1, a phytochrome-interacting factor negatively regulates drought tolerance and carotenoids biosynthesis in tobacco.

The phytochrome-interacting factors (PIFs) function crucially in multiple physiological processes, but the biological functions of some PIFs remain elusive in some species. Here, a PIF transcription factor NtPIF1 was cloned and characterized in tobacco (Nicotiana tabacum L.). The transcript of NtPIF1 was significantly induced by drought stress treatments, and it localized in the nuclear. Knockout of NtPIF1 by CRISPR/Cas9 system led to the improved drought tolerance of tobacco with increased osmotic adjustment, antioxidant activity, photosynthetic efficiency and decreased water loss rate. On the contrary, NtPIF1-overexpression plants displays drought-sensitive phenotypes. In addition, NtPIF1 reduced the biosynthesis of abscisic acid (ABA) and its upstream carotenoids by regulating the expression of genes involved in ABA and carotenoids biosynthetic pathway upon drought stress. Electrophoretic mobility shift and dual-luciferase assays illustrated that, NtPIF1 directly bind to the E-box elements within the promoters of NtNCED3, NtABI5, NtZDS and Ntß-LCY to repress their transcription. Overall, these data suggested that NtPIF1 negatively regulate tobacco adaptive response to drought stress and carotenoids biosynthesis; moreover, NtPIF1 has the potential to develop drought-tolerant tobacco plants using CRISPR/Cas9 system.

Bronchoscopic instillation of amphotericin B is a safe and effective measure to treat pulmonary mycosis.

Background and objectives: In recent years, there has been a significant increase in the prevalence of pulmonary mycosis disease, and its mortality has increased. There are very few studies on treating pulmonary mycosiss with bronchoscopic instillation of amphotericin B. This study investigated the clinical efficacy and safety of bronchoscopic instillation of amphotericin B for treating pulmonary mycosiss. Methods: This was a multi-centre, retrospective clinical study of 80 patients with pulmonary mycosiss who were treated with bronchoscopic instillation of amphotericin B. The efficacy and safety of this treatment were evaluated. Results: Eighty patients were included {51 males; mean [standard deviation (SD)] age, 46 (15.9) years}. The most common underlying cause was haematological malignancy (73.75%). The mean number of bronchoscopic instillations of amphotericin B was 2.4 (SD 1.5). In terms of treatment success, 58 (72.5%) patients achieved complete or partial changes on imaging after treatment. A total of 62 (77.5%) patients achieved complete or partial changes on imaging and/or local limitation of the mycosis infection. Seventy-six (95%) patients achieved complete or partial changes on imaging and/or local limitation of mycosis infection and/or an immunotherapy time window. The efficacy rates for treatment of Aspergillus and Mucor infections in terms of the three treatment success criteria described above were 73.81% vs. 63.64%, 80.95% vs. 72.73%, and 92.86% vs. 90.91%, respectively. Conclusion: Bronchoscopic instillation of amphotericin B is safe and effective for treatment of pulmonary mycosiss.

The identification of metabolism-related subtypes and potential treatments for idiopathic pulmonary fibrosis.

Background: Idiopathic pulmonary fibrosis (IPF) is caused by aberrant repair because of alveolar epithelial injury and can only be effectively treated with several compounds. Several metabolism-related biomolecular processes were found to be involved in IPF. We aimed to identify IPF subtypes based on metabolism-related pathways and explore potential drugs for each subtype. Methods: Gene profiles and clinical information were obtained from the Gene Expression Omnibus (GEO) database (GSE70867 and GSE93606). The enrichment scores for 41 metabolism-related pathways, immune cells, and immune pathways were calculated using the Gene Set Variation Analysis (GSVA) package. The ConsensusClusterPlus package was used to cluster samples. Novel modules and hub genes were identified using weighted correlation network analysis (WGCNA). Receiver operating characteristic (ROC) and calibration curves were plotted, and decision curve analysis (DCA) were performed to evaluate the model in the training and validation cohorts. A connectivity map was used as a drug probe. Results: Two subtypes with significant differences in prognosis were identified based on the metabolism-related pathways. Subtype C1 had a poor prognosis, low metabolic levels, and a unique immune signature. CDS2, LCLAT1, GPD1L, AGPAT1, ALDH3A1, LAP3, ADH5, AHCYL2, and MDH1 were used to distinguish between the two subtypes. Finally, subtype-specific drugs, which can potentially treat IPF, were identified. Conclusion: The aberrant activation of metabolism-related pathways contributes to differential prognoses in patients with IPF. Collectively, our findings provide novel mechanistic insights into subtyping IPF based on the metabolism-related pathway and potential treatments, which would help clinicians provide subtype-specific individualized therapeutic management to patients.

Segmentation of retinal detachment and retinoschisis in OCT images based on complementary multi-class segmentation networks.

Retinal detachment (RD) and retinoschisis (RS) are the main complications leading to vision loss in high myopia. Accurate segmentation of RD and RS, including its subcategories (outer, middle, and inner retinoschisis) in optical coherence tomography images is of great clinical significance in the diagnosis and management of high myopia. For this multi-class segmentation task, we propose a novel framework named complementary multi-class segmentation networks. Based on domain knowledge, a three-class segmentation path (TSP) and a five-class segmentation path (FSP) are designed, and their outputs are integrated through additional decision fusion layers to achieve improved segmentation in a complementary manner. In TSP, a cross-fusion global feature module is adopted to achieve global receptive field. In FSP, a novel three-dimensional contextual information perception module is proposed to capture long-range contexts, and a classification branch is designed to provide useful features for segmentation. A new category loss is also proposed in FSP to help better identify the lesion categories. Experiment results show that the proposed method achieves superior performance for joint segmentation of RD and the three subcategories of RS, with an average Dice coefficient of 84.83%.