RESUMO

The diagnosis of early chronic pancreatitis (ECP) is challenging due to the lack of standardized diagnostic criteria. EUS has been considered a sensitive diagnostic modality for chronic pancreatitis (CP), with advancements in technique such as EUS-guided fine needle aspiration and biopsy (EUS-FNA/FNB) being developed. However, their role in the diagnosis of ECP remains unelucidated. This review thereby aimed to provide an overview of the clinical landscape of EUS in the field of ECP.

RESUMO

The Yangtze River is one of the largest riverine ecosystems in the world and is a biodiversity hotspot. In recent years, this river ecosystem has undergone rapid habitat deterioration due to anthropogenic disturbances, leading to a decrease in freshwater biodiversity. Owing to these anthropogenic impacts, the Chinese government imposed a "Ten-year fishing ban" (TYFB) in the Yangtze River and its tributaries. Ecological changes associated with this decision have not been documented to evaluate the level of success. This study evaluates the success of the TYFB by analyzing the changes in phytoplankton communities and comparing them to periods before the TYFB was imposed. A total of 325 phytoplankton species belonging to 7 phyla and 103 genera dominated by Chlorophyceae and Bacillariophyceae were identified. Species diversity according to the Shannon-Wiener ranged between 1.19 and 3.00. The results indicated that phytoplankton diversity increased, while both density and biomass decreased after the TYFB. The health of the aquatic ecosystem appeared to have improved after the TYFB, as indicated by the phytoplankton-based index of biotic integrity. Significant seasonal and spatial differences were found among the number of species, density, and biomass of phytoplankton, where these differences were correlated with pH, water depth, chlorophyll-a, permanganate index, transparency, copper, ammonia nitrogen, and total phosphorus based on redundancy analysis. Results from this study indicate that the TYFB played an important role in the restoration of freshwater ecosystem in the Yangtze River and its tributaries.

RESUMO

BACKGROUND: Analyzing antidepressant prescribing in real-world settings can provide clinicians and health policymakers valuable information. AIM: This epidemiological study examined the status and trends in antidepressant prescribing among the Chinese population from July 1, 2017, to June 30, 2022. METHOD: A retrospective study was conducted in three hospitals. Data were collected 2.5 years before and 2.5 years after the onset of the COVID-19 pandemic. We analyzed the number of patients diagnosed with depression and their corresponding antidepressant prescriptions. Using the chi-square test, stratified analyses were performed to explore the characteristics of these prescriptions in different ages and sexes. RESULTS: The study included 124,355 patients and 400,840 antidepressant prescriptions. We observed fluctuating upward trends in the number of patients and antidepressant prescriptions. Post-COVID-19, the number of patients increased by 37.1% compared to the pre-pandemic period, and the number of antidepressant prescriptions rose by 88.3%. The three most frequently prescribed antidepressants for adolescents were sertraline, citalopram, and escitalopram. Among adults, citalopram, escitalopram, and sertraline were most common, while in older adults, citalopram, escitalopram, and mirtazapine were predominant. Male patients used mirtazapine, venlafaxine, paroxetine, bupropion, fluvoxamine, vortioxetine, and clomipramine more frequently compared to female patients, who were more likely to be prescribed citalopram, flupentixol/melitracen, agomelatine, and fluoxetine. Antidepressant monotherapy represented 76.6% of prescriptions, with the most common combination being antidepressants and anxiolytics. CONCLUSION: Over the past 5 years, both the number of patients and antidepressant prescriptions have shown upward trends, and the COVID-19 pandemic has impacted prescribing. Understanding the changes in antidepressant prescriptions can identify adherence to national guidelines.

Assuntos

Antidepressivos , COVID-19 , Humanos , Estudos Retrospectivos , Masculino , Feminino , Antidepressivos/uso terapêutico , COVID-19/epidemiologia , China/epidemiologia , Adulto , Pessoa de Meia-Idade , Adolescente , Adulto Jovem , Idoso , Instituições de Assistência Ambulatorial/estatística & dados numéricos , Depressão/tratamento farmacológico , Depressão/epidemiologia , Padrões de Prática Médica/tendências , Padrões de Prática Médica/estatística & dados numéricos , Criança , Prescrições de Medicamentos/estatística & dados numéricos

RESUMO

The Qinling water conveyance tunnel has a large buried depth and high in-situ stress level, and rockburst disasters frequently occurred during excavation. In order to find out the mechanical mechanism of rockburst, the research work in this paper is as follows: (1) In-situ three-dimensional hydraulic fracturing method was used to measure the in-situ stress of the deep buried tunnel crossing the ridge. (2) Based on the measured in-situ stress results, the stress distribution characteristics of the tunnel crossing the ridge were obtained by the multiple linear regression method, and the rockburst tendency during construction was predicted. (3) A three-dimensional numerical model of tunnel excavation was established to analyze the dynamic adjustment characteristics of the surrounding rock stress and elastic strain energy during TBM excavation, and to clarify the mechanical mechanism of rockburst. The research results show that the maximum principal stress of the deep-buried tunnel crossing the ridge of Qinling is 40-66 MPa, which belongs to extremely high in-situ stress level, and medium-strong rockburst may occur during excavation. In the process of TBM excavation, the stress of the surrounding rock in the range of 2.6 times the diameter of the tunnel before and after the working face is adjusted violently, and the concentrated zones after the stress redistribution are mainly distributed in the arch roof and arch bottom, and the stress concentration coefficient can reach 2.06. The arch roof, arch waist, and arch bottom are susceptible to immediate rockburst due to stress transient unloading at the moment of excavation. After the elastic strain energy of the surrounding rock at the arch roof and the arch bottom is released and accumulated, it is easy to cause time delayed rockburst, and the depth of the rockburst pit can reach 3.5 m, which is consistent with the rockburst phenomenon in the field.

RESUMO

As the most common energy source of spacecraft, photovoltaic (PV) power generation has become one of the hottest research fields. During the on-orbit operation of spacecraft, the influence of various uncertain factors and the unbalanced inertial force will make the solar PV wing vibrate and degrade its performance. In this study, we investigated the influence of mechanical vibration on the output characteristics of PV array systems. Specifically, we focused on a three-segment solar panel commonly found on satellites, analyzing both its dynamic response and electrical output characteristics under mechanical vibration using numerical simulation software. The correctness of the simulation model was partly confirmed by experiments. The results showed that the maximum output power of the selected solar panel was reduced by 5.53% and its fill factor exhibited a decline from the original value of 0.8031 to 0.7587, provided that the external load applied on the panel increased to 10 N/m2, i.e., the vibration frequency and the maximal deflection angle were 0.3754 Hz and 74.9871°, respectively. These findings highlight a significant decrease in the overall energy conversion efficiency of the solar panel when operating under vibration conditions.

RESUMO

Intestinal fibrosis, a severe complication of Crohn's disease (CD), is characterized by excessive extracellular matrix (ECM) deposition and induces intestinal strictures, but there are no effective antifibrosis drugs available for clinical application. We performed single-cell RNA sequencing (scRNA-Seq) of fibrotic and nonfibrotic ileal tissues from patients with CD with intestinal obstruction. Analysis revealed mesenchymal stromal cells (MSCs) as the major producers of ECM and the increased infiltration of its subset FAP+ fibroblasts in fibrotic sites, which was confirmed by immunofluorescence and flow cytometry. Single-cell transcriptomic profiling of chronic dextran sulfate sodium salt murine colitis model revealed that CD81+Pi16- fibroblasts exhibited transcriptomic and functional similarities to human FAP+ fibroblasts. Consistently, FAP+ fibroblasts were identified as the key subtype with the highest level of ECM production in fibrotic intestines. Furthermore, specific knockout or pharmacological inhibition of TWIST1, which was highly expressed by FAP+ fibroblasts, could significantly ameliorate fibrosis in mice. In addition, TWIST1 expression was induced by CXCL9+ macrophages enriched in fibrotic tissues via IL-1ß and TGF-ß signal. These findings suggest the inhibition of TWIST1 as a promising strategy for CD fibrosis treatment.

Assuntos

Doença de Crohn , Fibroblastos , Fibrose , Proteína 1 Relacionada a Twist , Doença de Crohn/patologia , Doença de Crohn/metabolismo , Doença de Crohn/genética , Animais , Proteína 1 Relacionada a Twist/metabolismo , Proteína 1 Relacionada a Twist/genética , Fibroblastos/metabolismo , Fibroblastos/patologia , Humanos , Camundongos , Proteínas Nucleares/genética , Proteínas Nucleares/metabolismo , Camundongos Knockout , Masculino , Feminino , Modelos Animais de Doenças , Íleo/patologia , Íleo/metabolismo , Endopeptidases/genética , Endopeptidases/metabolismo , Proteínas de Membrana

RESUMO

Continuous emergence of new variants of severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2), enhanced transmissibility, significant immune escape, and waning immunity call for booster vaccination. We evaluated the safety, immunogenicity, and efficacy of heterologous booster with a SARS-CoV-2 mRNA vaccine SYS6006 versus an active control vaccine in a randomized, open-label, active-controlled phase 3 trial in healthy adults aged 18 years or more who had received two or three doses of SARS-CoV-2 inactivated vaccine in China. The trial started in December 2022 and lasted for 6 months. The participants were randomized (overall ratio: 3:1) to receive one dose of SYS6006 (N = 2999) or an ancestral receptor binding region-based, alum-adjuvanted recombinant protein SARS-CoV-2 vaccine (N = 1000), including 520 participants in an immunogenicity subgroup. SYS6006 boosting showed good safety profiles with most AEs being grade 1 or 2, and induced robust wild-type and Omicron BA.5 neutralizing antibody response on Days 14 and 28, demonstrating immunogenicity superiority versus the control vaccine and meeting the primary objective. The relative vaccine efficacy against COVID-19 of any severity was 51.6% (95% CI, 35.5-63.7) for any variant, 66.8% (48.6-78.5) for BA.5, and 37.7% (2.4-60.3) for XBB, from Day 7 through Month 6. In the vaccinated and infected hybrid immune participants, the relative vaccine efficacy was 68.4% (31.1-85.5) against COVID-19 of any severity caused by a second infection. All COVID-19 cases were mild. SYS6006 heterologous boosting demonstrated good safety, superior immunogenicity and high efficacy against BA.5-associated COVID-19, and protected against XBB-associated COVID-19, particularly in the hybrid immune population.Trial registration: Chinese Clinical Trial Registry: ChiCTR2200066941.

Assuntos

Anticorpos Neutralizantes , Anticorpos Antivirais , Vacinas contra COVID-19 , COVID-19 , Imunização Secundária , Imunogenicidade da Vacina , SARS-CoV-2 , Vacinas de mRNA , Humanos , Vacinas contra COVID-19/imunologia , Vacinas contra COVID-19/administração & dosagem , Vacinas contra COVID-19/efeitos adversos , COVID-19/prevenção & controle , COVID-19/imunologia , COVID-19/virologia , Adulto , SARS-CoV-2/imunologia , SARS-CoV-2/genética , Feminino , Masculino , Anticorpos Antivirais/sangue , Anticorpos Antivirais/imunologia , China , Pessoa de Meia-Idade , Anticorpos Neutralizantes/sangue , Anticorpos Neutralizantes/imunologia , Adulto Jovem , Vacinas Sintéticas/imunologia , Vacinas Sintéticas/administração & dosagem , Vacinas Sintéticas/efeitos adversos , Adolescente , Eficácia de Vacinas , Vacinas de Produtos Inativados/imunologia , Vacinas de Produtos Inativados/administração & dosagem , Vacinas de Produtos Inativados/efeitos adversos , População do Leste Asiático

RESUMO

BACKGROUND: The stent embedded in the esophageal mucosa is one of the complications after stenting for esophageal stricture. We present a case of stent adjustment with the aid of a transparent cap after endoscopic injection of an esophageal varices stent. CASE SUMMARY: A 61-year-old male patient came to the hospital with discomfort of the chest after the stent implanted for the stenosis because of endoscopic injection of esophageal varices. The gastroscopy was performed, and the stent embedded into the esophageal mucosa. At first, we pulled the recycling line for shrinking the stent, however, the mucosa could not be removed from the stent. Then a forceps was performed to remove the mucosa in the stent, nevertheless, the bleeding form the mucosa was obvious. And then, we used a transparent cap to scrape the mucosa along the stent, and the mucosa were removed successfully without bleeding. CONCLUSION: A transparent cap helps gastroscopy to remove the mucosa embedded in the stent after endoscopic injection of the esophageal varices stent.

RESUMO

BACKGROUND: Venlafaxine is frequently prescribed for patients with depression. To control the concentration of venlafaxine within the therapeutic window for the best treatment effect, a model to predict venlafaxine concentration is necessary. AIM: Our objective was to develop a prediction model for venlafaxine concentration using real-world evidence based on machine learning and deep learning techniques. METHOD: Patients who underwent venlafaxine treatment between November 2019 and August 2022 were included in the study. Important variables affecting venlafaxine concentration were identified using a combination of univariate analysis, sequential forward selection, and machine learning techniques. Predictive performance of nine machine learning and deep learning algorithms were assessed, and the one with the optimal performance was selected for modeling. The final model was interpreted using SHapley Additive exPlanations. RESULTS: A total of 330 eligible patients were included. Five influential variables that affect venlafaxine concentration were venlafaxine daily dose, sex, age, hyperlipidemia, and adenosine deaminase. The venlafaxine concentration prediction model was developed using the eXtreme Gradient Boosting algorithm (R2 = 0.65, mean absolute error = 77.92, root mean square error = 93.58). In the testing cohort, the accuracy of the predicted concentration within ± 30% of the actual concentration was 73.49%. In the subgroup analysis, the prediction accuracy was 69.39% within the recommended therapeutic range of venlafaxine concentration within ± 30% of the actual value. CONCLUSION: The XGBoost model for predicting blood concentration of venlafaxine using real-world evidence was developed, guiding the adjustment of regimen in clinical practice.

Assuntos

Aprendizado de Máquina , Cloridrato de Venlafaxina , Cloridrato de Venlafaxina/farmacocinética , Cloridrato de Venlafaxina/uso terapêutico , Cloridrato de Venlafaxina/administração & dosagem , Humanos , Feminino , Masculino , Estudos Retrospectivos , Pessoa de Meia-Idade , Idoso , Adulto , Antidepressivos de Segunda Geração/farmacocinética , Depressão/tratamento farmacológico

RESUMO

BACKGROUND: Venlafaxine dose regimens vary considerably between individuals, requiring personalized dosing. AIM: This study aimed to identify dose-related influencing factors of venlafaxine through real-world data analysis and to construct a personalized dose model using advanced artificial intelligence techniques. METHOD: We conducted a retrospective study on patients with depression treated with venlafaxine. Significant variables were selected through a univariate analysis. Subsequently, the predictive performance of seven models (XGBoost, LightGBM, CatBoost, GBDT, ANN, TabNet, and DT) was compared. The algorithm that demonstrated optimal performance was chosen to establish the dose prediction model. Model validation used confusion matrices and ROC analysis. Additionally, a dose subgroup analysis was conducted. RESULTS: A total of 298 patients were included. TabNet was selected to establish the venlafaxine dose prediction model, which exhibited the highest performance with an accuracy of 0.80. The analysis identified seven crucial variables correlated with venlafaxine daily dose, including blood venlafaxine concentration, total protein, lymphocytes, age, globulin, cholinesterase, and blood platelet count. The area under the curve (AUC) for predicting venlafaxine doses of 75 mg, 150 mg, and 225 mg were 0.90, 0.85, and 0.90, respectively. CONCLUSION: We successfully developed a TabNet model to predict venlafaxine doses using real-world data. This model demonstrated substantial predictive accuracy, offering a personalized dosing regimen for venlafaxine. These findings provide valuable guidance for the clinical use of the drug.

Assuntos

Inteligência Artificial , Relação Dose-Resposta a Droga , Medicina de Precisão , Cloridrato de Venlafaxina , Humanos , Cloridrato de Venlafaxina/administração & dosagem , Estudos Retrospectivos , Feminino , Masculino , Pessoa de Meia-Idade , Adulto , Medicina de Precisão/métodos , Idoso , Antidepressivos de Segunda Geração/administração & dosagem , Depressão/tratamento farmacológico

RESUMO

Background: Growing evidence has shown that gut microbiome composition is associated with Biliary tract cancer (BTC), but the causality remains unknown. This study aimed to explore the causal relationship between gut microbiota and BTC, conduct an appraisal of the gut microbiome's utility in facilitating the early diagnosis of BTC. Methods: We acquired the summary data for Genome-wide Association Studies (GWAS) pertaining to BTC (418 cases and 159,201 controls) from the Biobank Japan (BBJ) database. Additionally, the GWAS summary data relevant to gut microbiota (N = 18,340) were sourced from the MiBioGen consortium. The primary methodology employed for the analysis consisted of Inverse Variance Weighting (IVW). Evaluations for sensitivity were carried out through the utilization of multiple statistical techniques, encompassing Cochrane's Q test, the MR-Egger intercept evaluation, the global test of MR-PRESSO, and a leave-one-out methodological analysis. Ultimately, a reverse Mendelian Randomization analysis was conducted to assess the potential for reciprocal causality. Results: The outcomes derived from IVW substantiated that the presence of Family Streptococcaceae (OR = 0.44, P = 0.034), Family Veillonellaceae (OR = 0.46, P = 0.018), and Genus Dorea (OR = 0.29, P = 0.041) exerted a protective influence against BTC. Conversely, Class Lentisphaeria (OR = 2.21, P = 0.017), Genus Lachnospiraceae FCS020 Group (OR = 2.30, P = 0.013), and Order Victivallales (OR = 2.21, P = 0.017) were associated with an adverse impact. To assess any reverse causal effect, we used BTC as the exposure and the gut microbiota as the outcome, and this analysis revealed associations between BTC and five different types of gut microbiota. The sensitivity analysis disclosed an absence of empirical indicators for either heterogeneity or pleiotropy. Conclusion: This investigation represents the inaugural identification of indicative data supporting either beneficial or detrimental causal relationships between gut microbiota and the risk of BTC, as determined through the utilization of MR methodologies. These outcomes could hold significance for the formulation of individualized therapeutic strategies aimed at BTC prevention and survival enhancement.

Assuntos

Neoplasias do Sistema Biliar , Microbioma Gastrointestinal , Humanos , Microbioma Gastrointestinal/genética , Estudo de Associação Genômica Ampla , Análise da Randomização Mendeliana , Neoplasias do Sistema Biliar/genética , Causalidade

RESUMO

Background: Numerous observational studies have identified a linkage between the gut microbiota and gastroesophageal reflux disease (GERD). However, a clear causative association between the gut microbiota and GERD has yet to be definitively ascertained, given the presence of confounding variables. Methods: The genome-wide association study (GWAS) pertaining to the microbiome, conducted by the MiBioGen consortium and comprising 18,340 samples from 24 population-based cohorts, served as the exposure dataset. Summary-level data for GERD were obtained from a recent publicly available genome-wide association involving 78 707 GERD cases and 288 734 controls of European descent. The inverse variance-weighted (IVW) method was performed as a primary analysis, the other four methods were used as supporting analyses. Furthermore, sensitivity analyses encompassing Cochran's Q statistics, MR-Egger intercept, MR-PRESSO global test, and leave-one-out methodology were carried out to identify potential heterogeneity and horizontal pleiotropy. Ultimately, a reverse MR assessment was conducted to investigate the potential for reverse causation. Results: The IVW method's findings suggested protective roles against GERD for the Family Clostridiales Vadin BB60 group (P = 0.027), Genus Lachnospiraceae UCG004 (P = 0.026), Genus Methanobrevibacter (P = 0.026), and Phylum Actinobacteria (P = 0.019). In contrast, Class Mollicutes (P = 0.037), Genus Anaerostipes (P = 0.049), and Phylum Tenericutes (P = 0.024) emerged as potential GERD risk factors. In assessing reverse causation with GERD as the exposure and gut microbiota as the outcome, the findings indicate that GERD leads to dysbiosis in 13 distinct gut microbiota classes. The MR results' reliability was confirmed by thorough assessments of heterogeneity and pleiotropy. Conclusions: For the first time, the MR analysis indicates a genetic link between gut microbiota abundance changes and GERD risk. This not only substantiates the potential of intestinal microecological therapy for GERD, but also establishes a basis for advanced research into the role of intestinal microbiota in the etiology of GERD.

Assuntos

Refluxo Gastroesofágico , Microbioma Gastrointestinal , Humanos , Microbioma Gastrointestinal/genética , Estudo de Associação Genômica Ampla , Análise da Randomização Mendeliana , Reprodutibilidade dos Testes , Refluxo Gastroesofágico/genética , Clostridiales

RESUMO

Background: Sertraline is a commonly employed antidepressant in clinical practice. In order to control the plasma concentration of sertraline within the therapeutic window to achieve the best effect and avoid adverse reactions, a personalized model to predict sertraline concentration is necessary. Aims: This study aimed to establish a personalized medication model for patients with depression receiving sertraline based on machine learning to provide a reference for clinicians to formulate drug regimens. Methods: A total of 415 patients with 496 samples of sertraline concentration from December 2019 to July 2022 at the First Hospital of Hebei Medical University were collected as the dataset. Nine different algorithms, namely, XGBoost, LightGBM, CatBoost, random forest, GBDT, SVM, lasso regression, ANN, and TabNet, were used for modeling to compare the model abilities to predict sertraline concentration. Results: XGBoost was chosen to establish the personalized medication model with the best performance (R 2 = 0.63). Five important variables, namely, sertraline dose, alanine transaminase, aspartate transaminase, uric acid, and sex, were shown to be correlated with sertraline concentration. The model prediction accuracy of sertraline concentration in the therapeutic window was 62.5%. Conclusion: In conclusion, the personalized medication model of sertraline for patients with depression based on XGBoost had good predictive ability, which provides guidance for clinicians in proposing an optimal medication regimen.

RESUMO

BACKGROUND: BEBT-109 is an oral pan-mutant-selective inhibitor of epidermal growth factor receptor (EGFR) that demonstrated promising antitumor potency in preclinical models. METHODS: This first-in-human study was a single-arm, open-label, two-stage study. Phase Ia dose-escalation study evaluated the safety and pharmacokinetics of BEBT-109 in 11 patients with EGFR T790M-mutated advanced non-small cell lung cancer (aNSCLC). Phase Ib dose-expansion study evaluated the safety and efficacy of BEBT-109 in 18 patients with EGFR exon 20 insertion (ex20ins)-mutated treatment-refractory aNSCLC. The primary outcomes were adverse events and antitumor activity. Clinical trial registration number CTR20192575. FINDINGS: The phase Ia study demonstrated no dose-limiting toxicity, no observation of the maximum tolerated dose, and no new safety signals with BEBT-109 in the dose range of 20-180 mg/d, suggesting that BEBT-109 had an acceptable safety profile among patients with EGFR T790M-mutated aNSCLC. Plasma pharmacokinetics of BEBT-109 showed a dose-proportional increase in the area under the curve and maximal concentration, with no significant drug accumulation. The dose-expansion study demonstrated that BEBT-109 treatment was tolerable across the three dose levels. The three most common treatment-related adverse events were diarrhea (100%; 22.2% ≥Grade 3), rash (66.7%; 5.6% ≥Grade 3), and anemia (61.1%; 0% ≥Grade 3). The objective response rate was 44.4% (8 of 18). Median progression-free survival was 8.0 months (95% confidence intervals, 1.33-14.67). CONCLUSION: Preliminary findings showed that BEBT-109 had an acceptable safety profile and favorable antitumor activity in patients with refractory EGFR ex20ins-mutated aNSCLC. FUNDING: National Natural Science Foundation of China.

Assuntos

Carcinoma Pulmonar de Células não Pequenas , Receptores ErbB , Éxons , Neoplasias Pulmonares , Humanos , Carcinoma Pulmonar de Células não Pequenas/tratamento farmacológico , Carcinoma Pulmonar de Células não Pequenas/genética , Carcinoma Pulmonar de Células não Pequenas/patologia , Receptores ErbB/genética , Receptores ErbB/antagonistas & inibidores , Masculino , Neoplasias Pulmonares/tratamento farmacológico , Neoplasias Pulmonares/genética , Neoplasias Pulmonares/patologia , Pessoa de Meia-Idade , Feminino , Idoso , Éxons/genética , Mutação , Dose Máxima Tolerável , Adulto , Relação Dose-Resposta a Droga , Antineoplásicos/farmacocinética , Antineoplásicos/uso terapêutico , Antineoplásicos/efeitos adversos , Antineoplásicos/administração & dosagem , Inibidores de Proteínas Quinases/farmacocinética , Inibidores de Proteínas Quinases/uso terapêutico , Inibidores de Proteínas Quinases/administração & dosagem , Inibidores de Proteínas Quinases/efeitos adversos

RESUMO

OBJECTIVE: To evaluate the diagnostic accuracy and safety of using magnetically guided capsule endoscopy with a detachable string (ds-MCE) for detecting and grading oesophagogastric varices in adults with cirrhosis. DESIGN: Prospective multicentre diagnostic accuracy study. SETTING: 14 medical centres in China. PARTICIPANTS: 607 adults (>18 years) with cirrhosis recruited between 7 January 2021 and 25 August 2022. Participants underwent ds-MCE (index test), followed by oesophagogastroduodenoscopy (OGD, reference test) within 48 hours. The participants were divided into development and validation cohorts in a ratio of 2:1. MAIN OUTCOME MEASURES: The primary outcomes were the sensitivity and specificity of ds-MCE in detecting oesophagogastric varices compared with OGD. Secondary outcomes included the sensitivity and specificity of ds-MCE for detecting high risk oesophageal varices and the diagnostic accuracy of ds-MCE for detecting high risk oesophagogastric varices, oesophageal varices, and gastric varices. RESULTS: ds-MCE and OGD examinations were completed in 582 (95.9%) of the 607 participants. Using OGD as the reference standard, ds-MCE had a sensitivity of 97.5% (95% confidence interval 95.5% to 98.7%) and specificity of 97.8% (94.4% to 99.1%) for detecting oesophagogastric varices (both P<0.001 compared with a prespecified 85% threshold). When using the optimal 18% threshold for luminal circumference of the oesophagus derived from the development cohort (n=393), the sensitivity and specificity of ds-MCE for detecting high risk oesophageal varices in the validation cohort (n=189) were 95.8% (89.7% to 98.4%) and 94.7% (88.2% to 97.7%), respectively. The diagnostic accuracy of ds-MCE for detecting high risk oesophagogastric varices, oesophageal varices, and gastric varices was 96.3% (92.6% to 98.2%), 96.9% (95.2% to 98.0%), and 96.7% (95.0% to 97.9%), respectively. Two serious adverse events occurred with OGD but none with ds-MCE. CONCLUSION: The findings of this study suggest that ds-MCE is a highly accurate and safe diagnostic tool for detecting and grading oesophagogastric varices and is a promising alternative to OGD for screening and surveillance of oesophagogastric varices in patients with cirrhosis. TRIAL REGISTRATION: ClinicalTrials.gov NCT03748563.

Assuntos

Endoscopia por Cápsula , Varizes Esofágicas e Gástricas , Varizes , Adulto , Humanos , Varizes Esofágicas e Gástricas/diagnóstico , Varizes Esofágicas e Gástricas/etiologia , Cirrose Hepática/complicações , Estudos Prospectivos

RESUMO

Stain variations pose a major challenge to deep learning segmentation algorithms in histopathology images. Current unsupervised domain adaptation methods show promise in improving model generalization across diverse staining appearances but demand abundant accurately labeled source domain data. This paper assumes a novel scenario, namely, unsupervised domain adaptation based segmentation task with incompletely labeled source data. This paper propose a Stain-Adaptive Segmentation Network with Incomplete Labels (SASN-IL). Specifically, the algorithm consists of two stages. The first stage is an incomplete label correction stage, involving reliable model selection and label correction to rectify false-negative regions in incomplete labels. The second stage is the unsupervised domain adaptation stage, achieving segmentation on the target domain. In this stage, we introduce an adaptive stain transformation module, which adjusts the degree of transformation based on segmentation performance. We evaluate our method on a gastric cancer dataset, demonstrating significant improvements, with a 10.01% increase in Dice coefficient compared to the baseline and competitive performance relative to existing methods.

Assuntos

Algoritmos , Neoplasias Gástricas , Humanos , Coloração e Rotulagem , Processamento de Imagem Assistida por Computador

RESUMO

Gastric precancerous lesions (GPL) significantly elevate the risk of gastric cancer, and precise diagnosis and timely intervention are critical for patient survival. Due to the elusive pathological features of precancerous lesions, the early detection rate is less than 10%, which hinders lesion localization and diagnosis. In this paper, we provide a GPL pathological dataset and propose a novel method for improving the segmentation accuracy on a limited-scale dataset, namely RGB and Hyperspectral dual-modal pathological image Cross-attention U-Net (CrossU-Net). Specifically, we present a self-supervised pre-training model for hyperspectral images to serve downstream segmentation tasks. Secondly, we design a dual-stream U-Net-based network to extract features from different modal images. To promote information exchange between spatial information in RGB images and spectral information in hyperspectral images, we customize the cross-attention mechanism between the two networks. Furthermore, we use an intermediate agent in this mechanism to improve computational efficiency. Finally, we add a distillation loss to align predicted results for both branches, improving network generalization. Experimental results show that our CrossU-Net achieves accuracy and Dice of 96.53% and 91.62%, respectively, for GPL lesion segmentation, providing a promising spectral research approach for the localization and subsequent quantitative analysis of pathological features in early diagnosis.

Assuntos

Lesões Pré-Cancerosas , Neoplasias Gástricas , Humanos , Neoplasias Gástricas/diagnóstico por imagem , Lesões Pré-Cancerosas/diagnóstico por imagem , Processamento de Imagem Assistida por Computador

RESUMO

BACKGROUND: Variability exists in sertraline pharmacokinetic parameters in individuals, especially obvious in adolescents. We aimed to establish an individualized dosing model of sertraline for adolescents with depression based on artificial intelligence (AI) techniques. METHODS: Data were collected from 258 adolescent patients treated at the First Hospital of Hebei Medical University between December 2019 to July 2022. Nine different algorithms were used for modeling to compare the prediction abilities on sertraline daily dose, including XGBoost, LGBM, CatBoost, GBDT, SVM, ANN, TabNet, KNN, and DT. Performance of four dose subgroups (50 mg, 100 mg, 150 mg, and 200 mg) were analyzed. RESULTS: CatBoost was chosen to establish the individualized medication model with the best performance. Six important variables were found to be correlated with sertraline dose, including plasma concentration, PLT, MPV, GL, A/G, and LDH. The ROC curve and confusion matrix exhibited the good prediction performance of CatBoost model in four dose subgroups (the AUC of 50 mg, 100 mg, 150 mg, and 200 mg were 0.93, 0.81, 0.93, and 0.93, respectively). CONCLUSION: The AI-based dose prediction model of sertraline in adolescents with depression had a good prediction ability, which provides guidance for clinicians to propose the optimal medication regimen.

Assuntos

Inteligência Artificial , Sertralina , Humanos , Adolescente , Sertralina/efeitos adversos , Algoritmos

RESUMO

BACKGROUND: Being one of the most widespread, pervasive, and troublesome illnesses in the world, depression causes dysfunction in various spheres of individual and social life. Regrettably, despite obtaining evidence-based antidepressant medication, up to 70% of people are going to continue to experience troublesome symptoms. Quetiapine, as one of the most commonly prescribed antipsychotic medication worldwide, has been reported as an effective augmentation strategy to antidepressants. The right quetiapine dose and personalized quetiapine treatment are frequently challenging for clinicians. This study aimed to identify important influencing variables for quetiapine dose by maximizing the use of data from real world, and develop a predictive model of quetiapine dose through machine learning techniques to support selections for treatment regimens. METHODS: The study comprised 308 depressed patients who were medicated with quetiapine and hospitalized in the First Hospital of Hebei Medical University, from November 1, 2019, to August 31, 2022. To identify the important variables influencing the dose of quetiapine, a univariate analysis was applied. The prediction abilities of nine machine learning models (XGBoost, LightGBM, RF, GBDT, SVM, LR, ANN, DT) were compared. Algorithm with the optimal model performance was chosen to develop the prediction model. RESULTS: Four predictors were selected from 38 variables by the univariate analysis (p < 0.05), including quetiapine TDM value, age, mean corpuscular hemoglobin concentration, and total bile acid. Ultimately, the XGBoost algorithm was used to create a prediction model for quetiapine dose that had the greatest predictive performance (accuracy = 0.69) out of nine models. In the testing cohort (62 cases), a total of 43 cases were correctly predicted of the quetiapine dose regimen. In dose subgroup analysis, AUROC for patients with daily dose of 100 mg, 200 mg, 300 mg and 400 mg were 0.99, 0.75, 0.93 and 0.86, respectively. CONCLUSIONS: In this work, machine learning techniques are used for the first time to estimate the dose of quetiapine for patients with depression, which is valuable for the clinical drug recommendations.